Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention最新文献
Pub Date : 2023-10-03DOI: 10.1007/978-3-031-16452-1_15
Weibin Liao, H. Xiong, Qingzhong Wang, Yan Mo, Xuhong Li, Yi Liu, Zeyu Chen, Siyu Huang, D. Dou
{"title":"MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-Ray Images of Multiple Body Parts","authors":"Weibin Liao, H. Xiong, Qingzhong Wang, Yan Mo, Xuhong Li, Yi Liu, Zeyu Chen, Siyu Huang, D. Dou","doi":"10.1007/978-3-031-16452-1_15","DOIUrl":"https://doi.org/10.1007/978-3-031-16452-1_15","url":null,"abstract":"","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"64 1","pages":"151-161"},"PeriodicalIF":0.0,"publicationDate":"2023-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72903973","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 : 2023-08-31DOI: 10.48550/arXiv.2308.16863
Chinmay Prabhakar, Hongwei Li, J. Paetzold, T. Loehr, Chen Niu, M. Muhlau, D. Rueckert, B. Wiestler, Bjoern H Menze
Multiple Sclerosis (MS) is a severe neurological disease characterized by inflammatory lesions in the central nervous system. Hence, predicting inflammatory disease activity is crucial for disease assessment and treatment. However, MS lesions can occur throughout the brain and vary in shape, size and total count among patients. The high variance in lesion load and locations makes it challenging for machine learning methods to learn a globally effective representation of whole-brain MRI scans to assess and predict disease. Technically it is non-trivial to incorporate essential biomarkers such as lesion load or spatial proximity. Our work represents the first attempt to utilize graph neural networks (GNN) to aggregate these biomarkers for a novel global representation. We propose a two-stage MS inflammatory disease activity prediction approach. First, a 3D segmentation network detects lesions, and a self-supervised algorithm extracts their image features. Second, the detected lesions are used to build a patient graph. The lesions act as nodes in the graph and are initialized with image features extracted in the first stage. Finally, the lesions are connected based on their spatial proximity and the inflammatory disease activity prediction is formulated as a graph classification task. Furthermore, we propose a self-pruning strategy to auto-select the most critical lesions for prediction. Our proposed method outperforms the existing baseline by a large margin (AUCs of 0.67 vs. 0.61 and 0.66 vs. 0.60 for one-year and two-year inflammatory disease activity, respectively). Finally, our proposed method enjoys inherent explainability by assigning an importance score to each lesion for the overall prediction. Code is available at https://github.com/chinmay5/ms_ida.git
多发性硬化症(MS)是一种以中枢神经系统炎症病变为特征的严重神经系统疾病。因此，预测炎症性疾病的活动性对疾病评估和治疗至关重要。然而，多发性硬化症病变可以发生在整个大脑中，并且在形状、大小和总数上各不相同。病变负荷和位置的高度差异使得机器学习方法难以学习全脑MRI扫描的全局有效表示来评估和预测疾病。从技术上讲，将必要的生物标志物(如损伤负荷或空间接近度)纳入其中是非常重要的。我们的工作代表了首次尝试利用图神经网络(GNN)来聚合这些生物标志物以获得新的全局表示。我们提出了一种两阶段MS炎症性疾病活动性预测方法。首先，用三维分割网络检测病灶，用自监督算法提取病灶的图像特征。其次，使用检测到的病变构建患者图。病灶作为图中的节点，用第一阶段提取的图像特征初始化。最后，根据病灶的空间接近性将其连接起来，并将炎症疾病活动预测制定为一个图分类任务。此外，我们提出了一种自修剪策略来自动选择最关键的病变进行预测。我们提出的方法在很大程度上优于现有基线(1年和2年炎症疾病活动性的auc分别为0.67 vs 0.61和0.66 vs 0.60)。最后，我们提出的方法具有固有的可解释性，通过为每个病变分配一个重要分数来进行整体预测。代码可从https://github.com/chinmay5/ms_ida.git获得
{"title":"Self-pruning Graph Neural Network for Predicting Inflammatory Disease Activity in Multiple Sclerosis from Brain MR Images","authors":"Chinmay Prabhakar, Hongwei Li, J. Paetzold, T. Loehr, Chen Niu, M. Muhlau, D. Rueckert, B. Wiestler, Bjoern H Menze","doi":"10.48550/arXiv.2308.16863","DOIUrl":"https://doi.org/10.48550/arXiv.2308.16863","url":null,"abstract":"Multiple Sclerosis (MS) is a severe neurological disease characterized by inflammatory lesions in the central nervous system. Hence, predicting inflammatory disease activity is crucial for disease assessment and treatment. However, MS lesions can occur throughout the brain and vary in shape, size and total count among patients. The high variance in lesion load and locations makes it challenging for machine learning methods to learn a globally effective representation of whole-brain MRI scans to assess and predict disease. Technically it is non-trivial to incorporate essential biomarkers such as lesion load or spatial proximity. Our work represents the first attempt to utilize graph neural networks (GNN) to aggregate these biomarkers for a novel global representation. We propose a two-stage MS inflammatory disease activity prediction approach. First, a 3D segmentation network detects lesions, and a self-supervised algorithm extracts their image features. Second, the detected lesions are used to build a patient graph. The lesions act as nodes in the graph and are initialized with image features extracted in the first stage. Finally, the lesions are connected based on their spatial proximity and the inflammatory disease activity prediction is formulated as a graph classification task. Furthermore, we propose a self-pruning strategy to auto-select the most critical lesions for prediction. Our proposed method outperforms the existing baseline by a large margin (AUCs of 0.67 vs. 0.61 and 0.66 vs. 0.60 for one-year and two-year inflammatory disease activity, respectively). Finally, our proposed method enjoys inherent explainability by assigning an importance score to each lesion for the overall prediction. Code is available at https://github.com/chinmay5/ms_ida.git","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"1 1","pages":"226-236"},"PeriodicalIF":0.0,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84841265","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 : 2023-08-23DOI: 10.48550/arXiv.2308.12394
Roy Hirsch, Mathilde Caron, Regev Cohen, Amir Livne, Ron Shapiro, Tomer Golany, Roman Goldenberg, Daniel Freedman, E. Rivlin
Self-supervised learning (SSL) has led to important breakthroughs in computer vision by allowing learning from large amounts of unlabeled data. As such, it might have a pivotal role to play in biomedicine where annotating data requires a highly specialized expertise. Yet, there are many healthcare domains for which SSL has not been extensively explored. One such domain is endoscopy, minimally invasive procedures which are commonly used to detect and treat infections, chronic inflammatory diseases or cancer. In this work, we study the use of a leading SSL framework, namely Masked Siamese Networks (MSNs), for endoscopic video analysis such as colonoscopy and laparoscopy. To fully exploit the power of SSL, we create sizable unlabeled endoscopic video datasets for training MSNs. These strong image representations serve as a foundation for secondary training with limited annotated datasets, resulting in state-of-the-art performance in endoscopic benchmarks like surgical phase recognition during laparoscopy and colonoscopic polyp characterization. Additionally, we achieve a 50% reduction in annotated data size without sacrificing performance. Thus, our work provides evidence that SSL can dramatically reduce the need of annotated data in endoscopy.
{"title":"Self-Supervised Learning for Endoscopic Video Analysis","authors":"Roy Hirsch, Mathilde Caron, Regev Cohen, Amir Livne, Ron Shapiro, Tomer Golany, Roman Goldenberg, Daniel Freedman, E. Rivlin","doi":"10.48550/arXiv.2308.12394","DOIUrl":"https://doi.org/10.48550/arXiv.2308.12394","url":null,"abstract":"Self-supervised learning (SSL) has led to important breakthroughs in computer vision by allowing learning from large amounts of unlabeled data. As such, it might have a pivotal role to play in biomedicine where annotating data requires a highly specialized expertise. Yet, there are many healthcare domains for which SSL has not been extensively explored. One such domain is endoscopy, minimally invasive procedures which are commonly used to detect and treat infections, chronic inflammatory diseases or cancer. In this work, we study the use of a leading SSL framework, namely Masked Siamese Networks (MSNs), for endoscopic video analysis such as colonoscopy and laparoscopy. To fully exploit the power of SSL, we create sizable unlabeled endoscopic video datasets for training MSNs. These strong image representations serve as a foundation for secondary training with limited annotated datasets, resulting in state-of-the-art performance in endoscopic benchmarks like surgical phase recognition during laparoscopy and colonoscopic polyp characterization. Additionally, we achieve a 50% reduction in annotated data size without sacrificing performance. Thus, our work provides evidence that SSL can dramatically reduce the need of annotated data in endoscopy.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"60 1","pages":"569-578"},"PeriodicalIF":0.0,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84519070","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 : 2023-08-22DOI: 10.48550/arXiv.2308.11144
Pingyi Chen, Chenglu Zhu, Zhongyi Shui, Jiatong Cai, S. Zheng, Shichuan Zhang, Lin Yang
The success of supervised deep learning models on cell recognition tasks relies on detailed annotations. Many previous works have managed to reduce the dependency on labels. However, considering the large number of cells contained in a patch, costly and inefficient labeling is still inevitable. To this end, we explored label-free methods for cell recognition. Prior self-activation maps (PSM) are proposed to generate pseudo masks as training targets. To be specific, an activation network is trained with self-supervised learning. The gradient information in the shallow layers of the network is aggregated to generate prior self-activation maps. Afterward, a semantic clustering module is then introduced as a pipeline to transform PSMs to pixel-level semantic pseudo masks for downstream tasks. We evaluated our method on two histological datasets: MoNuSeg (cell segmentation) and BCData (multi-class cell detection). Compared with other fully-supervised and weakly-supervised methods, our method can achieve competitive performance without any manual annotations. Our simple but effective framework can also achieve multi-class cell detection which can not be done by existing unsupervised methods. The results show the potential of PSMs that might inspire other research to deal with the hunger for labels in medical area.
{"title":"Exploring Unsupervised Cell Recognition with Prior Self-activation Maps","authors":"Pingyi Chen, Chenglu Zhu, Zhongyi Shui, Jiatong Cai, S. Zheng, Shichuan Zhang, Lin Yang","doi":"10.48550/arXiv.2308.11144","DOIUrl":"https://doi.org/10.48550/arXiv.2308.11144","url":null,"abstract":"The success of supervised deep learning models on cell recognition tasks relies on detailed annotations. Many previous works have managed to reduce the dependency on labels. However, considering the large number of cells contained in a patch, costly and inefficient labeling is still inevitable. To this end, we explored label-free methods for cell recognition. Prior self-activation maps (PSM) are proposed to generate pseudo masks as training targets. To be specific, an activation network is trained with self-supervised learning. The gradient information in the shallow layers of the network is aggregated to generate prior self-activation maps. Afterward, a semantic clustering module is then introduced as a pipeline to transform PSMs to pixel-level semantic pseudo masks for downstream tasks. We evaluated our method on two histological datasets: MoNuSeg (cell segmentation) and BCData (multi-class cell detection). Compared with other fully-supervised and weakly-supervised methods, our method can achieve competitive performance without any manual annotations. Our simple but effective framework can also achieve multi-class cell detection which can not be done by existing unsupervised methods. The results show the potential of PSMs that might inspire other research to deal with the hunger for labels in medical area.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"13 1","pages":"559-568"},"PeriodicalIF":0.0,"publicationDate":"2023-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84031220","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 : 2023-08-18DOI: 10.48550/arXiv.2308.09223
Xiaoxiao He, Chaowei Tan, Ligong Han, Bo Liu, L. Axel, Kang Li, Dimitris N. Metaxas
Accurate 3D cardiac reconstruction from cine magnetic resonance imaging (cMRI) is crucial for improved cardiovascular disease diagnosis and understanding of the heart's motion. However, current cardiac MRI-based reconstruction technology used in clinical settings is 2D with limited through-plane resolution, resulting in low-quality reconstructed cardiac volumes. To better reconstruct 3D cardiac volumes from sparse 2D image stacks, we propose a morphology-guided diffusion model for 3D cardiac volume reconstruction, DMCVR, that synthesizes high-resolution 2D images and corresponding 3D reconstructed volumes. Our method outperforms previous approaches by conditioning the cardiac morphology on the generative model, eliminating the time-consuming iterative optimization process of the latent code, and improving generation quality. The learned latent spaces provide global semantics, local cardiac morphology and details of each 2D cMRI slice with highly interpretable value to reconstruct 3D cardiac shape. Our experiments show that DMCVR is highly effective in several aspects, such as 2D generation and 3D reconstruction performance. With DMCVR, we can produce high-resolution 3D cardiac MRI reconstructions, surpassing current techniques. Our proposed framework has great potential for improving the accuracy of cardiac disease diagnosis and treatment planning. Code can be accessed at https://github.com/hexiaoxiao-cs/DMCVR.
{"title":"DMCVR: Morphology-Guided Diffusion Model for 3D Cardiac Volume Reconstruction","authors":"Xiaoxiao He, Chaowei Tan, Ligong Han, Bo Liu, L. Axel, Kang Li, Dimitris N. Metaxas","doi":"10.48550/arXiv.2308.09223","DOIUrl":"https://doi.org/10.48550/arXiv.2308.09223","url":null,"abstract":"Accurate 3D cardiac reconstruction from cine magnetic resonance imaging (cMRI) is crucial for improved cardiovascular disease diagnosis and understanding of the heart's motion. However, current cardiac MRI-based reconstruction technology used in clinical settings is 2D with limited through-plane resolution, resulting in low-quality reconstructed cardiac volumes. To better reconstruct 3D cardiac volumes from sparse 2D image stacks, we propose a morphology-guided diffusion model for 3D cardiac volume reconstruction, DMCVR, that synthesizes high-resolution 2D images and corresponding 3D reconstructed volumes. Our method outperforms previous approaches by conditioning the cardiac morphology on the generative model, eliminating the time-consuming iterative optimization process of the latent code, and improving generation quality. The learned latent spaces provide global semantics, local cardiac morphology and details of each 2D cMRI slice with highly interpretable value to reconstruct 3D cardiac shape. Our experiments show that DMCVR is highly effective in several aspects, such as 2D generation and 3D reconstruction performance. With DMCVR, we can produce high-resolution 3D cardiac MRI reconstructions, surpassing current techniques. Our proposed framework has great potential for improving the accuracy of cardiac disease diagnosis and treatment planning. Code can be accessed at https://github.com/hexiaoxiao-cs/DMCVR.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"83 1","pages":"132-142"},"PeriodicalIF":0.0,"publicationDate":"2023-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90314217","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 : 2023-08-11DOI: 10.48550/arXiv.2308.06332
Khondker Fariha Hossain, S. Kamran, Joshua Ong, Andrew Lee, A. Tavakkoli
The rapid accessibility of portable and affordable retinal imaging devices has made early differential diagnosis easier. For example, color funduscopy imaging is readily available in remote villages, which can help to identify diseases like age-related macular degeneration (AMD), glaucoma, or pathological myopia (PM). On the other hand, astronauts at the International Space Station utilize this camera for identifying spaceflight-associated neuro-ocular syndrome (SANS). However, due to the unavailability of experts in these locations, the data has to be transferred to an urban healthcare facility (AMD and glaucoma) or a terrestrial station (e.g, SANS) for more precise disease identification. Moreover, due to low bandwidth limits, the imaging data has to be compressed for transfer between these two places. Different super-resolution algorithms have been proposed throughout the years to address this. Furthermore, with the advent of deep learning, the field has advanced so much that x2 and x4 compressed images can be decompressed to their original form without losing spatial information. In this paper, we introduce a novel model called Swin-FSR that utilizes Swin Transformer with spatial and depth-wise attention for fundus image super-resolution. Our architecture achieves Peak signal-to-noise-ratio (PSNR) of 47.89, 49.00 and 45.32 on three public datasets, namely iChallenge-AMD, iChallenge-PM, and G1020. Additionally, we tested the model's effectiveness on a privately held dataset for SANS provided by NASA and achieved comparable results against previous architectures.
{"title":"Revolutionizing Space Health (Swin-FSR): Advancing Super-Resolution of Fundus Images for SANS Visual Assessment Technology","authors":"Khondker Fariha Hossain, S. Kamran, Joshua Ong, Andrew Lee, A. Tavakkoli","doi":"10.48550/arXiv.2308.06332","DOIUrl":"https://doi.org/10.48550/arXiv.2308.06332","url":null,"abstract":"The rapid accessibility of portable and affordable retinal imaging devices has made early differential diagnosis easier. For example, color funduscopy imaging is readily available in remote villages, which can help to identify diseases like age-related macular degeneration (AMD), glaucoma, or pathological myopia (PM). On the other hand, astronauts at the International Space Station utilize this camera for identifying spaceflight-associated neuro-ocular syndrome (SANS). However, due to the unavailability of experts in these locations, the data has to be transferred to an urban healthcare facility (AMD and glaucoma) or a terrestrial station (e.g, SANS) for more precise disease identification. Moreover, due to low bandwidth limits, the imaging data has to be compressed for transfer between these two places. Different super-resolution algorithms have been proposed throughout the years to address this. Furthermore, with the advent of deep learning, the field has advanced so much that x2 and x4 compressed images can be decompressed to their original form without losing spatial information. In this paper, we introduce a novel model called Swin-FSR that utilizes Swin Transformer with spatial and depth-wise attention for fundus image super-resolution. Our architecture achieves Peak signal-to-noise-ratio (PSNR) of 47.89, 49.00 and 45.32 on three public datasets, namely iChallenge-AMD, iChallenge-PM, and G1020. Additionally, we tested the model's effectiveness on a privately held dataset for SANS provided by NASA and achieved comparable results against previous architectures.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"118 1","pages":"693-703"},"PeriodicalIF":0.0,"publicationDate":"2023-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84731150","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 : 2023-08-11DOI: 10.48550/arXiv.2308.06420
Yen Nhi Truong Vu, Dan Guo, Ahmed Taha, Jason Su, Thomas P. Matthews
Deep-learning-based object detection methods show promise for improving screening mammography, but high rates of false positives can hinder their effectiveness in clinical practice. To reduce false positives, we identify three challenges: (1) unlike natural images, a malignant mammogram typically contains only one malignant finding; (2) mammography exams contain two views of each breast, and both views ought to be considered to make a correct assessment; (3) most mammograms are negative and do not contain any findings. In this work, we tackle the three aforementioned challenges by: (1) leveraging Sparse R-CNN and showing that sparse detectors are more appropriate than dense detectors for mammography; (2) including a multi-view cross-attention module to synthesize information from different views; (3) incorporating multi-instance learning (MIL) to train with unannotated images and perform breast-level classification. The resulting model, M&M, is a Multi-view and Multi-instance learning system that can both localize malignant findings and provide breast-level predictions. We validate M&M's detection and classification performance using five mammography datasets. In addition, we demonstrate the effectiveness of each proposed component through comprehensive ablation studies.
{"title":"M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector","authors":"Yen Nhi Truong Vu, Dan Guo, Ahmed Taha, Jason Su, Thomas P. Matthews","doi":"10.48550/arXiv.2308.06420","DOIUrl":"https://doi.org/10.48550/arXiv.2308.06420","url":null,"abstract":"Deep-learning-based object detection methods show promise for improving screening mammography, but high rates of false positives can hinder their effectiveness in clinical practice. To reduce false positives, we identify three challenges: (1) unlike natural images, a malignant mammogram typically contains only one malignant finding; (2) mammography exams contain two views of each breast, and both views ought to be considered to make a correct assessment; (3) most mammograms are negative and do not contain any findings. In this work, we tackle the three aforementioned challenges by: (1) leveraging Sparse R-CNN and showing that sparse detectors are more appropriate than dense detectors for mammography; (2) including a multi-view cross-attention module to synthesize information from different views; (3) incorporating multi-instance learning (MIL) to train with unannotated images and perform breast-level classification. The resulting model, M&M, is a Multi-view and Multi-instance learning system that can both localize malignant findings and provide breast-level predictions. We validate M&M's detection and classification performance using five mammography datasets. In addition, we demonstrate the effectiveness of each proposed component through comprehensive ablation studies.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"238 1","pages":"778-788"},"PeriodicalIF":0.0,"publicationDate":"2023-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77826255","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 : 2023-08-10DOI: 10.48550/arXiv.2308.05365
Jiaqi Cui, Pinxian Zeng, Xinyi Zeng, Peng Wang, Xi Wu, Jiliu Zhou, Yan Wang, Dinggang Shen
To obtain high-quality positron emission tomography (PET) images while minimizing radiation exposure, various methods have been proposed for reconstructing standard-dose PET (SPET) images from low-dose PET (LPET) sinograms directly. However, current methods often neglect boundaries during sinogram-to-image reconstruction, resulting in high-frequency distortion in the frequency domain and diminished or fuzzy edges in the reconstructed images. Furthermore, the convolutional architectures, which are commonly used, lack the ability to model long-range non-local interactions, potentially leading to inaccurate representations of global structures. To alleviate these problems, we propose a transformer-based model that unites triple domains of sinogram, image, and frequency for direct PET reconstruction, namely TriDo-Former. Specifically, the TriDo-Former consists of two cascaded networks, i.e., a sinogram enhancement transformer (SE-Former) for denoising the input LPET sinograms and a spatial-spectral reconstruction transformer (SSR-Former) for reconstructing SPET images from the denoised sinograms. Different from the vanilla transformer that splits an image into 2D patches, based specifically on the PET imaging mechanism, our SE-Former divides the sinogram into 1D projection view angles to maintain its inner-structure while denoising, preventing the noise in the sinogram from prorogating into the image domain. Moreover, to mitigate high-frequency distortion and improve reconstruction details, we integrate global frequency parsers (GFPs) into SSR-Former. The GFP serves as a learnable frequency filter that globally adjusts the frequency components in the frequency domain, enforcing the network to restore high-frequency details resembling real SPET images. Validations on a clinical dataset demonstrate that our TriDo-Former outperforms the state-of-the-art methods qualitatively and quantitatively.
{"title":"TriDo-Former: A Triple-Domain Transformer for Direct PET Reconstruction from Low-Dose Sinograms","authors":"Jiaqi Cui, Pinxian Zeng, Xinyi Zeng, Peng Wang, Xi Wu, Jiliu Zhou, Yan Wang, Dinggang Shen","doi":"10.48550/arXiv.2308.05365","DOIUrl":"https://doi.org/10.48550/arXiv.2308.05365","url":null,"abstract":"To obtain high-quality positron emission tomography (PET) images while minimizing radiation exposure, various methods have been proposed for reconstructing standard-dose PET (SPET) images from low-dose PET (LPET) sinograms directly. However, current methods often neglect boundaries during sinogram-to-image reconstruction, resulting in high-frequency distortion in the frequency domain and diminished or fuzzy edges in the reconstructed images. Furthermore, the convolutional architectures, which are commonly used, lack the ability to model long-range non-local interactions, potentially leading to inaccurate representations of global structures. To alleviate these problems, we propose a transformer-based model that unites triple domains of sinogram, image, and frequency for direct PET reconstruction, namely TriDo-Former. Specifically, the TriDo-Former consists of two cascaded networks, i.e., a sinogram enhancement transformer (SE-Former) for denoising the input LPET sinograms and a spatial-spectral reconstruction transformer (SSR-Former) for reconstructing SPET images from the denoised sinograms. Different from the vanilla transformer that splits an image into 2D patches, based specifically on the PET imaging mechanism, our SE-Former divides the sinogram into 1D projection view angles to maintain its inner-structure while denoising, preventing the noise in the sinogram from prorogating into the image domain. Moreover, to mitigate high-frequency distortion and improve reconstruction details, we integrate global frequency parsers (GFPs) into SSR-Former. The GFP serves as a learnable frequency filter that globally adjusts the frequency components in the frequency domain, enforcing the network to restore high-frequency details resembling real SPET images. Validations on a clinical dataset demonstrate that our TriDo-Former outperforms the state-of-the-art methods qualitatively and quantitatively.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"91 1","pages":"184-194"},"PeriodicalIF":0.0,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78035584","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 : 2023-08-09DOI: 10.1007/978-3-031-16452-1_3
Fan Bai, Xiaohan Xing, Yutian Shen, Han Ma, Max Q.-H. Meng
{"title":"Discrepancy-Based Active Learning for Weakly Supervised Bleeding Segmentation in Wireless Capsule Endoscopy Images","authors":"Fan Bai, Xiaohan Xing, Yutian Shen, Han Ma, Max Q.-H. Meng","doi":"10.1007/978-3-031-16452-1_3","DOIUrl":"https://doi.org/10.1007/978-3-031-16452-1_3","url":null,"abstract":"","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"2 1","pages":"24-34"},"PeriodicalIF":0.0,"publicationDate":"2023-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86075772","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 : 2023-08-09DOI: 10.48550/arXiv.2308.05768
Nina Weng, M. Płomecka, Manuel Kaufmann, Ard Kastrati, Roger Wattenhofer, N. Langer
Eye movements can reveal valuable insights into various aspects of human mental processes, physical well-being, and actions. Recently, several datasets have been made available that simultaneously record EEG activity and eye movements. This has triggered the development of various methods to predict gaze direction based on brain activity. However, most of these methods lack interpretability, which limits their technology acceptance. In this paper, we leverage a large data set of simultaneously measured Electroencephalography (EEG) and Eye tracking, proposing an interpretable model for gaze estimation from EEG data. More specifically, we present a novel attention-based deep learning framework for EEG signal analysis, which allows the network to focus on the most relevant information in the signal and discard problematic channels. Additionally, we provide a comprehensive evaluation of the presented framework, demonstrating its superiority over current methods in terms of accuracy and robustness. Finally, the study presents visualizations that explain the results of the analysis and highlights the potential of attention mechanism for improving the efficiency and effectiveness of EEG data analysis in a variety of applications.
{"title":"An Interpretable and Attention-based Method for Gaze Estimation Using Electroencephalography","authors":"Nina Weng, M. Płomecka, Manuel Kaufmann, Ard Kastrati, Roger Wattenhofer, N. Langer","doi":"10.48550/arXiv.2308.05768","DOIUrl":"https://doi.org/10.48550/arXiv.2308.05768","url":null,"abstract":"Eye movements can reveal valuable insights into various aspects of human mental processes, physical well-being, and actions. Recently, several datasets have been made available that simultaneously record EEG activity and eye movements. This has triggered the development of various methods to predict gaze direction based on brain activity. However, most of these methods lack interpretability, which limits their technology acceptance. In this paper, we leverage a large data set of simultaneously measured Electroencephalography (EEG) and Eye tracking, proposing an interpretable model for gaze estimation from EEG data. More specifically, we present a novel attention-based deep learning framework for EEG signal analysis, which allows the network to focus on the most relevant information in the signal and discard problematic channels. Additionally, we provide a comprehensive evaluation of the presented framework, demonstrating its superiority over current methods in terms of accuracy and robustness. Finally, the study presents visualizations that explain the results of the analysis and highlights the potential of attention mechanism for improving the efficiency and effectiveness of EEG data analysis in a variety of applications.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"1 1","pages":"734-743"},"PeriodicalIF":0.0,"publicationDate":"2023-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89691423","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}
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
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：