AIM:To find the effective contrast enhancement method on retinal images for effective segmentation of retinal features.METHODS:A novel image preprocessing method that used neighbourhood-based improved contrast limited...AIM:To find the effective contrast enhancement method on retinal images for effective segmentation of retinal features.METHODS:A novel image preprocessing method that used neighbourhood-based improved contrast limited adaptive histogram equalization(NICLAHE)to improve retinal image contrast was suggested to aid in the accurate identification of retinal disorders and improve the visibility of fine retinal structures.Additionally,a minimal-order filter was applied to effectively denoise the images without compromising important retinal structures.The novel NICLAHE algorithm was inspired by the classical CLAHE algorithm,but enhanced it by selecting the clip limits and tile sized in a dynamical manner relative to the pixel values in an image as opposed to using fixed values.It was evaluated on the Drive and high-resolution fundus(HRF)datasets on conventional quality measures.RESULTS:The new proposed preprocessing technique was applied to two retinal image databases,Drive and HRF,with four quality metrics being,root mean square error(RMSE),peak signal to noise ratio(PSNR),root mean square contrast(RMSC),and overall contrast.The technique performed superiorly on both the data sets as compared to the traditional enhancement methods.In order to assess the compatibility of the method with automated diagnosis,a deep learning framework named ResNet was applied in the segmentation of retinal blood vessels.Sensitivity,specificity,precision and accuracy were used to analyse the performance.NICLAHE–enhanced images outperformed the traditional techniques on both the datasets with improved accuracy.CONCLUSION:NICLAHE provides better results than traditional methods with less error and improved contrastrelated values.These enhanced images are subsequently measured by sensitivity,specificity,precision,and accuracy,which yield a better result in both datasets.展开更多
Underwater images are inherently degraded by color distortion,contrast reduction,and uneven brightness,primarily due to light absorption and scattering in water.To mitigate these challenges,a novel enhancement approac...Underwater images are inherently degraded by color distortion,contrast reduction,and uneven brightness,primarily due to light absorption and scattering in water.To mitigate these challenges,a novel enhancement approach is proposed,integrating Local Adaptive Color Correction(LACC)with contrast enhancement based on adaptive Rayleigh distribution stretching and CLAHE(LACC-RCE).Conventional color correction methods predominantly employ global adjustment strategies,which are often inadequate for handling spatially varying color distortions.In contrast,the proposed LACC method incorporates local color analysis,tone-weighted control,and spatially adaptive adjustments,allowing for region-specific color correction.This approach effectively enhances color fidelity and perceptual naturalness,addressing the limitations of global correction techniques.For contrast enhancement,the proposed method leverages the global mapping characteristics of the Rayleigh distribution to improve overall contrast,while CLAHE is employed to adaptively enhance local regions.A weighted fusion strategy is then applied to synthesize high-quality underwater images.Experimental results indicate that LACC-RCE surpasses conventional methods in color restoration,contrast optimization,and detail preservation,thereby enhancing the visual quality of underwater images.This improvement facilitates more reliable inputs for underwater object detection and recognition tasks.展开更多
A novel wavelet-based algorithm for image enhancement is proposed in the paper. On the basis of multiscale analysis, the proposed algorithm solves efficiently the problem of noise over-enhancement, which commonly occu...A novel wavelet-based algorithm for image enhancement is proposed in the paper. On the basis of multiscale analysis, the proposed algorithm solves efficiently the problem of noise over-enhancement, which commonly occurs in the traditional methods for contrast enhancement. The decomposed coefficients at same scales are processed by a nonlinear method, and the coefficients at different scales are enhanced in different degree. During the procedure, the method takes full advantage of the properties of Human visual system so as to achieve better performance. The simulations demonstrate that these characters of the proposed approach enable it to fully enhance the content in images, to efficiently alleviate the enhancement of noise and to achieve much better enhancement effect than the traditional approaches. Key words wavelet transform - image contrast enhancement - multiscale analysis CLC number TP 391 Foundation item: Supported by the National Natural Science Foundation of China (69931010)Biography: Wu Ying-qian (1974-), male, Ph. D, research direction: image processing, image compression and wavelet.展开更多
Histogram equalization is a traditional algorithm improving the image contrast,but it comes at the cost of mean brightness shift and details loss.In order to solve these problems,a novel approach to processing foregro...Histogram equalization is a traditional algorithm improving the image contrast,but it comes at the cost of mean brightness shift and details loss.In order to solve these problems,a novel approach to processing foreground pixels and background pixels independently is proposed and investigated.Since details are mainly contained in the foreground,the weighted coupling of histogram equalization and Laplace transform were adopted to balance contrast enhancement and details preservation.The weighting factors of image foreground and background were determined by the amount of their respective information.The proposed method was conducted to images acquired from CVG⁃UGR and US⁃SIPI image databases and then compared with other methods such as clipping histogram spikes,histogram addition,and non⁃linear transformation to verify its validity.Results show that the proposed algorithm can effectively enhance the contrast without introducing distortions,and preserve the mean brightness and details well at the same time.展开更多
A new method of contrast enhancement is proposed in the paper using multiscale edge representation of images, and is applied to the field of CT medical image processing. Comparing to the traditional Window technique, ...A new method of contrast enhancement is proposed in the paper using multiscale edge representation of images, and is applied to the field of CT medical image processing. Comparing to the traditional Window technique, our method is adaptive and meets the demand of radiology clinics more better. The clinical experiment results show the practicality and the potential applied value of our method in the field of CT medical images contrast enhancement.展开更多
This paper proposes a two-step general framework for reversible data hiding(RDH)schemes with controllable contrast enhancement.The first step aims at preserving visual perception as much as possible on the basis of ac...This paper proposes a two-step general framework for reversible data hiding(RDH)schemes with controllable contrast enhancement.The first step aims at preserving visual perception as much as possible on the basis of achieving high embedding capacity(EC),while the second step is used for increasing image contrast.In the second step,some peak-pairs are utilized so that the histogram of pixel values is modified to perform histogram equalization(HE),which would lead to the image contrast enhancement.However,for HE,the utilization of some peak-pairs easily leads to over-enhanced image contrast when a large number of bits are embedded.Therefore,in our proposed framework,contrast over-enhancement is avoided by controlling the degree of contrast enhancement.Since the second step can only provide a small amount of data due to controlled contrast enhancement,the first one helps to achieve a large amount of data without degrading visual quality.Any RDH method which can achieve high EC while preserve good visual quality,can be selected for the first step.In fact,Gao et al.’s method is a special case of our proposed framework.In addition,two simple and commonly-used RDH methods are also introduced to further demonstrate the generalization of our framework.展开更多
As one of the most popular digital image manipulations,contrast enhancement(CE)is frequently applied to improve the visual quality of the forged images and conceal traces of forgery,therefore it can provide evidence o...As one of the most popular digital image manipulations,contrast enhancement(CE)is frequently applied to improve the visual quality of the forged images and conceal traces of forgery,therefore it can provide evidence of tampering when verifying the authenticity of digital images.Contrast enhancement forensics techniques have always drawn significant attention for image forensics community,although most approaches have obtained effective detection results,existing CE forensic methods exhibit poor performance when detecting enhanced images stored in the JPEG format.The detection of forgery on contrast adjustments in the presence of JPEG post processing is still a challenging task.In this paper,we propose a new CE forensic method based on convolutional neural network(CNN),which is robust to JPEG compression.The proposed network relies on a Xception-based CNN with two preprocessing strategies.Firstly,unlike the conventional CNNs which accepts the original image as its input,we feed the CNN with the gray-level co-occurrence matrix(GLCM)of image which contains CE fingerprints,then the constrained convolutional layer is used to extract high-frequency details in GLCMs under JPEG compression,finally the output of the constrained convolutional layer becomes the input of Xception to extract multiple features for further classification.Experimental results show that the proposed detector achieves the best performance for CE forensics under JPEG post-processing compared with the existing methods.展开更多
A conventional global contrast enhancement is difficult to apply in various images because image quality and contrast enhancement are dependent on image characteristics largely. And a local contrast enhancement not on...A conventional global contrast enhancement is difficult to apply in various images because image quality and contrast enhancement are dependent on image characteristics largely. And a local contrast enhancement not only causes a washed-out effect, but also blocks. To solve these drawbacks, this paper derives an optimal global equalization function with variable size block based local contrast enhancement. The optimal equalization function makes it possible to get a good quality image through the global contrast enhancement. The variable size block segmentation is firstly exeoated using intensity differences as a measure of similarity. In the second step, the optimal global equalization function is obtained from the enhanced contrast image having variable size blocks. Conformed experiments have showed that the proposed algorithm produces a visually comfortable result image.展开更多
Determining whether sevoflurane sedation in children leads to“pseudo”prominent leptomeningeal contrast enhancement(pLMCE)on 3 Tesla magnetic resonance imaging will help reduce overdiagnosis by radiologists and clari...Determining whether sevoflurane sedation in children leads to“pseudo”prominent leptomeningeal contrast enhancement(pLMCE)on 3 Tesla magnetic resonance imaging will help reduce overdiagnosis by radiologists and clarify the pathophysiological changes of pLMCE.展开更多
Recent contrast enhancement(CE)methods,with a few exceptions,predominantly focus on enhancing gray-scale images.This paper proposes a bi-histogram shifting contrast enhancement for color images based on the RGB(red,gr...Recent contrast enhancement(CE)methods,with a few exceptions,predominantly focus on enhancing gray-scale images.This paper proposes a bi-histogram shifting contrast enhancement for color images based on the RGB(red,green,and blue)color model.The proposed method selects the two highest bins and two lowest bins from the image histogram,performs an equalized number of bidirectional histogram shifting repetitions on each RGB channel while embedding secret data into marked images.The proposed method simultaneously performs both right histogram shifting(RHS)and left histogram shifting(LHS)in each histogram shifting repetition to embed and split the highest bins while combining the lowest bins with their neighbors to achieve histogram equalization(HE).The least maximum number of histograms shifting repetitions among the three RGB channels is used as the default number of histograms shifting repetitions performed to enhance original images.Compared to an existing contrast enhancement method for color images and evaluated with PSNR,SSIM,RCE,and RMBE quality assessment metrics,the experimental results show that the proposed method's enhanced images are visually and qualitatively superior with a more evenly distributed histogram.The proposed method achieves higher embedding capacities and embedding rates in all images,with an average increase in embedding capacity of 52.1%.展开更多
Prior versions of reversible data hiding with contrast enhancement(RDHCE)algorithms strongly focused on enhancing the contrast of grayscale images.However,RDHCE has recently witnessed a rise in contrast enhance-ment a...Prior versions of reversible data hiding with contrast enhancement(RDHCE)algorithms strongly focused on enhancing the contrast of grayscale images.However,RDHCE has recently witnessed a rise in contrast enhance-ment algorithms concentrating on color images.This paper implies a method for color images that uses the RGB(red,green,and blue)color model and is based on bi-histogram shifting and image adjustment.Bi-histogram shifting is used to embed data and image adjustment to achieve contrast enhancement by adjusting the images resulting from each channel of the color images before combining them to generate the final enhanced image.Images are first divided into three channels-R,G,and B-and the Max,Med,and Min channels are then determined from these.Before histogram shifting,some calculations are done to determine how many iterations there will be for each channel.The images are adjusted to improve visual quality in the enhanced images after data has been embedded in each channel.The experimental results show that the enhanced images produced by the proposed method are qualitatively and aesthetically superior to those produced by some earlier methods,and their quality was assessed using PSNR,SSIM,RCE,RMBE,and CIEDE2000.The embedding rate obtained by the suggested method is acceptable.展开更多
We propose a new variational model in Sobolev-Orlicz spaces with non-standard growth conditions of the objective functional and discuss its applications to the simultaneous contrast enhancement and denoising of color ...We propose a new variational model in Sobolev-Orlicz spaces with non-standard growth conditions of the objective functional and discuss its applications to the simultaneous contrast enhancement and denoising of color images.The characteristic feature of the proposed model is that we deal with a constrained non-convex minimization problem that lives in variable Sobolev-Orlicz spaces where the variable exponent is unknown a priori and it depends on a particular function that belongs to the domain of the objective functional.In contrast to the standard approach,we do not apply any spatial regularization to the image gradient.We discuss the consistency of the variational model,give the scheme for its regularization,derive the corresponding optimality system,and propose an iterative algorithm for practical implementations.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
Medical Named Entity Recognition(NER)plays a crucial role in attaining precise patient portraits as well as providing support for intelligent diagnosis and treatment decisions.Federated Learning(FL)enables collaborati...Medical Named Entity Recognition(NER)plays a crucial role in attaining precise patient portraits as well as providing support for intelligent diagnosis and treatment decisions.Federated Learning(FL)enables collaborative modeling and training across multiple endpoints without exposing the original data.However,the statistical heterogeneity exhibited by clinical medical text records poses a challenge for FL methods to support the training of NER models in such scenarios.We propose a Federated Contrast Enhancement(FedCE)method for NER to address the challenges faced by non-large-scale pre-trained models in FL for labelheterogeneous.The method leverages a multi-view encoder structure to capture both global and local semantic information,and employs contrastive learning to enhance the interoperability of global knowledge and local context.We evaluate the performance of the FedCE method on three real-world clinical record datasets.We investigate the impact of factors,such as pooling methods,maximum input text length,and training rounds on FedCE.Additionally,we assess how well FedCE adapts to the base NER models and evaluate its generalization performance.The experimental results show that the FedCE method has obvious advantages and can be effectively applied to various basic models,which is of great theoretical and practical significance for advancing FL in healthcare settings.展开更多
We demonstrate a novel picosecond optical parametric preamplification to generate high-stability, high-energy and high-contrast seed pulses. The 5ps seed pulse is amplified from 60pJ to 300μJ with an 8.6ps/ 3mJ pump ...We demonstrate a novel picosecond optical parametric preamplification to generate high-stability, high-energy and high-contrast seed pulses. The 5ps seed pulse is amplified from 60pJ to 300μJ with an 8.6ps/ 3mJ pump laser in a signal stage of short pulse non-collinear optical parametric chirped pulse amplification. The total gain is more than 106 and the rms energy stability is under 1.35%. The contrast ratio is higher than 10s within a scale of 20ps before the main pulse. Consequently, the improvement factor of the signal contrast is approximately equal to the gain 106 outside the pump window.展开更多
Magnetic resonance imaging(MRI)plays an important role in precision medicine that is hampered by the lack of contrast agents with high efficiency and the ability to translate diagnostic accuracy into therapeutic inter...Magnetic resonance imaging(MRI)plays an important role in precision medicine that is hampered by the lack of contrast agents with high efficiency and the ability to translate diagnostic accuracy into therapeutic intervention.Herein,we demonstrate a DNA-based MRI probe that overcomes previous single-mode enhancement and provides a mechanism of action for aggregationinduced dual-modal MRI signal enhancement.A facile method is developed to produce aggregated T_(1)/T_(2)dual-modal NaGdF_(4):Dy@PDA-DNA(PDA=polydopamine)MRI probes.When aggregated,this probe can further amplify MRI signal intensity and exhibit improved geometrical and positional stability in vivo.The performance of the NaGdF_(4):Dy@PDA-DNA MRI probe toward MRI-guided preoperative planning and visualization-guided surgery is verified using an orthotopic tumor-bearing mouse model.The result shows that the rapid metabolism of the degraded probe leads to the mitigation of long-term toxic effects.Therefore,the developed high-performance MRI probe is of great significance for enhancing MRI diagnostic accuracy into precision medical therapeutic interventions.展开更多
The present work encompasses a new image enhancement algorithm using newly constructed Chebyshev fractional order differentiator. We have used Chebyshev polynomials to design Chebyshev fractional order differentiator....The present work encompasses a new image enhancement algorithm using newly constructed Chebyshev fractional order differentiator. We have used Chebyshev polynomials to design Chebyshev fractional order differentiator. We have generated the high pass filter corresponding to it. The designed filters are applied for decomposing the input image into four bands and low-low(L-L) sub-band is updated using correction coefficients. Reconstructed image with updated L-L sub-band provides the enhanced image. The visual results obtained are encouraging for image enhancement. The applicability of the developed algorithm is illustrated on three different test images.The effects of order of differentiation on the edges of images have also been presented and discussed.展开更多
Background Quantitative dynamic contrast enhancement MR imaging(DCE-MRI),used to measure properties of tissue microvasculature and tumor angiogenesis,is a promising method for distinguishing benign and malignant tumor...Background Quantitative dynamic contrast enhancement MR imaging(DCE-MRI),used to measure properties of tissue microvasculature and tumor angiogenesis,is a promising method for distinguishing benign and malignant tumors and characterizing tumor response to antiangiogenic treatment.The aim of this study was to assess the feasibility of quantitative parameters derived from clinically used DCE-MRI for distinguishing benign from malignant tumors in the sinonasal area,which may be potentially useful for prediction and monitoring of treatment response to chemoradiotherapy of sinonasal tumors.Methods One hundred and forty-three patients with sinonasal tumors,including 78 malignant tumors and 65 benign tumors and tumor-like lesions,underwent clinically used DCE-MRI.Parametric maps were obtained for quantitative parameters including Ktrans,kep and ve.Two radiologists reviewed these maps and measured Ktrans,kep and ve in the tumor tissue.Data were analyzed using independent T-test or Mann-Whitney U test analysis and receiver operating characteristic curves.Results Ktrans,kep and ve showed significant differences between benign and malignant tumors in the sinonasal area(P=-0.0001).The accuracy of Ktrans,kep and ve in differentiation between benign and malignant sinonasal tumors were 72.0%,76.2%and 67.1%,respectively.There were significant differences in kep and ve between malignant epithelial sinonasal tumors and lymphomas(P<0.05).Using a ve value of 0.213 as the threshold value differentiated malignant epithelial tumors from lymphomas with an accuracy of 78.3%,sensitivity of 88.2%,specificity of 68.0%,positive predictive value of 66.7%,and negative predictive value of 90.9%.However,no significant difference in Ktrans and kep was found between malignant epithelial and non-epithelial tumors in the sinonasal area(P>0.05).Conclusions It is feasible that quantitative parameters of tumors can be derived from clinically used DCE-MRI in the sinonasal region.Preliminary findings suggest an increased value for quantitative DCE-MRI in the evaluation of sinonasal tumors in clinical practice.展开更多
BACKGROUND Rectal cancer is a common malignant tumor of the digestive system,with older patients representing the predominantly affected population.Magnetic resonance imaging(MRI)has been widely applied in preoperativ...BACKGROUND Rectal cancer is a common malignant tumor of the digestive system,with older patients representing the predominantly affected population.Magnetic resonance imaging(MRI)has been widely applied in preoperative tumor assessment;however,the value of high-resolution MRI(HR-MRI)combined with dynamic contrast-enhanced(DCE)scanning in the preoperative diagnosis of rectal cancer in older patients remains unclear.AIM To evaluate the value of HR-MRI combined with DCE scanning in the preoperative diagnosis of rectal cancer in older patients.METHODS This retrospective study included 148 consecutive older female patients with rectal cancer who were treated at our hospital between December 2020 and December 2024.Clinical data and HR-MRI and DCE scan findings were collected.Histopathological examination after surgical resection served as the gold standard.The diagnostic accuracy of MRI for preoperative T and N staging was calculated.Consistency,sensitivity,and specificity between HR-MRI combined with DCE scanning and pathological staging were analyzed using the k test.Among the 148 patients,the overall accuracy of T staging was 84.5%.Sensitivity for T1,T2,T3,and T4 staging was 75.00%,62.50%,89.47%,and 90.48%,respectively,whereas specificity was 100.00%,94.35%,79.25%,and 96.06%,respectively.T staging based on HR-MRI combined with DCE scanning showed good agreement with pathological staging(k=0.8176,P<0.001).For N staging,sensitivity and specificity were 54.88%and 84.85%for N0,36.96%and 72.55%for N1,and 70.00%and 73.44%for N2,respectively;agreement with pathological N staging was poor(k=0.259,P<0.001).CONCLUSION HR-MRI combined with DCE scanning demonstrates high diagnostic accuracy for T staging of rectal cancer in older patients and can provide a theoretical basis for treatment planning.However,its diagnostic accuracy for N staging requires improvement.展开更多
AIM: To establish the extent to which contrast enhancement with SonoVue in combination with quantitative evaluation of contrast-medium dynamics facilitates the detection of hepatic tumors. METHODS: One hundred patient...AIM: To establish the extent to which contrast enhancement with SonoVue in combination with quantitative evaluation of contrast-medium dynamics facilitates the detection of hepatic tumors. METHODS: One hundred patients with histologically confirmed malignant or benign hepatic tumor (maximum size 5 cm) were analyzed. Contrast-enhanced ultrasound (bolus injection 2.5 mL SonoVue) was carried out with intermittent breath-holding technique using a multifrequency transducer (2.5-4 MHz). Native vascularization was analyzed with power Doppler. The contrast-enhanced dynamic ultrasound investigation was carried out with contrast harmonic imaging in true detection mode during the arterial,portal venous and late phases. Mechanical index was set at 0.15. Perfusion analysis was performed by post-processing of the raw data time intensity curve (TIC) analysis. The cut-off of the gray value differences between tumor and normal liver tissue was established using Receiver Operating Characteristic (ROC) analysis 64-line multi-slice computed tomography served as reference method in all cases. Magnetic resonance tomography was used additionally in 19 cases. RESULTS: One hundred patients with 59 malignant (43 colon,5 breast,2 endocrine metastases,7 hepatocellular carcinomas and 2 kidney cancers) and 41 benign (15 hemangiomas,7 focal nodular hyperplasias,5 complicated cysts,2 abscesses and 12 circumscribed fatty changes) tumors were included. The late venous phase proved to be the most sensitive for classification of the tumor type. Fifty-eight of the 59 malignant tumors were classified as true positive,and one as false negative. This resulted in a sensitivity of 98.3%. Of the 41 benign tumors,37 were classified as true negative and 4 as false negative,which corresponds to a specificity of 90.2%. Altogether,95.0% of the diagnoses were classified as correct on the basis of the histological classification. No investigator-dependency (P = 0.23) was noted. CONCLUSION: The results show the possibility of accurate prediction of malignancy of hepatic tumors with a positive prognostic value of 93.5% using advanced contrast-enhanced ultrasound. Contrast enhancement with SonoVue in combination with quantitative evaluation of contrast-medium dynamics is a valuable tool to discriminate hepatic tumors.展开更多
文摘AIM:To find the effective contrast enhancement method on retinal images for effective segmentation of retinal features.METHODS:A novel image preprocessing method that used neighbourhood-based improved contrast limited adaptive histogram equalization(NICLAHE)to improve retinal image contrast was suggested to aid in the accurate identification of retinal disorders and improve the visibility of fine retinal structures.Additionally,a minimal-order filter was applied to effectively denoise the images without compromising important retinal structures.The novel NICLAHE algorithm was inspired by the classical CLAHE algorithm,but enhanced it by selecting the clip limits and tile sized in a dynamical manner relative to the pixel values in an image as opposed to using fixed values.It was evaluated on the Drive and high-resolution fundus(HRF)datasets on conventional quality measures.RESULTS:The new proposed preprocessing technique was applied to two retinal image databases,Drive and HRF,with four quality metrics being,root mean square error(RMSE),peak signal to noise ratio(PSNR),root mean square contrast(RMSC),and overall contrast.The technique performed superiorly on both the data sets as compared to the traditional enhancement methods.In order to assess the compatibility of the method with automated diagnosis,a deep learning framework named ResNet was applied in the segmentation of retinal blood vessels.Sensitivity,specificity,precision and accuracy were used to analyse the performance.NICLAHE–enhanced images outperformed the traditional techniques on both the datasets with improved accuracy.CONCLUSION:NICLAHE provides better results than traditional methods with less error and improved contrastrelated values.These enhanced images are subsequently measured by sensitivity,specificity,precision,and accuracy,which yield a better result in both datasets.
基金Graduate Student Innovation Projects of Beijing University of Civil Engineering and Architecture(No.PG2024121)。
文摘Underwater images are inherently degraded by color distortion,contrast reduction,and uneven brightness,primarily due to light absorption and scattering in water.To mitigate these challenges,a novel enhancement approach is proposed,integrating Local Adaptive Color Correction(LACC)with contrast enhancement based on adaptive Rayleigh distribution stretching and CLAHE(LACC-RCE).Conventional color correction methods predominantly employ global adjustment strategies,which are often inadequate for handling spatially varying color distortions.In contrast,the proposed LACC method incorporates local color analysis,tone-weighted control,and spatially adaptive adjustments,allowing for region-specific color correction.This approach effectively enhances color fidelity and perceptual naturalness,addressing the limitations of global correction techniques.For contrast enhancement,the proposed method leverages the global mapping characteristics of the Rayleigh distribution to improve overall contrast,while CLAHE is employed to adaptively enhance local regions.A weighted fusion strategy is then applied to synthesize high-quality underwater images.Experimental results indicate that LACC-RCE surpasses conventional methods in color restoration,contrast optimization,and detail preservation,thereby enhancing the visual quality of underwater images.This improvement facilitates more reliable inputs for underwater object detection and recognition tasks.
文摘A novel wavelet-based algorithm for image enhancement is proposed in the paper. On the basis of multiscale analysis, the proposed algorithm solves efficiently the problem of noise over-enhancement, which commonly occurs in the traditional methods for contrast enhancement. The decomposed coefficients at same scales are processed by a nonlinear method, and the coefficients at different scales are enhanced in different degree. During the procedure, the method takes full advantage of the properties of Human visual system so as to achieve better performance. The simulations demonstrate that these characters of the proposed approach enable it to fully enhance the content in images, to efficiently alleviate the enhancement of noise and to achieve much better enhancement effect than the traditional approaches. Key words wavelet transform - image contrast enhancement - multiscale analysis CLC number TP 391 Foundation item: Supported by the National Natural Science Foundation of China (69931010)Biography: Wu Ying-qian (1974-), male, Ph. D, research direction: image processing, image compression and wavelet.
基金Sponsored by the National Key R&D Program of China(Grant No.2018YFB1308700)the Research and Development Project of Key Core Technology and Common Technology in Shanxi Province(Grant Nos.2020XXX001,2020XXX009)。
文摘Histogram equalization is a traditional algorithm improving the image contrast,but it comes at the cost of mean brightness shift and details loss.In order to solve these problems,a novel approach to processing foreground pixels and background pixels independently is proposed and investigated.Since details are mainly contained in the foreground,the weighted coupling of histogram equalization and Laplace transform were adopted to balance contrast enhancement and details preservation.The weighting factors of image foreground and background were determined by the amount of their respective information.The proposed method was conducted to images acquired from CVG⁃UGR and US⁃SIPI image databases and then compared with other methods such as clipping histogram spikes,histogram addition,and non⁃linear transformation to verify its validity.Results show that the proposed algorithm can effectively enhance the contrast without introducing distortions,and preserve the mean brightness and details well at the same time.
基金Supported by National Natural Science Foundation of China,under Grant No.6 0 2 710 15
文摘A new method of contrast enhancement is proposed in the paper using multiscale edge representation of images, and is applied to the field of CT medical image processing. Comparing to the traditional Window technique, our method is adaptive and meets the demand of radiology clinics more better. The clinical experiment results show the practicality and the potential applied value of our method in the field of CT medical images contrast enhancement.
基金This work was supported in part by National NSF of China(Nos.61872095,61872128,61571139 and 61201393)New Star of Pearl River on Science and Technology of Guangzhou(No.2014J2200085)+2 种基金the Open Project Program of Shenzhen Key Laboratory of Media Security(Grant No.ML-2018-03)the Opening Project of Guang Dong Province Key Laboratory of Information Security Technology(Grant No.2017B030314131-15)Natural Science Foundation of Xizang(No.2016ZR-MZ-01).
文摘This paper proposes a two-step general framework for reversible data hiding(RDH)schemes with controllable contrast enhancement.The first step aims at preserving visual perception as much as possible on the basis of achieving high embedding capacity(EC),while the second step is used for increasing image contrast.In the second step,some peak-pairs are utilized so that the histogram of pixel values is modified to perform histogram equalization(HE),which would lead to the image contrast enhancement.However,for HE,the utilization of some peak-pairs easily leads to over-enhanced image contrast when a large number of bits are embedded.Therefore,in our proposed framework,contrast over-enhancement is avoided by controlling the degree of contrast enhancement.Since the second step can only provide a small amount of data due to controlled contrast enhancement,the first one helps to achieve a large amount of data without degrading visual quality.Any RDH method which can achieve high EC while preserve good visual quality,can be selected for the first step.In fact,Gao et al.’s method is a special case of our proposed framework.In addition,two simple and commonly-used RDH methods are also introduced to further demonstrate the generalization of our framework.
基金This work was supported in part by the National Key Research and Development of China(2018YFC0807306)National NSF of China(U1936212,61672090)Beijing Fund-Municipal Education Commission Joint Project(KZ202010015023).
文摘As one of the most popular digital image manipulations,contrast enhancement(CE)is frequently applied to improve the visual quality of the forged images and conceal traces of forgery,therefore it can provide evidence of tampering when verifying the authenticity of digital images.Contrast enhancement forensics techniques have always drawn significant attention for image forensics community,although most approaches have obtained effective detection results,existing CE forensic methods exhibit poor performance when detecting enhanced images stored in the JPEG format.The detection of forgery on contrast adjustments in the presence of JPEG post processing is still a challenging task.In this paper,we propose a new CE forensic method based on convolutional neural network(CNN),which is robust to JPEG compression.The proposed network relies on a Xception-based CNN with two preprocessing strategies.Firstly,unlike the conventional CNNs which accepts the original image as its input,we feed the CNN with the gray-level co-occurrence matrix(GLCM)of image which contains CE fingerprints,then the constrained convolutional layer is used to extract high-frequency details in GLCMs under JPEG compression,finally the output of the constrained convolutional layer becomes the input of Xception to extract multiple features for further classification.Experimental results show that the proposed detector achieves the best performance for CE forensics under JPEG post-processing compared with the existing methods.
文摘A conventional global contrast enhancement is difficult to apply in various images because image quality and contrast enhancement are dependent on image characteristics largely. And a local contrast enhancement not only causes a washed-out effect, but also blocks. To solve these drawbacks, this paper derives an optimal global equalization function with variable size block based local contrast enhancement. The optimal equalization function makes it possible to get a good quality image through the global contrast enhancement. The variable size block segmentation is firstly exeoated using intensity differences as a measure of similarity. In the second step, the optimal global equalization function is obtained from the enhanced contrast image having variable size blocks. Conformed experiments have showed that the proposed algorithm produces a visually comfortable result image.
基金Supported by the Chongging Medical Scientific Research Project(Joint Project of Chongqing Health Commission and Science and Technology Bureau),No.2022QNXM013 and No.2023MSXM016.
文摘Determining whether sevoflurane sedation in children leads to“pseudo”prominent leptomeningeal contrast enhancement(pLMCE)on 3 Tesla magnetic resonance imaging will help reduce overdiagnosis by radiologists and clarify the pathophysiological changes of pLMCE.
基金supported in part by the National Natural Science Foundation of China under Grant No.61662039in part by the Jiangxi Key Natural Science Foundation under No.20192ACBL20031+1 种基金in part by the Startup Foundation for Introducing Talent of Nanjing University of Information Science and Technology(NUIST)under Grant No.2019r070in part by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)Fund.
文摘Recent contrast enhancement(CE)methods,with a few exceptions,predominantly focus on enhancing gray-scale images.This paper proposes a bi-histogram shifting contrast enhancement for color images based on the RGB(red,green,and blue)color model.The proposed method selects the two highest bins and two lowest bins from the image histogram,performs an equalized number of bidirectional histogram shifting repetitions on each RGB channel while embedding secret data into marked images.The proposed method simultaneously performs both right histogram shifting(RHS)and left histogram shifting(LHS)in each histogram shifting repetition to embed and split the highest bins while combining the lowest bins with their neighbors to achieve histogram equalization(HE).The least maximum number of histograms shifting repetitions among the three RGB channels is used as the default number of histograms shifting repetitions performed to enhance original images.Compared to an existing contrast enhancement method for color images and evaluated with PSNR,SSIM,RCE,and RMBE quality assessment metrics,the experimental results show that the proposed method's enhanced images are visually and qualitatively superior with a more evenly distributed histogram.The proposed method achieves higher embedding capacities and embedding rates in all images,with an average increase in embedding capacity of 52.1%.
基金This work was supported in part by the National Natural Science Foundation of China under Grant No.61662039in part by the Jiangxi Key Natural Science Foundation under No.20192ACBL20031+1 种基金in part by the Startup Foundation for Introducing Talent of Nanjing University of Information Science and Technology(NUIST)under Grant No.2019r070in part by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)Fund.
文摘Prior versions of reversible data hiding with contrast enhancement(RDHCE)algorithms strongly focused on enhancing the contrast of grayscale images.However,RDHCE has recently witnessed a rise in contrast enhance-ment algorithms concentrating on color images.This paper implies a method for color images that uses the RGB(red,green,and blue)color model and is based on bi-histogram shifting and image adjustment.Bi-histogram shifting is used to embed data and image adjustment to achieve contrast enhancement by adjusting the images resulting from each channel of the color images before combining them to generate the final enhanced image.Images are first divided into three channels-R,G,and B-and the Max,Med,and Min channels are then determined from these.Before histogram shifting,some calculations are done to determine how many iterations there will be for each channel.The images are adjusted to improve visual quality in the enhanced images after data has been embedded in each channel.The experimental results show that the enhanced images produced by the proposed method are qualitatively and aesthetically superior to those produced by some earlier methods,and their quality was assessed using PSNR,SSIM,RCE,RMBE,and CIEDE2000.The embedding rate obtained by the suggested method is acceptable.
基金funding provided by Universitàdegli Studi di Salerno within the CRUI-CARE Agreementsupported by Visiting Professors Program-UNISA Call 2022.
文摘We propose a new variational model in Sobolev-Orlicz spaces with non-standard growth conditions of the objective functional and discuss its applications to the simultaneous contrast enhancement and denoising of color images.The characteristic feature of the proposed model is that we deal with a constrained non-convex minimization problem that lives in variable Sobolev-Orlicz spaces where the variable exponent is unknown a priori and it depends on a particular function that belongs to the domain of the objective functional.In contrast to the standard approach,we do not apply any spatial regularization to the image gradient.We discuss the consistency of the variational model,give the scheme for its regularization,derive the corresponding optimality system,and propose an iterative algorithm for practical implementations.
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 Key Research and Development Program of China(Nos.2023YFC3502604,2022YFC2403902,2020YFC0841600,and 2020YFC0845000-4)the National Natural Science Foundation of China(Nos.82374302,82174533,82204941,and U23B2062)+3 种基金the Natural Science Foundation of Beijing(No.L232033)the Key R&D project of Ningxia Autonomous Region(No.2022BEG02036)the Noncommunicable Chronic Diseases-National Science and Technology Major Project(No.2023ZD0505700)the Fundamental Research Funds for the Central Universities(No.2024JBMC007).
文摘Medical Named Entity Recognition(NER)plays a crucial role in attaining precise patient portraits as well as providing support for intelligent diagnosis and treatment decisions.Federated Learning(FL)enables collaborative modeling and training across multiple endpoints without exposing the original data.However,the statistical heterogeneity exhibited by clinical medical text records poses a challenge for FL methods to support the training of NER models in such scenarios.We propose a Federated Contrast Enhancement(FedCE)method for NER to address the challenges faced by non-large-scale pre-trained models in FL for labelheterogeneous.The method leverages a multi-view encoder structure to capture both global and local semantic information,and employs contrastive learning to enhance the interoperability of global knowledge and local context.We evaluate the performance of the FedCE method on three real-world clinical record datasets.We investigate the impact of factors,such as pooling methods,maximum input text length,and training rounds on FedCE.Additionally,we assess how well FedCE adapts to the base NER models and evaluate its generalization performance.The experimental results show that the FedCE method has obvious advantages and can be effectively applied to various basic models,which is of great theoretical and practical significance for advancing FL in healthcare settings.
基金Supported by the National Natural Science Foundation of China under Grant Nos 11604350 and 61405211
文摘We demonstrate a novel picosecond optical parametric preamplification to generate high-stability, high-energy and high-contrast seed pulses. The 5ps seed pulse is amplified from 60pJ to 300μJ with an 8.6ps/ 3mJ pump laser in a signal stage of short pulse non-collinear optical parametric chirped pulse amplification. The total gain is more than 106 and the rms energy stability is under 1.35%. The contrast ratio is higher than 10s within a scale of 20ps before the main pulse. Consequently, the improvement factor of the signal contrast is approximately equal to the gain 106 outside the pump window.
基金supported by the National Natural Science Foundation of China(22134006,21721003,22204161,U2241287)the Natural Science Foundation of Shandong Province(ZR2020MB063)the Program of Science and Technology Development Plan of Jilin Province(20230101039JC)。
文摘Magnetic resonance imaging(MRI)plays an important role in precision medicine that is hampered by the lack of contrast agents with high efficiency and the ability to translate diagnostic accuracy into therapeutic intervention.Herein,we demonstrate a DNA-based MRI probe that overcomes previous single-mode enhancement and provides a mechanism of action for aggregationinduced dual-modal MRI signal enhancement.A facile method is developed to produce aggregated T_(1)/T_(2)dual-modal NaGdF_(4):Dy@PDA-DNA(PDA=polydopamine)MRI probes.When aggregated,this probe can further amplify MRI signal intensity and exhibit improved geometrical and positional stability in vivo.The performance of the NaGdF_(4):Dy@PDA-DNA MRI probe toward MRI-guided preoperative planning and visualization-guided surgery is verified using an orthotopic tumor-bearing mouse model.The result shows that the rapid metabolism of the degraded probe leads to the mitigation of long-term toxic effects.Therefore,the developed high-performance MRI probe is of great significance for enhancing MRI diagnostic accuracy into precision medical therapeutic interventions.
文摘The present work encompasses a new image enhancement algorithm using newly constructed Chebyshev fractional order differentiator. We have used Chebyshev polynomials to design Chebyshev fractional order differentiator. We have generated the high pass filter corresponding to it. The designed filters are applied for decomposing the input image into four bands and low-low(L-L) sub-band is updated using correction coefficients. Reconstructed image with updated L-L sub-band provides the enhanced image. The visual results obtained are encouraging for image enhancement. The applicability of the developed algorithm is illustrated on three different test images.The effects of order of differentiation on the edges of images have also been presented and discussed.
基金This work was supported by grants from Beijing Excellent Talents Foundation(No.2010D003034000033)Beijing Municipal Natural Science Foundation(No.7112030),High Levels of Health Technical Personnel in Beijing City(No.2011-3-047)China Postdoctoral Science Foundation(No.2011M500026).
文摘Background Quantitative dynamic contrast enhancement MR imaging(DCE-MRI),used to measure properties of tissue microvasculature and tumor angiogenesis,is a promising method for distinguishing benign and malignant tumors and characterizing tumor response to antiangiogenic treatment.The aim of this study was to assess the feasibility of quantitative parameters derived from clinically used DCE-MRI for distinguishing benign from malignant tumors in the sinonasal area,which may be potentially useful for prediction and monitoring of treatment response to chemoradiotherapy of sinonasal tumors.Methods One hundred and forty-three patients with sinonasal tumors,including 78 malignant tumors and 65 benign tumors and tumor-like lesions,underwent clinically used DCE-MRI.Parametric maps were obtained for quantitative parameters including Ktrans,kep and ve.Two radiologists reviewed these maps and measured Ktrans,kep and ve in the tumor tissue.Data were analyzed using independent T-test or Mann-Whitney U test analysis and receiver operating characteristic curves.Results Ktrans,kep and ve showed significant differences between benign and malignant tumors in the sinonasal area(P=-0.0001).The accuracy of Ktrans,kep and ve in differentiation between benign and malignant sinonasal tumors were 72.0%,76.2%and 67.1%,respectively.There were significant differences in kep and ve between malignant epithelial sinonasal tumors and lymphomas(P<0.05).Using a ve value of 0.213 as the threshold value differentiated malignant epithelial tumors from lymphomas with an accuracy of 78.3%,sensitivity of 88.2%,specificity of 68.0%,positive predictive value of 66.7%,and negative predictive value of 90.9%.However,no significant difference in Ktrans and kep was found between malignant epithelial and non-epithelial tumors in the sinonasal area(P>0.05).Conclusions It is feasible that quantitative parameters of tumors can be derived from clinically used DCE-MRI in the sinonasal region.Preliminary findings suggest an increased value for quantitative DCE-MRI in the evaluation of sinonasal tumors in clinical practice.
基金Supported by Tianjin Key Medical Discipline(Specialty)Construction Project,No.TJYXZDXK-3-012B.
文摘BACKGROUND Rectal cancer is a common malignant tumor of the digestive system,with older patients representing the predominantly affected population.Magnetic resonance imaging(MRI)has been widely applied in preoperative tumor assessment;however,the value of high-resolution MRI(HR-MRI)combined with dynamic contrast-enhanced(DCE)scanning in the preoperative diagnosis of rectal cancer in older patients remains unclear.AIM To evaluate the value of HR-MRI combined with DCE scanning in the preoperative diagnosis of rectal cancer in older patients.METHODS This retrospective study included 148 consecutive older female patients with rectal cancer who were treated at our hospital between December 2020 and December 2024.Clinical data and HR-MRI and DCE scan findings were collected.Histopathological examination after surgical resection served as the gold standard.The diagnostic accuracy of MRI for preoperative T and N staging was calculated.Consistency,sensitivity,and specificity between HR-MRI combined with DCE scanning and pathological staging were analyzed using the k test.Among the 148 patients,the overall accuracy of T staging was 84.5%.Sensitivity for T1,T2,T3,and T4 staging was 75.00%,62.50%,89.47%,and 90.48%,respectively,whereas specificity was 100.00%,94.35%,79.25%,and 96.06%,respectively.T staging based on HR-MRI combined with DCE scanning showed good agreement with pathological staging(k=0.8176,P<0.001).For N staging,sensitivity and specificity were 54.88%and 84.85%for N0,36.96%and 72.55%for N1,and 70.00%and 73.44%for N2,respectively;agreement with pathological N staging was poor(k=0.259,P<0.001).CONCLUSION HR-MRI combined with DCE scanning demonstrates high diagnostic accuracy for T staging of rectal cancer in older patients and can provide a theoretical basis for treatment planning.However,its diagnostic accuracy for N staging requires improvement.
文摘AIM: To establish the extent to which contrast enhancement with SonoVue in combination with quantitative evaluation of contrast-medium dynamics facilitates the detection of hepatic tumors. METHODS: One hundred patients with histologically confirmed malignant or benign hepatic tumor (maximum size 5 cm) were analyzed. Contrast-enhanced ultrasound (bolus injection 2.5 mL SonoVue) was carried out with intermittent breath-holding technique using a multifrequency transducer (2.5-4 MHz). Native vascularization was analyzed with power Doppler. The contrast-enhanced dynamic ultrasound investigation was carried out with contrast harmonic imaging in true detection mode during the arterial,portal venous and late phases. Mechanical index was set at 0.15. Perfusion analysis was performed by post-processing of the raw data time intensity curve (TIC) analysis. The cut-off of the gray value differences between tumor and normal liver tissue was established using Receiver Operating Characteristic (ROC) analysis 64-line multi-slice computed tomography served as reference method in all cases. Magnetic resonance tomography was used additionally in 19 cases. RESULTS: One hundred patients with 59 malignant (43 colon,5 breast,2 endocrine metastases,7 hepatocellular carcinomas and 2 kidney cancers) and 41 benign (15 hemangiomas,7 focal nodular hyperplasias,5 complicated cysts,2 abscesses and 12 circumscribed fatty changes) tumors were included. The late venous phase proved to be the most sensitive for classification of the tumor type. Fifty-eight of the 59 malignant tumors were classified as true positive,and one as false negative. This resulted in a sensitivity of 98.3%. Of the 41 benign tumors,37 were classified as true negative and 4 as false negative,which corresponds to a specificity of 90.2%. Altogether,95.0% of the diagnoses were classified as correct on the basis of the histological classification. No investigator-dependency (P = 0.23) was noted. CONCLUSION: The results show the possibility of accurate prediction of malignancy of hepatic tumors with a positive prognostic value of 93.5% using advanced contrast-enhanced ultrasound. Contrast enhancement with SonoVue in combination with quantitative evaluation of contrast-medium dynamics is a valuable tool to discriminate hepatic tumors.
