MTL-ABS3Net: Atlas-Based Semi-Supervised Organ Segmentation Network With Multi-Task Learning for Medical Images
MTL-ABS3Net: Atlas-Based Semi-Supervised Organ Segmentation Network With Multi-Task Learning for Medical Images
复制标题
基于atlas的医学图像多任务学习半监督器官分割网络
DOI：
10.1109/jbhi.2022.3153406
复制
发表时间：
2022-02
影响因子：
7.7
通讯作者：
Huimin Huang;Qingqing Chen;Lanfen Lin;Ming Cai;Qiaowei Zhang;Yutaro Iwamoto;Xianhua Han;Akira Furukaw
中科院分区：
文献类型：
--
作者：
Huimin Huang;Qingqing Chen;Lanfen Lin;Ming Cai;Qiaowei Zhang;Yutaro Iwamoto;Xianhua Han;Akira Furukaw
器官分割是各种医学图像分析任务的重要步骤之一。近年来，半监督学习（semi-supervised learning， SSL）因降低标注成本而备受关注。然而，现有的SSLs大多忽略了医学图像的先验形状和位置信息，导致物体定位不理想，不光滑。本文提出了一种新的基于图谱的医学器官多任务学习半监督分割网络MTL-ABS3Net，该网络结合解剖先验，充分利用未标记数据进行自我训练和多任务学习。MTL-ABS3Net由两个部分组成：基于atlas的半监督分割网络（ABS3Net）和重构辅助模块（RAM）。具体来说，ABS3Net利用atlas先验对现有ssl进行改进，以自我训练的方式生成可信的伪标签；RAM以多任务学习的方式从原始图像中捕获解剖结构，进一步辅助分割网络。利用MS-SSIM损失函数获得了较好的重构质量，进一步提高了分割精度。肝脏和脾脏数据集的实验结果表明，与现有的最先进的方法相比，我们的方法的性能得到了显着提高。
Organ segmentation is one of the most important step for various medical image analysis tasks. Recently, semi-supervised learning (SSL) has attracted much attentions by reducing labeling cost. However, most of the existing SSLs neglected the prior shape and position information specialized in the medical images, leading to unsatisfactory localization and non-smooth of objects. In this paper, we propose a novel atlas-based semi-supervised segmentation network with multi-task learning for medical organs, named MTL-ABS3Net, which incorporates the anatomical priors and makes full use of unlabeled data in a self-training and multi-task learning manner. The MTL-ABS3Net consists of two components: an Atlas-Based Semi-Supervised Segmentation Network (ABS3Net) and Reconstruction-Assisted Module (RAM). Specifically, the ABS3Net improves the existing SSLs by utilizing atlas prior, which generates credible pseudo labels in a self-training manner; while the RAM further assists the segmentation network by capturing the anatomical structures from the original images in a multi-task learning manner. Better reconstruction quality is achieved by using MS-SSIM loss function, which further improves the segmentation accuracy. Experimental results from the liver and spleen datasets demonstrated that the performance of our method was significantly improved compared to existing state-of-the-art methods.