In recent years,deep learning has been introduced into the field of Single-pixel imaging(SPI),garnering significant attention.However,conventional networks still exhibit limitations in preserving image details.To addr...In recent years,deep learning has been introduced into the field of Single-pixel imaging(SPI),garnering significant attention.However,conventional networks still exhibit limitations in preserving image details.To address this issue,we integrate Large Kernel Convolution(LKconv)into the U-Net framework,proposing an enhanced network structure named U-LKconv network,which significantly enhances the capability to recover image details even under low sampling conditions.展开更多
Previous research utilizing Cartoon Generative Adversarial Network(CartoonGAN)has encountered limitations in managing intricate outlines and accurately representing lighting effects,particularly in complex scenes requ...Previous research utilizing Cartoon Generative Adversarial Network(CartoonGAN)has encountered limitations in managing intricate outlines and accurately representing lighting effects,particularly in complex scenes requiring detailed shading and contrast.This paper presents a novel Enhanced Pixel Integration(EPI)technique designed to improve the visual quality of images generated by CartoonGAN.Rather than modifying the core model,the EPI approach employs post-processing adjustments that enhance images without significant computational overhead.In this method,images produced by CartoonGAN are converted from Red-Green-Blue(RGB)to Hue-Saturation-Value(HSV)format,allowing for precise adjustments in hue,saturation,and brightness,thereby improving color fidelity.Specific correction values are applied to fine-tune colors,ensuring they closely match the original input while maintaining the characteristic,stylized effect of CartoonGAN.The corrected images are blended with the originals to retain aesthetic appeal and visual distinctiveness,resulting in improved color accuracy and overall coherence.Experimental results demonstrate that EPI significantly increases similarity to original input images compared to the standard CartoonGAN model,achieving a 40.14%enhancement in visual similarity in Learned Perceptual Image Patch Similarity(LPIPS),a 30.21%improvement in structural consistency in Structural Similarity Index Measure(SSIM),and an 11.81%reduction in pixel-level error in Mean Squared Error(MSE).By addressing limitations present in the traditional CartoonGAN pipeline,EPI offers practical enhancements for creative applications,particularly within media and design fields where visual fidelity and artistic style preservation are critical.These improvements align with the goals of Fog and Edge Computing,which also seek to enhance processing efficiency and application performance in sensitive industries such as healthcare,logistics,and education.This research not only resolves key deficiencies in existing CartoonGAN models but also expands its potential applications in image-based content creation,bridging gaps between technical constraints and creative demands.Future studies may explore the adaptability of EPI across various datasets and artistic styles,potentially broadening its impact on visual transformation tasks.展开更多
Objective:In the Radiology Department of Mzuzu Central Hospital(MCH),daily training for radiographers now includes content on Computed Tomography(CT)image quality control and equipment maintenance to ensure the normal...Objective:In the Radiology Department of Mzuzu Central Hospital(MCH),daily training for radiographers now includes content on Computed Tomography(CT)image quality control and equipment maintenance to ensure the normal,continuous,and stable operation of the 16-slice spiral CT scanner.Methods:Through comprehensive analysis of relevant equipment,we have identified key parameters that significantly impact CT image quality.Innovative optimization strategies and solutions targeting these parameters have been developed and integrated into daily training programs.Furthermore,starting from an examination of prevalent failure modes observed in CT equipment,we delve into essential maintenance and preservation techniques that CT technologists must master to ensure optimal system performance.Results:(1)Crucial factors affecting CT image quality include artifacts,noise,partial volume effects,and surrounding gap phenomena,alongside spatial and density resolutions,CT dose,reconstruction algorithms,and human factors during the scanning process.In the daily training for radiographers,emphasis is placed on strictly implementing image quality control measures at every stage of the CT scanning process and skillfully applying advanced scanning and image processing techniques.By doing so,we can provide clinicians with accurate and reliable imaging references for diagnosis and treatment.(2)Strategies for CT equipment maintenance:①Environmental inspection of the CT room to ensure cleanliness and hygiene.②Rational and accurate operation,including calibration software proficiency.③Regular maintenance and servicing for minimizing machine downtime.④Maintenance of the CT X-ray tube.CT technicians can become proficient in equipment maintenance and upkeep techniques through training,which can significantly extend the service life of CT systems and reduce the occurrence of malfunctions.Conclusion:Through the regular implementation of rigorous CT image quality control training for radiology technicians,coupled with diligent and proactive CT equipment maintenance,we have observed profound and beneficial impacts on improving image quality.The accuracy and fidelity of radiological data ultimately leads to more accurate diagnoses and effective treatments.展开更多
Neutron radiographic images(NRIs)typically suffer from multiple distortions,including various types of noise,geometric unsharpness,and white spots.Image quality assessment(IQA)can guide on-site image screening and eve...Neutron radiographic images(NRIs)typically suffer from multiple distortions,including various types of noise,geometric unsharpness,and white spots.Image quality assessment(IQA)can guide on-site image screening and even provide metrics for subsequent image processing.However,existing IQA methods for NRIs cannot effectively evaluate the quality of real NRIs with a specific distortion of white spots,limiting their practical application.In this paper,a novel no-reference IQA method is proposed to comprehensively evaluate the quality of real NRIs with multiple distortions.First,we construct large-scale NRI datasets with more than 20,000 images,including high-quality original NRIs and synthetic NRIs with various distortions.Next,an image quality calibration method based on visual salience and a local quality map is introduced to label the NRI dataset with quality scores.Finally,a lightweight convolutional neural network(CNN)model is designed to learn the abstract relationship between the NRIs and quality scores using the constructed NRI training dataset.Extensive experimental results demonstrate that the proposed method exhibits good consistency with human visual perception when evaluating both real NRIs and processed NRIs using enhancement and restoration algorithms,highlighting its application potential.展开更多
Recent deep neural network(DNN)based blind image quality assessment(BIQA)approaches take mean opinion score(MOS)as ground-truth labels,which would lead to cross-datasets biases and limited generalization ability of th...Recent deep neural network(DNN)based blind image quality assessment(BIQA)approaches take mean opinion score(MOS)as ground-truth labels,which would lead to cross-datasets biases and limited generalization ability of the DNN-based BIQA model.This work validates the natural instability of MOS through investigating the neuropsychological characteristics inside the human visual system during quality perception.By combining persistent homology analysis with electroencephalogram(EEG),the physiologically meaningful features of the brain responses to different distortion levels are extracted.The physiological features indicate that although volunteers view exactly the same image content,their EEG features are quite varied.Based on the physiological results,we advocate treating MOS as noisy labels and optimizing the DNN based BIQA model with earlystop strategies.Experimental results on both innerdataset and cross-dataset demonstrate the superiority of our optimization approach in terms of generalization ability.展开更多
Most blind image quality assessment(BIQA)methods require a large amount of time to collect human opinion scores as training labels,which limits their usability in practice.Thus,we present an opinion-unaware BIQA metho...Most blind image quality assessment(BIQA)methods require a large amount of time to collect human opinion scores as training labels,which limits their usability in practice.Thus,we present an opinion-unaware BIQA method based on deep reinforcement learning which is trained without subjective scores,named DRL-IQA.Inspired by the human visual perception process,our model is formulated as a quality reinforced agent,which consists of the dynamic distortion generation part and the quality perception part.By considering the image distortion degradation process as a sequential decision-making process,the dynamic distortion generation part can develop a strategy to add as many different distortions as possible to an image,which enriches the distortion space to alleviate overfitting.A reward function calculated from quality degradation after adding distortion is utilized to continuously optimize the strategy.Furthermore,the quality perception part can extract rich quality features from the quality degradation process without using subjective scores,and accurately predict the state values that represent the image quality.Experimental results reveal that our method achieves competitive quality prediction performance compared to other state-of-the-art BIQA methods.展开更多
The energy of light exposed on human skin is compulsively limited for safety reasons which affects the power of photoacoustic （PA） signal and its signal-to-noise ratio （SNR） level. Thus, the final reconstructed PA...The energy of light exposed on human skin is compulsively limited for safety reasons which affects the power of photoacoustic （PA） signal and its signal-to-noise ratio （SNR） level. Thus, the final reconstructed PA image quality is degraded. This Letter proposes an adaptive multi-sample-based approach to enhance the SNR of PA signals and in addition, detailed information in rebuilt PA images that used to be buried in the noise can be distinguished. Both ex vivo and in vivo experiments are conducted to validate the effectiveness of our proposed method which provides its potential value in clinical trials.展开更多
The coherent-mode representation theory is firstly used to analyze lensless two-color ghost imaging. A quite complicated expression about the point-spread function（PSF） needs to be given to analyze which wavelength ...The coherent-mode representation theory is firstly used to analyze lensless two-color ghost imaging. A quite complicated expression about the point-spread function（PSF） needs to be given to analyze which wavelength has a stronger affect on imaging quality when the usual integral representation theory is used to ghost imaging. Unlike this theory, the coherent-mode representation theory shows that imaging quality depends crucially on the distribution of the decomposition coefficients of the object imaged in a two-color ghost imaging. The analytical expression of the decomposition coefficients of the object is unconcerned with the wavelength of the light used in the reference arm, but has relevance with the wavelength in the object arm. In other words, imaging quality of two-color ghost imaging depends primarily on the wavelength of the light illuminating the object. Our simulation results also demonstrate this conclusion.展开更多
To further explore the human visual system（ HVS）,the perceptual grouping（ PG）, which has been proven to play an important role in the HVS, is adopted to design an effective image quality assessment（ IQA） model. ...To further explore the human visual system（ HVS）,the perceptual grouping（ PG）, which has been proven to play an important role in the HVS, is adopted to design an effective image quality assessment（ IQA） model. Compared with the existing fixed-window-based models, the proposed one is an adaptive window-like model that introduces the perceptual grouping strategy into the IQA model. It works as follows： first,it preprocesses the images by clustering similar pixels into a group to the greatest extent; then the structural similarity is used to compute the similarity of the superpixels between reference and distorted images; finally, it integrates all the similarity of superpixels of an image to yield a quality score. Experimental results on three databases（ LIVE, IVC and MICT） showthat the proposed method yields good performance in terms of correlation with human judgments of visual quality.展开更多
Combining bright-feld and edge-enhanced imaging affords an effective avenue for extracting complex morphological information from objects,which is particularly beneficial for biological imaging.Multiplexing metalenses...Combining bright-feld and edge-enhanced imaging affords an effective avenue for extracting complex morphological information from objects,which is particularly beneficial for biological imaging.Multiplexing metalenses present promising candidates for achieving this functionality.However,current multiplexing meta-lenses lack spectral modulation,and crosstalk between different wavelengths hampers the imaging quality,especilly for biological samples requiring precise wavelength specificity.Here,we experimentally demonstrate the nonlocal Huygens'meta-lens for high-quality-factor spin-multiplexing imaging.Quasi-bound states in the continuum(q-BlCs)are excited to provide a high quality factor of 90 and incident-angle dependence.The generalized Kerker condition,driven by Fano-like interactions between q-BIC and in-plane Mie resonances,breaks the radiation symmetry,resulting in a transmission peak with a geometric phase for polarization-converted light,while unconverted light exhibits a transmission dip without a geometric phase.Enhanced polarization conversion efficiency of 65%is achieved,accompanied by a minimal unconverted value,surpassing the theoretical limit of traditional thin nonlocal metasurfaces.Leveraging these effects,the output polarization-converted state exhibits an efficient wavelengthselective focusing phase profle.The unconverted counterpart serves as an effective spatial frequency filter based on incident-angular dispersion,passing high-frequency edge details.Bright-field imaging and edge detection are thus presented under two output spin states.This work provides a versatile framework for nonlocal metasurfaces,boosting biomedical imaging and sensing applications.展开更多
Imaging quality is a critical component of compressive imaging in real applications. In this study, we propose a compressive imaging method based on multi-scale modulation and reconstruction in the spatial frequency d...Imaging quality is a critical component of compressive imaging in real applications. In this study, we propose a compressive imaging method based on multi-scale modulation and reconstruction in the spatial frequency domain. Theoretical analysis and simulation show the relation between the measurement matrix resolution and compressive sensing(CS)imaging quality. The matrix design is improved to provide multi-scale modulations, followed by individual reconstruction of images of different spatial frequencies. Compared with traditional single-scale CS imaging, the multi-scale method provides high quality imaging in both high and low frequencies, and effectively decreases the overall reconstruction error.Experimental results confirm the feasibility of this technique, especially at low sampling rate. The method may thus be helpful in promoting the implementation of compressive imaging in real applications.展开更多
BACKGROUND A key cardiac magnetic resonance(CMR)challenge is breath-holding duration,difficult for cardiac patients.AIM To evaluate whether artificial intelligence-assisted compressed sensing CINE(AICS-CINE)reduces im...BACKGROUND A key cardiac magnetic resonance(CMR)challenge is breath-holding duration,difficult for cardiac patients.AIM To evaluate whether artificial intelligence-assisted compressed sensing CINE(AICS-CINE)reduces image acquisition time of CMR compared to conventional CINE(C-CINE).METHODS Cardio-oncology patients(n=60)and healthy volunteers(n=29)underwent sequential C-CINE and AI-CS-CINE with a 1.5-T scanner.Acquisition time,visual image quality assessment,and biventricular metrics(end-diastolic volume,endsystolic volume,stroke volume,ejection fraction,left ventricular mass,and wall thickness)were analyzed and compared between C-CINE and AI-CS-CINE with Bland–Altman analysis,and calculation of intraclass coefficient(ICC).RESULTS In 89 participants(58.5±16.8 years,42 males,47 females),total AI-CS-CINE acquisition and reconstruction time(37 seconds)was 84%faster than C-CINE(238 seconds).C-CINE required repeats in 23%(20/89)of cases(approximately 8 minutes lost),while AI-CS-CINE only needed one repeat(1%;2 seconds lost).AICS-CINE had slightly lower contrast but preserved structural clarity.Bland-Altman plots and ICC(0.73≤r≤0.98)showed strong agreement for left ventricle(LV)and right ventricle(RV)metrics,including those in the cardiac amyloidosis subgroup(n=31).AI-CS-CINE enabled faster,easier imaging in patients with claustrophobia,dyspnea,arrhythmias,or restlessness.Motion-artifacted C-CINE images were reliably interpreted from AI-CS-CINE.CONCLUSION AI-CS-CINE accelerated CMR image acquisition and reconstruction,preserved anatomical detail,and diminished impact of patient-related motion.Quantitative AI-CS-CINE metrics agreed closely with C-CINE in cardio-oncology patients,including the cardiac amyloidosis cohort,as well as healthy volunteers regardless of left and right ventricular size and function.AI-CS-CINE significantly enhanced CMR workflow,particularly in challenging cases.The strong analytical concordance underscores reliability and robustness of AI-CS-CINE as a valuable tool.展开更多
Objective:To analyze the application effect of hysterosalpingography in infertility and provide a reference for the clinical diagnosis of infertility.Methods:A total of 80 infertile patients admitted to Guangdong Wome...Objective:To analyze the application effect of hysterosalpingography in infertility and provide a reference for the clinical diagnosis of infertility.Methods:A total of 80 infertile patients admitted to Guangdong Women and Children’s Hospital from March 2023 to March 2024 were selected as the research objects.They were randomly divided into two groups:the control group and the observation group,with 40 patients in each group,and 80 fallopian tubes were observed in each group.The control group underwent traditional gynecological examinations,while the observation group underwent X-ray hysterosalpingography[1].Four indicators,namely diagnostic accuracy,specificity,sensitivity,and excellent/good rate of image quality,were compared between the two groups to evaluate the diagnostic effect on the fallopian tubes.Results:The values of the above four indicators in the observation group were 95.00%,93.33%,95.38%,and 97.50%respectively,while those in the control group were 76.25%,73.33%,70.77%,and 80.00%respectively.There were statistically significant differences in the four indicators between the two groups(P<0.05).The incidence of adverse reactions in the observation group was 5.00%,and that in the control group was 25.00%,showing a significant difference with statistical significance(χ^(2)=6.275,P<0.05).Conclusion:Modified hysterosalpingography for infertile patients can significantly improve the diagnostic effect of infertility and reduce the incidence of adverse reactions,which has high clinical promotion value.展开更多
BACKGROUND Three-phase dynamic computed tomography imaging is particularly useful in the liver region.However,dynamic imaging with contrast media has the disadvantage of increased radiation exposure due to multiple im...BACKGROUND Three-phase dynamic computed tomography imaging is particularly useful in the liver region.However,dynamic imaging with contrast media has the disadvantage of increased radiation exposure due to multiple imaging sessions.We hypothesized that the contrast enhancement boost(CE-boost)technique could be used to enhance the contrast in equilibrium phase(EP)images and produce enhancement similar to that of portal vein phase(PVP)images,and if this is possible,EP imaging could play the same role as PVP imaging.We also speculated that this might allow the conversion of three-phase dynamic imaging to biphasic dynamic imaging,reducing patients’radiation exposure.AIM To determine if the CE-boost of EP,CE-boost(EP)is useful compared to a conventional image.METHODS We retrospectively analyzed the cases of 52 patients who were diagnosed with liver cancer between January 2016 and October 2022 at our institution.From these computed tomography images,CE-boost images were generated from the EP and plane images.We compared the PVP,EP,and CE-boost(EP)for blood vessels and hepatic parenchyma based on the contrast-to-noise ratio(CNR),signal-to-noise ratio,and figure-of-merit(FOM).Visual assessments were also performed for vessel visualization,lesion conspicuity,and image noise.RESULTS The CE-boost(EP)images showed significant superiority compared to the PVP images in the CNR,signal-to-noise ratio,and FOM except regarding the hepatic parenchyma.No significant differences were detected in CNR or FOM comparisons within the hepatic parenchyma(P=0.62,0.67).The comparison of the EP and CE-boost(EP)images consistently favored CE-boost(EP).Regarding the visual assessment,the CE-boost(EP)images were significantly superior to the PVP images in lesion conspicuity,and the PVP in image noise.The CE-boost(EP)images were significantly better than the EP images in the vessel visualization of segmental branches of the portal vein and lesion conspicuity,and the EP in image noise.CONCLUSION The image quality of CE-boost(EP)images was comparable or superior to that of conventional PVP and EP.CEboost(EP)images might provide information comparable to the conventional PVP.展开更多
Background:Contrast-enhanced magnetic resonance neurography(ceMRN)can enhance brachial plexus visualization and quality of imaging.However,the interval between contrast injection and scanning that provides the highest...Background:Contrast-enhanced magnetic resonance neurography(ceMRN)can enhance brachial plexus visualization and quality of imaging.However,the interval between contrast injection and scanning that provides the highest-quality images is not known.Methods:Fifteen patients underwent brachial plexus imaging using the 3D T2-NerveView sequence with a scanning duration of 5 min.A consecutive six-phase scan was initiated immediately at the start of contrast agent injection.Subsequently,all patients'images were classified into six groups according to the phases:group A(phase 1,delay 0 min),group B(phase 2,delay 5 min),group C(phase 3,delay 10 min),group D(phase 4,delay 15 min),group E(phase 5,delay 20 min),and group F(phase 6,delay 25 min).The image quality in each group was assessed based on nerve signal(signalnerve),muscle signal(signalmuscle),lymph node signal(signallymph node),background noise(BN),signal-to-noise ratio(SNR),contrast-to-noise ratio(CNR),and subjective score.Results:Signalnerve,signalmuscle,BN,and SNR did not significantly differ among the six groups(p>0.05).However,significant differences(p<0.05)were observed in signallymph node(F=16.067),CNR(F=9.495),and subjective score(χ^(2)=23.586).As the scanning delay increased,signallymph node intensity gradually increased whereas the CNR gradually decreased.The subjective score was significantly higher in groups B(4.830.24),C(4.900.21),D(4.870.30),E(4.830.31),and F(4.830.31)than in group A(4.470.30).Conclusion:We recommend performing brachial plexus ceMRN 5 min after contrast injection.With this delay,the brachial plexus can be visualized optimally with minimal interference from background signals.展开更多
BACKGROUND Primary ciliary dyskinesia(PCD)is a rare condition characterised by dysmotile,immotile,or absent cilia.As a result of the impairment in respiratory mucociliary clearance,patients with PCD typically develop ...BACKGROUND Primary ciliary dyskinesia(PCD)is a rare condition characterised by dysmotile,immotile,or absent cilia.As a result of the impairment in respiratory mucociliary clearance,patients with PCD typically develop neonatal respiratory distress,nasal congestion,otitis media and recurrent respiratory infections leading to bronchiectasis and structural lung changes.These changes have been shown by chest computed tomography(CT)to develop in infancy and early childhood.Recent development and refinement of radiation-reducing CT techniques have allowed significant radiation dose reductions,with chest CT doses now in the range of chest radiography(CR).AIM To evaluate the efficacy of ultra-low dose CT(ULDCT)chest in identifying pulmonary changes within a PCD paediatric patient cohort.METHODS Paediatric patients with PCD who presented for routine clinical outpatient follow-up within the study period,were eligible for inclusion in the study.ULDCT and CR were performed on these patients and the results compared.Comparison metrics included radiation dose,subjective and objective image quality and disease severity.RESULTS Six paediatric patients(mean age 9 years)underwent clinically indicated ULDCT chest examinations and CR for surveillance of their PCD.The mean effective dose was 0.08±0.02 mSv,a dose that approximates that of a frontal and lateral chest radiograph.The average Brody II score across the entire cohort was 12.92,with excellent interrater reliability and intra-class correlation coefficient(ICC)of 0.98.The average Chrispin-Norman score on CR was 1 with excellent inter-rater reliability and ICC of 0.92.CONCLUSION ULDCT demonstrates superior diagnostic capabilities,minimal radiation dose penalty,and high interobserver reliability in comparison to CR.Thus,we advocate for ULDCT to be the preferred modality for surveillance imaging in paediatric PCD.展开更多
Deep learning(DL)is making significant inroads into biomedical imaging as it provides novel and powerful ways of accurately and efficiently improving the image quality of photoacoustic microscopy(PAM).Off-the-shelf DL...Deep learning(DL)is making significant inroads into biomedical imaging as it provides novel and powerful ways of accurately and efficiently improving the image quality of photoacoustic microscopy(PAM).Off-the-shelf DL models,however,do not necessarily obey the fundamental governing laws of PAM physical systems,nor do they generalize well to scenarios on which they have not been trained.In this work,a physics-embedded degeneration learning(PEDL)approach is proposed to enhance the image quality of PAM with a self-attention enhanced U-Net network,which obtains greater physical consistency,improves data efficiency,and higher adaptability.The proposed method is demonstrated on both synthetic and real datasets,including animal experiments in vivo(blood vessels of mouse's ear and brain).And the results show that compared with previous DL methods,the PEDL algorithm exhibits good performance in recovering PAM images qualitatively and quantitatively.It overcomes the challenges related to training data,accuracy,and robustness which a typical data-driven approach encounters,whose exemplary application envisions to provide a new perspective for existing DL tools of enhanced PAM.展开更多
AIM: To compare the effect of oral erythromycin vs no preparation with prokinetics on the transit time and the image quality of capsule endoscopy (CE) in evaluating small bowel (SB) pathology. METHODS: We conducted a ...AIM: To compare the effect of oral erythromycin vs no preparation with prokinetics on the transit time and the image quality of capsule endoscopy (CE) in evaluating small bowel (SB) pathology. METHODS: We conducted a retrospective, blinded (to the type of preparation) review of 100 CE studies, 50 with no preparation with prokinetics from one medical center (Group A) and 50 from another center with administration of a single dose of 200 mg oral erythromycin 1 h prior to CE (Group B). Gastric, SB and total transit times were calculated, the presence of bile in the duodenum was scored, as was cleanliness within the proximal, middle and distal intestine. RESULTS: The erythromycin group had a slightly shorter gastric transit time (21 min vs 28 min, with no statistical significance). SB transit time was similar for both groups (all P > 0.05). Total transit time was almost identical in both groups. The rate of incomplete examination was 16% for Group A and 10% for Group B (P = 0.37). Bile and cleanliness scores in different parts of the intestine were similar for the two groups (P > 0.05). CONCLUSION: Preparation for capsule endoscopy with erythromycin does not affect SB or total transit time. It tends to reduce gastric transit time, but it does not increase the cecum-reaching rate. Erythromycin does not adversely affect image quality. We consider the routine use of oral erythromycin preparation as being unjustified, although it might be considered in patients with known prolonged gastric emptying time.展开更多
Neural network methods have recently emerged as a hot topic in computed tomography(CT) imaging owing to their powerful fitting ability;however, their potential applications still need to be carefully studied because t...Neural network methods have recently emerged as a hot topic in computed tomography(CT) imaging owing to their powerful fitting ability;however, their potential applications still need to be carefully studied because their results are often difficult to interpret and are ambiguous in generalizability. Thus, quality assessments of the results obtained from a neural network are necessary to evaluate the neural network. Assessing the image quality of neural networks using traditional objective measurements is not appropriate because neural networks are nonstationary and nonlinear. In contrast, subjective assessments are trustworthy, although they are time-and energy-consuming for radiologists. Model observers that mimic subjective assessment require the mean and covariance of images, which are calculated from numerous image samples;however, this has not yet been applied to the evaluation of neural networks. In this study, we propose an analytical method for noise propagation from a single projection to efficiently evaluate convolutional neural networks(CNNs) in the CT imaging field. We propagate noise through nonlinear layers in a CNN using the Taylor expansion. Nesting of the linear and nonlinear layer noise propagation constitutes the covariance estimation of the CNN. A commonly used U-net structure is adopted for validation. The results reveal that the covariance estimation obtained from the proposed analytical method agrees well with that obtained from the image samples for different phantoms, noise levels, and activation functions, demonstrating that propagating noise from only a single projection is feasible for CNN methods in CT reconstruction. In addition, we use covariance estimation to provide three measurements for the qualitative and quantitative performance evaluation of U-net. The results indicate that the network cannot be applied to projections with high noise levels and possesses limitations in terms of efficiency for processing low-noise projections. U-net is more effective in improving the image quality of smooth regions compared with that of the edge. LeakyReLU outperforms Swish in terms of noise reduction.展开更多
Objective To retrospectively evaluate the effects of saline administration following contrast material injection, abdominal compression and two delay phase acquisition on image quality improvement of computed tomograp...Objective To retrospectively evaluate the effects of saline administration following contrast material injection, abdominal compression and two delay phase acquisition on image quality improvement of computed tomographic urography (CTU). Methods Medical records and informed consents of patients were obtained. In totally 122 patients (50 men, 72 women), two delay phase images with CTU were performed. Scans began simultaneously with a contrast bolus injection of 100 mL (300 mgI/mL) followed by a saline bolus injection of 100 mL at a rate of 5 mL/s. Two delay phase images were taken at 400 and 550 seconds for each patient. Examinations were taken by using abdominal compression or not. The distention and opacification of the urinary tract were evaluated by two interpreters together on transverse images and post-processing images. Effects of four techniques (saline administration and abdominal compression, saline administration only, compression only, and neither saline administration nor compression) and two delay phase acquisition on image quality improvement were analysed by using ANOVA and Chi-square test. Results Saline administration improved opacification (P<0.05) and increased overall image quality (P<0.01) of the intrarenal collecting system and proximal ureter. Abdominal compression (P<0.05) and delayed phase image acquisition of 550 seconds (P<0.01) all improved distention of the intrarenal collecting system and proximal ureter but did not improve opacification. No statistically significant effects on the distal ureter were found. However, there were more visualized distal ureteral segments with the longer imaging delay. Conclusion Saline administration, abdominal compression and longer imaging delays are all effective in improving image quality of 64-detector row CTU.展开更多
文摘In recent years,deep learning has been introduced into the field of Single-pixel imaging(SPI),garnering significant attention.However,conventional networks still exhibit limitations in preserving image details.To address this issue,we integrate Large Kernel Convolution(LKconv)into the U-Net framework,proposing an enhanced network structure named U-LKconv network,which significantly enhances the capability to recover image details even under low sampling conditions.
基金supported by the National Research Foundation of Korea(NRF)under Grant RS-2022-NR-069955(2022R1A2C1092178).
文摘Previous research utilizing Cartoon Generative Adversarial Network(CartoonGAN)has encountered limitations in managing intricate outlines and accurately representing lighting effects,particularly in complex scenes requiring detailed shading and contrast.This paper presents a novel Enhanced Pixel Integration(EPI)technique designed to improve the visual quality of images generated by CartoonGAN.Rather than modifying the core model,the EPI approach employs post-processing adjustments that enhance images without significant computational overhead.In this method,images produced by CartoonGAN are converted from Red-Green-Blue(RGB)to Hue-Saturation-Value(HSV)format,allowing for precise adjustments in hue,saturation,and brightness,thereby improving color fidelity.Specific correction values are applied to fine-tune colors,ensuring they closely match the original input while maintaining the characteristic,stylized effect of CartoonGAN.The corrected images are blended with the originals to retain aesthetic appeal and visual distinctiveness,resulting in improved color accuracy and overall coherence.Experimental results demonstrate that EPI significantly increases similarity to original input images compared to the standard CartoonGAN model,achieving a 40.14%enhancement in visual similarity in Learned Perceptual Image Patch Similarity(LPIPS),a 30.21%improvement in structural consistency in Structural Similarity Index Measure(SSIM),and an 11.81%reduction in pixel-level error in Mean Squared Error(MSE).By addressing limitations present in the traditional CartoonGAN pipeline,EPI offers practical enhancements for creative applications,particularly within media and design fields where visual fidelity and artistic style preservation are critical.These improvements align with the goals of Fog and Edge Computing,which also seek to enhance processing efficiency and application performance in sensitive industries such as healthcare,logistics,and education.This research not only resolves key deficiencies in existing CartoonGAN models but also expands its potential applications in image-based content creation,bridging gaps between technical constraints and creative demands.Future studies may explore the adaptability of EPI across various datasets and artistic styles,potentially broadening its impact on visual transformation tasks.
基金supported by the First Affiliated Hospital of Xi’an Jiaotong University Teaching Reform Project(Grant No.JG2023-0206 and JG2022-0324).
文摘Objective:In the Radiology Department of Mzuzu Central Hospital(MCH),daily training for radiographers now includes content on Computed Tomography(CT)image quality control and equipment maintenance to ensure the normal,continuous,and stable operation of the 16-slice spiral CT scanner.Methods:Through comprehensive analysis of relevant equipment,we have identified key parameters that significantly impact CT image quality.Innovative optimization strategies and solutions targeting these parameters have been developed and integrated into daily training programs.Furthermore,starting from an examination of prevalent failure modes observed in CT equipment,we delve into essential maintenance and preservation techniques that CT technologists must master to ensure optimal system performance.Results:(1)Crucial factors affecting CT image quality include artifacts,noise,partial volume effects,and surrounding gap phenomena,alongside spatial and density resolutions,CT dose,reconstruction algorithms,and human factors during the scanning process.In the daily training for radiographers,emphasis is placed on strictly implementing image quality control measures at every stage of the CT scanning process and skillfully applying advanced scanning and image processing techniques.By doing so,we can provide clinicians with accurate and reliable imaging references for diagnosis and treatment.(2)Strategies for CT equipment maintenance:①Environmental inspection of the CT room to ensure cleanliness and hygiene.②Rational and accurate operation,including calibration software proficiency.③Regular maintenance and servicing for minimizing machine downtime.④Maintenance of the CT X-ray tube.CT technicians can become proficient in equipment maintenance and upkeep techniques through training,which can significantly extend the service life of CT systems and reduce the occurrence of malfunctions.Conclusion:Through the regular implementation of rigorous CT image quality control training for radiology technicians,coupled with diligent and proactive CT equipment maintenance,we have observed profound and beneficial impacts on improving image quality.The accuracy and fidelity of radiological data ultimately leads to more accurate diagnoses and effective treatments.
基金supported by the National Natural Science Foundation of China(Nos.11905028 and 12105040)Scientific Research Project of the Education Department of Jilin Province(No.JJKH20231294KJ)the Youth Growth Technology Project of the Science and Technology Department of Jilin Province(No.20210508027RQ).
文摘Neutron radiographic images(NRIs)typically suffer from multiple distortions,including various types of noise,geometric unsharpness,and white spots.Image quality assessment(IQA)can guide on-site image screening and even provide metrics for subsequent image processing.However,existing IQA methods for NRIs cannot effectively evaluate the quality of real NRIs with a specific distortion of white spots,limiting their practical application.In this paper,a novel no-reference IQA method is proposed to comprehensively evaluate the quality of real NRIs with multiple distortions.First,we construct large-scale NRI datasets with more than 20,000 images,including high-quality original NRIs and synthetic NRIs with various distortions.Next,an image quality calibration method based on visual salience and a local quality map is introduced to label the NRI dataset with quality scores.Finally,a lightweight convolutional neural network(CNN)model is designed to learn the abstract relationship between the NRIs and quality scores using the constructed NRI training dataset.Extensive experimental results demonstrate that the proposed method exhibits good consistency with human visual perception when evaluating both real NRIs and processed NRIs using enhancement and restoration algorithms,highlighting its application potential.
基金supported by the Medium and Long-term Science and Technology Plan for Radio,Television,and Online Audiovisuals(2023AC0200)the Public Welfare Technology Application Research Project of Zhejiang Province,China(No.LGF21F010001).
文摘Recent deep neural network(DNN)based blind image quality assessment(BIQA)approaches take mean opinion score(MOS)as ground-truth labels,which would lead to cross-datasets biases and limited generalization ability of the DNN-based BIQA model.This work validates the natural instability of MOS through investigating the neuropsychological characteristics inside the human visual system during quality perception.By combining persistent homology analysis with electroencephalogram(EEG),the physiologically meaningful features of the brain responses to different distortion levels are extracted.The physiological features indicate that although volunteers view exactly the same image content,their EEG features are quite varied.Based on the physiological results,we advocate treating MOS as noisy labels and optimizing the DNN based BIQA model with earlystop strategies.Experimental results on both innerdataset and cross-dataset demonstrate the superiority of our optimization approach in terms of generalization ability.
基金supported by the Fundamental Research Funds for the Central Universities.
文摘Most blind image quality assessment(BIQA)methods require a large amount of time to collect human opinion scores as training labels,which limits their usability in practice.Thus,we present an opinion-unaware BIQA method based on deep reinforcement learning which is trained without subjective scores,named DRL-IQA.Inspired by the human visual perception process,our model is formulated as a quality reinforced agent,which consists of the dynamic distortion generation part and the quality perception part.By considering the image distortion degradation process as a sequential decision-making process,the dynamic distortion generation part can develop a strategy to add as many different distortions as possible to an image,which enriches the distortion space to alleviate overfitting.A reward function calculated from quality degradation after adding distortion is utilized to continuously optimize the strategy.Furthermore,the quality perception part can extract rich quality features from the quality degradation process without using subjective scores,and accurately predict the state values that represent the image quality.Experimental results reveal that our method achieves competitive quality prediction performance compared to other state-of-the-art BIQA methods.
基金supported by the National Natural Science Foundation of China(No.61201425)the Natural Science Foundation of Jinagsu Province(No.BK20131280)the Priority Academic Program Development of Jiangsu Higher Education Institutions
文摘The energy of light exposed on human skin is compulsively limited for safety reasons which affects the power of photoacoustic （PA） signal and its signal-to-noise ratio （SNR） level. Thus, the final reconstructed PA image quality is degraded. This Letter proposes an adaptive multi-sample-based approach to enhance the SNR of PA signals and in addition, detailed information in rebuilt PA images that used to be buried in the noise can be distinguished. Both ex vivo and in vivo experiments are conducted to validate the effectiveness of our proposed method which provides its potential value in clinical trials.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61771067,61631014,61471051,and 61401036)the Youth Research and Innovation Program of Beijing University of Posts and Telecommunications,China(Grant Nos.2015RC12 and 2017RC10)
文摘The coherent-mode representation theory is firstly used to analyze lensless two-color ghost imaging. A quite complicated expression about the point-spread function（PSF） needs to be given to analyze which wavelength has a stronger affect on imaging quality when the usual integral representation theory is used to ghost imaging. Unlike this theory, the coherent-mode representation theory shows that imaging quality depends crucially on the distribution of the decomposition coefficients of the object imaged in a two-color ghost imaging. The analytical expression of the decomposition coefficients of the object is unconcerned with the wavelength of the light used in the reference arm, but has relevance with the wavelength in the object arm. In other words, imaging quality of two-color ghost imaging depends primarily on the wavelength of the light illuminating the object. Our simulation results also demonstrate this conclusion.
基金The National Natural Science Foundation of China(No.81272501)the National Basic Research Program of China(973Program)(No.2011CB707904)Taishan Scholars Program of Shandong Province,China(No.ts20120505)
文摘To further explore the human visual system（ HVS）,the perceptual grouping（ PG）, which has been proven to play an important role in the HVS, is adopted to design an effective image quality assessment（ IQA） model. Compared with the existing fixed-window-based models, the proposed one is an adaptive window-like model that introduces the perceptual grouping strategy into the IQA model. It works as follows： first,it preprocesses the images by clustering similar pixels into a group to the greatest extent; then the structural similarity is used to compute the similarity of the superpixels between reference and distorted images; finally, it integrates all the similarity of superpixels of an image to yield a quality score. Experimental results on three databases（ LIVE, IVC and MICT） showthat the proposed method yields good performance in terms of correlation with human judgments of visual quality.
基金supported by the University Grants Committee/Research Grants Council of the Hong Kong Special Administrative Region,China[Project No.AoE/P-502/20,CRF Project:C5031-22G,GRF Project:CityU15303521,CityU11305223,CityU11300224]City University of Hong Kong[Project No.9380131 and 7005867]+3 种基金National Natural Science Foundation of China[Grant No.62375232]S.X.acknowledges financial support from National Natural Science Foundation of China(Grant Nos.62125501,and 6233000076)Fundamental Research Funds for the Central Universities(Grant No.2022FRRK030004)Shenzhen Fundamental Research Projects(Grant Nos.JCYJ20220818102218040).
文摘Combining bright-feld and edge-enhanced imaging affords an effective avenue for extracting complex morphological information from objects,which is particularly beneficial for biological imaging.Multiplexing metalenses present promising candidates for achieving this functionality.However,current multiplexing meta-lenses lack spectral modulation,and crosstalk between different wavelengths hampers the imaging quality,especilly for biological samples requiring precise wavelength specificity.Here,we experimentally demonstrate the nonlocal Huygens'meta-lens for high-quality-factor spin-multiplexing imaging.Quasi-bound states in the continuum(q-BlCs)are excited to provide a high quality factor of 90 and incident-angle dependence.The generalized Kerker condition,driven by Fano-like interactions between q-BIC and in-plane Mie resonances,breaks the radiation symmetry,resulting in a transmission peak with a geometric phase for polarization-converted light,while unconverted light exhibits a transmission dip without a geometric phase.Enhanced polarization conversion efficiency of 65%is achieved,accompanied by a minimal unconverted value,surpassing the theoretical limit of traditional thin nonlocal metasurfaces.Leveraging these effects,the output polarization-converted state exhibits an efficient wavelengthselective focusing phase profle.The unconverted counterpart serves as an effective spatial frequency filter based on incident-angular dispersion,passing high-frequency edge details.Bright-field imaging and edge detection are thus presented under two output spin states.This work provides a versatile framework for nonlocal metasurfaces,boosting biomedical imaging and sensing applications.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61601442,61605218,and 61575207)the National Key Research and Development Program of China(Grant No.2018YFB0504302)the Youth Innovation Promotion Association of the Chinese Academy of Sciences(Grant Nos.2015124 and 2019154)。
文摘Imaging quality is a critical component of compressive imaging in real applications. In this study, we propose a compressive imaging method based on multi-scale modulation and reconstruction in the spatial frequency domain. Theoretical analysis and simulation show the relation between the measurement matrix resolution and compressive sensing(CS)imaging quality. The matrix design is improved to provide multi-scale modulations, followed by individual reconstruction of images of different spatial frequencies. Compared with traditional single-scale CS imaging, the multi-scale method provides high quality imaging in both high and low frequencies, and effectively decreases the overall reconstruction error.Experimental results confirm the feasibility of this technique, especially at low sampling rate. The method may thus be helpful in promoting the implementation of compressive imaging in real applications.
基金Supported by James Russell Hornsby and Jun Xiong Fund and United Imaging Healthcare.
文摘BACKGROUND A key cardiac magnetic resonance(CMR)challenge is breath-holding duration,difficult for cardiac patients.AIM To evaluate whether artificial intelligence-assisted compressed sensing CINE(AICS-CINE)reduces image acquisition time of CMR compared to conventional CINE(C-CINE).METHODS Cardio-oncology patients(n=60)and healthy volunteers(n=29)underwent sequential C-CINE and AI-CS-CINE with a 1.5-T scanner.Acquisition time,visual image quality assessment,and biventricular metrics(end-diastolic volume,endsystolic volume,stroke volume,ejection fraction,left ventricular mass,and wall thickness)were analyzed and compared between C-CINE and AI-CS-CINE with Bland–Altman analysis,and calculation of intraclass coefficient(ICC).RESULTS In 89 participants(58.5±16.8 years,42 males,47 females),total AI-CS-CINE acquisition and reconstruction time(37 seconds)was 84%faster than C-CINE(238 seconds).C-CINE required repeats in 23%(20/89)of cases(approximately 8 minutes lost),while AI-CS-CINE only needed one repeat(1%;2 seconds lost).AICS-CINE had slightly lower contrast but preserved structural clarity.Bland-Altman plots and ICC(0.73≤r≤0.98)showed strong agreement for left ventricle(LV)and right ventricle(RV)metrics,including those in the cardiac amyloidosis subgroup(n=31).AI-CS-CINE enabled faster,easier imaging in patients with claustrophobia,dyspnea,arrhythmias,or restlessness.Motion-artifacted C-CINE images were reliably interpreted from AI-CS-CINE.CONCLUSION AI-CS-CINE accelerated CMR image acquisition and reconstruction,preserved anatomical detail,and diminished impact of patient-related motion.Quantitative AI-CS-CINE metrics agreed closely with C-CINE in cardio-oncology patients,including the cardiac amyloidosis cohort,as well as healthy volunteers regardless of left and right ventricular size and function.AI-CS-CINE significantly enhanced CMR workflow,particularly in challenging cases.The strong analytical concordance underscores reliability and robustness of AI-CS-CINE as a valuable tool.
文摘Objective:To analyze the application effect of hysterosalpingography in infertility and provide a reference for the clinical diagnosis of infertility.Methods:A total of 80 infertile patients admitted to Guangdong Women and Children’s Hospital from March 2023 to March 2024 were selected as the research objects.They were randomly divided into two groups:the control group and the observation group,with 40 patients in each group,and 80 fallopian tubes were observed in each group.The control group underwent traditional gynecological examinations,while the observation group underwent X-ray hysterosalpingography[1].Four indicators,namely diagnostic accuracy,specificity,sensitivity,and excellent/good rate of image quality,were compared between the two groups to evaluate the diagnostic effect on the fallopian tubes.Results:The values of the above four indicators in the observation group were 95.00%,93.33%,95.38%,and 97.50%respectively,while those in the control group were 76.25%,73.33%,70.77%,and 80.00%respectively.There were statistically significant differences in the four indicators between the two groups(P<0.05).The incidence of adverse reactions in the observation group was 5.00%,and that in the control group was 25.00%,showing a significant difference with statistical significance(χ^(2)=6.275,P<0.05).Conclusion:Modified hysterosalpingography for infertile patients can significantly improve the diagnostic effect of infertility and reduce the incidence of adverse reactions,which has high clinical promotion value.
文摘BACKGROUND Three-phase dynamic computed tomography imaging is particularly useful in the liver region.However,dynamic imaging with contrast media has the disadvantage of increased radiation exposure due to multiple imaging sessions.We hypothesized that the contrast enhancement boost(CE-boost)technique could be used to enhance the contrast in equilibrium phase(EP)images and produce enhancement similar to that of portal vein phase(PVP)images,and if this is possible,EP imaging could play the same role as PVP imaging.We also speculated that this might allow the conversion of three-phase dynamic imaging to biphasic dynamic imaging,reducing patients’radiation exposure.AIM To determine if the CE-boost of EP,CE-boost(EP)is useful compared to a conventional image.METHODS We retrospectively analyzed the cases of 52 patients who were diagnosed with liver cancer between January 2016 and October 2022 at our institution.From these computed tomography images,CE-boost images were generated from the EP and plane images.We compared the PVP,EP,and CE-boost(EP)for blood vessels and hepatic parenchyma based on the contrast-to-noise ratio(CNR),signal-to-noise ratio,and figure-of-merit(FOM).Visual assessments were also performed for vessel visualization,lesion conspicuity,and image noise.RESULTS The CE-boost(EP)images showed significant superiority compared to the PVP images in the CNR,signal-to-noise ratio,and FOM except regarding the hepatic parenchyma.No significant differences were detected in CNR or FOM comparisons within the hepatic parenchyma(P=0.62,0.67).The comparison of the EP and CE-boost(EP)images consistently favored CE-boost(EP).Regarding the visual assessment,the CE-boost(EP)images were significantly superior to the PVP images in lesion conspicuity,and the PVP in image noise.The CE-boost(EP)images were significantly better than the EP images in the vessel visualization of segmental branches of the portal vein and lesion conspicuity,and the EP in image noise.CONCLUSION The image quality of CE-boost(EP)images was comparable or superior to that of conventional PVP and EP.CEboost(EP)images might provide information comparable to the conventional PVP.
基金supported by the National Natural Science Foundation of China(Grant No.82302173).
文摘Background:Contrast-enhanced magnetic resonance neurography(ceMRN)can enhance brachial plexus visualization and quality of imaging.However,the interval between contrast injection and scanning that provides the highest-quality images is not known.Methods:Fifteen patients underwent brachial plexus imaging using the 3D T2-NerveView sequence with a scanning duration of 5 min.A consecutive six-phase scan was initiated immediately at the start of contrast agent injection.Subsequently,all patients'images were classified into six groups according to the phases:group A(phase 1,delay 0 min),group B(phase 2,delay 5 min),group C(phase 3,delay 10 min),group D(phase 4,delay 15 min),group E(phase 5,delay 20 min),and group F(phase 6,delay 25 min).The image quality in each group was assessed based on nerve signal(signalnerve),muscle signal(signalmuscle),lymph node signal(signallymph node),background noise(BN),signal-to-noise ratio(SNR),contrast-to-noise ratio(CNR),and subjective score.Results:Signalnerve,signalmuscle,BN,and SNR did not significantly differ among the six groups(p>0.05).However,significant differences(p<0.05)were observed in signallymph node(F=16.067),CNR(F=9.495),and subjective score(χ^(2)=23.586).As the scanning delay increased,signallymph node intensity gradually increased whereas the CNR gradually decreased.The subjective score was significantly higher in groups B(4.830.24),C(4.900.21),D(4.870.30),E(4.830.31),and F(4.830.31)than in group A(4.470.30).Conclusion:We recommend performing brachial plexus ceMRN 5 min after contrast injection.With this delay,the brachial plexus can be visualized optimally with minimal interference from background signals.
文摘BACKGROUND Primary ciliary dyskinesia(PCD)is a rare condition characterised by dysmotile,immotile,or absent cilia.As a result of the impairment in respiratory mucociliary clearance,patients with PCD typically develop neonatal respiratory distress,nasal congestion,otitis media and recurrent respiratory infections leading to bronchiectasis and structural lung changes.These changes have been shown by chest computed tomography(CT)to develop in infancy and early childhood.Recent development and refinement of radiation-reducing CT techniques have allowed significant radiation dose reductions,with chest CT doses now in the range of chest radiography(CR).AIM To evaluate the efficacy of ultra-low dose CT(ULDCT)chest in identifying pulmonary changes within a PCD paediatric patient cohort.METHODS Paediatric patients with PCD who presented for routine clinical outpatient follow-up within the study period,were eligible for inclusion in the study.ULDCT and CR were performed on these patients and the results compared.Comparison metrics included radiation dose,subjective and objective image quality and disease severity.RESULTS Six paediatric patients(mean age 9 years)underwent clinically indicated ULDCT chest examinations and CR for surveillance of their PCD.The mean effective dose was 0.08±0.02 mSv,a dose that approximates that of a frontal and lateral chest radiograph.The average Brody II score across the entire cohort was 12.92,with excellent interrater reliability and intra-class correlation coefficient(ICC)of 0.98.The average Chrispin-Norman score on CR was 1 with excellent inter-rater reliability and ICC of 0.92.CONCLUSION ULDCT demonstrates superior diagnostic capabilities,minimal radiation dose penalty,and high interobserver reliability in comparison to CR.Thus,we advocate for ULDCT to be the preferred modality for surveillance imaging in paediatric PCD.
基金supported by National Natural Science Foundation of China(62227818,12204239,62275121)Youth Foundation of Jiangsu Province(BK20220946)+1 种基金Fundamental Research Funds for the Central Universities(30923011024)Open Research Fund of Jiangsu Key Laboratory of Spectral Imaging&Intelligent Sense(JSGP202201).
文摘Deep learning(DL)is making significant inroads into biomedical imaging as it provides novel and powerful ways of accurately and efficiently improving the image quality of photoacoustic microscopy(PAM).Off-the-shelf DL models,however,do not necessarily obey the fundamental governing laws of PAM physical systems,nor do they generalize well to scenarios on which they have not been trained.In this work,a physics-embedded degeneration learning(PEDL)approach is proposed to enhance the image quality of PAM with a self-attention enhanced U-Net network,which obtains greater physical consistency,improves data efficiency,and higher adaptability.The proposed method is demonstrated on both synthetic and real datasets,including animal experiments in vivo(blood vessels of mouse's ear and brain).And the results show that compared with previous DL methods,the PEDL algorithm exhibits good performance in recovering PAM images qualitatively and quantitatively.It overcomes the challenges related to training data,accuracy,and robustness which a typical data-driven approach encounters,whose exemplary application envisions to provide a new perspective for existing DL tools of enhanced PAM.
文摘AIM: To compare the effect of oral erythromycin vs no preparation with prokinetics on the transit time and the image quality of capsule endoscopy (CE) in evaluating small bowel (SB) pathology. METHODS: We conducted a retrospective, blinded (to the type of preparation) review of 100 CE studies, 50 with no preparation with prokinetics from one medical center (Group A) and 50 from another center with administration of a single dose of 200 mg oral erythromycin 1 h prior to CE (Group B). Gastric, SB and total transit times were calculated, the presence of bile in the duodenum was scored, as was cleanliness within the proximal, middle and distal intestine. RESULTS: The erythromycin group had a slightly shorter gastric transit time (21 min vs 28 min, with no statistical significance). SB transit time was similar for both groups (all P > 0.05). Total transit time was almost identical in both groups. The rate of incomplete examination was 16% for Group A and 10% for Group B (P = 0.37). Bile and cleanliness scores in different parts of the intestine were similar for the two groups (P > 0.05). CONCLUSION: Preparation for capsule endoscopy with erythromycin does not affect SB or total transit time. It tends to reduce gastric transit time, but it does not increase the cecum-reaching rate. Erythromycin does not adversely affect image quality. We consider the routine use of oral erythromycin preparation as being unjustified, although it might be considered in patients with known prolonged gastric emptying time.
基金supported by the National Natural Science Foundation of China(Nos.62031020 and 61771279)。
文摘Neural network methods have recently emerged as a hot topic in computed tomography(CT) imaging owing to their powerful fitting ability;however, their potential applications still need to be carefully studied because their results are often difficult to interpret and are ambiguous in generalizability. Thus, quality assessments of the results obtained from a neural network are necessary to evaluate the neural network. Assessing the image quality of neural networks using traditional objective measurements is not appropriate because neural networks are nonstationary and nonlinear. In contrast, subjective assessments are trustworthy, although they are time-and energy-consuming for radiologists. Model observers that mimic subjective assessment require the mean and covariance of images, which are calculated from numerous image samples;however, this has not yet been applied to the evaluation of neural networks. In this study, we propose an analytical method for noise propagation from a single projection to efficiently evaluate convolutional neural networks(CNNs) in the CT imaging field. We propagate noise through nonlinear layers in a CNN using the Taylor expansion. Nesting of the linear and nonlinear layer noise propagation constitutes the covariance estimation of the CNN. A commonly used U-net structure is adopted for validation. The results reveal that the covariance estimation obtained from the proposed analytical method agrees well with that obtained from the image samples for different phantoms, noise levels, and activation functions, demonstrating that propagating noise from only a single projection is feasible for CNN methods in CT reconstruction. In addition, we use covariance estimation to provide three measurements for the qualitative and quantitative performance evaluation of U-net. The results indicate that the network cannot be applied to projections with high noise levels and possesses limitations in terms of efficiency for processing low-noise projections. U-net is more effective in improving the image quality of smooth regions compared with that of the edge. LeakyReLU outperforms Swish in terms of noise reduction.
文摘Objective To retrospectively evaluate the effects of saline administration following contrast material injection, abdominal compression and two delay phase acquisition on image quality improvement of computed tomographic urography (CTU). Methods Medical records and informed consents of patients were obtained. In totally 122 patients (50 men, 72 women), two delay phase images with CTU were performed. Scans began simultaneously with a contrast bolus injection of 100 mL (300 mgI/mL) followed by a saline bolus injection of 100 mL at a rate of 5 mL/s. Two delay phase images were taken at 400 and 550 seconds for each patient. Examinations were taken by using abdominal compression or not. The distention and opacification of the urinary tract were evaluated by two interpreters together on transverse images and post-processing images. Effects of four techniques (saline administration and abdominal compression, saline administration only, compression only, and neither saline administration nor compression) and two delay phase acquisition on image quality improvement were analysed by using ANOVA and Chi-square test. Results Saline administration improved opacification (P<0.05) and increased overall image quality (P<0.01) of the intrarenal collecting system and proximal ureter. Abdominal compression (P<0.05) and delayed phase image acquisition of 550 seconds (P<0.01) all improved distention of the intrarenal collecting system and proximal ureter but did not improve opacification. No statistically significant effects on the distal ureter were found. However, there were more visualized distal ureteral segments with the longer imaging delay. Conclusion Saline administration, abdominal compression and longer imaging delays are all effective in improving image quality of 64-detector row CTU.
