A clinically applicable AI system for detection and diagnosis of bone metastases using CT scans
Yun Zhang, Jiao Li, Qiuxia Yang, Shaohan Yin, Jing Hou, Xiaohuan Cao, Shanshan Ma, Bin Wang, Ma Luo, Fan Zhou, Jiahui Xu, Shiyuan Wang, Yi Wu, Jian Zhang, Xiao Luo, Zehong Yang, Weimei Ma, Daiying Lin, Yiqiang Zhan, Xiang Sean Zhou, Xiaoping Yu, Dinggang Shen, Rong Zhang, Chuanmiao Xie
Abstract
Manual interpretation of CT images for bone metastasis (BM) detection in primary cancer remains challenging. We present an automated Bone Lesion Detection System (BLDS) developed using CT scans from 2518 patients (9177 BMs; 12,824 non-BM lesions) across five hospitals. The system, developed on 1271 patients and tested on 1247 multicenter cases, demonstrates 89.1% lesion-wise sensitivity (1.40 false-positives/case [FPPC]) in detecting bone lesions on non-contrast CT scans, with 92.3% and 91.1% accuracy in classifying BM/non-BM lesions for internal and external test sets, respectively. Outperforming radiologists in lesion detection (40.5% sensitivity; 0.65 FPPC), BLDS shows lower BM detection sensitivity than junior radiologists, though comparable to trainees. BLDS improves radiologists’ lesion-wise sensitivity by 22.2% in BM detection and reduces reading time by 26.4%, while maintaining 90.2% patient-wise sensitivity and 98.2% negative predictive value in real-world validation (n = 54,610). The system demonstrates significant potential to enhance CT-based BM interpretation, particularly benefiting trainees. Interpreting bone metastases (BMs) from computed tomography (CT) images remains challenging. Here, the authors develop an AI-based Bone Lesion Detection System - BLDS - and validate it in a cohort of 2,518 patients across five hospitals, showing highly sensitive and accurate performance for BM detection from CT scans.