用于筛查数字乳腺断层合成的商用人工智能工具:与基于AI的乳腺癌检出相关的因素
该回顾性研究纳入2016年1月至2019年6月连续筛查数字乳腺断层合成检查7500例,评估商用AI辅助检测/诊断算法检出癌症的相关因素。AI在放射科医师真阳性中检出并正确定位89.8%(449/500),在假阴性中为32.0%(32/100)。某些癌症特征与AI检出相关。
要点
- AI对放射科医师真阳性病例的检出并正确定位率为89.8%(449/500),对假阴性病例为32.0%(32/100)。
- 在放射科医师真阳性中,AI检出率随浸润性癌组织学类型(p=.049)和分级(p=.03)不同而变化。
- AI检出与年龄、种族、乳腺密度、钼靶表现类型、肿瘤大小、激素受体状态或淋巴结受累无显著关联(p>.05)。
核心结论
- AI检出并正确定位了89.8%的放射科医师真阳性病例和32.0%的假阴性病例;某些癌症特征与AI检出相关。
研究设计与样本
- 回顾性研究,纳入2016年1月至2019年6月连续筛查数字乳腺断层合成检查7500例(7500名患者,平均年龄59±12岁),依据放射科医师临床解读和1年随访结果分为真阳性500例、假阴性100例、真阴性4400例、假阳性2500例;使用商用AI辅助检测/诊断算法(Genius AI Detection 2.0软件,Hologic)进行分析。
诊断标准与关键数值
- AI在放射科医师真阳性中检出并正确定位89.8%(449/500),在假阴性中为32.0%(32/100)。
- AI将放射科医师真阴性中的55.1%(2426/4400)和假阳性中的38.9%(972/2500)正确分类为阴性。
- 在放射科医师真阳性中,AI检出并正确定位浸润性导管癌92.4%、浸润性小叶癌81.6%、其他浸润性癌86.7%、导管原位癌85.7%(p=.049)。
- 在放射科医师真阳性中,AI检出并正确定位1级、2级、3级浸润性癌分别为84.4%、91.5%、95.2%(p=.03)。
- 在放射科医师假阴性中,有 vs 无钼靶表现(后续诊断检查中报告)的癌症AI检出并正确定位分别为41.2% vs 8.3%(p=.04)。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND. Research on artificial intelligence (AI)-based computer-assisted detection and diagnosis (CADe/CADx) algorithms has focused primarily on digital mammography rather than on digital breast tomosynthesis (DBT). Additionally, DBT-related studies have not comprehensively stratified performance by cancer characteristics. OBJECTIVE. This study's purpose was to evaluate factors associated with cancer detection for a commercial AI-based CADe/CADx algorithm for DBT interpretation. METHODS. This retrospective study included consecutive screening DBT examinations performed from January 2016 to June 2019 that were classified in the institution's breast imaging reporting system as true-positive (n = 500), false-negative (n = 100), true-negative (n = 4400), or false-positive (n = 2500) cases based on radiologists' clinical interpretations and 1-year follow-up outcomes. A commercial AI-based CADe/CADx DBT algorithm (Genius AI Detection 2.0 software, Hologic) analyzed examinations for investigational purposes. A breast imaging radiologist reviewed radiologist true-positive and false-negative examinations with positive AI results to determine whether AI-annotated lesions corresponded to the locations of diagnosed cancers. Factors associated with AI detection were evaluated. RESULTS. The study included 7500 patients (mean age, 59 ± 12 [SD] years) who underwent 7500 DBT examinations. AI detected and correctly localized cancers in 89.8% (449/500) of radiologist true-positives and 32.0% (32/100) of radiologist false-negatives. AI correctly categorized 55.1% (2426/4400) of radiologist true-negatives and 38.9% (972/2500) of radiologist false-positives as negative. Among radiologist true-positives, AI detected and correctly localized 92.4%, 81.6%, 86.7%, and 85.7% of invasive ductal carcinomas, invasive lobular carcinomas, other invasive carcinomas, and cases of ductal carcinoma in situ, respectively (p = .049); AI detected and correctly localized 84.4%, 91.5%, and 95.2% of grade 1, 2, and 3 invasive carcinomas, respectively (p = .03). Among radiologist false-negatives, AI detected and correctly localized 41.2% and 8.3% of cancers with versus without a mammographic finding reported during later diagnostic workup (p = .04). AI detection showed no significant association with age, race, breast density, mammographic finding type, tumor size at surgery, hormone receptor status, or lymph node involvement in either group (p > .05). CONCLUSION. AI detected and correctly localized 89.8% of radiologist true-positive and 32.0% of radiologist false-negative cases. Certain cancer characteristics were associated with AI detection. CLINICAL IMPACT. The results may help radiologists understand the algorithm's strengths and limitations and inform algorithm refinement efforts.
引用
- Bahl M, Kim K, Kim H, et al. Commercial Artificial Intelligence (AI) Tool for Screening Digital Breast Tomosynthesis: Factors Associated With AI-Based Breast Cancer Detection. AJR Am J Roentgenol. 2025. PMID: 41334895. doi:10.2214/AJR.25.33792
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。