Comparison of machine learning models based on multi-parametric magnetic resonance imaging and ultrasound videos for the prediction of prostate cancer

Frontiers in Oncology

Oncology

Xingbo Sun¹  Zhengbiao Hu¹  Liyuan Jin¹  Maoliang Zhang¹  Zhengping Wang¹  Kai Wang¹  Xiaoyang Qi¹  Cheng Lv¹  Jie Yang¹  Bojian Feng²  Jincao Yao²  Lingyan Zhou² 

[1] Department of Ultrasound, The Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, Zhejiang, China;Department of Ultrasound, The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Hangzhou, Zhejiang, China;Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, Zhejiang, China;Key Laboratory of Head & Neck Cancer Translational Research of Zhejiang Province, The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital) Zhejiang Provincial Research Center for Cancer Intelligent Diagnosis and Molecular Technology, Hangzhou, Zhejiang, China;

关键词: radiomics;    prostate cancer;    machine learning;    ultrasound;    magnetic resonance imaging;    support vector machines;   

DOI  :  10.3389/fonc.2023.1157949

 received in 2023-02-08, accepted in 2023-05-04,  发布年份 2023

来源: Frontiers

【 摘 要 】

ObjectiveTo establish machine learning (ML) prediction models for prostate cancer (PCa) using transrectal ultrasound videos and multi-parametric magnetic resonance imaging (mpMRI) and compare their diagnostic performance.Materials and methodsWe systematically collated the data of 383 patients, including 187 with PCa and 196 with benign lesions. Of them, 307 patients (150 with PCa and 157 with benign lesions) were randomly selected to train and validate the ML models, 76 patients were used as test set. B-Ultrasound videos (BUS), mpMRI T2 sequence (T2), and ADC sequence (ADC) were obtained from all patients. We extracted 851 features of each patient in the BUS, T2, and ADC groups and used a t-test, the Mann–Whitney U test, and LASSO regression to screen the features. Support vector machine (SVM), random forest (RF), adaptive boosting (ADB), and gradient boosting machine (GBM) models were used to establish radiomics models. In addition, we fused the features screened via LASSO regression from three groups as new features and rebuilt ML models. The performance of the ML models in diagnosing PCa in the BUS, T2, ADC, and fusion groups was compared using the area under the ROC curve (AUC), sensitivity, specificity, and accuracy.ResultsIn the test cohort, the AUC of each model in the ADC group was higher than that of in the.BUS and T2 groups. Among the models, the RF model had the best diagnostic performance, with an AUC of 0.85, sensitivity of 0.78 (0.61–0.89), specificity of 0.84 (0.69–0.94), and accuracy of 0.83 (0.66–0.93). The SVM model in both the BUS and T2 groups performed best. Based on the features screened in the BUS, T2, and ADC groups fused to construct the models, the SVM model was found to perform best, with an AUC of 0.87, sensitivity of 0.73 (0.56–0.86), specificity of 0.79 (0.63–0.90), and accuracy of 0.77 (0.59–0.89). The difference in the results was statistically significant (p<0.05).ConclusionThe ML prediction models had a good diagnostic ability for PCa. Among them, the SVM model in the fusion group showed the best performance in diagnosing PCa. These prediction models can help radiologists make better diagnoses.

【 授权许可】

Unknown   
Copyright © 2023 Qi, Wang, Feng, Sun, Yang, Hu, Zhang, Lv, Jin, Zhou, Wang and Yao