文献类型：期刊文献

英文题名：Fusing Diverse Decision Rules in 3D-Radiomics for Assisting Diagnosis of Lung Adenocarcinoma

作者：Ren, He[1,2,3];Wang, Qiubo[1];Xiao, Zhengguang[4];Mo, Runwei[5];Guo, Jiachen[2,3];Hide, Gareth Richard[6];Tu, Mengting[2,3];Zeng, Yanan[2,3];Ling, Chen[2,3];Li, Ping[2,3]

机构：[1]Shanghai Univ Med & Hlth Sci, Zhoupu Hosp, Resp Dept, Shanghai, Peoples R China;[2]Shanghai Univ Med & Hlth Sci, Coll Med Instrumentat, Shanghai, Peoples R China;[3]Shanghai Univ Med & Hlth Sci, Collaborat Innovat Canter, Shanghai, Peoples R China;[4]Shanghai Jiao Tong Univ, Shanghai Tongren Hosp, Dept Radiol, Sch Med, Shanghai, Peoples R China;[5]East China Univ Sci & Technol, Sch Mech & Power Engn, Shanghai 200030, Peoples R China;[6]Univ Witwatersrand, Fac Hlth Sci, Dept Surg, Med Sch, Johannesburg, South Africa

年份：2024

卷号：37

期号：5

起止页码：2135

外文期刊名：JOURNAL OF IMAGING INFORMATICS IN MEDICINE

收录：;EI(收录号：20252418595033);WOS:【SCI-EXPANDED(收录号:WOS:001195754200002)】；

基金：The study was supported by The Science and Technology Commission of Shanghai Municipality (grant no. 22S31904600).

语种：英文

外文关键词：Diverse decision rules; 3D radiomics; Lung adenocarcinoma; Assisted diagnosis

摘要：This study aimed to develop an interpretable diagnostic model for subtyping of pulmonary adenocarcinoma, including minimally invasive adenocarcinoma (MIA), adenocarcinoma in situ (AIS), and invasive adenocarcinoma (IAC), by integrating 3D-radiomic features and clinical data. Data from multiple hospitals were collected, and 10 key features were selected from 1600 3D radiomic signatures and 11 radiological features. Diverse decision rules were extracted using ensemble learning methods (gradient boosting, random forest, and AdaBoost), fused, ranked, and selected via RuleFit and SHAP to construct a rule-based diagnostic model. The model's performance was evaluated using AUC, precision, accuracy, recall, and F1-score and compared with other models. The rule-based diagnostic model exhibited excellent performance in the training, testing, and validation cohorts, with AUC values of 0.9621, 0.9529, and 0.8953, respectively. This model outperformed counterparts relying solely on selected features and previous research models. Specifically, the AUC values for the previous research models in the three cohorts were 0.851, 0.893, and 0.836. It is noteworthy that individual models employing GBDT, random forest, and AdaBoost demonstrated AUC values of 0.9391, 0.8681, and 0.9449 in the training cohort, 0.9093, 0.8722, and 0.9363 in the testing cohort, and 0.8440, 0.8640, and 0.8750 in the validation cohort, respectively. These results highlight the superiority of the rule-based diagnostic model in the assessment of lung adenocarcinoma subtypes, while also providing insights into the performance of individual models. Integrating diverse decision rules enhanced the accuracy and interpretability of the diagnostic model for lung adenocarcinoma subtypes. This approach bridges the gap between complex predictive models and clinical utility, offering valuable support to healthcare professionals and patients.