[论文解读] Deep learning to estimate the physical proportion of infected region of lung for COVID-19 pneumonia with CT image set

Wei Wu, Yu Shi+6 more|arXiv (Cornell University)|Jun 9, 2020

COVID-19 diagnosis using AI参考文献 7被引用 5

一句话总结

本研究提出一种基于2.5D UNet的深度学习框架，通过CT扫描估算COVID-19患者肺部受感染的物理比例。通过结合基于Hounsfield值的初始化与放射科医生验证的掩码，该方法在感染区域实现了0.757的Dice分数，并与真实值的相关系数达到0.961，实现了对疾病严重程度的精确、定量评估。

ABSTRACT

Utilizing computed tomography (CT) images to quickly estimate the severity of cases with COVID-19 is one of the most straightforward and efficacious methods. Two tasks were studied in this present paper. One was to segment the mask of intact lung in case of pneumonia. Another was to generate the masks of regions infected by COVID-19. The masks of these two parts of images then were converted to corresponding volumes to calculate the physical proportion of infected region of lung. A total of 129 CT image set were herein collected and studied. The intrinsic Hounsfiled value of CT images was firstly utilized to generate the initial dirty version of labeled masks both for intact lung and infected regions. Then, the samples were carefully adjusted and improved by two professional radiologists to generate the final training set and test benchmark. Two deep learning models were evaluated: UNet and 2.5D UNet. For the segment of infected regions, a deep learning based classifier was followed to remove unrelated blur-edged regions that were wrongly segmented out such as air tube and blood vessel tissue etc. For the segmented masks of intact lung and infected regions, the best method could achieve 0.972 and 0.757 measure in mean Dice similarity coefficient on our test benchmark. As the overall proportion of infected region of lung, the final result showed 0.961 (Pearson's correlation coefficient) and 11.7% (mean absolute percent error). The instant proportion of infected regions of lung could be used as a visual evidence to assist clinical physician to determine the severity of the case. Furthermore, a quantified report of infected regions can help predict the prognosis for COVID-19 cases which were scanned periodically within the treatment cycle.

研究动机与目标

• 开发一种深度学习方法，用于自动分割COVID-19 CT扫描中的健康与感染肺部区域。
• 估算感染肺组织的物理体积比例，以支持临床严重程度评估。
• 通过结合Hounsfield值先验与专家标注的真实标签，提高分割精度。
• 生成可量化、可重复的指标，用于监测治疗期间疾病进展。

提出的方法

• 利用CT扫描中的固有Hounsfield单位（HU）值，生成健康与感染肺部区域的初始分割掩码。
• 采用两阶段优化流程：首先，基于HU值的阈值处理生成初始脏标签掩码；其次，放射科医生手动校正这些掩码，以生成高质量的训练与测试数据集。
• 训练两种深度学习模型——标准UNet与2.5D UNet——以优化健康与感染肺部区域的分割效果。
• 应用后处理分类器，从感染区域预测中移除如气道和血管等假阳性结果。
• 通过将分割掩码转换为3D体积，计算最终的感染体积，实现物理比例的估算。
• 使用Dice相似系数与放射科医生验证的真实标签之间的皮尔逊相关系数评估模型性能。

实验结果

研究问题

• RQ1 基于HU值初始化与专家标注数据，深度学习模型能否在COVID-19 CT扫描中准确分割健康与感染肺部区域？
• RQ2 2.5D UNet架构在从CT图像分割感染肺部区域方面，与标准UNet相比表现如何？
• RQ3 预测的感染体积在多大程度上能与真实肺部受累的物理比例相关？
• RQ4 该框架能否生成可靠、可量化的感染负担报告，以支持临床监测与预后评估？

主要发现

• 在测试集中，该模型对健康肺部分割的平均Dice相似系数达到0.972。
• 对于感染肺部区域的分割，最佳模型的Dice分数为0.757。
• 预测的感染体积与真实物理比例之间的皮尔逊相关系数为0.961。
• 估算感染体积比例的平均绝对百分比误差为11.7%。
• 通过专用的后处理分类器，该框架成功减少了气道和血管等结构引起的假阳性结果。
• 最终生成的物理比例估算值为评估疾病严重程度与追踪治疗反应提供了可靠、可量化的指标。