Mammographie-Screening-Zentrum, Paderborn, NRW, Germany.
WIPM Charterhouse Square London, UK.
J Med Screen. 2021 Sep;28(3):365-368. doi: 10.1177/0969141320984198. Epub 2021 Jan 5.
To examine the breast cancer detection rate by single reading of an experienced radiologist supported by an artificial intelligence (AI) system, and compare with two-dimensional full-field digital mammography (2D-FFDM) double reading.
Images (3D-tomosynthesis) of 161 biopsy-proven cancers were re-read by the AI algorithm and compared to the results of first human reader, second human reader and consensus following double reading in screening. Detection was assessed in subgroups by tumour type, breast density and grade, and at two operating points, referred to as a lower and a higher sensitivity threshold.
The AI algorithm method gave similar results to double-reading 2D-FFDM, and the detection rate was significantly higher compared to single-reading 2D-FFDM. At the lower sensitivity threshold, the algorithm was significantly more sensitive than reader A (97.5% vs. 89.4%, = 0.02), non-significantly more sensitive than reader B (97.5% vs. 94.4%, = 0.2) and non-significantly less sensitive than the consensus from double reading (97.5% vs. 99.4%, = 0.2). At the higher sensitivity threshold, the algorithm was significantly more sensitive than reader A (99.4% vs. 89.4%, p < 0.001) and reader B (99.4% vs. 94.4%, = 0.02) and identical to the consensus sensitivity (99.7% in both cases, = 1.0). There were no significant differences in the detection capability of the AI system by tumour type, grading and density.
In this proof of principle study, we show that sensitivity using single reading with a suitable AI algorithm is non-inferior to that of standard of care using 2D mammography with double reading, when tomosynthesis is the primary screening examination.
通过单读一位有经验的放射科医生辅以人工智能（AI）系统来检查乳腺癌的检出率，并与二维全数字乳腺摄影（2D-FFDM）双读进行比较。
对 161 例经活检证实的癌症的图像（3D 断层合成）进行 AI 算法重新读取，并与筛查时首次人类读者、第二次人类读者和双读后的共识结果进行比较。通过肿瘤类型、乳腺密度和分级以及两个操作点（称为较低和较高灵敏度阈值）对检测进行亚组评估。
AI 算法与双读 2D-FFDM 结果相似，且检出率明显高于单读 2D-FFDM。在较低的灵敏度阈值下，该算法明显比读者 A 更敏感（97.5%比 89.4%，=0.02），与读者 B 相比不显著更敏感（97.5%比 94.4%，=0.2），与双读共识相比不显著更不敏感（97.5%比 99.4%，=0.2）。在较高的灵敏度阈值下，该算法明显比读者 A（99.4%比 89.4%，p<0.001）和读者 B（99.4%比 94.4%，=0.02）更敏感，与共识灵敏度相同（两种情况下均为 99.7%，=1.0）。AI 系统的检测能力在肿瘤类型、分级和密度方面没有显著差异。
在这项原理验证研究中，我们表明，当断层合成术是主要的筛查检查时，使用合适的 AI 算法进行单读的灵敏度与标准护理使用 2D 乳腺摄影进行双读的灵敏度相当。
