D-UNet: a dimension-fusion U shape network for chronic stroke lesion segmentation
Shenzhen University（深圳大学）；University of Sydney（悉尼大学）；Northwestern Polytechnical University（西北工业大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Yongjin Zhou, Weijian Huang, Pei Dong, Yong Xia, Shanshan Wang
发表信息：
IEEE/ACM Transactions on Computational Biology and Bioinformatics (2019)
Assessing the location and extent of lesions caused by chronic stroke is critical for medical diagnosis, surgical planning, and prognosis. In recent years, with the rapid development of 2D and 3D convolutional neural networks (CNN), the encoder-decoder structure has shown great potential in the field of medical image segmentation. However, the 2D CNN ignores the 3D information of medical images, while the 3D CNN suffers from high computational resource demands. This paper proposes a new architecture called dimension-fusion-UNet (D-UNet), which combines 2D and 3D convolution innovatively in the encoding stage. The proposed architecture achieves a better segmentation performance than 2D networks, while requiring significantly less computation time in comparison to 3D networks. Furthermore, to alleviate the data imbalance issue between positive and negative samples for the network training, we propose a new loss function called Enhance Mixing Loss (EML). This function adds a weighted focal coefficient and combines two traditional loss functions. The proposed method has been tested on the ATLAS dataset and compared to three state-of-the-art methods. The results demonstrate that the proposed method achieves the best quality performance in terms of DSC = 0.5349+0.2763 and precision = 0.6331+0.295).
University of Chinese Academy of Sciences（中国科学院大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Guizhou Provincial People’s Hospital（贵州省人民医院）；Henan Provincial People’s Hospital（河南省人民医院）；Shenzhen University（深圳大学）
Segmenting stroke lesions from T1-weighted MR images is of great value for large-scale stroke rehabilitation neuroimaging analyses. Nevertheless, there are great challenges with this task, such as large range of stroke lesion scales and the tissue intensity similarity. The famous encoder-decoder convolutional neural network, which although has made great achievements in medical image segmentation areas, may fail to address these challenges due to the insufficient uses of multi-scale features and context information. To address these challenges, this paper proposes a Cross-Level fusion and Cont…
Geisel School of Medicine at Dartmouth（达特茅斯盖泽尔医学院）；Dartmouth College（达特茅斯学院）；Dartmouth-Hitchcock Medical Center（达特茅斯-希区柯克医学中心）
In this paper, we demonstrate the feasibility and performance of deep residual neural networks for volumetric segmentation of irreversibly damaged brain tissue lesions on T1-weighted MRI scans for chronic stroke patients. A total of 239 T1-weighted MRI scans of chronic ischemic stroke patients from a public dataset were retrospectively analyzed by 3D deep convolutional segmentation models with residual learning, using a novel zoom-in&out strategy. Dice similarity coefficient (DSC), Average symmetric surface distance (ASSD), and Hausdorff distance (HD) of the identified lesions were measured by…
An Automatic Cascaded Model for Hemorrhagic Stroke Segmentation and Hemorrhagic Volume Estimation
Beijing University of Posts and Telecommunications（北京邮电大学）；Tianjin Medical University General Hospital（天津医科大学总医院）；Kailuan General Hospital（开滦总医院）；Erasmus MC（伊拉斯姆斯大学医学中心）
Domain-Agnostic Stroke Lesion Segmentation Using Physics-Constrained Synthetic Data
Department of Imaging Neuroscience, University College London（影像神经科学系，伦敦大学学院）；Institute of Cognitive Neuroscience, University College London（认知神经科学研究所，伦敦大学学院）
A region and category confidence-based multi-task network for carotid ultrasound image segmentation and classification
Hubei University of Technology（湖北工业大学）；Liyuan Hospital, Tongji Medical College, Huazhong University of Science and Technology（华中科技大学同济医学院附属梨园医院）；Zhongnan Hospital, Wuhan University（武汉大学中南医院）；Robarts Research Institute, Western University（西安大略大学罗伯茨研究所）
Dual-Encoder Transformer-Based Multimodal Learning for Ischemic Stroke Lesion Segmentation Using Diffusion MRI
Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University（麻醉学、围术期与疼痛医学系，斯坦福大学）；Department of Biomedical Sciences, Seoul National University（生物医学科学系，首尔国立大学）；Department of Computer Engineering, National University of Sciences and Technology (NUST)（计算机工程系，国立科学与技术大学（NUST））；Department of Computer Science, The University of Alabama（计算机科学系，阿拉巴马大学）；Department of Computer Science, Hanyang University（计算机科学系，翰阳大学）
Meta-Analysis of Transfer Learning for Segmentation of Brain Lesions
Institute for Applied Life Sciences, University of Massachusetts（马萨诸塞大学应用生命科学研究所）；Manning College of Information and Computer Sciences, University of Massachusetts（马萨诸塞大学曼宁信息与计算机科学学院）；Department of Biomedical Engineering, University of Massachusetts（马萨诸塞大学生物医学工程系）；Baystate Medical Center（贝州医疗中心）；UMass Chan Medical School - Baystate Campus（马萨诸塞大学陈医学院贝州校区）；Department of Electrical and Computer Engineering, University of Massachusetts（马萨诸塞大学电气与计算机工程系）；Department of Neurology, Baystate Medical Center（贝州医疗中心神经内科）
An automated framework for brain vessel centerline extraction from CTA images
Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（西安交通大学人工智能与机器人研究所）；Department of Radiology, Erasmus MC（伊拉斯姆斯大学医学中心放射科）；Department of Radiology, Maastricht UMC（马斯特里赫特大学医学中心放射科）；Faculty of Applied Sciences, Delft University of Technology（代尔夫特理工大学应用科学学院）
City College New York（纽约市立学院）；Memorial Sloan Kettering Cancer Center（纪念斯隆凯特琳癌症中心）
Purpose: Conventional automated segmentation of the head anatomy in MRI distinguishes different brain and non-brain tissues based on image intensities and prior tissue probability maps (TPM). This works well for normal head anatomies, but fails in the presence of unexpected lesions. Deep convolutional neural networks leverage instead spatial patterns and can learn to segment lesions, but often ignore prior probabilities. Approach: We add three sources of prior information to a three-dimensional convolutional network, namely, spatial priors with a TPM, morphological priors with conditional rand…
