Deep Learning for Classification of Bone Lesions on Routine MRI

Abstract

Background: Radiologists have difficulty distinguishing benign from malignant bone lesions because these lesions may have similar imaging appearances. The purpose of this study was to develop a deep learning algorithm that can differentiate benign and malignant bone lesions using routine magnetic resonance imaging (MRI) and patient demographics. Methods: 1,060 histologically confirmed bone lesions with T1- and T2-weighted pre-operative MRI were retrospectively identified and included, with lesions from 4 institutions used for model development and internal validation, and data from a fifth institution used for external validation. Image-based models were generated using the EfficientNet-B0 architecture and a logistic regression model was trained using patient age, sex, and lesion location. A voting ensemble was created as the final model. The performance of the model was compared to classification performance by radiology experts. Findings: The cohort had a mean age of 30±23 years and was 58.3% male, with 582 benign lesions and 478 malignant. Compared to a contrived expert committee result, the ensemble deep learning model achieved identical accuracy (0·73 vs. 0·73, p=1·0), sensitivity (0·81 vs. 0·81, p=1·0) and specificity (0·66 vs. 0·66, p=1·0), with a ROC AUC of 0·82. On external testing, the model achieved ROC AUC of 0·77. Interpretation: Deep learning can be used to distinguish benign and malignant bone lesions on par with experts. These findings could aid in the development of computer-aided diagnostic tools to reduce unnecessary referrals to specialized centers from community clinics and limit unnecessary biopsies. Funding: This work was funded by a Radiological Society of North America Research Medical Student Grant (#RMS2013). Declaration of Interest: The authors have no competing interests to disclose. Ethical Approval: Our study received a waiver of informed consent and exempt status from the institutional review boards of the Hospital of the University of Pennsylvania (HUP) and the Children’s Hospital of Pennsylvania (CHOP) in Philadelphia, PA, and Rhode Island Hospital (RIH) in Providence, Rhode Island. The study was also approved by the institutional review boards of the Xiangya Hospital (XH) and Second Xiangya Hospital (SXH) of Central South University in Hunan, China.