PDF(Pubmed)
Abstract：
BACKGROUND: Schistosomiasis japonica represents a significant public health concern in South Asia. There is an urgent need to optimize existing schistosomiasis diagnostic techniques. This study aims to develop models for the different stages of liver fibrosis caused by Schistosoma infection utilizing ultrasound radiomics and machine learning techniques.
METHODS: From 2018 to 2022, we retrospectively collected data on 1,531 patients and 5,671 B-mode ultrasound images from the Second People\'s Hospital of Duchang City, Jiangxi Province, China. The datasets were screened based on inclusion and exclusion criteria suitable for radiomics models. Liver fibrosis due to Schistosoma infection (LFSI) was categorized into four stages: grade 0, grade 1, grade 2, and grade 3. The data were divided into six binary classification problems, such as group 1 (grade 0 vs. grade 1) and group 2 (grade 0 vs. grade 2). Key radiomic features were extracted using Pyradiomics, the Mann-Whitney U test, and the Least Absolute Shrinkage and Selection Operator (LASSO). Machine learning models were constructed using Support Vector Machine (SVM), and the contribution of different features in the model was described by applying Shapley Additive Explanations (SHAP).
RESULTS: This study ultimately included 1,388 patients and their corresponding images. A total of 851 radiomics features were extracted for each binary classification problems. Following feature selection, 18 to 76 features were retained from each groups. The area under the receiver operating characteristic curve (AUC) for the validation cohorts was 0.834 (95% CI: 0.779-0.885) for the LFSI grade 0 vs. LFSI grade 1, 0.771 (95% CI: 0.713-0.835) for LFSI grade 1 vs. LFSI grade 2, and 0.830 (95% CI: 0.762-0.885) for LFSI grade 2 vs. LFSI grade 3.
CONCLUSIONS: Machine learning models based on ultrasound radiomics are feasible for classifying different stages of liver fibrosis caused by Schistosoma infection.
METHODS: From 2018 to 2022, we retrospectively collected data on 1,531 patients and 5,671 B-mode ultrasound images from the Second People\'s Hospital of Duchang City, Jiangxi Province, China. The datasets were screened based on inclusion and exclusion criteria suitable for radiomics models. Liver fibrosis due to Schistosoma infection (LFSI) was categorized into four stages: grade 0, grade 1, grade 2, and grade 3. The data were divided into six binary classification problems, such as group 1 (grade 0 vs. grade 1) and group 2 (grade 0 vs. grade 2). Key radiomic features were extracted using Pyradiomics, the Mann-Whitney U test, and the Least Absolute Shrinkage and Selection Operator (LASSO). Machine learning models were constructed using Support Vector Machine (SVM), and the contribution of different features in the model was described by applying Shapley Additive Explanations (SHAP).
RESULTS: This study ultimately included 1,388 patients and their corresponding images. A total of 851 radiomics features were extracted for each binary classification problems. Following feature selection, 18 to 76 features were retained from each groups. The area under the receiver operating characteristic curve (AUC) for the validation cohorts was 0.834 (95% CI: 0.779-0.885) for the LFSI grade 0 vs. LFSI grade 1, 0.771 (95% CI: 0.713-0.835) for LFSI grade 1 vs. LFSI grade 2, and 0.830 (95% CI: 0.762-0.885) for LFSI grade 2 vs. LFSI grade 3.
CONCLUSIONS: Machine learning models based on ultrasound radiomics are feasible for classifying different stages of liver fibrosis caused by Schistosoma infection.
摘要：
背景：日本血吸虫病在南亚是一个重要的公共卫生问题。迫切需要优化现有的血吸虫病诊断技术。本研究旨在利用超声影像组学和机器学习技术开发由血吸虫感染引起的肝纤维化的不同阶段的模型。
方法：从2018年至2022年，我们回顾性收集了都昌市第二人民医院1,531例患者和5,671例B超图像，江西省,中国。根据适用于影像组学模型的纳入和排除标准筛选数据集。由血吸虫感染（LFSI）引起的肝纤维化分为四个阶段：0级，1级，2级和3级。数据分为六个二元分类问题，如第1组(0级与1年级)和2组(0年级与Grade2).使用Pyradiomics提取了关键的放射学特征，Mann-WhitneyU测试,和最小绝对收缩和选择算子(LASSO)。使用支持向量机(SVM)构建机器学习模型，并通过应用Shapley加法解释（SHAP）描述了模型中不同特征的贡献。
结果：这项研究最终包括1,388例患者及其相应图像。对于每个二元分类问题，总共提取了851个影像组学特征。在选择功能之后，每组保留18至76个特征。对于LFSI等级0，验证队列的受试者工作特征曲线下面积（AUC）为0.834（95％CI：0.779-0.885）LFSI1级，0.771（95%CI：0.713-0.835）LFSI2级，LFSI2级为0.830（95%CI：0.762-0.885）LFSI3级。
结论：基于超声影像组学的机器学习模型对血吸虫感染引起的肝纤维化的不同阶段进行分类是可行的。
方法：从2018年至2022年，我们回顾性收集了都昌市第二人民医院1,531例患者和5,671例B超图像，江西省,中国。根据适用于影像组学模型的纳入和排除标准筛选数据集。由血吸虫感染（LFSI）引起的肝纤维化分为四个阶段：0级，1级，2级和3级。数据分为六个二元分类问题，如第1组(0级与1年级)和2组(0年级与Grade2).使用Pyradiomics提取了关键的放射学特征，Mann-WhitneyU测试,和最小绝对收缩和选择算子(LASSO)。使用支持向量机(SVM)构建机器学习模型，并通过应用Shapley加法解释（SHAP）描述了模型中不同特征的贡献。
结果：这项研究最终包括1,388例患者及其相应图像。对于每个二元分类问题，总共提取了851个影像组学特征。在选择功能之后，每组保留18至76个特征。对于LFSI等级0，验证队列的受试者工作特征曲线下面积（AUC）为0.834（95％CI：0.779-0.885）LFSI1级，0.771（95%CI：0.713-0.835）LFSI2级，LFSI2级为0.830（95%CI：0.762-0.885）LFSI3级。
结论：基于超声影像组学的机器学习模型对血吸虫感染引起的肝纤维化的不同阶段进行分类是可行的。
