文献速递乳腺乳腺X线

AI与放射科医生在乳腺X线筛查中病灶检测能力对比

From shadows to signals: exploring the strengths and limitations of artificial intelligence in breast cancer lesion detection on screening mammograms compared to radiologists and radiology trainees.
PubMed 文献 · Br J Radiol · 2026-01-01

本研究基于9个BREAST测试集540例筛查数字化乳腺X线片(179例癌、361例正常),比较AI(GMIC+CLAHE)与17名放射科医生、26名规培医生的病灶级与病例级表现。AI病例级AUC为0.974,高于放射科医生(0.82±0.06)和规培医生(0.74±0.05);病灶级灵敏度AI为66.3%,与放射科医生67.0%相当,高于规培医生55.0%。

要点

  • AI病例级AUC显著高于放射科医生和规培医生,可作为筛查辅助工具。
  • AI对结构扭曲病灶漏检率最高(43.8%),报告中应警惕该征象。
  • AI对小病灶(≤15 mm)和混合型病灶检测优于规培医生,可用于培训场景。

核心结论

  • AI在乳腺癌筛查中病例级诊断准确性优于放射科医生和规培医生。
  • AI病灶级总体表现与放射科医生相当,优于规培医生。
  • AI对结构扭曲病灶漏检率最高(43.8%),对混合型病灶漏检率最低(25.0%)。
  • AI对特定病灶类型的定位能力存在变异,建议作为人工阅片的辅助手段。

研究设计与样本

  • 研究类型为回顾性测试集分析,纳入9个BREAST测试集共540例筛查数字化乳腺X线片。
  • 样本包括179例乳腺癌和361例正常病例,由17名放射科医生和26名规培医生独立阅片。
  • AI模型为GMIC结合CLAHE预处理,参考标准为病理或随访确认。
  • AI恶性评分采用Youden指数确定二分类阈值。

关键影像表现/征象

  • AI对混合型病灶的检出灵敏度为75%,高于规培医生的55%(OR=2.4)。
  • AI对小病灶(≤15 mm)的检出灵敏度为65.7%,高于规培医生的55%(OR=1.6)。
  • 结构扭曲是AI最易漏诊的征象,漏检率达43.8%。
  • AI病灶级总体灵敏度为66.3%,与放射科医生67.0%接近。

诊断标准与关键数值

  • AI病灶级灵敏度为66.3%,放射科医生为67.0%,规培医生为55.0%。
  • 不同乳腺密度分组中AI病例级AUC均保持优势。

临床应用与阅片要点

  • AI可作为乳腺X线筛查的辅助判读工具,尤其适用于病例级风险分层。
  • 阅片时对AI输出为低风险的结构扭曲病灶仍需保持高度警惕。
  • AI对混合型和小病灶的检测优势可弥补规培医生经验不足。
  • 日常报告中不能以AI结果取代对病灶形态学的独立判读。

局限性

  • 研究仅在测试集层面进行回顾性评估,未模拟真实前瞻性筛查流程。
  • AI模型为单一算法组合,尚未与其他商用AI系统做对比。

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

OBJECTIVES: Breast cancer screening with mammography reduces mortality, but interpretation errors persist. While artificial intelligence (AI) shows promise, most studies focus on case-level accuracy and overlook lesion-level performance. This study evaluated the AI (GMIC + CLAHE) model against radiologists and radiology trainees, considering breast density and lesion characteristics.

METHODS: Nine BREAST test sets of screening digital mammograms (540 cases: 179 cancer, 361 normal) were analyzed. AI performance was compared with 17 radiologists and 26 trainees. Case- and lesion-level performance were assessed across breast density, lesion type, and size. AI malignancy scores were dichotomized using Youden's index. Sensitivity, specificity, ROC AUC, lesion localization, and odds ratios (ORs) were calculated.

RESULTS: AI achieved higher case-level AUC (0.974) than radiologists (0.82 ± 0.06; P = .01) and trainees (0.74 ± 0.05; P < .0001) across breast densities. At lesion level, AI matched radiologists and outperformed trainees (OR = 1.6; P = .03), with lesion sensitivities of 66.3% (AI), 67.0% (radiologists), and 55.0% (trainees). AI also outperformed trainees in detecting mixed-type lesions (75% vs 55%; OR = 2.4) and small lesions ≤15 mm (65.7% vs 55%; OR = 1.6). Architectural distortion had the highest miss rate (43.8%) whereas mixed-type lesions demonstrated the lowest miss rate (25.0%) by AI.

CONCLUSIONS: AI demonstrated superior case-level accuracy compared with radiologists and trainees, but limitations in localizing specific lesion types, supporting its role as an adjunct to human readers in screening and training.

ADVANCES IN KNOWLEDGE: This study integrates case-and-lesion-level evaluation in different case characteristics, identifying key strengths and limitations for clinical implementation. Despite superior case-level accuracy, variability in lesion localization across cancer types and sizes highlights important considerations for its integration into screening services.

来源:Br J Radiol,查看原文。版权归原作者所有。

引用

  1. Trieu, Jiang, Tavakoli Taba, et al. From shadows to signals: exploring the strengths and limitations of artificial intelligence in breast cancer lesion detection on screening mammograms compared to radiologists and radiology trainees. Br J Radiol. 2026. PMID: 42538818. doi:10.1093/bjr/tqag177

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。