Prediction of carcinogenic human papillomavirus types in cervical cancer from multiparametric magnetic resonance images with machine learning-based radiomics models

• Published in: Diagnostic and interventional radiology (Ankara, Turkey) Turkey), 2023-05, Vol.29 (3), p.460-468
• Main Authors: İnce, Okan, Uysal, Emre, Durak, Görkem, Önol, Suzan, Dönmez Yılmaz, Binnur, Ertürk, Şükrü Mehmet, Önder, Hakan
• Format: Article
• Language: English
• Subjects: Algorithms; artificial intelligence; Artificial Intelligence and Informatics - Original; Carcinogens; Cervical cancer; Complications and side effects; Data mining; Diagnosis; Female; human papillomavirus dna tests; Human Papillomavirus Viruses; Humans; Machine Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Methods; Papillomavirus infections; Papillomavirus Infections - diagnostic imaging; radiology; Retrospective Studies; Risk factors; uterine cervical neoplasms; Uterine Cervical Neoplasms - diagnostic imaging; Uterine Cervical Neoplasms - pathology
• ISSN: 1305-3825; 1305-3612
• DOI: 10.4274/dir.2022.221335

This study aimed to evaluate the potential of machine learning-based models for predicting carcinogenic human papillomavirus (HPV) oncogene types using radiomics features from magnetic resonance imaging (MRI). Pre-treatment MRI images of patients with cervical cancer were collected retrospectively. An HPV DNA oncogene analysis was performed based on cervical biopsy specimens. Radiomics features were extracted from contrast-enhanced T1-weighted images (CE-T1) and T2-weighted images (T2WI). A third feature subset was created as a combined group by concatenating the CE-T1 and T2WI subsets. Feature selection was performed using Pearson's correlation coefficient and wrapper- based sequential-feature selection. Two models were built with each feature subset, using support vector machine (SVM) and logistic regression (LR) classifiers. The models were validated using a five-fold cross-validation technique and compared using Wilcoxon's signed rank and Friedman's tests. Forty-one patients were enrolled in the study (26 were positive for carcinogenic HPV oncogenes, and 15 were negative). A total of 851 features were extracted from each imaging sequence. After feature selection, 5, 17, and 20 features remained in the CE-T1, T2WI, and combined groups, respectively. The SVM models showed 83%, 95%, and 95% accuracy scores, and the LR models revealed 83%, 81%, and 92.5% accuracy scores in the CE-T1, T2WI, and combined groups, respectively. The SVM algorithm performed better than the LR algorithm in the T2WI feature subset ( = 0.005), and the feature sets in the T2WI and the combined group performed better than CE-T1 in the SVM model ( = 0.033 and 0.006, respectively). The combined group feature subset performed better than T2WI in the LR model ( = 0.023). Machine learning-based radiomics models based on pre-treatment MRI can detect carcinogenic HPV status with discriminative accuracy.