Machine learning-based Radiomics analysis for differentiation degree and lymphatic node metastasis of extrahepatic cholangiocarcinoma

BMC Cancer

Song Su¹  Jian Shu²  Chun Mei Yang²  Li Ping Fan³  Yong Tang⁴  Wei Jia Wang⁵ 

[1] Department of Hepatobiliary Surgery, The Affiliated Hospital of Southwest Medical University, 25 Taiping Street, 646000, Luzhou, Sichuan, China;Department of Radiology, The Affiliated Hospital of Southwest Medical University, and Nuclear Medicine and Molecular Imaging Key Laboratory of Sichuan Province, 646000, Luzhou, Sichuan, China;Department of Ultrasound, The Affiliated Hospital of Southwest Medical University, 25 Taiping Street, 646000, Luzhou, Sichuan, China;School of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 4, Section 2, North Jianshe Road, 610054, Chengdu, Sichuan, China;School of Information and Software Engineering, University of Electronic Science and Technology of China, No. 4, Section 2, North Jianshe Road, 610054, Chengdu, Sichuan, China;

关键词: Extrahepatic cholangiocarcinoma;    Cell differentiation;    Lymphatic metastasis;    Machine learning;    Radiomics;   

DOI  :  10.1186/s12885-021-08947-6

来源: Springer

【 摘 要 】

BackgroundRadiomics may provide more objective and accurate predictions for extrahepatic cholangiocarcinoma (ECC). In this study, we developed radiomics models based on magnetic resonance imaging (MRI) and machine learning to preoperatively predict differentiation degree (DD) and lymph node metastasis (LNM) of ECC.MethodsA group of 100 patients diagnosed with ECC was included. The ECC status of all patients was confirmed by pathology. A total of 1200 radiomics features were extracted from axial T1 weighted imaging (T1WI), T2-weighted imaging (T2WI), diffusion weighted imaging (DWI), and apparent diffusion coefficient (ADC) images. A systematical framework considering combinations of five feature selection methods and ten machine learning classification algorithms (classifiers) was developed and investigated. The predictive capabilities for DD and LNM were evaluated in terms of area under precision recall curve (AUPRC), area under the receiver operating characteristic (ROC) curve (AUC), negative predictive value (NPV), accuracy (ACC), sensitivity, and specificity. The prediction performance among models was statistically compared using DeLong test.ResultsFor DD prediction, the feature selection method joint mutual information (JMI) and Bagging Classifier achieved the best performance (AUPRC = 0.65, AUC = 0.90 (95% CI 0.75–1.00), ACC = 0.85 (95% CI 0.69–1.00), sensitivity = 0.75 (95% CI 0.30–0.95), and specificity = 0.88 (95% CI 0.64–0.97)), and the radiomics signature was composed of 5 selected features. For LNM prediction, the feature selection method minimum redundancy maximum relevance and classifier eXtreme Gradient Boosting achieved the best performance (AUPRC = 0.95, AUC = 0.98 (95% CI 0.94–1.00), ACC = 0.90 (95% CI 0.77–1.00), sensitivity = 0.75 (95% CI 0.30–0.95), and specificity = 0.94 (95% CI 0.72–0.99)), and the radiomics signature was composed of 30 selected features. However, these two chosen models were not significantly different to other models of higher AUC values in DeLong test, though they were significantly different to most of all models.ConclusionMRI radiomics analysis based on machine learning demonstrated good predictive accuracies for DD and LNM of ECC. This shed new light on the noninvasive diagnosis of ECC.

【 授权许可】

CC BY