Pub Date : 2023-04-27DOI: 10.48550/arXiv.2304.14071
Yuchen Zhang, Y. Meng, Yalin Zheng
Atrial fibrillation (AF) is the most common cardiac arrhythmia. Accurate segmentation of the left atrial (LA) and LA scars can provide valuable information to predict treatment outcomes in AF. In this paper, we proposed to automatically segment LA cavity and quantify LA scars with late gadolinium enhancement Magnetic Resonance Imagings (LGE-MRIs). We adopted nnU-Net as the baseline model and exploited the importance of LA boundary characteristics with the TopK loss as the loss function. Specifically, a focus on LA boundary pixels is achieved during training, which provides a more accurate boundary prediction. On the other hand, a distance map transformation of the predicted LA boundary is regarded as an additional input for the LA scar prediction, which provides marginal constraint on scar locations. We further designed a novel uncertainty-aware module (UAM) to produce better results for predictions with high uncertainty. Experiments on the LAScarQS 2022 dataset demonstrated our model's superior performance on the LA cavity and LA scar segmentation. Specifically, we achieved 88.98% and 64.08% Dice coefficient for LA cavity and scar segmentation, respectively. We will make our implementation code public available at https://github.com/level6626/Boundary-focused-nnU-Net.
{"title":"Automatically Segment the Left Atrium and Scars from LGE-MRIs Using a Boundary-focused nnU-Net","authors":"Yuchen Zhang, Y. Meng, Yalin Zheng","doi":"10.48550/arXiv.2304.14071","DOIUrl":"https://doi.org/10.48550/arXiv.2304.14071","url":null,"abstract":"Atrial fibrillation (AF) is the most common cardiac arrhythmia. Accurate segmentation of the left atrial (LA) and LA scars can provide valuable information to predict treatment outcomes in AF. In this paper, we proposed to automatically segment LA cavity and quantify LA scars with late gadolinium enhancement Magnetic Resonance Imagings (LGE-MRIs). We adopted nnU-Net as the baseline model and exploited the importance of LA boundary characteristics with the TopK loss as the loss function. Specifically, a focus on LA boundary pixels is achieved during training, which provides a more accurate boundary prediction. On the other hand, a distance map transformation of the predicted LA boundary is regarded as an additional input for the LA scar prediction, which provides marginal constraint on scar locations. We further designed a novel uncertainty-aware module (UAM) to produce better results for predictions with high uncertainty. Experiments on the LAScarQS 2022 dataset demonstrated our model's superior performance on the LA cavity and LA scar segmentation. Specifically, we achieved 88.98% and 64.08% Dice coefficient for LA cavity and scar segmentation, respectively. We will make our implementation code public available at https://github.com/level6626/Boundary-focused-nnU-Net.","PeriodicalId":138957,"journal":{"name":"LAScarQS@MICCAI","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115094108","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}
Thanks to the capacity for long-range dependencies and robustness to irregular shapes, vision transformers and deformable convolutions are emerging as powerful vision techniques of segmentation.Meanwhile, Graph Convolution Networks (GCN) optimize local features based on global topological relationship modeling. Particularly, they have been proved to be effective in addressing issues in medical imaging segmentation tasks including multi-domain generalization for low-quality images. In this paper, we present a novel, effective, and robust framework for medical image segmentation, namely, UGformer. It unifies novel transformer blocks, GCN bridges, and convolution decoders originating from U-Net to predict left atriums (LAs) and LA scars. We have identified two appealing findings of the proposed UGformer: 1). an enhanced transformer module with deformable convolutions to improve the blending of the transformer information with convolutional information and help predict irregular LAs and scar shapes. 2). Using a bridge incorporating GCN to further overcome the difficulty of capturing condition inconsistency across different Magnetic Resonance Images scanners with various inconsistent domain information. The proposed UGformer model exhibits outstanding ability to segment the left atrium and scar on the LAScarQS 2022 dataset, outperforming several recent state-of-the-arts.
{"title":"UGformer for Robust Left Atrium and Scar Segmentation Across Scanners","authors":"Tianyi Liu, Size Hou, Jiayu Zhu, Zilong Zhao, Haochuan Jiang","doi":"10.48550/arXiv.2210.05151","DOIUrl":"https://doi.org/10.48550/arXiv.2210.05151","url":null,"abstract":"Thanks to the capacity for long-range dependencies and robustness to irregular shapes, vision transformers and deformable convolutions are emerging as powerful vision techniques of segmentation.Meanwhile, Graph Convolution Networks (GCN) optimize local features based on global topological relationship modeling. Particularly, they have been proved to be effective in addressing issues in medical imaging segmentation tasks including multi-domain generalization for low-quality images. In this paper, we present a novel, effective, and robust framework for medical image segmentation, namely, UGformer. It unifies novel transformer blocks, GCN bridges, and convolution decoders originating from U-Net to predict left atriums (LAs) and LA scars. We have identified two appealing findings of the proposed UGformer: 1). an enhanced transformer module with deformable convolutions to improve the blending of the transformer information with convolutional information and help predict irregular LAs and scar shapes. 2). Using a bridge incorporating GCN to further overcome the difficulty of capturing condition inconsistency across different Magnetic Resonance Images scanners with various inconsistent domain information. The proposed UGformer model exhibits outstanding ability to segment the left atrium and scar on the LAScarQS 2022 dataset, outperforming several recent state-of-the-arts.","PeriodicalId":138957,"journal":{"name":"LAScarQS@MICCAI","volume":"272 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133852040","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}
Automatic segmentation of left atrial (LA) scars from late gadolinium enhanced CMR images is a crucial step for atrial fibrillation (AF) recurrence analysis. However, delineating LA scars is tedious and error-prone due to the variation of scar shapes. In this work, we propose a boundary-aware LA scar segmentation network, which is composed of two branches to segment LA and LA scars, respectively. We explore the inherent spatial relationship between LA and LA scars. By introducing a Sobel fusion module between the two segmentation branches, the spatial information of LA boundaries can be propagated from the LA branch to the scar branch. Thus, LA scar segmentation can be performed condition on the LA boundaries regions. In our experiments, 40 labeled images were used to train the proposed network, and the remaining 20 labeled images were used for evaluation. The network achieved an average Dice score of 0.608 for LA scar segmentation.
{"title":"Multi-Depth Boundary-Aware Left Atrial Scar Segmentation Network","authors":"Meng-Yun Wu, Wangbin Ding, Mingjing Yang, Liqin Huang","doi":"10.48550/arXiv.2208.04940","DOIUrl":"https://doi.org/10.48550/arXiv.2208.04940","url":null,"abstract":"Automatic segmentation of left atrial (LA) scars from late gadolinium enhanced CMR images is a crucial step for atrial fibrillation (AF) recurrence analysis. However, delineating LA scars is tedious and error-prone due to the variation of scar shapes. In this work, we propose a boundary-aware LA scar segmentation network, which is composed of two branches to segment LA and LA scars, respectively. We explore the inherent spatial relationship between LA and LA scars. By introducing a Sobel fusion module between the two segmentation branches, the spatial information of LA boundaries can be propagated from the LA branch to the scar branch. Thus, LA scar segmentation can be performed condition on the LA boundaries regions. In our experiments, 40 labeled images were used to train the proposed network, and the remaining 20 labeled images were used for evaluation. The network achieved an average Dice score of 0.608 for LA scar segmentation.","PeriodicalId":138957,"journal":{"name":"LAScarQS@MICCAI","volume":"350 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126951274","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 : 1900-01-01DOI: 10.1007/978-3-031-31778-1_15
Moona Mazher, Abdul Qayyum, M. Abdel-Nasser, D. Puig
{"title":"Automatic Semi-supervised Left Atrial Segmentation Using Deep-Supervision 3DResUnet with Pseudo Labeling Approach for LAScarQS 2022 Challenge","authors":"Moona Mazher, Abdul Qayyum, M. Abdel-Nasser, D. Puig","doi":"10.1007/978-3-031-31778-1_15","DOIUrl":"https://doi.org/10.1007/978-3-031-31778-1_15","url":null,"abstract":"","PeriodicalId":138957,"journal":{"name":"LAScarQS@MICCAI","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114977137","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 : 1900-01-01DOI: 10.1007/978-3-031-31778-1_10
S. Ogbomo-Harmitt, Jakub Grzelak, A. Qureshi, A. King, O. Aslanidi
{"title":"TESSLA: Two-Stage Ensemble Scar Segmentation for the Left Atrium","authors":"S. Ogbomo-Harmitt, Jakub Grzelak, A. Qureshi, A. King, O. Aslanidi","doi":"10.1007/978-3-031-31778-1_10","DOIUrl":"https://doi.org/10.1007/978-3-031-31778-1_10","url":null,"abstract":"","PeriodicalId":138957,"journal":{"name":"LAScarQS@MICCAI","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114155623","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 : 1900-01-01DOI: 10.1007/978-3-031-31778-1_12
Feiyan Li, Weisheng Li
{"title":"Cross-Domain Segmentation of Left Atrium Based on Multi-scale Decision Level Fusion","authors":"Feiyan Li, Weisheng Li","doi":"10.1007/978-3-031-31778-1_12","DOIUrl":"https://doi.org/10.1007/978-3-031-31778-1_12","url":null,"abstract":"","PeriodicalId":138957,"journal":{"name":"LAScarQS@MICCAI","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131870488","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 : 1900-01-01DOI: 10.1007/978-3-031-31778-1_13
T. Arega, S. Bricq, F. Mériaudeau
{"title":"Using Polynomial Loss and Uncertainty Information for Robust Left Atrial and Scar Quantification and Segmentation","authors":"T. Arega, S. Bricq, F. Mériaudeau","doi":"10.1007/978-3-031-31778-1_13","DOIUrl":"https://doi.org/10.1007/978-3-031-31778-1_13","url":null,"abstract":"","PeriodicalId":138957,"journal":{"name":"LAScarQS@MICCAI","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123350071","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 : 1900-01-01DOI: 10.1007/978-3-031-31778-1_14
K. Punithakumar, M. Noga
{"title":"Automated Segmentation of the Left Atrium and Scar Using Deep Convolutional Neural Networks","authors":"K. Punithakumar, M. Noga","doi":"10.1007/978-3-031-31778-1_14","DOIUrl":"https://doi.org/10.1007/978-3-031-31778-1_14","url":null,"abstract":"","PeriodicalId":138957,"journal":{"name":"LAScarQS@MICCAI","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131246644","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 : 1900-01-01DOI: 10.1007/978-3-031-31778-1_11
Lei Jiang, Yan Li, Y. Wang, Hengfei Cui, Yong Xia, Yanning Zhang
{"title":"Deep U-Net Architecture with Curriculum Learning for Left Atrial Segmentation","authors":"Lei Jiang, Yan Li, Y. Wang, Hengfei Cui, Yong Xia, Yanning Zhang","doi":"10.1007/978-3-031-31778-1_11","DOIUrl":"https://doi.org/10.1007/978-3-031-31778-1_11","url":null,"abstract":"","PeriodicalId":138957,"journal":{"name":"LAScarQS@MICCAI","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127187330","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：