Yu Hanyi, Sharifai Nima, Jiang Kun, Wang Fusheng, Teodoro George, Farris Alton B, Kong Jun
Department of Computer Science, Emory University, Atlanta, 30322, GA, USA.
Department of Pathology, University of Maryland School of Medicine, Baltimore, 21201, MD, USA.
Comput Biol Med. 2022 Nov;150:106089. doi: 10.1016/j.compbiomed.2022.106089. Epub 2022 Sep 6.
Liver fibrosis staging is clinically important for liver disease progression prediction. As the portal tract fibrotic quantity and size in a liver biopsy correlate with the fibrosis stage, an accurate analysis of portal tract regions is clinically critical. Manual annotations of portal tract regions, however, are time-consuming and subject to large inter- and intra-observer variability. To address such a challenge, we develop a Multiple Up-sampling and Spatial Attention guided UNet model (MUSA-UNet) to segment liver portal tract regions in whole-slide images of liver tissue slides. To enhance the segmentation performance, we propose to use depth-wise separable convolution, the spatial attention mechanism, the residual connection, and multiple up-sampling paths in the developed model. This study includes 53 histopathology whole slide images from patients who received liver transplantation. In total, 6,012 patches derived from 30 images are used for our deep learning model training and validation. The remaining 23 whole slide images are utilized for the model testing. The average liver portal tract segmentation performance of the developed MUSA-UNet is 0.94 (Precision), 0.85 (Recall), 0.89 (F1 Score), 0.89 (Accuracy), 0.80 (Jaccard Index), and 0.91 (Fowlkes-Mallows Index), respectively. The clinical Scheuer fibrosis stage presents a strong correlation with the resulting average portal tract fibrotic area (R = 0.681, p<0.001) and portal tract percentage (R = 0.335, p = 0.02) computed from the MUSA-UNet segmentation results. In conclusion, our developed deep learning model MUSA-UNet can accurately segment portal tract regions from whole-slide images of liver tissue biopsies, presenting its promising potential to assist liver disease diagnosis in a computational manner.
肝纤维化分期对于预测肝脏疾病进展具有重要的临床意义。由于肝活检中门管区纤维化的数量和大小与纤维化分期相关，因此对门管区进行准确分析在临床上至关重要。然而，手动标注门管区既耗时，又容易受到观察者间和观察者内的较大差异影响。为应对这一挑战，我们开发了一种多重上采样和空间注意力引导的UNet模型（MUSA-UNet），用于在肝组织切片的全切片图像中分割肝门管区。为提高分割性能，我们建议在开发的模型中使用深度可分离卷积、空间注意力机制、残差连接和多重上采样路径。本研究纳入了53例接受肝移植患者的组织病理学全切片图像。总共从30张图像中提取了6012个图像块，用于我们的深度学习模型训练和验证。其余23张全切片图像用于模型测试。所开发的MUSA-UNet的平均肝门管区分割性能分别为0.94（精确率）、0.85（召回率）、0.89（F1分数）、0.89（准确率）、0.80（杰卡德指数）和0.91（福克思-马洛斯指数）。临床Scheuer纤维化分期与根据MUSA-UNet分割结果计算得出的平均门管区纤维化面积（R = 0.681，p<0.001）和门管区百分比（R = 0.335，p = 0.02）呈现出强烈的相关性。总之，我们开发的深度学习模型MUSA-UNet能够从肝组织活检的全切片图像中准确分割门管区，展现出以计算方式辅助肝脏疾病诊断的巨大潜力。
