Makris Georgios-Marios, Pouliakis Abraham, Siristatidis Charalampos, Margari Niki, Terzakis Emmanouil, Koureas Nikolaos, Pergialiotis Vasilios, Papantoniou Nikolaos, Karakitsos Petros
Unit of Gynecological Oncology, Third Department of Obstetrics and Gynecology, General Hospital "Attikon", Medical School, National and Kapodistrian University of Athens, Athens, Greece.
Department of Cytopathology, General Hospital "Attikon", Medical School, National and Kapodistrian University of Athens, Athens, Greece.
Diagn Cytopathol. 2017 Mar;45(3):202-211. doi: 10.1002/dc.23649. Epub 2017 Feb 3.
This study aims to investigate the efficacy of an Artificial Neural Network based on Multi-Layer Perceptron (ANN-MPL) to discriminate between benign and malignant endometrial nuclei and lesions in cytological specimens.
We collected 416 histologically confirmed liquid-based cytological smears from 168 healthy patients, 152 patients with malignancy, 52 with hyperplasia without atypia, 20 with hyperplasia with atypia, and 24 patients with endometrial polyps. The morphometric characteristics of 90 nuclei per case were analyzed using a custom image analysis system; half of them were used to train the MPL-ANN model, which classified each nucleus as benign or malignant. Data from the remaining 50% of cases were used to evaluate the performance and stability of the ANN. The MLP-ANN for the nuclei classification (numeric and percentage classifiers) and the algorithms for the determination of the optimum threshold values were estimated with in-house developed software for the MATLAB v2011b programming environment; the diagnostic accuracy measures were also calculated.
The accuracy of the MPL-ANN model for the classification of endometrial nuclei was 81.33%, while specificity was 88.84% and sensitivity 69.38%. For the case classification based on numeric classifier the overall accuracy was 90.87%, the specificity 93.03% and the sensitivity 87.79%; the indices for the percentage classifier were 95.91%, 93.44%, and 99.42%, respectively.
Computerized systems based on ANNs can aid the cytological classification of endometrial nuclei and lesions with sufficient sensitivity and specificity. Diagn. Cytopathol. 2017;45:202-211. © 2016 Wiley Periodicals, Inc.
本研究旨在探讨基于多层感知器的人工神经网络（ANN-MPL）在鉴别细胞学标本中良性和恶性子宫内膜细胞核及病变方面的疗效。
我们收集了416份经组织学确诊的液基细胞学涂片，这些涂片来自168名健康患者、152名恶性肿瘤患者、52名无异型增生患者、20名异型增生患者以及24名子宫内膜息肉患者。使用定制的图像分析系统分析每例标本中90个细胞核的形态计量学特征；其中一半用于训练MPL-ANN模型，该模型将每个细胞核分类为良性或恶性。其余50%病例的数据用于评估ANN的性能和稳定性。使用为MATLAB v2011b编程环境自行开发的软件估计用于细胞核分类的MLP-ANN（数值和百分比分类器）以及确定最佳阈值的算法；还计算了诊断准确性指标。
MPL-ANN模型对子宫内膜细胞核分类的准确率为81.33%，特异性为88.84%，敏感性为69.38%。基于数值分类器的病例分类总体准确率为90.87%，特异性为93.03%，敏感性为87.79%；百分比分类器的指标分别为95.91%、93.44%和99.42%。
基于人工神经网络的计算机系统能够以足够的敏感性和特异性辅助子宫内膜细胞核及病变的细胞学分类。诊断细胞病理学。2017；45：202 - 211。©2016威利期刊公司。
