Zhang Yun, Li Jiao, Yang Qiuxia, Yin Shaohan, Hou Jing, Cao Xiaohuan, Ma Shanshan, Wang Bin, Luo Ma, Zhou Fan, Xu Jiahui, Wang Shiyuan, Wu Yi, Zhang Jian, Luo Xiao, Yang Zehong, Ma Weimei, Lin Daiying, Zhan Yiqiang, Zhou Xiang Sean, Yu Xiaoping, Shen Dinggang, Zhang Rong, Xie Chuanmiao
Department of Radiology, Sun Yat-sen University Cancer Center, 510060, Guangzhou, Guangdong, P.R. China.
State Key Laboratory of Oncology in South China, 510060, Guangzhou, Guangdong, P.R. China.
Nat Commun. 2025 May 13;16(1):4444. doi: 10.1038/s41467-025-59433-7.
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.
在原发性癌症中，通过人工解读CT图像来检测骨转移（BM）仍然具有挑战性。我们展示了一种自动骨病变检测系统（BLDS），该系统是利用来自五家医院的2518例患者的CT扫描图像（9177处骨转移；12,824处非骨转移病变）开发的。该系统基于1271例患者的数据开发，并在1247例多中心病例上进行了测试，在检测非增强CT扫描上的骨病变时，其病变敏感性为89.1%（每例1.40个假阳性[FPPC]），对内部和外部测试集的骨转移/非骨转移病变分类的准确率分别为92.3%和91.1%。在病变检测方面（敏感性为40.5%；FPPC为0.65），BLDS优于放射科医生，不过其骨转移检测敏感性低于初级放射科医生，但与实习医生相当。在实际应用验证中（n = 54,610），BLDS在骨转移检测中可将放射科医生的病变敏感性提高22.2%，并将阅读时间减少26.4%，同时保持90.2%的患者敏感性和98.2%的阴性预测值。该系统显示出在增强基于CT的骨转移解读方面具有巨大潜力，尤其对实习医生有益。
