Erler B S, Hsu L, Truong H M, Petrovic L M, Kim S S, Huh M H, Ferrell L D, Thung S N, Geller S A, Marchevsky A M
Department of Pathology, Cedars-Sinai Medical Center, Los Angeles, California.
Lab Invest. 1994 Sep;71(3):446-51.
Hepatocellular carcinoma (HCC) is often difficult to diagnose in cytologic material and small tissue biopsies since histomorphologic information is minimal or absent. The potential for misdiagnosis is greatest in attempting to discriminate well-differentiated HCC from dysplastic hepatocytes in cirrhosis. We investigated the feasibility of developing artificial intelligence classification methods based on nuclear image analysis data for use as adjuncts to the morphologic diagnosis of HCC.
Ninety hematoxylin-eosin stained histologic slides including 56 with well- to poorly differentiated HCC and 34 showing a morphologic continuum from normal to markedly dysplastic benign hepatocytes were assembled from four laboratories. A relatively inexpensive PC-based image analysis system was used to measure 35 nuclear morphometric and densitometric parameters of 100 nuclei in each specimen. The data were randomized into classification training and testing sets containing equal numbers of benign and HCC samples. Objective diagnostic classification criteria for HCC based on neural networks and multivariate discriminant functions (DFs) were developed for the most discriminatory subsets of morphometric, densitometric, and combined morphometric/densitometric variables as selected by stepwise discriminant analysis of training data.
Morphometric parameters provided the best results with the following testing data positive and negative predictive values (PV+ and PV-) for HCC classification: 86.2% PV+ and 81.3% PV- for a linear DF, 85.7% PV+ and 76.5% PV- for a quadratic DF and 100% PV+ and 85.0% PV- for a neural network.
Our results demonstrate that nuclear image analysis-based objective classification criteria for HCC can be developed using artificial intelligence methods and that histologic material prepared at different institutions can be reliably classified. Neural networks for HCC classification were superior to linear and quadratic DFs. Morphometric data yielded the best results compared with densitometric or combined morphometric/densitometric data.
肝细胞癌（HCC）在细胞学材料和小组织活检中往往难以诊断，因为组织形态学信息极少或不存在。在试图将高分化HCC与肝硬化中的发育异常肝细胞区分开来时，误诊的可能性最大。我们研究了基于核图像分析数据开发人工智能分类方法作为HCC形态学诊断辅助手段的可行性。
从四个实验室收集了90张苏木精-伊红染色的组织学切片，其中56张为高分化至低分化的HCC，34张显示从正常到明显发育异常的良性肝细胞的形态学连续变化。使用相对便宜的基于个人电脑的图像分析系统测量每个标本中100个细胞核的35个核形态计量和光密度参数。数据被随机分为分类训练集和测试集，其中良性和HCC样本数量相等。基于神经网络和多变量判别函数（DFs）的HCC客观诊断分类标准是针对通过训练数据的逐步判别分析选择的最具判别力的形态计量、光密度和形态计量/光密度组合变量子集制定的。
形态计量参数提供了最佳结果，以下是HCC分类测试数据的阳性和阴性预测值（PV+和PV-）：线性DF的PV+为86.2%，PV-为81.3%；二次DF的PV+为85.7%，PV-为76.5%；神经网络的PV+为100%，PV-为85.0%。
我们的结果表明，可以使用人工智能方法制定基于核图像分析的HCC客观分类标准，并且不同机构制备的组织学材料可以可靠分类。用于HCC分类的神经网络优于线性和二次DFs。与光密度或形态计量/光密度组合数据相比，形态计量数据产生了最佳结果。
