[论文解读] Lung Infection Quantification of COVID-19 in CT Images with Deep Learning

Fei Shan, Yaozong Gao+7 more|arXiv (Cornell University)|Mar 10, 2020

COVID-19 diagnosis using AI参考文献 35被引用 537

一句话总结

一个深度学习分割系统自动量化 CT 扫描中的 COVID-19 肺部感染，与手工注释高度一致，感染百分比误差低，并在人的参与回路策略帮助下加速训练与纠正。

ABSTRACT

CT imaging is crucial for diagnosis, assessment and staging COVID-19 infection. Follow-up scans every 3-5 days are often recommended for disease progression. It has been reported that bilateral and peripheral ground glass opacification (GGO) with or without consolidation are predominant CT findings in COVID-19 patients. However, due to lack of computerized quantification tools, only qualitative impression and rough description of infected areas are currently used in radiological reports. In this paper, a deep learning (DL)-based segmentation system is developed to automatically quantify infection regions of interest (ROIs) and their volumetric ratios w.r.t. the lung. The performance of the system was evaluated by comparing the automatically segmented infection regions with the manually-delineated ones on 300 chest CT scans of 300 COVID-19 patients. For fast manual delineation of training samples and possible manual intervention of automatic results, a human-in-the-loop (HITL) strategy has been adopted to assist radiologists for infection region segmentation, which dramatically reduced the total segmentation time to 4 minutes after 3 iterations of model updating. The average Dice simiarility coefficient showed 91.6% agreement between automatic and manual infaction segmentations, and the mean estimation error of percentage of infection (POI) was 0.3% for the whole lung. Finally, possible applications, including but not limited to analysis of follow-up CT scans and infection distributions in the lobes and segments correlated with clinical findings, were discussed.

研究动机与目标

• 开发基于 DL 的系统，自动量化来自 CT 图像的肺部感染区域（ROI）及其体积比。
• 在尽量少的人工干预下提供自动分割。
• 通过 HITL 实现快速的训练样本轮廓绘制与纠正更新，以加速工作流程。

提出的方法

• 训练深度学习分割模型以识别胸部 CT 扫描中的感染区域。
• 在来自 300 名患者的 300 次扫描上，将自动分割与手动勾画进行比较。
• 将人-in-loop（HITL）策略融入，以帮助放射科医生更快完成勾画并进行模型更新（3 次迭代）。
• 使用自动分割与手动分割之间的 Dice 相似系数来评估性能。
• 报告全肺感染百分比（POI）的平均误差。

实验结果

研究问题

• RQ1 基于 DL 的分割系统能否在 COVID-19 CT 图像中准确量化感染区域？
• RQ2 在大规模患者集上，自动与手动感染分割之间的一致性是多少？
• RQ3 HITL 方法是否在迭代过程中降低手动勾画时间并改善分割更新？
• RQ4 全肺感染比例（POI）估计的准确性是多少？

主要发现

• 自动与手动感染分割之间的 Dice 相似系数平均为 91.6%。
• 全肺感染百分比（POI）的平均估计误差为 0.3%。
• HITL 方法在模型更新 3 次迭代后将总分割时间显著降低至 4 分钟。