Pub Date : 2024-09-23DOI: 10.1109/TRPMS.2024.3465561
Tao Lei;Yi Wang;Xingwu Wang;Xuan Wang;Bin Hu;Asoke K. Nandi
Existing semi-supervised medical image segmentation methods based on the teacher-student model often employ unweighted pixel-level consistency loss, neglecting the varying difficulties of different pixels and resulting in significant deficits in segmenting challenging regions. Additionally, consistency learning often excludes pixels with high uncertainty, which destroys the semantic integrity of a medical image. To address these issues, we propose a novel unified feature consistency (UFC) of under-performing pixels (UPPs) and valid regions for semi-supervised medical image segmentation: 1) high-performing pixels (HPPs) and UPPs are distinguished by confidence differences between the student and teacher models, and then UPPs are mapped into a latent feature space to improve consistency learning effect (UPPFC); 2) in order to obtain richer semantic information from a medical image, vectors of valid regions are selected from both image- and patch-level class feature vectors by using the output probabilities of the teacher model; and 3) these vectors are mapped into the latent feature space for class feature consistency (CFC) learning as a supplement to UPPFC which only focuses on challenging regions for pixel-level consistency learning, thereby enhancing the model’s ability to learn structured semantic information from images themselves. Experimental results demonstrate that the proposed UFC achieves sufficient learning for challenging regions and retains the semantic integrity of medical images. Encouragingly, our proposed UFC provides better-segmentation results than the current state-of-the-art methods on three publicly available datasets. Our codes will be released at: https://github.com/SUST-reynole.
{"title":"Unified Feature Consistency of Under-Performing Pixels and Valid Regions for Semi-Supervised Medical Image Segmentation","authors":"Tao Lei;Yi Wang;Xingwu Wang;Xuan Wang;Bin Hu;Asoke K. Nandi","doi":"10.1109/TRPMS.2024.3465561","DOIUrl":"https://doi.org/10.1109/TRPMS.2024.3465561","url":null,"abstract":"Existing semi-supervised medical image segmentation methods based on the teacher-student model often employ unweighted pixel-level consistency loss, neglecting the varying difficulties of different pixels and resulting in significant deficits in segmenting challenging regions. Additionally, consistency learning often excludes pixels with high uncertainty, which destroys the semantic integrity of a medical image. To address these issues, we propose a novel unified feature consistency (UFC) of under-performing pixels (UPPs) and valid regions for semi-supervised medical image segmentation: 1) high-performing pixels (HPPs) and UPPs are distinguished by confidence differences between the student and teacher models, and then UPPs are mapped into a latent feature space to improve consistency learning effect (UPPFC); 2) in order to obtain richer semantic information from a medical image, vectors of valid regions are selected from both image- and patch-level class feature vectors by using the output probabilities of the teacher model; and 3) these vectors are mapped into the latent feature space for class feature consistency (CFC) learning as a supplement to UPPFC which only focuses on challenging regions for pixel-level consistency learning, thereby enhancing the model’s ability to learn structured semantic information from images themselves. Experimental results demonstrate that the proposed UFC achieves sufficient learning for challenging regions and retains the semantic integrity of medical images. Encouragingly, our proposed UFC provides better-segmentation results than the current state-of-the-art methods on three publicly available datasets. Our codes will be released at: <uri>https://github.com/SUST-reynole</uri>.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 2","pages":"169-181"},"PeriodicalIF":4.6,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10685517","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cone-beam CT (CBCT) is commonly used in treatment imaging, but its limited soft tissue contrast presents challenges for liver tumor localization. As a result, indirect localization methods relying on the liver’s boundary are commonly utilized, which have limited accuracy for tumor localization. On-board MRI offers superior soft tissue contrast but is limited by the cost. To address this, we devised a method to generate onboard virtual MRI by integrating pretreatment MRI with onboard CBCT, enhancing liver stereotactic body radiation therapy (SBRT) tumor localization accuracy. We employed a finite element method (FEM) for deformable mapping, deforming prior liver MR images onto CBCT geometry to create a virtual MRI. This hybrid virtual-MRI/CBCT (hMRI-CBCT) approach was evaluated in a pilot study involving 48 patients. The hMRI-CBCT demonstrated superb soft-tissue contrast with clear tumor visualization. Registration accuracy of hMRI-CBCT to planning CT significantly surpasses the onboard CBCT to planning CT registration, particularly for tumors not near the liver boundary, with an average error reduction of $1.53~pm ~2$ .16 mm. Our study demonstrated that hybrid MRI/CBCT can apparently reduce localization errors in liver SBRT, potentially improving tumor control and reducing toxicities, and opening avenues for further margin reduction and dose escalation.
{"title":"Finite Element Method-Based Hybrid MRI/CBCT Generation to Improve Liver Stereotactic Body Radiation Therapy Targets Localization Accuracy","authors":"Zeyu Zhang;Mark Chen;Ke Lu;Dongyang Guo;Zhuoran Jiang;Hualiang Zhong;Jason Molitoris;Phuoc T. Tran;Fang-Fang Yin;Lei Ren","doi":"10.1109/TRPMS.2024.3466184","DOIUrl":"https://doi.org/10.1109/TRPMS.2024.3466184","url":null,"abstract":"Cone-beam CT (CBCT) is commonly used in treatment imaging, but its limited soft tissue contrast presents challenges for liver tumor localization. As a result, indirect localization methods relying on the liver’s boundary are commonly utilized, which have limited accuracy for tumor localization. On-board MRI offers superior soft tissue contrast but is limited by the cost. To address this, we devised a method to generate onboard virtual MRI by integrating pretreatment MRI with onboard CBCT, enhancing liver stereotactic body radiation therapy (SBRT) tumor localization accuracy. We employed a finite element method (FEM) for deformable mapping, deforming prior liver MR images onto CBCT geometry to create a virtual MRI. This hybrid virtual-MRI/CBCT (hMRI-CBCT) approach was evaluated in a pilot study involving 48 patients. The hMRI-CBCT demonstrated superb soft-tissue contrast with clear tumor visualization. Registration accuracy of hMRI-CBCT to planning CT significantly surpasses the onboard CBCT to planning CT registration, particularly for tumors not near the liver boundary, with an average error reduction of <inline-formula> <tex-math>$1.53~pm ~2$ </tex-math></inline-formula>.16 mm. Our study demonstrated that hybrid MRI/CBCT can apparently reduce localization errors in liver SBRT, potentially improving tumor control and reducing toxicities, and opening avenues for further margin reduction and dose escalation.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 3","pages":"372-381"},"PeriodicalIF":4.6,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Deep learning (DL) models, which have significantly promoted medical imaging, typically assume that training and testing data come from the same domain and distribution. However, these models struggle with unseen testing variations, like different imaging scanners or protocols, leading to suboptimal results from distribution mismatches between training and testing data. Despite extensive research, the issue of distribution mismatch in DL-based medical imaging has been largely overlooked in current literature. To improve the performance with mismatched testing data, this article proposes an orthogonal meta-learning (OML) framework for test-time adaptation (TTA) in medical imaging. Specifically, during training, we develop supervised meta-training reconstruction tasks to guide the self-supervised meta-testing task. Additionally, we introduce an orthogonal learning strategy to enforce orthogonality of pretrained parameters during training, which accelerates convergence during TTA and enhances performance. During the testing stage, the fine-tuned meta-learned parameters effectively reconstruct new, unseen testing data. Extensive experiments on magnetic resonance imaging and computed tomography datasets were conducted to validate our method’s effectiveness against other state-of-the-art methods, including supervised ones, in various mismatch scenarios.
{"title":"Test-Time Adaptation via Orthogonal Meta-Learning for Medical Imaging","authors":"Zhiwen Wang;Zexin Lu;Tao Wang;Ziyuan Yang;Hui Yu;Zhongxian Wang;Yinyu Chen;Jingfeng Lu;Yi Zhang","doi":"10.1109/TRPMS.2024.3462542","DOIUrl":"https://doi.org/10.1109/TRPMS.2024.3462542","url":null,"abstract":"Deep learning (DL) models, which have significantly promoted medical imaging, typically assume that training and testing data come from the same domain and distribution. However, these models struggle with unseen testing variations, like different imaging scanners or protocols, leading to suboptimal results from distribution mismatches between training and testing data. Despite extensive research, the issue of distribution mismatch in DL-based medical imaging has been largely overlooked in current literature. To improve the performance with mismatched testing data, this article proposes an orthogonal meta-learning (OML) framework for test-time adaptation (TTA) in medical imaging. Specifically, during training, we develop supervised meta-training reconstruction tasks to guide the self-supervised meta-testing task. Additionally, we introduce an orthogonal learning strategy to enforce orthogonality of pretrained parameters during training, which accelerates convergence during TTA and enhances performance. During the testing stage, the fine-tuned meta-learned parameters effectively reconstruct new, unseen testing data. Extensive experiments on magnetic resonance imaging and computed tomography datasets were conducted to validate our method’s effectiveness against other state-of-the-art methods, including supervised ones, in various mismatch scenarios.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 2","pages":"215-227"},"PeriodicalIF":4.6,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-10DOI: 10.1109/TRPMS.2024.3457618
Daehee Lee;Sun Il Kwon
We propose an field-programmable gate array (FPGA)-based time-to-digital converter (TDC) that utilizes a virtual bin (VB) approach with opposite-transition (OT) inputs on two tapped-delay lines (TDLs) to obtain less-correlated time bins. The VBs from the proposed OT TDC were obtained by comparing and segmenting the less-correlated bins collected from the two TDLs. The OT TDC was implemented on a 7-series FPGA (Xilinx) to verify performance. A conventional monotonic-transition (MT) TDC, which used identical transition inputs (0-to-1 or 1-to-0 transition) for the two TDLs, was also implemented as a control group. The results were compared with those from the MT TDC and other studies. The proposed method effectively improves time resolution and integral linearity while keeping resource usage low by exploiting these characteristics. The average bin size and RMS value were 5.5 and 4.2 ps, respectively. Moreover, the proposed method exhibits stable performance under temperature variations and implementation location changes. The VB OT TDC, which applies the VB method to the OT TDC, successfully measures detection time differences of two signals from two Cerenkov radiator integrated microchannel plate photomultiplier tubes (CRI-MCP-PMTs) with a high-timing precision of sub-100 ps. The VB OT TDC can be used for next-generation applications that require fast-timing measurements.
{"title":"Implementation of a FPGA-Based Time-to-Digital Converter Utilizing Opposite-Transition Propagation and Virtual Bin Method","authors":"Daehee Lee;Sun Il Kwon","doi":"10.1109/TRPMS.2024.3457618","DOIUrl":"https://doi.org/10.1109/TRPMS.2024.3457618","url":null,"abstract":"We propose an field-programmable gate array (FPGA)-based time-to-digital converter (TDC) that utilizes a virtual bin (VB) approach with opposite-transition (OT) inputs on two tapped-delay lines (TDLs) to obtain less-correlated time bins. The VBs from the proposed OT TDC were obtained by comparing and segmenting the less-correlated bins collected from the two TDLs. The OT TDC was implemented on a 7-series FPGA (Xilinx) to verify performance. A conventional monotonic-transition (MT) TDC, which used identical transition inputs (0-to-1 or 1-to-0 transition) for the two TDLs, was also implemented as a control group. The results were compared with those from the MT TDC and other studies. The proposed method effectively improves time resolution and integral linearity while keeping resource usage low by exploiting these characteristics. The average bin size and RMS value were 5.5 and 4.2 ps, respectively. Moreover, the proposed method exhibits stable performance under temperature variations and implementation location changes. The VB OT TDC, which applies the VB method to the OT TDC, successfully measures detection time differences of two signals from two Cerenkov radiator integrated microchannel plate photomultiplier tubes (CRI-MCP-PMTs) with a high-timing precision of sub-100 ps. The VB OT TDC can be used for next-generation applications that require fast-timing measurements.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 2","pages":"148-156"},"PeriodicalIF":4.6,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Positron emission tomography (PET) scanners use scintillation crystals to stop high-energy photons. The ensuing lower-energy photons are then detected via photomultipliers. We study the performance of a stack of monolithic silicon-pixel detectors as an alternative to the combination of crystals and photomultipliers. The resulting design allows for pitches as small as $100~ {mu }$ m and greatly mitigates depth-of-interaction problems. We develop a theory to optimize the sensitivity of these and other scanners under design constraints. The insight is complemented by Monte Carlo simulations and reconstructions thereof. Experiments and theory alike suggest that our approach has the potential to move PET closer to the microscopic scale. The volumetric resolution is an order of magnitude better than that of the state of the art and the parallax error is very small. A small-animal scanner is now under construction.
{"title":"A Silicon-Pixel Paradigm for PET","authors":"Aleix Boquet-Pujadas;Jihad Saidi;Mateus Vicente;Lorenzo Paolozzi;Jonathan Dong;Pol Del Aguila Pla;Giuseppe Iacobucci;Michael Unser","doi":"10.1109/TRPMS.2024.3456241","DOIUrl":"https://doi.org/10.1109/TRPMS.2024.3456241","url":null,"abstract":"Positron emission tomography (PET) scanners use scintillation crystals to stop high-energy photons. The ensuing lower-energy photons are then detected via photomultipliers. We study the performance of a stack of monolithic silicon-pixel detectors as an alternative to the combination of crystals and photomultipliers. The resulting design allows for pitches as small as <inline-formula> <tex-math>$100~ {mu }$ </tex-math></inline-formula>m and greatly mitigates depth-of-interaction problems. We develop a theory to optimize the sensitivity of these and other scanners under design constraints. The insight is complemented by Monte Carlo simulations and reconstructions thereof. Experiments and theory alike suggest that our approach has the potential to move PET closer to the microscopic scale. The volumetric resolution is an order of magnitude better than that of the state of the art and the parallax error is very small. A small-animal scanner is now under construction.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 2","pages":"228-246"},"PeriodicalIF":4.6,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10669392","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/TRPMS.2024.3449313
{"title":"IEEE Transactions on Radiation and Plasma Medical Sciences Publication Information","authors":"","doi":"10.1109/TRPMS.2024.3449313","DOIUrl":"https://doi.org/10.1109/TRPMS.2024.3449313","url":null,"abstract":"","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 7","pages":"C3-C3"},"PeriodicalIF":4.6,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10669124","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142143580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/TRPMS.2024.3449311
{"title":"IEEE Transactions on Radiation and Plasma Medical Sciences Information for Authors","authors":"","doi":"10.1109/TRPMS.2024.3449311","DOIUrl":"https://doi.org/10.1109/TRPMS.2024.3449311","url":null,"abstract":"","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 7","pages":"C2-C2"},"PeriodicalIF":4.6,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10669129","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142143652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/TRPMS.2024.3453689
{"title":"Member Get-a-Member (MGM) Program","authors":"","doi":"10.1109/TRPMS.2024.3453689","DOIUrl":"https://doi.org/10.1109/TRPMS.2024.3453689","url":null,"abstract":"","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 7","pages":"850-850"},"PeriodicalIF":4.6,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10669127","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142143609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.1109/TRPMS.2024.3453691
{"title":"IEEE DataPort","authors":"","doi":"10.1109/TRPMS.2024.3453691","DOIUrl":"https://doi.org/10.1109/TRPMS.2024.3453691","url":null,"abstract":"","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 7","pages":"851-851"},"PeriodicalIF":4.6,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10669128","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142143678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-05DOI: 10.1109/TRPMS.2024.3453009
Yu Guan;Bohui Shen;Shirui Jiang;Xinchong Shi;Xiangsong Zhang;Bingxuan Li;Qiegen Liu
Attenuation correction (AC) is essential for the generation of artifact-free and quantitatively accurate positron emission tomography (PET) images. Nowadays, deep-learning-based methods have been extensively applied to PET AC tasks, yielding promising results. Therefore, this article develops an innovative approach to generate continuously valued CT images from nonattenuation corrected PET images for AC on brain PET imaging. Specifically, an invertible neural network combined with the variable augmentation strategy that can achieve the bidirectional inference processes is proposed for synthetic CT generation. On the one hand, invertible architecture ensures a bijective mapping between the PET and synthetic CT image spaces, which can potentially improve the robustness of the prediction and provide a way to validate the synthetic CT by checking the consistency of the inverse mapping. On the other hand, the variable augmentation strategy enriches the training process and leverages the intrinsic data properties more effectively. Therefore, the combination provides for superior performance in PET AC by preserving information throughout the network and by better handling of the data variability inherent PET AC. To evaluate the performance of the proposed algorithm, we conducted a comprehensive study on a total of 1480 2-D slices from 37 whole-body 18F-FDG clinical patients using comparative algorithms (such as cycle-generative adversarial network and Pix2pix). Perceptual analysis and quantitative evaluations illustrate that the invertible network for PET AC outperforms other existing AC models, which demonstrates the feasibility of achieving brain PET AC without additional anatomical information.
{"title":"Synthetic CT Generation via Variant Invertible Network for Brain PET Attenuation Correction","authors":"Yu Guan;Bohui Shen;Shirui Jiang;Xinchong Shi;Xiangsong Zhang;Bingxuan Li;Qiegen Liu","doi":"10.1109/TRPMS.2024.3453009","DOIUrl":"https://doi.org/10.1109/TRPMS.2024.3453009","url":null,"abstract":"Attenuation correction (AC) is essential for the generation of artifact-free and quantitatively accurate positron emission tomography (PET) images. Nowadays, deep-learning-based methods have been extensively applied to PET AC tasks, yielding promising results. Therefore, this article develops an innovative approach to generate continuously valued CT images from nonattenuation corrected PET images for AC on brain PET imaging. Specifically, an invertible neural network combined with the variable augmentation strategy that can achieve the bidirectional inference processes is proposed for synthetic CT generation. On the one hand, invertible architecture ensures a bijective mapping between the PET and synthetic CT image spaces, which can potentially improve the robustness of the prediction and provide a way to validate the synthetic CT by checking the consistency of the inverse mapping. On the other hand, the variable augmentation strategy enriches the training process and leverages the intrinsic data properties more effectively. Therefore, the combination provides for superior performance in PET AC by preserving information throughout the network and by better handling of the data variability inherent PET AC. To evaluate the performance of the proposed algorithm, we conducted a comprehensive study on a total of 1480 2-D slices from 37 whole-body 18F-FDG clinical patients using comparative algorithms (such as cycle-generative adversarial network and Pix2pix). Perceptual analysis and quantitative evaluations illustrate that the invertible network for PET AC outperforms other existing AC models, which demonstrates the feasibility of achieving brain PET AC without additional anatomical information.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"9 3","pages":"325-336"},"PeriodicalIF":4.6,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10666843","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：