X-ray Image Segmentation using Multi-task Learning
X-ray Image Segmentation using Multi-task Learning
复制标题
DOI：
10.3837/tiis.2020.03.011
复制
发表时间：
2020-03-31
影响因子：
1.5
通讯作者：
Moon, Young Shik
中科院分区：
文献类型：
--
作者：
Park, Sejin;Jeong, Woojin;Moon, Young Shik
胸部 X 光检查是诊断肺癌或肺炎的常用方法。尤其是肺结节的发现是肺癌早期发现的最重要问题。最近，人们研究了很多自动诊断算法来寻找医生遗漏的肺结节。这些算法通常基于 U-Net 等分割网络。然而，类似于肺外存在的肺结节的假阳性的发生会严重降低性能。在本研究中，我们提出了一种多任务学习方法，基于肺结节仅存在于肺部的先验知识，同时学习肺部区域和结节标记数据。与U-net模型单任务学习的66.6 F1分数相比，该方法显着减少了肺外的误报，并将肺结节的识别率提高到83.8 F1分数。 JSRT公共数据集上的实验结果证明了该方法与其他基线方法相比的有效性。
The chest X-rays are a common way to diagnose lung cancer or pneumonia. In particular, the finding of a lung nodule is the most important problem in the early detection of lung cancer. Recently, a lot of automatic diagnosis algorithms have been studied to find the lung nodules missed by doctors. The algorithms are typically based on segmentation network like U-Net. However, the occurrence of false positives that similar to lung nodules present outside the lungs can severely degrade performance. In this study, we propose a multi-task learning method that simultaneously learns the lung region and nodule-labeled data based on the prior knowledge that lung nodules exist only in the lung. The proposed method significantly reduces false positives outside the lung and improves the recognition rate of lung nodules to 83.8 F1 score compared to 66.6 F1 score of single task learning with U-net model. The experimental results on the JSRT public dataset demonstrate the effectiveness of the proposed method compared with other baseline methods.