IEEE J Biomed Health Inform. 2021 Jun;25(6):1864-1872. doi: 10.1109/JBHI.2021.3067465. Epub 2021 Jun 3.
Chest computed tomography (CT) image data is necessary for early diagnosis, treatment, and prognosis of Coronavirus Disease 2019 (COVID-19). Artificial intelligence has been tried to help clinicians in improving the diagnostic accuracy and working efficiency of CT. Whereas, existing supervised approaches on CT image of COVID-19 pneumonia require voxel-based annotations for training, which take a lot of time and effort. This paper proposed a weakly-supervised method for COVID-19 lesion localization based on generative adversarial network (GAN) with image-level labels only. We first introduced a GAN-based framework to generate normal-looking CT slices from CT slices with COVID-19 lesions. We then developed a novel feature match strategy to improve the reality of generated images by guiding the generator to capture the complex texture of chest CT images. Finally, the localization map of lesions can be easily obtained by subtracting the output image from its corresponding input image. By adding a classifier branch to the GAN-based framework to classify localization maps, we can further develop a diagnosis system with improved classification accuracy. Three CT datasets from hospitals of Sao Paulo, Italian Society of Medical and Interventional Radiology, and China Medical University about COVID-19 were collected in this article for evaluation. Our weakly supervised learning method obtained AUC of 0.883, dice coefficient of 0.575, accuracy of 0.884, sensitivity of 0.647, specificity of 0.929, and F1-score of 0.640, which exceeded other widely used weakly supervised object localization methods by a significant margin. We also compared the proposed method with fully supervised learning methods in COVID-19 lesion segmentation task, the proposed weakly supervised method still leads to a competitive result with dice coefficient of 0.575. Furthermore, we also analyzed the association between illness severity and visual score, we found that the common severity cohort had the largest sample size as well as the highest visual score which suggests our method can help rapid diagnosis of COVID-19 patients, especially in massive common severity cohort. In conclusion, we proposed this novel method can serve as an accurate and efficient tool to alleviate the bottleneck of expert annotation cost and advance the progress of computer-aided COVID-19 diagnosis.
胸部计算机断层扫描（CT）图像数据对于 2019 年冠状病毒病（COVID-19）的早期诊断、治疗和预后是必要的。人工智能已被尝试用于帮助临床医生提高 CT 的诊断准确性和工作效率。然而，现有的 COVID-19 肺炎 CT 图像的监督方法需要基于体素的注释进行训练，这需要大量的时间和精力。本文提出了一种基于生成对抗网络（GAN）的弱监督方法，仅使用图像级标签进行 COVID-19 病变定位。我们首先引入了一个基于 GAN 的框架，从具有 COVID-19 病变的 CT 切片中生成看起来正常的 CT 切片。然后，我们开发了一种新的特征匹配策略，通过指导生成器捕获胸部 CT 图像的复杂纹理，来提高生成图像的真实性。最后，通过从其相应的输入图像中减去输出图像，可以很容易地获得病变的定位图。通过在基于 GAN 的框架中添加分类器分支对定位图进行分类，我们可以进一步开发具有更高分类准确性的诊断系统。本文从圣保罗的医院、意大利医学和介入放射学会以及中国医科大学收集了三个 COVID-19 的 CT 数据集进行评估。我们的弱监督学习方法获得了 0.883 的 AUC、0.575 的骰子系数、0.884 的准确性、0.647 的敏感性、0.929 的特异性和 0.640 的 F1 分数，这显著超过了其他广泛使用的弱监督目标定位方法。我们还将所提出的方法与 COVID-19 病变分割任务中的完全监督学习方法进行了比较，所提出的弱监督方法仍然以 0.575 的骰子系数产生了有竞争力的结果。此外，我们还分析了疾病严重程度与视觉评分之间的关联，我们发现常见严重程度队列具有最大的样本量和最高的视觉评分，这表明我们的方法可以帮助 COVID-19 患者的快速诊断，特别是在大量常见严重程度的队列中。总之，我们提出的这种新方法可以作为一种准确高效的工具，缓解专家注释成本的瓶颈，推进计算机辅助 COVID-19 诊断的进展。
