Department of Engineering and Applied Physics, University of Science and Technology of China, Hefei, China.
Department of Radiology, the First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China.
Med Phys. 2022 Jul;49(7):4632-4641. doi: 10.1002/mp.15661. Epub 2022 Apr 22.
Coronavirus disease 2019 (COVID-19) has become a global pandemic and is still posing a severe health risk to the public. Accurate and efficient segmentation of pneumonia lesions in computed tomography (CT) scans is vital for treatment decision-making. We proposed a novel unsupervised approach using a cycle consistent generative adversarial network (cycle-GAN) which automates and accelerates the process of lesion delineation.
The workflow includes lung volume segmentation, healthy lung image synthesis, infected and healthy image subtraction, and binary lesion mask generation. The lung volume was first delineated using a pre-trained U-net and worked as the input for the following network. A cycle-GAN was trained to generate synthetic healthy lung CT images from infected lung images. After that, the pneumonia lesions were extracted by subtracting the synthetic healthy lung CT images from the infected lung CT images. A median filter and k-means clustering were then applied to contour the lesions. The auto segmentation approach was validated on three different datasets.
The average Dice coefficient reached 0.666 ± 0.178 on the three datasets. Especially, the dice reached 0.748 ± 0.121 and 0.730 ± 0.095, respectively, on two public datasets Coronacases and Radiopedia. Meanwhile, the average precision and sensitivity for lesion segmentation on the three datasets were 0.679 ± 0.244 and 0.756 ± 0.162. The performance is comparable to existing supervised segmentation networks and outperforms unsupervised ones.
The proposed label-free segmentation method achieved high accuracy and efficiency in automatic COVID-19 lesion delineation. The segmentation result can serve as a baseline for further manual modification and a quality assurance tool for lesion diagnosis. Furthermore, due to its unsupervised nature, the result is not influenced by physicians' experience which otherwise is crucial for supervised methods.
2019 年冠状病毒病（COVID-19）已成为全球性大流行病，仍然对公众健康构成严重威胁。在计算机断层扫描（CT）扫描中准确且高效地分割肺炎病变对于治疗决策至关重要。我们提出了一种新颖的无监督方法，使用循环一致生成对抗网络（cycle-GAN），实现病变勾画的自动化和加速。
该工作流程包括肺容积分割、健康肺图像合成、感染和健康图像相减以及二值病变掩模生成。首先使用预训练的 U-net 进行肺容积勾画，并作为后续网络的输入。训练一个循环-GAN 从感染肺图像生成合成的健康肺 CT 图像。然后，通过从感染肺 CT 图像中减去合成的健康肺 CT 图像来提取肺炎病变。然后应用中值滤波器和 K 均值聚类来勾勒病变轮廓。该自动分割方法在三个不同的数据集上进行了验证。
三个数据集的平均 Dice 系数达到 0.666±0.178。特别是，在两个公共数据集 Coronacases 和 Radiopedia 上，Dice 系数分别达到 0.748±0.121 和 0.730±0.095。同时，三个数据集上的病变分割平均精度和敏感度分别为 0.679±0.244 和 0.756±0.162。该性能可与现有的有监督分割网络相媲美，优于无监督方法。
所提出的无标签分割方法在 COVID-19 病变自动勾画中达到了高精度和高效率。分割结果可作为进一步手动修改的基线，并作为病变诊断的质量保证工具。此外，由于其无监督性质，结果不受医师经验的影响，而这对有监督方法至关重要。
