{Reference Type}: English Abstract
{Title}: [Deep learning-based fully automated intelligent and precise diagnosis for melanocytic lesions].
{Author}: Shi T;Zhang J;Bao Y;Gao X;
{Journal}: Sheng Wu Yi Xue Gong Cheng Xue Za Zhi
{Volume}: 39
{Issue}: 5
{Year}: Oct 2022 25
暂无{DOI}: 10.7507/1001-5515.202203080
{Abstract}: Melanocytic lesions occur on the surface of the skin, in which the malignant type is melanoma with a high fatality rate, seriously endangering human health. The histopathological analysis is the gold standard for diagnosis of melanocytic lesions. In this study, a fully automated intelligent diagnosis method based on deep learning was proposed to classify the pathological whole slide images (WSI) of melanocytic lesions. Firstly, the color normalization based on CycleGAN neural network was performed on multi-center pathological WSI; Secondly, ResNet-152 neural network-based deep convolutional network prediction model was built using 745 WSI; Then, a decision fusion model was cascaded, which calculates the average prediction probability of each WSI; Finally, the diagnostic performance of the proposed method was verified by internal and external test sets containing 182 and 54 WSI, respectively. Experimental results showed that the overall diagnostic accuracy of the proposed method reached 94.12% in the internal test set and exceeded 90% in the external test set. Furthermore, the color normalization method adopted was superior to the traditional color statistics-based and staining separation-based methods in terms of structure preservation and artifact suppression. The results demonstrate that the proposed method can achieve high precision and strong robustness in pathological WSI classification of melanocytic lesions, which has the potential in promoting the clinical application of computer-aided pathological diagnosis.<BR>黑色素细胞病变发生于皮肤表层，恶性病变即为致死率极高的黑色素瘤，严重危害人类健康，病理组织学分析是其诊断的金标准。本文对黑色素细胞病变病理全切片图像（WSI）进行分类研究，提出一种基于深度学习的黑色素细胞病变全流程智能化诊断方法。首先，基于CycleGAN神经网络对多中心病理WSI进行颜色校正；其次，通过745张WSI构建以ResNet-152神经网络为架构的深度卷积网络预测模块；然后，级联以预测概率平均值计算为核心的决策融合模块；最终，分别采用包含182张和54张WSI的内外部测试集验证所提方法的诊断性能。实验结果显示，所提方法的整体准确率在内部测试集上达到94.12%，在外部测试集上超越90%；采用的颜色校正方式在组织结构保持、伪影抑制方面均优于传统基于颜色统计或染色分离的方式。研究证实了本文所提方法可实现高精度、强鲁棒的黑色素细胞病变病理WSI分类，对推动临床病理人工智能辅助诊断具有重要的指导意义。.