Pub Date : 2023-01-01DOI: 10.1007/978-3-031-34048-2_63
Xiaodong Wu, Leixin Zhou, F. Zaman, B. Qiu, J. Buatti
{"title":"Model-Informed Deep Learning for Surface Segmentation in Medical Imaging","authors":"Xiaodong Wu, Leixin Zhou, F. Zaman, B. Qiu, J. Buatti","doi":"10.1007/978-3-031-34048-2_63","DOIUrl":"https://doi.org/10.1007/978-3-031-34048-2_63","url":null,"abstract":"","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"46 1","pages":"822-834"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81145586","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 : 2023-01-01DOI: 10.1007/978-3-031-34048-2
{"title":"Information Processing in Medical Imaging: 28th International Conference, IPMI 2023, San Carlos de Bariloche, Argentina, June 18–23, 2023, Proceedings","authors":"","doi":"10.1007/978-3-031-34048-2","DOIUrl":"https://doi.org/10.1007/978-3-031-34048-2","url":null,"abstract":"","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78651196","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 : 2023-01-01DOI: 10.1007/978-3-031-34048-2_19
Jianghao Wu, Ran Gu, Tao Lu, Shaoting Zhang, Guotai Wang
{"title":"UPL-TTA: Uncertainty-Aware Pseudo Label Guided Fully Test Time Adaptation for Fetal Brain Segmentation","authors":"Jianghao Wu, Ran Gu, Tao Lu, Shaoting Zhang, Guotai Wang","doi":"10.1007/978-3-031-34048-2_19","DOIUrl":"https://doi.org/10.1007/978-3-031-34048-2_19","url":null,"abstract":"","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"4 1","pages":"237-249"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83209823","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 : 2023-01-01DOI: 10.1007/978-3-031-34048-2_3
Huan Liu, Tingting Dan, Zhuobin Huang, Defu Yang, Won Hwa Kim, Minjeong Kim, P. Laurienti, Guorong Wu
{"title":"HoloBrain: A Harmonic Holography for Self-organized Brain Function","authors":"Huan Liu, Tingting Dan, Zhuobin Huang, Defu Yang, Won Hwa Kim, Minjeong Kim, P. Laurienti, Guorong Wu","doi":"10.1007/978-3-031-34048-2_3","DOIUrl":"https://doi.org/10.1007/978-3-031-34048-2_3","url":null,"abstract":"","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"32 1","pages":"29-40"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75504741","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 : 2023-01-01DOI: 10.1007/978-3-031-34048-2_39
Fergus Shone, N. Ravikumar, T. Lassila, Michael MacRaild, Yongxing Wang, Z. Taylor, P. Jimack, E. D. Armellina, Alejandro F Frangi
{"title":"Deep Physics-Informed Super-Resolution of Cardiac 4D-Flow MRI","authors":"Fergus Shone, N. Ravikumar, T. Lassila, Michael MacRaild, Yongxing Wang, Z. Taylor, P. Jimack, E. D. Armellina, Alejandro F Frangi","doi":"10.1007/978-3-031-34048-2_39","DOIUrl":"https://doi.org/10.1007/978-3-031-34048-2_39","url":null,"abstract":"","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"34 1","pages":"511-522"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84007690","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 : 2023-01-01DOI: 10.1007/978-3-031-34048-2_21
Taiyo Hasegawa, Helena Arvidsson, N. Tudzarovski, K. Meinke, R. Sugars, A. Nair
{"title":"Edge-Based Graph Neural Networks for Cell-Graph Modeling and Prediction","authors":"Taiyo Hasegawa, Helena Arvidsson, N. Tudzarovski, K. Meinke, R. Sugars, A. Nair","doi":"10.1007/978-3-031-34048-2_21","DOIUrl":"https://doi.org/10.1007/978-3-031-34048-2_21","url":null,"abstract":"","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"1 1","pages":"265-277"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89766452","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 : 2022-12-16DOI: 10.48550/arXiv.2212.08479
Wenqi Huang, Hongwei Li, G. Cruz, Jia-Yu Pan, D. Rueckert, K. Hammernik
In this work, we propose a novel image reconstruction framework that directly learns a neural implicit representation in k-space for ECG-triggered non-Cartesian Cardiac Magnetic Resonance Imaging (CMR). While existing methods bin acquired data from neighboring time points to reconstruct one phase of the cardiac motion, our framework allows for a continuous, binning-free, and subject-specific k-space representation.We assign a unique coordinate that consists of time, coil index, and frequency domain location to each sampled k-space point. We then learn the subject-specific mapping from these unique coordinates to k-space intensities using a multi-layer perceptron with frequency domain regularization. During inference, we obtain a complete k-space for Cartesian coordinates and an arbitrary temporal resolution. A simple inverse Fourier transform recovers the image, eliminating the need for density compensation and costly non-uniform Fourier transforms for non-Cartesian data. This novel imaging framework was tested on 42 radially sampled datasets from 6 subjects. The proposed method outperforms other techniques qualitatively and quantitatively using data from four and one heartbeat(s) and 30 cardiac phases. Our results for one heartbeat reconstruction of 50 cardiac phases show improved artifact removal and spatio-temporal resolution, leveraging the potential for real-time CMR.
{"title":"Neural Implicit k-Space for Binning-free Non-Cartesian Cardiac MR Imaging","authors":"Wenqi Huang, Hongwei Li, G. Cruz, Jia-Yu Pan, D. Rueckert, K. Hammernik","doi":"10.48550/arXiv.2212.08479","DOIUrl":"https://doi.org/10.48550/arXiv.2212.08479","url":null,"abstract":"In this work, we propose a novel image reconstruction framework that directly learns a neural implicit representation in k-space for ECG-triggered non-Cartesian Cardiac Magnetic Resonance Imaging (CMR). While existing methods bin acquired data from neighboring time points to reconstruct one phase of the cardiac motion, our framework allows for a continuous, binning-free, and subject-specific k-space representation.We assign a unique coordinate that consists of time, coil index, and frequency domain location to each sampled k-space point. We then learn the subject-specific mapping from these unique coordinates to k-space intensities using a multi-layer perceptron with frequency domain regularization. During inference, we obtain a complete k-space for Cartesian coordinates and an arbitrary temporal resolution. A simple inverse Fourier transform recovers the image, eliminating the need for density compensation and costly non-uniform Fourier transforms for non-Cartesian data. This novel imaging framework was tested on 42 radially sampled datasets from 6 subjects. The proposed method outperforms other techniques qualitatively and quantitatively using data from four and one heartbeat(s) and 30 cardiac phases. Our results for one heartbeat reconstruction of 50 cardiac phases show improved artifact removal and spatio-temporal resolution, leveraging the potential for real-time CMR.","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"59 1","pages":"548-560"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85622232","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}
{"title":"SADM: Sequence-Aware Diffusion Model for Longitudinal Medical Image Generation","authors":"Jee Seok Yoon, Chenghao Zhang, Heung-Il Suk, Jia Guo, Xiaoxia Li","doi":"10.1007/978-3-031-34048-2_30","DOIUrl":"https://doi.org/10.1007/978-3-031-34048-2_30","url":null,"abstract":"","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"20 1","pages":"388-400"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82576653","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 : 2022-11-26DOI: 10.48550/arXiv.2211.14491
W. Pan, Jiangpeng Yan, Hanbo Chen, Jiawei Yang, Zhe Xu, Xiu Li, Jianhua Yao
Recently, deep neural networks have greatly advanced histopathology image segmentation but usually require abundant annotated data. However, due to the gigapixel scale of whole slide images and pathologists' heavy daily workload, obtaining pixel-level labels for supervised learning in clinical practice is often infeasible. Alternatively, weakly-supervised segmentation methods have been explored with less laborious image-level labels, but their performance is unsatisfactory due to the lack of dense supervision. Inspired by the recent success of self-supervised learning methods, we present a label-efficient tissue prototype dictionary building pipeline and propose to use the obtained prototypes to guide histopathology image segmentation. Particularly, taking advantage of self-supervised contrastive learning, an encoder is trained to project the unlabeled histopathology image patches into a discriminative embedding space where these patches are clustered to identify the tissue prototypes by efficient pathologists' visual examination. Then, the encoder is used to map the images into the embedding space and generate pixel-level pseudo tissue masks by querying the tissue prototype dictionary. Finally, the pseudo masks are used to train a segmentation network with dense supervision for better performance. Experiments on two public datasets demonstrate that our human-machine interactive tissue prototype learning method can achieve comparable segmentation performance as the fully-supervised baselines with less annotation burden and outperform other weakly-supervised methods. Codes will be available upon publication.
{"title":"Human-machine Interactive Tissue Prototype Learning for Label-efficient Histopathology Image Segmentation","authors":"W. Pan, Jiangpeng Yan, Hanbo Chen, Jiawei Yang, Zhe Xu, Xiu Li, Jianhua Yao","doi":"10.48550/arXiv.2211.14491","DOIUrl":"https://doi.org/10.48550/arXiv.2211.14491","url":null,"abstract":"Recently, deep neural networks have greatly advanced histopathology image segmentation but usually require abundant annotated data. However, due to the gigapixel scale of whole slide images and pathologists' heavy daily workload, obtaining pixel-level labels for supervised learning in clinical practice is often infeasible. Alternatively, weakly-supervised segmentation methods have been explored with less laborious image-level labels, but their performance is unsatisfactory due to the lack of dense supervision. Inspired by the recent success of self-supervised learning methods, we present a label-efficient tissue prototype dictionary building pipeline and propose to use the obtained prototypes to guide histopathology image segmentation. Particularly, taking advantage of self-supervised contrastive learning, an encoder is trained to project the unlabeled histopathology image patches into a discriminative embedding space where these patches are clustered to identify the tissue prototypes by efficient pathologists' visual examination. Then, the encoder is used to map the images into the embedding space and generate pixel-level pseudo tissue masks by querying the tissue prototype dictionary. Finally, the pseudo masks are used to train a segmentation network with dense supervision for better performance. Experiments on two public datasets demonstrate that our human-machine interactive tissue prototype learning method can achieve comparable segmentation performance as the fully-supervised baselines with less annotation burden and outperform other weakly-supervised methods. Codes will be available upon publication.","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"89 1","pages":"679-691"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77622616","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}
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：