文献速递乳腺乳腺X线

基于人工智能的乳腺X线摄影检测支持软件提升放射科医生诊断效能:一项多阅片者研究

Improving the Performance of Radiologists Using Artificial Intelligence-Based Detection Support Software for Mammography: A Multi-Reader Study.
PubMed 文献 · Korean J Radiol · 2022-04-04

本研究使用一家医院200例患者的乳腺X线摄影数据验证一款商用深度学习软件,并由5名乳腺专科放射科医生和5名普通放射科医生在有、无AI辅助两种条件下以7分制评估恶性可能性。AI辅助后两组AUROC和敏感度均显著提高,特异度无显著差异;乳腺专科医生阅片时间缩短而普通放射科医生延长。

要点

  • AI辅助使乳腺专科放射科医生AUROC从0.813升至0.884,普通放射科医生从0.684升至0.833。
  • AI辅助使两组敏感度分别从74.6%升至88.6%、从52.1%升至79.4%,特异度无显著差异。
  • AI辅助使乳腺专科医生平均阅片时间从82.73秒降至73.04秒,普通放射科医生从35.44秒增至42.52秒。

核心结论

  • 基于AI的软件可改善放射科医生的诊断效能,无论其经验水平如何,并影响阅片时间。

研究设计与样本

  • 多阅片者研究,使用一家医院200例患者的外部数据(100例乳腺癌、40例良性病变、60例无病变)验证商用深度学习乳腺X线摄影软件。

诊断标准与关键数值

  • AI单独AUROC为0.915(95%CI 0.876-0.954)。
  • 乳腺专科放射科医生组(5名平均)无AI辅助时AUROC为0.813(95%CI 0.756-0.870),有AI辅助时为0.884(95%CI 0.840-0.928),p=0.007。
  • 普通放射科医生组(5名平均)无AI辅助时AUROC为0.684(95%CI 0.616-0.752),有AI辅助时为0.833(95%CI 0.779-0.887),p<0.001。
  • 乳腺专科放射科医生组敏感度无AI辅助74.6% vs 有AI辅助88.6%(p<0.001),特异度无AI辅助66.6% vs 有AI辅助66.4%(p=0.238)。
  • 普通放射科医生组敏感度无AI辅助52.1% vs 有AI辅助79.4%(p<0.001),特异度无AI辅助70.8% vs 有AI辅助70.0%(p=0.689)。

临床应用与阅片要点

  • 阅片者使用7分制评估乳腺X线摄影恶性可能性,AI辅助可提高诊断效能。
  • AI辅助对乳腺专科和普通放射科医生的敏感度均有提升,特异度无显著变化。
  • AI辅助缩短乳腺专科放射科医生阅片时间(82.73秒 vs 73.04秒,p<0.001),但延长普通放射科医生阅片时间(35.44秒 vs 42.52秒,p<0.001)。

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

OBJECTIVE: To evaluate whether artificial intelligence (AI) for detecting breast cancer on mammography can improve the performance and time efficiency of radiologists reading mammograms.

MATERIALS AND METHODS: A commercial deep learning-based software for mammography was validated using external data collected from 200 patients, 100 each with and without breast cancer (40 with benign lesions and 60 without lesions) from one hospital. Ten readers, including five breast specialist radiologists (BSRs) and five general radiologists (GRs), assessed all mammography images using a seven-point scale to rate the likelihood of malignancy in two sessions, with and without the aid of the AI-based software, and the reading time was automatically recorded using a web-based reporting system. Two reading sessions were conducted with a two-month washout period in between. Differences in the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and reading time between reading with and without AI were analyzed, accounting for data clustering by readers when indicated.

RESULTS: The AUROC of the AI alone, BSR (average across five readers), and GR (average across five readers) groups was 0.915 (95% confidence interval, 0.876-0.954), 0.813 (0.756-0.870), and 0.684 (0.616-0.752), respectively. With AI assistance, the AUROC significantly increased to 0.884 (0.840-0.928) and 0.833 (0.779-0.887) in the BSR and GR groups, respectively (p = 0.007 and p < 0.001, respectively). Sensitivity was improved by AI assistance in both groups (74.6% vs. 88.6% in BSR, p < 0.001; 52.1% vs. 79.4% in GR, p < 0.001), but the specificity did not differ significantly (66.6% vs. 66.4% in BSR, p = 0.238; 70.8% vs. 70.0% in GR, p = 0.689). The average reading time pooled across readers was significantly decreased by AI assistance for BSRs (82.73 vs. 73.04 seconds, p < 0.001) but increased in GRs (35.44 vs. 42.52 seconds, p < 0.001).

CONCLUSION: AI-based software improved the performance of radiologists regardless of their experience and affected the reading time.

来源:Korean J Radiol,查看原文。版权归原作者所有。

引用

  1. Lee, Kim, Lee, et al. Improving the Performance of Radiologists Using Artificial Intelligence-Based Detection Support Software for Mammography: A Multi-Reader Study. Korean J Radiol. 2022. PMID: 35434976. doi:10.3348/kjr.2021.0476

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。