Yu S M, Young C Y M, Chan Y H, Chan Y S, Tsoi C, Choi M N Y, Chan T H, Leung J, Chu W C W, Hung E H Y, Chau H H L
Department of Imaging and Interventional Radiology, Prince of Wales Hospital, Hong Kong SAR, China.
The Jockey Club Centre for Osteoporosis Care and Control, The Chinese University of Hong Kong, Hong Kong SAR, China.
Hong Kong Med J. 2024 Dec;30(6):468-477. doi: 10.12809/hkmj2310920. Epub 2024 Dec 19.
Research concerning artificial intelligence in breast cancer detection has primarily focused on population screening. However, Hong Kong lacks a population-based screening programme. This study aimed to evaluate the potential of artificial intelligence-based computer-assisted diagnosis (AI-CAD) program in symptomatic clinics in Hong Kong and analyse the impact of radio-pathological breast cancer phenotype on AI-CAD performance.
In total, 398 consecutive patients with 414 breast cancers were retrospectively identified from a local, prospectively maintained database managed by two tertiary referral centres between January 2020 and September 2022. The full-field digital mammography images were processed using a commercial AI-CAD algorithm. An abnormality score <30 was considered a false negative, whereas a score of ≥90 indicated a high-score tumour. Abnormality scores were analysed with respect to the clinical and radio-pathological characteristics of breast cancer, tumour-to-breast area ratio (TBAR), and tumour distance from the chest wall for cancers presenting as a mass.
The median abnormality score across the 414 breast cancers was 95.6; sensitivity was 91.5% and specificity was 96.3%. High-score cancers were more often palpable, invasive, and presented as masses or architectural distortion (P<0.001). False-negative cancers were smaller, more common in dense breast tissue, and presented as asymmetrical densities (P<0.001). Large tumours with extreme TBARs and locations near the chest wall were associated with lower abnormality scores (P<0.001). Several strengths and limitations of AI-CAD were observed and discussed in detail.
Artificial intelligence-based computer-assisted diagnosis shows potential value as a tool for breast cancer detection in symptomatic setting, which could provide substantial benefits to patients.
关于人工智能在乳腺癌检测中的研究主要集中在人群筛查方面。然而，香港缺乏基于人群的筛查计划。本研究旨在评估基于人工智能的计算机辅助诊断（AI-CAD）程序在香港有症状门诊中的潜力，并分析乳腺放射病理癌症表型对AI-CAD性能的影响。
从2020年1月至2022年9月期间由两个三级转诊中心管理的本地前瞻性维护数据库中，回顾性识别出总共398例患有414例乳腺癌的连续患者。使用商业AI-CAD算法处理全场数字化乳腺X线摄影图像。异常分数<30被视为假阴性，而分数≥90表明为高分肿瘤。针对乳腺癌的临床和放射病理特征、肿瘤与乳腺面积比（TBAR）以及表现为肿块的癌症与胸壁的距离，分析异常分数。
414例乳腺癌的中位异常分数为95.6；敏感性为91.5%，特异性为96.3%。高分癌症更常可触及、具有侵袭性，并表现为肿块或结构扭曲（P<0.001）。假阴性癌症较小，在致密乳腺组织中更常见，并表现为不对称密度（P<0.001）。具有极端TBARs且位置靠近胸壁的大肿瘤与较低的异常分数相关（P<0.001）。详细观察并讨论了AI-CAD的几个优点和局限性。
基于人工智能的计算机辅助诊断在有症状情况下作为乳腺癌检测工具显示出潜在价值，可为患者带来实质性益处。
