BACKGROUND It has been reported that deep learning-based reconstruction(DLR)can reduce image noise and artifacts,thereby improving the signal-to-noise ratio and image sharpness.However,no previous studies have evaluat...BACKGROUND It has been reported that deep learning-based reconstruction(DLR)can reduce image noise and artifacts,thereby improving the signal-to-noise ratio and image sharpness.However,no previous studies have evaluated the efficacy of DLR in improving image quality in reduced-field-of-view(reduced-FOV)diffusionweighted imaging(DWI)[field-of-view optimized and constrained undistorted single-shot(FOCUS)]of the pancreas.We hypothesized that a combination of these techniques would improve DWI image quality without prolonging the scan time but would influence the apparent diffusion coefficient calculation.AIM To evaluate the efficacy of DLR for image quality improvement of FOCUS of the pancreas.METHODS This was a retrospective study evaluated 37 patients with pancreatic cystic lesions who underwent magnetic resonance imaging between August 2021 and October 2021.We evaluated three types of FOCUS examinations:FOCUS with DLR(FOCUS-DLR+),FOCUS without DLR(FOCUS-DLR−),and conventional FOCUS(FOCUS-conv).The three types of FOCUS and their apparent diffusion coefficient(ADC)maps were compared qualitatively and quantitatively.RESULTS FOCUS-DLR+(3.62,average score of two radiologists)showed significantly better qualitative scores for image noise than FOCUS-DLR−(2.62)and FOCUS-conv(2.88)(P<0.05).Furthermore,FOCUS-DLR+showed the highest contrast ratio and 600 s/mm^(2)(0.72±0.08 and 0.68±0.08)and FOCUS-DLR−showed the highest CR between cystic lesions and the pancreatic parenchyma for the b-values of 0 and 600 s/mm2(0.62±0.21 and 0.62±0.21)(P<0.05),respectively.FOCUS-DLR+provided significantly higher ADCs of the pancreas and lesion(1.44±0.24 and 3.00±0.66)compared to FOCUS-DLR−(1.39±0.22 and 2.86±0.61)and significantly lower ADCs compared to FOCUS-conv(1.84±0.45 and 3.32±0.70)(P<0.05),respectively.CONCLUSION This study evaluated the efficacy of DLR for image quality improvement in reduced-FOV DWI of the pancreas.DLR can significantly denoise images without prolonging the scan time or decreasing the spatial resolution.The denoising level of DWI can be controlled to make the images appear more natural to the human eye.However,this study revealed that DLR did not ameliorate pancreatic distortion.Additionally,physicians should pay attention to the interpretation of ADCs after DLR application because ADCs are significantly changed by DLR.展开更多
Purpose:To assess the clinical efficacy of integrating deep learning reconstruction(DLR)with contrast-enhancement-boost(CE-boost)in 80 kVp head and neck CT angiography(CTA)using substantially lowered radiation and con...Purpose:To assess the clinical efficacy of integrating deep learning reconstruction(DLR)with contrast-enhancement-boost(CE-boost)in 80 kVp head and neck CT angiography(CTA)using substantially lowered radiation and contrast medium(CM)doses,compared to the standard 100 kVp protocol using hybrid iterative reconstruction(HIR).Methods:Sixty-six patients were prospectively enrolled and randomly assigned to one of two groups:the low-dose group(n=33),receiving 80 kVp and 28 mL contrast medium(CM)with a noise index(NI)of 15;and the regular-dose group(n=33),receiving 100 kVp and 40 mL CM with an NI of 10.For the lowdose group,images underwent reconstruction using both hybrid iterative reconstruction(HIR)and deep learning reconstruction(DLR)at mild-,standard-,and strong-strength levels,both before and after combination with contrast enhancement-boost(CE-boost).This generated eight distinct datasets:L-HIR,L-DLR_(mild),L-DLR_(standard),L-DLR_(strong),L-HIR-CE,L-DLR_(mild)-CE,L-DLR_(standard)-CE,and L-DLR_(strong)-CE.Images for the regular-dose group were reconstructed solely with HIR(R-HIR).Quantitative analysis involved calculating and comparing CT attenuation,image noise,signal-to-noise ratio(SNR),and contrast-to-noise ratio(CNR)within six key vessels:the aortic arch(AA),internal carotid artery(ICA),external carotid artery(ECA),vertebral arteries(VA),basilar artery(BA),and middle cerebral artery(MCA).Two radiologists independently assessed subjective image quality using a 5-point scale,with statistical significance defined as P<0.05.Results:Compared to the regular-dose group,the low-dose protocol achieved a substantial reduction in contrast media volume(28 mL versus 40 mL,a 30%decrease)and radiation exposure((0.41±0.08)mSv versus(1.18±0.12)mSv,a 65%reduction).Both L-DLR_(standard) and L-DLR_(strong) delivered comparable or superior SNR and CNR across all vascular segments relative to R-HIR.However,subjective image quality scores for L-DLR at all strength levels fell below those for R-HIR(all P<0.05 for both readers).Combining CE-boost with the low-dose protocol significantly enhanced the objective image performance of L-DLR_(strong)-CE(all P<0.05)and produced subjective image scores comparable to R-HIR(reader 1:P=0.15;reader 2:P=0.06).Conclusion:When compared to the standard 100 kVp head and neck CTA,the combination of the DLR and CE-boost techniques at 80 kVp can achieve a 30%reduction in contrast dose and a 65%reduction in radiation dose,while maintaining both objective and subjective image quality.展开更多
Objective To compare the impact of different reconstruction algorithms on the image quality of 60 kVp head and neck CT angiography(CTA)using subjective and objective metrics,with a focus on vessel edge sharpness.Metho...Objective To compare the impact of different reconstruction algorithms on the image quality of 60 kVp head and neck CT angiography(CTA)using subjective and objective metrics,with a focus on vessel edge sharpness.Methods This prospective study enrolled 45 patients who underwent ultra-low-voltage(60 kVp)head and neck CTA.Image datasets were reconstructed with filtered back-projection(FBP),ClearView(CV)and ClearInfinity(CI)algorithms at low(30%),medium(50%),and high(70%)strengths.Image quality was assessed subjectively and objectively via the Kruskal‒Wallis test for multiple comparisons.Objective parameters,including edge rise slope(ERS)and edge rise distance(ERD),were analyzed via the Friedman test of multiple comparisons statistics.Results Subjective assessments favored the CI50 reconstruction algorithm,demonstrating superior or satisfactory results compared to the other algorithms,with significantly better vessel delineation,edge definition and diagnostic confidence(all P<0.05).Objective analysis revealed that the CV50 and CV70 algorithms significantly reduced ERS and/or elevated ERD(both P<0.05).However,the CI50 algorithm maintained comparable vessel edge sharpness(P>0.05)across all evaluated head and neck vascular segments when compared with the FBP algorithm.Conclusions The CI50 reconstruction algorithm optimizes image quality in 60 kVp head and neck CTA.It provides vessel edge sharpness comparable to FBP while offering superior vessel delineation,edge definition,and diagnostic confidence compared to FBP and CV algorithm.These findings suggest that CI50 has the potential to improve diagnostic accuracy in low-dose vascular imaging.展开更多
With increasingly more smart cameras deployed in infrastructure and commercial buildings,3D reconstruction can quickly obtain cities’information and improve the efficiency of government services.Images collected in o...With increasingly more smart cameras deployed in infrastructure and commercial buildings,3D reconstruction can quickly obtain cities’information and improve the efficiency of government services.Images collected in outdoor hazy environments are prone to color distortion and low contrast;thus,the desired visual effect cannot be achieved and the difficulty of target detection is increased.Artificial intelligence(AI)solutions provide great help for dehazy images,which can automatically identify patterns or monitor the environment.Therefore,we propose a 3D reconstruction method of dehazed images for smart cities based on deep learning.First,we propose a fine transmission image deep convolutional regression network(FT-DCRN)dehazing algorithm that uses fine transmission image and atmospheric light value to compute dehazed image.The DCRN is used to obtain the coarse transmission image,which can not only expand the receptive field of the network but also retain the features to maintain the nonlinearity of the overall network.The fine transmission image is obtained by refining the coarse transmission image using a guided filter.The atmospheric light value is estimated according to the position and brightness of the pixels in the original hazy image.Second,we use the dehazed images generated by the FT-DCRN dehazing algorithm for 3D reconstruction.An advanced relaxed iterative fine matching based on the structure from motion(ARI-SFM)algorithm is proposed.The ARISFM algorithm,which obtains the fine matching corner pairs and reduces the number of iterations,establishes an accurate one-to-one matching corner relationship.The experimental results show that our FT-DCRN dehazing algorithm improves the accuracy compared to other representative algorithms.In addition,the ARI-SFM algorithm guarantees the precision and improves the efficiency.展开更多
Abdominal magnetic resonance imaging(MRI)and computed tomography(CT)are commonly used for disease screening,diagnosis,and treatment guidance.However,abdominal MRI has disadvantages including slow speed and vulnerabili...Abdominal magnetic resonance imaging(MRI)and computed tomography(CT)are commonly used for disease screening,diagnosis,and treatment guidance.However,abdominal MRI has disadvantages including slow speed and vulnerability to motions,while CT suffers from problems of radiation.It has been reported that deep learning reconstruction can solve such problems while maintaining good image quality.Recently,deep learning-based image reconstruction has become a hot topic in the field of medical imaging.This study reviews the latest research on deep learning reconstruction in abdominal imaging,including the widely used convolutional neural network,generative adversarial network,and recurrent neural network.展开更多
The three-dimensional(3D)model is of great significance to analyze the performance of nonwovens.However,the existing modelling methods could not reconstruct the 3D structure of nonwovens at low cost.A new method based...The three-dimensional(3D)model is of great significance to analyze the performance of nonwovens.However,the existing modelling methods could not reconstruct the 3D structure of nonwovens at low cost.A new method based on deep learning was proposed to reconstruct 3D models of nonwovens from multi-focus images.A convolutional neural network was trained to extract clear fibers from sequence images.Image processing algorithms were used to obtain the radius,the central axis,and depth information of fibers from the extraction results.Based on this information,3D models were built in 3D space.Furthermore,self-developed algorithms optimized the central axis and depth of fibers,which made fibers more realistic and continuous.The method with lower cost could reconstruct 3D models of nonwovens conveniently.展开更多
Photoacoustic imaging(PAI)is a noninvasive emerging imaging method based on the photoacoustic effect,which provides necessary assistance for medical diagnosis.It has the characteristics of large imaging depth and high...Photoacoustic imaging(PAI)is a noninvasive emerging imaging method based on the photoacoustic effect,which provides necessary assistance for medical diagnosis.It has the characteristics of large imaging depth and high contrast.However,limited by the equipment cost and reconstruction time requirements,the existing PAI systems distributed with annular array transducers are difficult to take into account both the image quality and the imaging speed.In this paper,a triple-path feature transform network(TFT-Net)for ring-array photoacoustic tomography is proposed to enhance the imaging quality from limited-view and sparse measurement data.Specifically,the network combines the raw photoacoustic pressure signals and conventional linear reconstruction images as input data,and takes the photoacoustic physical model as a prior information to guide the reconstruction process.In addition,to enhance the ability of extracting signal features,the residual block and squeeze and excitation block are introduced into the TFT-Net.For further efficient reconstruction,the final output of photoacoustic signals uses‘filter-then-upsample’operation with a pixel-shuffle multiplexer and a max out module.Experiment results on simulated and in-vivo data demonstrate that the constructed TFT-Net can restore the target boundary clearly,reduce background noise,and realize fast and high-quality photoacoustic image reconstruction of limited view with sparse sampling.展开更多
In this editorial,we review recent progress on the applications of artificial intelligence(AI)in image reconstruction for biomedical imaging.Because it abandons prior information of traditional artificial design and a...In this editorial,we review recent progress on the applications of artificial intelligence(AI)in image reconstruction for biomedical imaging.Because it abandons prior information of traditional artificial design and adopts a completely data-driven mode to obtain deeper prior information via learning,AI technology plays an increasingly important role in biomedical image reconstruction.The combination of AI technology and the biomedical image reconstruction method has become a hotspot in the field.Favoring AI,the performance of biomedical image reconstruction has been improved in terms of accuracy,resolution,imaging speed,etc.We specifically focus on how to use AI technology to improve the performance of biomedical image reconstruction,and propose possible future directions in this field.展开更多
The algorithm used for reconstruction or resolution enhancement is one of the factors affectingthe quality of super-resolution images obtained by fluorescence microscopy.Deep-learning-basedalgorithms have achieved sta...The algorithm used for reconstruction or resolution enhancement is one of the factors affectingthe quality of super-resolution images obtained by fluorescence microscopy.Deep-learning-basedalgorithms have achieved stateof-the-art performance in super-resolution fluorescence micros-copy and are becoming increasingly attractive.We firstly introduce commonly-used deep learningmodels,and then review the latest applications in terms of the net work architectures,the trainingdata and the loss functions.Additionally,we discuss the challenges and limits when using deeplearning to analyze the fluorescence microscopic data,and suggest ways to improve the reliability and robustness of deep learning applications.展开更多
Multispectral imaging,which simultaneously captures the spatial and spectral information of a scene,is widely used across diverse fields,including remote sensing,biomedical imaging,and agricultural monitoring.We intro...Multispectral imaging,which simultaneously captures the spatial and spectral information of a scene,is widely used across diverse fields,including remote sensing,biomedical imaging,and agricultural monitoring.We introduce a snapshot multispectral imaging approach employing a standard monochrome image sensor with no additional spectral filters or customized components.Our system leverages the inherent chromatic aberration of wavelength-dependent defocusing as a natural source of physical encoding of multispectral information;this encoded image information is rapidly decoded via a deep learning-based multispectral Fourier imager network(mFIN).We experimentally tested our method with six illumination bands and demonstrated an overall accuracy of 98.25%for predicting the illumination channels at the input and achieved a robust multispectral image reconstruction on various test objects.This deep learning-powered framework achieves high-quality multispectral image reconstruction using snapshot image acquisition with a monochrome image sensor and could be useful for applications in biomedicine,industrial quality control,and agriculture,among others.展开更多
3D medical image reconstruction has significantly enhanced diagnostic accuracy,yet the reliance on densely sampled projection data remains a major limitation in clinical practice.Sparse-angle X-ray imaging,though safe...3D medical image reconstruction has significantly enhanced diagnostic accuracy,yet the reliance on densely sampled projection data remains a major limitation in clinical practice.Sparse-angle X-ray imaging,though safer and faster,poses challenges for accurate volumetric reconstruction due to limited spatial information.This study proposes a 3D reconstruction neural network based on adaptive weight fusion(AdapFusionNet)to achieve high-quality 3D medical image reconstruction from sparse-angle X-ray images.To address the issue of spatial inconsistency in multi-angle image reconstruction,an innovative adaptive fusion module was designed to score initial reconstruction results during the inference stage and perform weighted fusion,thereby improving the final reconstruction quality.The reconstruction network is built on an autoencoder(AE)framework and uses orthogonal-angle X-ray images(frontal and lateral projections)as inputs.The encoder extracts 2D features,which the decoder maps into 3D space.This study utilizes a lung CT dataset to obtain complete three-dimensional volumetric data,from which digitally reconstructed radiographs(DRR)are generated at various angles to simulate X-ray images.Since real-world clinical X-ray images rarely come with perfectly corresponding 3D“ground truth,”using CT scans as the three-dimensional reference effectively supports the training and evaluation of deep networks for sparse-angle X-ray 3D reconstruction.Experiments conducted on the LIDC-IDRI dataset with simulated X-ray images(DRR images)as training data demonstrate the superior performance of AdapFusionNet compared to other fusion methods.Quantitative results show that AdapFusionNet achieves SSIM,PSNR,and MAE values of 0.332,13.404,and 0.163,respectively,outperforming other methods(SingleViewNet:0.289,12.363,0.182;AvgFusionNet:0.306,13.384,0.159).Qualitative analysis further confirms that AdapFusionNet significantly enhances the reconstruction of lung and chest contours while effectively reducing noise during the reconstruction process.The findings demonstrate that AdapFusionNet offers significant advantages in 3D reconstruction of sparse-angle X-ray images.展开更多
In agricultural production,crop images are commonly used for the classification and identification of various crops.However,several challenges arise,including low image clarity,elevated noise levels,low accuracy,and p...In agricultural production,crop images are commonly used for the classification and identification of various crops.However,several challenges arise,including low image clarity,elevated noise levels,low accuracy,and poor robustness of existing classification models.To address these issues,this research proposes an innovative crop image classification model named Lap-FEHRNet,which integrates a Laplacian Pyramid Super Resolution Network(LapSRN)with a feature enhancement high-resolution network based on attention mechanisms(FEHRNet).To mitigate noise interference,this research incorporates the LapSRN network,which utilizes a Laplacian pyramid structure to extract multi-level feature details from low-resolution images through a systematic layer-by-layer amplification and pixel detail superposition process.This gradual reconstruction enhances the high-frequency information of the image,enabling super-resolution reconstruction of low-quality images.To obtain a broader range of comprehensive and diverse features,this research employs the FEHRNetmodel for both deep and shallow feature extraction.This approach results in features that encapsulate multi-scale information and integrate both deep and shallow insights.To effectively fuse these complementary features,this research introduces an attention mechanism during the feature enhancement stage.This mechanism highlights important regions within the image,assigning greater weights to salient features and resulting in a more comprehensive and effective image feature representation.Consequently,the accuracy of image classification is significantly improved.Experimental results demonstrate that the Lap-FEHRNetmodel achieves impressive classification accuracies of 98.8%on the crop classification dataset and 98.57%on the rice leaf disease dataset,underscoring the model’s outstanding accuracy,robustness,and generalization capability.展开更多
Three-dimensional (3D) visualization of dynamic biological processes in deep tissue remains challenging due to the trade-off between temporal resolution and imaging depth. Here, we present a novel near-infrared-II (NI...Three-dimensional (3D) visualization of dynamic biological processes in deep tissue remains challenging due to the trade-off between temporal resolution and imaging depth. Here, we present a novel near-infrared-II (NIR-II, 900–1880nm) fluorescence volumetric microscopic imaging method that combines an electrically tunable lens (ETL) with deep learning approaches for rapid 3D imaging. The technology achieves volumetric imaging at 4.2 frames per second (fps) across a 200 μm depth range in live mouse brain vasculature. Two specialized neural networks are utilized: a scale-recurrent network (SRN) for image enhancement and a cerebral vessel interpolation (CVI) network that enables 16-fold axial upsampling. The SRN, trained on two-photon fluorescence microscopic data, improves both lateral and axial resolution of NIR-II fluorescence wide-field microscopic images. The CVI network, adapted from video interpolation techniques, generates intermediate frames between acquired axial planes, resulting in smooth and continuous 3D vessel reconstructions. Using this integrated system, we visualize and quantify blood flow dynamics in individual vessels and are capable of measuring blood velocity at different depths. This approach maintains high lateral resolution while achieving rapid volumetric imaging, and is particularly suitable for studying dynamic vascular processes in deep tissue. Our method demonstrates the potential of combining optical engineering with artificial intelligence to advance biological imaging capabilities.展开更多
Deep learning is capable of greatly promoting the progress of super-resolution imaging technology in terms of imaging and reconstruction speed,imaging resolution,and imagingflux.This paper proposes a deep neural netwo...Deep learning is capable of greatly promoting the progress of super-resolution imaging technology in terms of imaging and reconstruction speed,imaging resolution,and imagingflux.This paper proposes a deep neural network based on a generative adversarial network(GAN).The generator employs a U-Net-based network,which integrates Dense Net for the downsampling component.The proposed method has excellent properties,for example,the network model is trained with several different datasets of biological structures;the trained model can improve the imaging resolution of different microscopy imaging modalities such as confocal imaging and wide-field imaging;and the model demonstrates a generalized ability to improve the resolution of different biological structures even out of the datasets.In addition,experimental results showed that the method improved the resolution of caveolin-coated pits(CCPs)structures from 264 nm to 138 nm,a 1.91-fold increase,and nearly doubled the resolution of DNA molecules imaged while being transported through microfluidic channels.展开更多
Deep learning(DL)has shown unprecedented performance for many image analysis and image enhancement tasks.Yet,solving large-scale inverse problems like tomographic reconstruction remains challenging for DL.These proble...Deep learning(DL)has shown unprecedented performance for many image analysis and image enhancement tasks.Yet,solving large-scale inverse problems like tomographic reconstruction remains challenging for DL.These problems involve non-local and space-variant integral transforms between the input and output domains,for which no efficient neural network models are readily available.A prior attempt to solve tomographic reconstruction problems with supervised learning relied on a brute-force fully connected network and only allowed reconstruction with a 128^(4)system matrix size.This cannot practically scale to realistic data sizes such as 512^(4)and 512^(6)for three-dimensional datasets.Here we present a novel framework to solve such problems with DL by casting the original problem as a continuum of intermediate representations between the input and output domains.The original problem is broken down into a sequence of simpler transformations that can be well mapped onto an efficient hierarchical network architecture,with exponentially fewer parameters than a fully connected network would need.We applied the approach to computed tomography(CT)image reconstruction for a 5124 system matrix size.This work introduces a new kind of data-driven DL solver for full-size CT reconstruction without relying on the structure of direct(analytical)or iterative(numerical)inversion techniques.This work presents a feasibility demonstration of full-scale learnt reconstruction,whereas more developments will be needed to demonstrate superiority relative to traditional reconstruction approaches.The proposed approach is also extendable to other imaging problems such as emission and magnetic resonance reconstruction.More broadly,hierarchical DL opens the door to a new class of solvers for general inverse problems,which could potentially lead to improved signal-to-noise ratio,spatial resolution and computational efficiency in various areas.展开更多
Single image super resolution(SISR)techniques produce images of high resolution(HR)as output from input images of low resolution(LR).Motivated by the effectiveness of deep learning methods,we provide a framework based...Single image super resolution(SISR)techniques produce images of high resolution(HR)as output from input images of low resolution(LR).Motivated by the effectiveness of deep learning methods,we provide a framework based on deep learning to achieve super resolution(SR)by utilizing deep singular-residual neural network(DSRNN)in training phase.Residuals are obtained from the difference between HR and LR images to generate LR-residual example pairs.Singular value decomposition(SVD)is applied to each LR-residual image pair to decompose into subbands of low and high frequency components.Later,DSRNN is trained on these subbands through input and output channels by optimizing the weights and biases of the network.With fewer layers in DSRNN,the influence of exploding gradients is reduced.This speeds up the learning process and also improves accuracy by using skip connections.The trained DSRNN parameters yield residuals to recover the HR subbands in the testing phase.Experimental analysis shows that the proposed method results in superior performance to existingmethods in terms of subjective quality.Extensive testing results on popular benchmark datasets such as set5,set14,and urban100 for a scaling factor of 4 show the effectiveness of the proposed method across different qualitative evaluation metrics.展开更多
Early diagnosis and accurate prognosis of colorectal cancer is critical for determining optimal treatment plans and maximizing patient outcomes,especially as the disease progresses into liver metastases.Computed tomog...Early diagnosis and accurate prognosis of colorectal cancer is critical for determining optimal treatment plans and maximizing patient outcomes,especially as the disease progresses into liver metastases.Computed tomography(CT)is a frontline tool for this task;however,the preservation of predictive radiomic features is highly dependent on the scanning protocol and reconstruction algorithm.We hypothesized that image reconstruction with a highfrequency kernel could result in a better characterization of liver metastases features via deep neural networks.This kernel produces images that appear noisier but preserve more sinogram information.A simulation pipeline was developed to study the effects of imaging parameters on the ability to characterize the features of liver metastases.This pipeline utilizes a fractal approach to generate a diverse population of shapes representing virtual metastases,and then it superimposes them on a realistic CT liver region to perform a virtual CT scan using CatSim.Datasets of 10,000 liver metastases were generated,scanned,and reconstructed using either standard or high-frequency kernels.These data were used to train and validate deep neural networks to recover crafted metastases characteristics,such as internal heterogeneity,edge sharpness,and edge fractal dimension.In the absence of noise,models scored,on average,12.2%(α=0.012)and 7.5%(α=0.049)lower squared error for characterizing edge sharpness and fractal dimension,respectively,when using high-frequency reconstructions compared to standard.However,the differences in performance were statistically insignificant when a typical level of CT noise was simulated in the clinical scan.Our results suggest that high-frequency reconstruction kernels can better preserve information for downstream artificial intelligence-based radiomic characterization,provided that noise is limited.Future work should investigate the informationpreserving kernels in datasets with clinical labels.展开更多
4-Dimensional cone-beam computed tomography(4D-CBCT)offers several key advantages over conventional 3DCBCT in moving target localization/delineation,structure de-blurring,target motion tracking,treatment dose accumul...4-Dimensional cone-beam computed tomography(4D-CBCT)offers several key advantages over conventional 3DCBCT in moving target localization/delineation,structure de-blurring,target motion tracking,treatment dose accumulation and adaptive radiation therapy.However,the use of the 4D-CBCT in current radiation therapy practices has been limited,mostly due to its sub-optimal image quality from limited angular sampling of conebeam projections.In this study,we summarized the recent developments of 4D-CBCT reconstruction techniques for image quality improvement,and introduced our developments of a new 4D-CBCT reconstruction technique which features simultaneous motion estimation and image reconstruction(SMEIR).Based on the original SMEIR scheme,biomechanical modeling-guided SMEIR(SMEIR-Bio)was introduced to further improve the reconstruction accuracy of fine details in lung 4D-CBCTs.To improve the efficiency of reconstruction,we recently developed a U-net-based deformation-vector-field(DVF)optimization technique to leverage a population-based deep learning scheme to improve the accuracy of intra-lung DVFs(SMEIR-Unet),without explicit biomechanical modeling.Details of each of the SMEIR,SMEIR-Bio and SMEIR-Unet techniques were included in this study,along with the corresponding results comparing the reconstruction accuracy in terms of CBCT images and the DVFs.We also discussed the application prospects of the SMEIR-type techniques in image-guided radiation therapy and adaptive radiation therapy,and presented potential schemes on future developments to achieve faster and more accurate 4D-CBCT imaging.展开更多
In order to reconstruct and render the weak and repetitive texture of the damaged functional surface of aviation,an improved neural radiance field,named TranSR-NeRF,is proposed.In this paper,a data acquisition system ...In order to reconstruct and render the weak and repetitive texture of the damaged functional surface of aviation,an improved neural radiance field,named TranSR-NeRF,is proposed.In this paper,a data acquisition system was designed and built.The acquired images generated initial point clouds through TransMVSNet.Meanwhile,after extracting features from the images through the improved SE-ConvNeXt network,the extracted features were aligned and fused with the initial point cloud to generate high-quality neural point cloud.After ray-tracing and sampling of the neural point cloud,the ResMLP neural network designed in this paper was used to regress the volume density and radiance under a given viewing angle,which introduced spatial coordinate and relative positional encoding.The reconstruction and rendering of arbitrary-scale super-resolution of damaged functional surface is realized.In this paper,the influence of illumination conditions and background environment on the model performance is also studied through experiments,and the comparison and ablation experiments for the improved methods proposed in this paper is conducted.The experimental results show that the improved model has good effect.Finally,the application experiment of object detection task is carried out,and the experimental results show that the model has good practicability.展开更多
Over recent years,the importance of the patent literature has become increasingly more recognized in the aca-demic setting.In the context of artificial intelligence,deep learning,and data sciences,patents are relevant...Over recent years,the importance of the patent literature has become increasingly more recognized in the aca-demic setting.In the context of artificial intelligence,deep learning,and data sciences,patents are relevant to not only industry but also academe and other communities.In this article,we focus on deep tomographic imaging and perform a preliminary landscape analysis of the related patent literature.Our search tool is PatSeer.Our patent biblio-metric data is summarized in various figures and tables.In particular,we qualitatively analyze key deep tomographic patent literature.展开更多
文摘BACKGROUND It has been reported that deep learning-based reconstruction(DLR)can reduce image noise and artifacts,thereby improving the signal-to-noise ratio and image sharpness.However,no previous studies have evaluated the efficacy of DLR in improving image quality in reduced-field-of-view(reduced-FOV)diffusionweighted imaging(DWI)[field-of-view optimized and constrained undistorted single-shot(FOCUS)]of the pancreas.We hypothesized that a combination of these techniques would improve DWI image quality without prolonging the scan time but would influence the apparent diffusion coefficient calculation.AIM To evaluate the efficacy of DLR for image quality improvement of FOCUS of the pancreas.METHODS This was a retrospective study evaluated 37 patients with pancreatic cystic lesions who underwent magnetic resonance imaging between August 2021 and October 2021.We evaluated three types of FOCUS examinations:FOCUS with DLR(FOCUS-DLR+),FOCUS without DLR(FOCUS-DLR−),and conventional FOCUS(FOCUS-conv).The three types of FOCUS and their apparent diffusion coefficient(ADC)maps were compared qualitatively and quantitatively.RESULTS FOCUS-DLR+(3.62,average score of two radiologists)showed significantly better qualitative scores for image noise than FOCUS-DLR−(2.62)and FOCUS-conv(2.88)(P<0.05).Furthermore,FOCUS-DLR+showed the highest contrast ratio and 600 s/mm^(2)(0.72±0.08 and 0.68±0.08)and FOCUS-DLR−showed the highest CR between cystic lesions and the pancreatic parenchyma for the b-values of 0 and 600 s/mm2(0.62±0.21 and 0.62±0.21)(P<0.05),respectively.FOCUS-DLR+provided significantly higher ADCs of the pancreas and lesion(1.44±0.24 and 3.00±0.66)compared to FOCUS-DLR−(1.39±0.22 and 2.86±0.61)and significantly lower ADCs compared to FOCUS-conv(1.84±0.45 and 3.32±0.70)(P<0.05),respectively.CONCLUSION This study evaluated the efficacy of DLR for image quality improvement in reduced-FOV DWI of the pancreas.DLR can significantly denoise images without prolonging the scan time or decreasing the spatial resolution.The denoising level of DWI can be controlled to make the images appear more natural to the human eye.However,this study revealed that DLR did not ameliorate pancreatic distortion.Additionally,physicians should pay attention to the interpretation of ADCs after DLR application because ADCs are significantly changed by DLR.
基金National Natural Science Foundation of China(82001814)National High Level Hospital Clinical Research Funding(grant number 2022-PUMCH-B-067)+1 种基金National High Level Hospital Clinical Research Funding(grant number 2022-PUMCH-B-068)2021 SKY Imaging Research Fund of the Chinese Internatinal Medical Foundation(Z-2014-07-2101).
文摘Purpose:To assess the clinical efficacy of integrating deep learning reconstruction(DLR)with contrast-enhancement-boost(CE-boost)in 80 kVp head and neck CT angiography(CTA)using substantially lowered radiation and contrast medium(CM)doses,compared to the standard 100 kVp protocol using hybrid iterative reconstruction(HIR).Methods:Sixty-six patients were prospectively enrolled and randomly assigned to one of two groups:the low-dose group(n=33),receiving 80 kVp and 28 mL contrast medium(CM)with a noise index(NI)of 15;and the regular-dose group(n=33),receiving 100 kVp and 40 mL CM with an NI of 10.For the lowdose group,images underwent reconstruction using both hybrid iterative reconstruction(HIR)and deep learning reconstruction(DLR)at mild-,standard-,and strong-strength levels,both before and after combination with contrast enhancement-boost(CE-boost).This generated eight distinct datasets:L-HIR,L-DLR_(mild),L-DLR_(standard),L-DLR_(strong),L-HIR-CE,L-DLR_(mild)-CE,L-DLR_(standard)-CE,and L-DLR_(strong)-CE.Images for the regular-dose group were reconstructed solely with HIR(R-HIR).Quantitative analysis involved calculating and comparing CT attenuation,image noise,signal-to-noise ratio(SNR),and contrast-to-noise ratio(CNR)within six key vessels:the aortic arch(AA),internal carotid artery(ICA),external carotid artery(ECA),vertebral arteries(VA),basilar artery(BA),and middle cerebral artery(MCA).Two radiologists independently assessed subjective image quality using a 5-point scale,with statistical significance defined as P<0.05.Results:Compared to the regular-dose group,the low-dose protocol achieved a substantial reduction in contrast media volume(28 mL versus 40 mL,a 30%decrease)and radiation exposure((0.41±0.08)mSv versus(1.18±0.12)mSv,a 65%reduction).Both L-DLR_(standard) and L-DLR_(strong) delivered comparable or superior SNR and CNR across all vascular segments relative to R-HIR.However,subjective image quality scores for L-DLR at all strength levels fell below those for R-HIR(all P<0.05 for both readers).Combining CE-boost with the low-dose protocol significantly enhanced the objective image performance of L-DLR_(strong)-CE(all P<0.05)and produced subjective image scores comparable to R-HIR(reader 1:P=0.15;reader 2:P=0.06).Conclusion:When compared to the standard 100 kVp head and neck CTA,the combination of the DLR and CE-boost techniques at 80 kVp can achieve a 30%reduction in contrast dose and a 65%reduction in radiation dose,while maintaining both objective and subjective image quality.
基金the Grant from the National Key Research and Development Program of China(No.2024YFC2419300)the National Natural Science Foundation of China(No.82471967)+1 种基金the Hubei Provincial Key Research and Development Program(No.2024BCB008)the Hubei Provincial Natural Science Foundation of China(No.2025AFB733).
文摘Objective To compare the impact of different reconstruction algorithms on the image quality of 60 kVp head and neck CT angiography(CTA)using subjective and objective metrics,with a focus on vessel edge sharpness.Methods This prospective study enrolled 45 patients who underwent ultra-low-voltage(60 kVp)head and neck CTA.Image datasets were reconstructed with filtered back-projection(FBP),ClearView(CV)and ClearInfinity(CI)algorithms at low(30%),medium(50%),and high(70%)strengths.Image quality was assessed subjectively and objectively via the Kruskal‒Wallis test for multiple comparisons.Objective parameters,including edge rise slope(ERS)and edge rise distance(ERD),were analyzed via the Friedman test of multiple comparisons statistics.Results Subjective assessments favored the CI50 reconstruction algorithm,demonstrating superior or satisfactory results compared to the other algorithms,with significantly better vessel delineation,edge definition and diagnostic confidence(all P<0.05).Objective analysis revealed that the CV50 and CV70 algorithms significantly reduced ERS and/or elevated ERD(both P<0.05).However,the CI50 algorithm maintained comparable vessel edge sharpness(P>0.05)across all evaluated head and neck vascular segments when compared with the FBP algorithm.Conclusions The CI50 reconstruction algorithm optimizes image quality in 60 kVp head and neck CTA.It provides vessel edge sharpness comparable to FBP while offering superior vessel delineation,edge definition,and diagnostic confidence compared to FBP and CV algorithm.These findings suggest that CI50 has the potential to improve diagnostic accuracy in low-dose vascular imaging.
基金supported in part by the National Natural Science Foundation of China under Grant 61902311in part by the Japan Society for the Promotion of Science(JSPS)Grants-in-Aid for Scientific Research(KAKENHI)under Grant JP18K18044.
文摘With increasingly more smart cameras deployed in infrastructure and commercial buildings,3D reconstruction can quickly obtain cities’information and improve the efficiency of government services.Images collected in outdoor hazy environments are prone to color distortion and low contrast;thus,the desired visual effect cannot be achieved and the difficulty of target detection is increased.Artificial intelligence(AI)solutions provide great help for dehazy images,which can automatically identify patterns or monitor the environment.Therefore,we propose a 3D reconstruction method of dehazed images for smart cities based on deep learning.First,we propose a fine transmission image deep convolutional regression network(FT-DCRN)dehazing algorithm that uses fine transmission image and atmospheric light value to compute dehazed image.The DCRN is used to obtain the coarse transmission image,which can not only expand the receptive field of the network but also retain the features to maintain the nonlinearity of the overall network.The fine transmission image is obtained by refining the coarse transmission image using a guided filter.The atmospheric light value is estimated according to the position and brightness of the pixels in the original hazy image.Second,we use the dehazed images generated by the FT-DCRN dehazing algorithm for 3D reconstruction.An advanced relaxed iterative fine matching based on the structure from motion(ARI-SFM)algorithm is proposed.The ARISFM algorithm,which obtains the fine matching corner pairs and reduces the number of iterations,establishes an accurate one-to-one matching corner relationship.The experimental results show that our FT-DCRN dehazing algorithm improves the accuracy compared to other representative algorithms.In addition,the ARI-SFM algorithm guarantees the precision and improves the efficiency.
基金National Natural Science Foundation of China,No.61902338 and No.62001120Shanghai Sailing Program,No.20YF1402400.
文摘Abdominal magnetic resonance imaging(MRI)and computed tomography(CT)are commonly used for disease screening,diagnosis,and treatment guidance.However,abdominal MRI has disadvantages including slow speed and vulnerability to motions,while CT suffers from problems of radiation.It has been reported that deep learning reconstruction can solve such problems while maintaining good image quality.Recently,deep learning-based image reconstruction has become a hot topic in the field of medical imaging.This study reviews the latest research on deep learning reconstruction in abdominal imaging,including the widely used convolutional neural network,generative adversarial network,and recurrent neural network.
基金National Natural Science Foundation of China(No.61771123)。
文摘The three-dimensional(3D)model is of great significance to analyze the performance of nonwovens.However,the existing modelling methods could not reconstruct the 3D structure of nonwovens at low cost.A new method based on deep learning was proposed to reconstruct 3D models of nonwovens from multi-focus images.A convolutional neural network was trained to extract clear fibers from sequence images.Image processing algorithms were used to obtain the radius,the central axis,and depth information of fibers from the extraction results.Based on this information,3D models were built in 3D space.Furthermore,self-developed algorithms optimized the central axis and depth of fibers,which made fibers more realistic and continuous.The method with lower cost could reconstruct 3D models of nonwovens conveniently.
基金supported by National Key R&D Program of China[2022YFC2402400]the National Natural Science Foundation of China[Grant No.62275062]Guangdong Provincial Key Laboratory of Biomedical Optical Imaging Technology[Grant No.2020B121201010-4].
文摘Photoacoustic imaging(PAI)is a noninvasive emerging imaging method based on the photoacoustic effect,which provides necessary assistance for medical diagnosis.It has the characteristics of large imaging depth and high contrast.However,limited by the equipment cost and reconstruction time requirements,the existing PAI systems distributed with annular array transducers are difficult to take into account both the image quality and the imaging speed.In this paper,a triple-path feature transform network(TFT-Net)for ring-array photoacoustic tomography is proposed to enhance the imaging quality from limited-view and sparse measurement data.Specifically,the network combines the raw photoacoustic pressure signals and conventional linear reconstruction images as input data,and takes the photoacoustic physical model as a prior information to guide the reconstruction process.In addition,to enhance the ability of extracting signal features,the residual block and squeeze and excitation block are introduced into the TFT-Net.For further efficient reconstruction,the final output of photoacoustic signals uses‘filter-then-upsample’operation with a pixel-shuffle multiplexer and a max out module.Experiment results on simulated and in-vivo data demonstrate that the constructed TFT-Net can restore the target boundary clearly,reduce background noise,and realize fast and high-quality photoacoustic image reconstruction of limited view with sparse sampling.
基金Supported by The National Key R&D Program of China,No.2018YFC0910600the National Natural Science Foundation of China No.81627807 and 11727813+2 种基金Shaanxi Science Funds for Distinguished Young Scholars,No.2020JC-27the Fok Ying Tung Education Foundation,No.161104and Program for the Young Topnotch Talent of Shaanxi Province.
文摘In this editorial,we review recent progress on the applications of artificial intelligence(AI)in image reconstruction for biomedical imaging.Because it abandons prior information of traditional artificial design and adopts a completely data-driven mode to obtain deeper prior information via learning,AI technology plays an increasingly important role in biomedical image reconstruction.The combination of AI technology and the biomedical image reconstruction method has become a hotspot in the field.Favoring AI,the performance of biomedical image reconstruction has been improved in terms of accuracy,resolution,imaging speed,etc.We specifically focus on how to use AI technology to improve the performance of biomedical image reconstruction,and propose possible future directions in this field.
基金supported by the National Key R&D Program of China(2021YFF0502900)the National Natural Science Foundation of China(61835009/62127819).
文摘The algorithm used for reconstruction or resolution enhancement is one of the factors affectingthe quality of super-resolution images obtained by fluorescence microscopy.Deep-learning-basedalgorithms have achieved stateof-the-art performance in super-resolution fluorescence micros-copy and are becoming increasingly attractive.We firstly introduce commonly-used deep learningmodels,and then review the latest applications in terms of the net work architectures,the trainingdata and the loss functions.Additionally,we discuss the challenges and limits when using deeplearning to analyze the fluorescence microscopic data,and suggest ways to improve the reliability and robustness of deep learning applications.
文摘Multispectral imaging,which simultaneously captures the spatial and spectral information of a scene,is widely used across diverse fields,including remote sensing,biomedical imaging,and agricultural monitoring.We introduce a snapshot multispectral imaging approach employing a standard monochrome image sensor with no additional spectral filters or customized components.Our system leverages the inherent chromatic aberration of wavelength-dependent defocusing as a natural source of physical encoding of multispectral information;this encoded image information is rapidly decoded via a deep learning-based multispectral Fourier imager network(mFIN).We experimentally tested our method with six illumination bands and demonstrated an overall accuracy of 98.25%for predicting the illumination channels at the input and achieved a robust multispectral image reconstruction on various test objects.This deep learning-powered framework achieves high-quality multispectral image reconstruction using snapshot image acquisition with a monochrome image sensor and could be useful for applications in biomedicine,industrial quality control,and agriculture,among others.
基金Supported by Sichuan Science and Technology Program(2023YFSY0026,2023YFH0004).
文摘3D medical image reconstruction has significantly enhanced diagnostic accuracy,yet the reliance on densely sampled projection data remains a major limitation in clinical practice.Sparse-angle X-ray imaging,though safer and faster,poses challenges for accurate volumetric reconstruction due to limited spatial information.This study proposes a 3D reconstruction neural network based on adaptive weight fusion(AdapFusionNet)to achieve high-quality 3D medical image reconstruction from sparse-angle X-ray images.To address the issue of spatial inconsistency in multi-angle image reconstruction,an innovative adaptive fusion module was designed to score initial reconstruction results during the inference stage and perform weighted fusion,thereby improving the final reconstruction quality.The reconstruction network is built on an autoencoder(AE)framework and uses orthogonal-angle X-ray images(frontal and lateral projections)as inputs.The encoder extracts 2D features,which the decoder maps into 3D space.This study utilizes a lung CT dataset to obtain complete three-dimensional volumetric data,from which digitally reconstructed radiographs(DRR)are generated at various angles to simulate X-ray images.Since real-world clinical X-ray images rarely come with perfectly corresponding 3D“ground truth,”using CT scans as the three-dimensional reference effectively supports the training and evaluation of deep networks for sparse-angle X-ray 3D reconstruction.Experiments conducted on the LIDC-IDRI dataset with simulated X-ray images(DRR images)as training data demonstrate the superior performance of AdapFusionNet compared to other fusion methods.Quantitative results show that AdapFusionNet achieves SSIM,PSNR,and MAE values of 0.332,13.404,and 0.163,respectively,outperforming other methods(SingleViewNet:0.289,12.363,0.182;AvgFusionNet:0.306,13.384,0.159).Qualitative analysis further confirms that AdapFusionNet significantly enhances the reconstruction of lung and chest contours while effectively reducing noise during the reconstruction process.The findings demonstrate that AdapFusionNet offers significant advantages in 3D reconstruction of sparse-angle X-ray images.
文摘In agricultural production,crop images are commonly used for the classification and identification of various crops.However,several challenges arise,including low image clarity,elevated noise levels,low accuracy,and poor robustness of existing classification models.To address these issues,this research proposes an innovative crop image classification model named Lap-FEHRNet,which integrates a Laplacian Pyramid Super Resolution Network(LapSRN)with a feature enhancement high-resolution network based on attention mechanisms(FEHRNet).To mitigate noise interference,this research incorporates the LapSRN network,which utilizes a Laplacian pyramid structure to extract multi-level feature details from low-resolution images through a systematic layer-by-layer amplification and pixel detail superposition process.This gradual reconstruction enhances the high-frequency information of the image,enabling super-resolution reconstruction of low-quality images.To obtain a broader range of comprehensive and diverse features,this research employs the FEHRNetmodel for both deep and shallow feature extraction.This approach results in features that encapsulate multi-scale information and integrate both deep and shallow insights.To effectively fuse these complementary features,this research introduces an attention mechanism during the feature enhancement stage.This mechanism highlights important regions within the image,assigning greater weights to salient features and resulting in a more comprehensive and effective image feature representation.Consequently,the accuracy of image classification is significantly improved.Experimental results demonstrate that the Lap-FEHRNetmodel achieves impressive classification accuracies of 98.8%on the crop classification dataset and 98.57%on the rice leaf disease dataset,underscoring the model’s outstanding accuracy,robustness,and generalization capability.
基金supported by the National Key R&D Program of China (No. 2024YFF1206700)the National Natural Science Foundation of China (No. U23A20487)the Hangzhou Chengxi Sci-tech Innovation Corridor Management Committee.
文摘Three-dimensional (3D) visualization of dynamic biological processes in deep tissue remains challenging due to the trade-off between temporal resolution and imaging depth. Here, we present a novel near-infrared-II (NIR-II, 900–1880nm) fluorescence volumetric microscopic imaging method that combines an electrically tunable lens (ETL) with deep learning approaches for rapid 3D imaging. The technology achieves volumetric imaging at 4.2 frames per second (fps) across a 200 μm depth range in live mouse brain vasculature. Two specialized neural networks are utilized: a scale-recurrent network (SRN) for image enhancement and a cerebral vessel interpolation (CVI) network that enables 16-fold axial upsampling. The SRN, trained on two-photon fluorescence microscopic data, improves both lateral and axial resolution of NIR-II fluorescence wide-field microscopic images. The CVI network, adapted from video interpolation techniques, generates intermediate frames between acquired axial planes, resulting in smooth and continuous 3D vessel reconstructions. Using this integrated system, we visualize and quantify blood flow dynamics in individual vessels and are capable of measuring blood velocity at different depths. This approach maintains high lateral resolution while achieving rapid volumetric imaging, and is particularly suitable for studying dynamic vascular processes in deep tissue. Our method demonstrates the potential of combining optical engineering with artificial intelligence to advance biological imaging capabilities.
基金Subjects funded by the National Natural Science Foundation of China(Nos.62275216 and 61775181)the Natural Science Basic Research Programme of Shaanxi Province-Major Basic Research Special Project(Nos.S2018-ZC-TD-0061 and TZ0393)the Special Project for the Development of National Key Scientific Instruments and Equipment No.(51927804).
文摘Deep learning is capable of greatly promoting the progress of super-resolution imaging technology in terms of imaging and reconstruction speed,imaging resolution,and imagingflux.This paper proposes a deep neural network based on a generative adversarial network(GAN).The generator employs a U-Net-based network,which integrates Dense Net for the downsampling component.The proposed method has excellent properties,for example,the network model is trained with several different datasets of biological structures;the trained model can improve the imaging resolution of different microscopy imaging modalities such as confocal imaging and wide-field imaging;and the model demonstrates a generalized ability to improve the resolution of different biological structures even out of the datasets.In addition,experimental results showed that the method improved the resolution of caveolin-coated pits(CCPs)structures from 264 nm to 138 nm,a 1.91-fold increase,and nearly doubled the resolution of DNA molecules imaged while being transported through microfluidic channels.
基金Research reported in this publication was partially supported by NIH,Nos.R01EB031102,R01HL151561,and R01CA233888The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH。
文摘Deep learning(DL)has shown unprecedented performance for many image analysis and image enhancement tasks.Yet,solving large-scale inverse problems like tomographic reconstruction remains challenging for DL.These problems involve non-local and space-variant integral transforms between the input and output domains,for which no efficient neural network models are readily available.A prior attempt to solve tomographic reconstruction problems with supervised learning relied on a brute-force fully connected network and only allowed reconstruction with a 128^(4)system matrix size.This cannot practically scale to realistic data sizes such as 512^(4)and 512^(6)for three-dimensional datasets.Here we present a novel framework to solve such problems with DL by casting the original problem as a continuum of intermediate representations between the input and output domains.The original problem is broken down into a sequence of simpler transformations that can be well mapped onto an efficient hierarchical network architecture,with exponentially fewer parameters than a fully connected network would need.We applied the approach to computed tomography(CT)image reconstruction for a 5124 system matrix size.This work introduces a new kind of data-driven DL solver for full-size CT reconstruction without relying on the structure of direct(analytical)or iterative(numerical)inversion techniques.This work presents a feasibility demonstration of full-scale learnt reconstruction,whereas more developments will be needed to demonstrate superiority relative to traditional reconstruction approaches.The proposed approach is also extendable to other imaging problems such as emission and magnetic resonance reconstruction.More broadly,hierarchical DL opens the door to a new class of solvers for general inverse problems,which could potentially lead to improved signal-to-noise ratio,spatial resolution and computational efficiency in various areas.
文摘Single image super resolution(SISR)techniques produce images of high resolution(HR)as output from input images of low resolution(LR).Motivated by the effectiveness of deep learning methods,we provide a framework based on deep learning to achieve super resolution(SR)by utilizing deep singular-residual neural network(DSRNN)in training phase.Residuals are obtained from the difference between HR and LR images to generate LR-residual example pairs.Singular value decomposition(SVD)is applied to each LR-residual image pair to decompose into subbands of low and high frequency components.Later,DSRNN is trained on these subbands through input and output channels by optimizing the weights and biases of the network.With fewer layers in DSRNN,the influence of exploding gradients is reduced.This speeds up the learning process and also improves accuracy by using skip connections.The trained DSRNN parameters yield residuals to recover the HR subbands in the testing phase.Experimental analysis shows that the proposed method results in superior performance to existingmethods in terms of subjective quality.Extensive testing results on popular benchmark datasets such as set5,set14,and urban100 for a scaling factor of 4 show the effectiveness of the proposed method across different qualitative evaluation metrics.
基金Research reported in this publication was supported by the NIH/NCI,No.R01CA233888the National Science Foundation Graduate Research Fellowship,No.DGE2147721.
文摘Early diagnosis and accurate prognosis of colorectal cancer is critical for determining optimal treatment plans and maximizing patient outcomes,especially as the disease progresses into liver metastases.Computed tomography(CT)is a frontline tool for this task;however,the preservation of predictive radiomic features is highly dependent on the scanning protocol and reconstruction algorithm.We hypothesized that image reconstruction with a highfrequency kernel could result in a better characterization of liver metastases features via deep neural networks.This kernel produces images that appear noisier but preserve more sinogram information.A simulation pipeline was developed to study the effects of imaging parameters on the ability to characterize the features of liver metastases.This pipeline utilizes a fractal approach to generate a diverse population of shapes representing virtual metastases,and then it superimposes them on a realistic CT liver region to perform a virtual CT scan using CatSim.Datasets of 10,000 liver metastases were generated,scanned,and reconstructed using either standard or high-frequency kernels.These data were used to train and validate deep neural networks to recover crafted metastases characteristics,such as internal heterogeneity,edge sharpness,and edge fractal dimension.In the absence of noise,models scored,on average,12.2%(α=0.012)and 7.5%(α=0.049)lower squared error for characterizing edge sharpness and fractal dimension,respectively,when using high-frequency reconstructions compared to standard.However,the differences in performance were statistically insignificant when a typical level of CT noise was simulated in the clinical scan.Our results suggest that high-frequency reconstruction kernels can better preserve information for downstream artificial intelligence-based radiomic characterization,provided that noise is limited.Future work should investigate the informationpreserving kernels in datasets with clinical labels.
基金This work was supported in part by grants from the US National Institutes of Health,Nos.R01 EB020366 and R01 EB027898the Cancer Prevention and Research Institute of Texas,Nos.RP130109 and RP160661from the University of Texas Southwestern Medical Center(Radiation Oncology Seed Grant).
文摘4-Dimensional cone-beam computed tomography(4D-CBCT)offers several key advantages over conventional 3DCBCT in moving target localization/delineation,structure de-blurring,target motion tracking,treatment dose accumulation and adaptive radiation therapy.However,the use of the 4D-CBCT in current radiation therapy practices has been limited,mostly due to its sub-optimal image quality from limited angular sampling of conebeam projections.In this study,we summarized the recent developments of 4D-CBCT reconstruction techniques for image quality improvement,and introduced our developments of a new 4D-CBCT reconstruction technique which features simultaneous motion estimation and image reconstruction(SMEIR).Based on the original SMEIR scheme,biomechanical modeling-guided SMEIR(SMEIR-Bio)was introduced to further improve the reconstruction accuracy of fine details in lung 4D-CBCTs.To improve the efficiency of reconstruction,we recently developed a U-net-based deformation-vector-field(DVF)optimization technique to leverage a population-based deep learning scheme to improve the accuracy of intra-lung DVFs(SMEIR-Unet),without explicit biomechanical modeling.Details of each of the SMEIR,SMEIR-Bio and SMEIR-Unet techniques were included in this study,along with the corresponding results comparing the reconstruction accuracy in terms of CBCT images and the DVFs.We also discussed the application prospects of the SMEIR-type techniques in image-guided radiation therapy and adaptive radiation therapy,and presented potential schemes on future developments to achieve faster and more accurate 4D-CBCT imaging.
基金supported by the National Science and Technology Major Project,China(No.J2019-Ⅲ-0009-0053)the National Natural Science Foundation of China(No.12075319)。
文摘In order to reconstruct and render the weak and repetitive texture of the damaged functional surface of aviation,an improved neural radiance field,named TranSR-NeRF,is proposed.In this paper,a data acquisition system was designed and built.The acquired images generated initial point clouds through TransMVSNet.Meanwhile,after extracting features from the images through the improved SE-ConvNeXt network,the extracted features were aligned and fused with the initial point cloud to generate high-quality neural point cloud.After ray-tracing and sampling of the neural point cloud,the ResMLP neural network designed in this paper was used to regress the volume density and radiance under a given viewing angle,which introduced spatial coordinate and relative positional encoding.The reconstruction and rendering of arbitrary-scale super-resolution of damaged functional surface is realized.In this paper,the influence of illumination conditions and background environment on the model performance is also studied through experiments,and the comparison and ablation experiments for the improved methods proposed in this paper is conducted.The experimental results show that the improved model has good effect.Finally,the application experiment of object detection task is carried out,and the experimental results show that the model has good practicability.
基金US National Institutes of Health,Nos.R01EB026646,R01CA233888,R01CA237267,R01HL151561,R21CA264772,and R01EB031102.
文摘Over recent years,the importance of the patent literature has become increasingly more recognized in the aca-demic setting.In the context of artificial intelligence,deep learning,and data sciences,patents are relevant to not only industry but also academe and other communities.In this article,we focus on deep tomographic imaging and perform a preliminary landscape analysis of the related patent literature.Our search tool is PatSeer.Our patent biblio-metric data is summarized in various figures and tables.In particular,we qualitatively analyze key deep tomographic patent literature.
