He Siqi, Xiao Bo, Wei Huajiang, Huang Shenjiao, Chen Tongsheng
Key Laboratory of Laser Life Science, Ministry of Education, College of Biophotonics, South China Normal University, Guangzhou, Guangdong, China.
GuangZhou Woman and Children's Medical Center, Guangzhou, Guangzhou, China.
Technol Health Care. 2023;31(1):69-80. doi: 10.3233/THC-220031.
Cervical histopathology image classification is a crucial indicator in cervical biopsy results.
The objective of this study is to identify histopathology images of cervical cancer at an early stage by extracting texture and morphological features for the Support Vector Machine (SVM) classifier.
We extract three different texture features and one morphological feature of cervical histopathology images: first-order histogram, K-means clustering, Gray Level Co-occurrence Matrix (GLCM) and nucleus feature. The original dataset used in our experiment is obtained from 20 patients diagnosed with cervical cancer, including 135 whole slide images (WSIs). Given an entire WSI, the patches on its tissue region are extracted randomly.
We finally obtain 3,000 patches, including 1,000 normal, 1,000 hysteromyoma and 1,000 cancer images. Among them, 80% of the entire data set is randomly selected as training set and the remaining 20% as test set. The accuracy of SVM classification using first-order histogram, K-means clustering, GLAM and nucleus feature for extracting features are respectively 87.4%, 90.6%, 91.6% and 93.5%.
The classification accuracy of the SVM combining the four features is 96.8%, and the proposed nucleus feature plays a key role in the SVM classification of cervical histopathology images.
宫颈组织病理学图像分类是宫颈活检结果的关键指标。
本研究的目的是通过提取纹理和形态特征，为支持向量机（SVM）分类器识别早期宫颈癌的组织病理学图像。
我们提取了宫颈组织病理学图像的三种不同纹理特征和一种形态特征：一阶直方图、K均值聚类、灰度共生矩阵（GLCM）和细胞核特征。我们实验中使用的原始数据集来自20例被诊断为宫颈癌的患者，包括135张全切片图像（WSIs）。对于一张完整的WSI，随机提取其组织区域上的图像块。
我们最终获得了3000个图像块，包括1000个正常图像、1000个子宫肌瘤图像和1000个癌症图像。其中，整个数据集的80%被随机选作训练集，其余20%作为测试集。使用一阶直方图、K均值聚类、灰度共生矩阵（GLAM）和细胞核特征进行特征提取的SVM分类准确率分别为87.4%、90.6%、91.6%和93.5%。
结合这四种特征的SVM分类准确率为96.8%，所提出的细胞核特征在宫颈组织病理学图像的SVM分类中起关键作用。
