Wei Zeliang, Chen Xicheng, Huang Jialu, Wang Zhenyan, Yao Tianhua, Gao Chengcheng, Wang Haojia, Li Pengpeng, Ye Wei, Li Yang, Yao Ning, Zhang Rui, Tang Ning, Wang Fei, Hu Jun, Yi Dong, Wu Yazhou
Department of Health Statistics, College of Preventive Medicine, Army Medical University, Chongqing, China.
Department of Neurology, Southwest Hospital, Army Medical University, Chongqing, China.
Front Bioeng Biotechnol. 2022 Jul 20;10:937314. doi: 10.3389/fbioe.2022.937314. eCollection 2022.
The detection and segmentation of cerebral microbleeds (CMBs) images are the focus of clinical diagnosis and treatment. However, segmentation is difficult in clinical practice, and missed diagnosis may occur. Few related studies on the automated segmentation of CMB images have been performed, and we provide the most effective CMB segmentation to date using an automated segmentation system. From a research perspective, we focused on the automated segmentation of CMB targets in susceptibility weighted imaging (SWI) for the first time and then constructed a deep learning network focused on the segmentation of micro-objects. We collected and marked clinical datasets and proposed a new medical micro-object cascade network (MMOC-Net). In the first stage, U-Net was utilized to select the region of interest (ROI). In the second stage, we utilized a full-resolution network (FRN) to complete fine segmentation. We also incorporated residual atrous spatial pyramid pooling (R-ASPP) and a new joint loss function. The most suitable segmentation result was achieved with a ROI size of 32 × 32. To verify the validity of each part of the method, ablation studies were performed, which showed that the best segmentation results were obtained when FRN, R-ASPP and the combined loss function were used simultaneously. Under these conditions, the obtained Dice similarity coefficient (DSC) value was 87.93% and the F2-score (F2) value was 90.69%. We also innovatively developed a visual clinical diagnosis system that can provide effective support for clinical diagnosis and treatment decisions. We created the MMOC-Net method to perform the automated segmentation task of CMBs in an SWI and obtained better segmentation performance; hence, this pioneering method has research significance.
脑微出血（CMB）图像的检测与分割是临床诊断和治疗的重点。然而，在临床实践中分割存在困难，可能会出现漏诊。目前关于CMB图像自动分割的相关研究较少，我们使用自动分割系统提供了迄今为止最有效的CMB分割方法。从研究角度来看，我们首次专注于对磁敏感加权成像（SWI）中的CMB目标进行自动分割，然后构建了一个专注于微物体分割的深度学习网络。我们收集并标记了临床数据集，提出了一种新的医学微物体级联网络（MMOC-Net）。在第一阶段，利用U-Net选择感兴趣区域（ROI）。在第二阶段，我们利用全分辨率网络（FRN）完成精细分割。我们还纳入了残差空洞空间金字塔池化（R-ASPP）和一种新的联合损失函数。当ROI大小为32×32时，获得了最合适的分割结果。为了验证该方法各部分的有效性，进行了消融研究，结果表明当同时使用FRN、R-ASPP和联合损失函数时，获得了最佳分割结果。在这些条件下，获得的骰子相似系数（DSC）值为87.93%，F2分数（F2）值为90.69%。我们还创新性地开发了一种视觉临床诊断系统，可为临床诊断和治疗决策提供有效支持。我们创建了MMOC-Net方法来执行SWI中CMB的自动分割任务，并获得了更好的分割性能；因此，这种开创性方法具有研究意义。
