2023-11-17 インペリアル・カレッジ・ロンドン(ICL)
◆2020年には全世界で2,300,000人の女性が乳がんに診断され、685,000人が亡くなっており、早期検知は治療と死亡率の低減に寄与する。ハンガリーでの研究ではMiaが人の「読者」が見逃す可能性のあるがん組織を検出し、通常の読影を補完。
◆三つのフェーズで行われた研究では、AI読者は標準の人間読影よりも24件多くのがんを発見し、70人多くを再調査した。Miaは特に早期検出が重要な浸潤性がんを83%検出。研究者は今後、他の国での結果再現や患者の長期追跡が必要と指摘。UKでの研究や米国での導入も進行中。
<関連情報>
- https://www.imperial.ac.uk/news/249573/new-ai-tool-detects-13-more/
- https://www.nature.com/articles/s41591-023-02625-9
乳がんの早期発見を改善するためのAI支援スクリーン読影の前向き導入 Prospective implementation of AI-assisted screen reading to improve early detection of breast cancer
Annie Y. Ng,Cary J. G. Oberije,Éva Ambrózay,Endre Szabó,Orsolya Serfőző,Edit Karpati,Georgia Fox,Ben Glocker,Elizabeth A. Morris,Gábor Forrai & Peter D. Kecskemethy
Nature Medicine Published:16 November 2023
DOI:https://doi.org/10.1038/s41591-023-02625-9
Abstract
Artificial intelligence (AI) has the potential to improve breast cancer screening; however, prospective evidence of the safe implementation of AI into real clinical practice is limited. A commercially available AI system was implemented as an additional reader to standard double reading to flag cases for further arbitration review among screened women. Performance was assessed prospectively in three phases: a single-center pilot rollout, a wider multicenter pilot rollout and a full live rollout. The results showed that, compared to double reading, implementing the AI-assisted additional-reader process could achieve 0.7–1.6 additional cancer detection per 1,000 cases, with 0.16–0.30% additional recalls, 0–0.23% unnecessary recalls and a 0.1–1.9% increase in positive predictive value (PPV) after 7–11% additional human reads of AI-flagged cases (equating to 4–6% additional overall reading workload). The majority of cancerous cases detected by the AI-assisted additional-reader process were invasive (83.3%) and small-sized (≤10 mm, 47.0%). This evaluation suggests that using AI as an additional reader can improve the early detection of breast cancer with relevant prognostic features, with minimal to no unnecessary recalls. Although the AI-assisted additional-reader workflow requires additional reads, the higher PPV suggests that it can increase screening effectiveness.
