Department of Radiology, Stavanger University Hospital, Stavanger, Norway.
Faculty of Health Sciences, University of Stavanger, Stavanger, Norway.
Eur Radiol. 2024 Sep;34(9):6158-6167. doi: 10.1007/s00330-024-10662-2. Epub 2024 Feb 23.
To compare the location of AI markings on screening mammograms with cancer location on diagnostic mammograms, and to classify interval cancers with high AI score as false negative, minimal sign, or true negative.
In a retrospective study from 2022, we compared the performance of an AI system with independent double reading according to cancer detection. We found 93% (880/949) of the screen-detected cancers, and 40% (122/305) of the interval cancers to have the highest AI risk score (AI score of 10). In this study, four breast radiologists reviewed mammograms from 126 randomly selected screen-detected cancers and all 120 interval cancers with an AI score of 10. The location of the AI marking was stated as correct/not correct in craniocaudal and mediolateral oblique view. Interval cancers with an AI score of 10 were classified as false negative, minimal sign significant/non-specific, or true negative.
All screen-detected cancers and 78% (93/120) of the interval cancers with an AI score of 10 were correctly located by the AI system. The AI markings matched in both views for 79% (100/126) of the screen-detected cancers and 22% (26/120) of the interval cancers. For interval cancers with an AI score of 10, 11% (13/120) were correctly located and classified as false negative, 10% (12/120) as minimal sign significant, 26% (31/120) as minimal sign non-specific, and 31% (37/120) as true negative.
AI markings corresponded to cancer location for all screen-detected cancers and 78% of the interval cancers with high AI score, indicating a potential for reducing the number of interval cancers. However, it is uncertain whether interval cancers with subtle findings in only one view are actionable for recall in a true screening setting.
In this study, AI markings corresponded to the location of the cancer in a high percentage of cases, indicating that the AI system accurately identifies the cancer location in mammograms with a high AI score.
• All screen-detected and 78% of the interval cancers with high AI risk score (AI score of 10) had AI markings in one or two views corresponding to the location of the cancer on diagnostic images. • Among all 120 interval cancers with an AI score of 10, 21% (25/120) were classified as a false negative or minimal sign significant and had AI markings matching the cancer location, suggesting they may be visible on prior screening. • Most of the correctly located interval cancers matched only in one view, and the majority were classified as either true negative or minimal sign non-specific, indicating low potential for being detected earlier in a real screening setting.
比较 AI 标记在筛查性乳房 X 光片中的位置与诊断性乳房 X 光片中癌症的位置，并将高 AI 评分的间隔性癌症归类为假阴性、微小征象或真阴性。
在 2022 年的一项回顾性研究中，我们根据癌症检测比较了人工智能系统与独立双读的性能。我们发现，93%（880/949）的筛查检出癌症和 40%（122/305）的间隔性癌症具有最高的 AI 风险评分（AI 评分 10）。在这项研究中，四位乳腺放射科医生对 126 例随机选择的筛查检出癌症和所有 120 例 AI 评分 10 的间隔性癌症的乳房 X 光片进行了回顾。AI 标记在头尾位和内外斜位上的位置被陈述为正确/不正确。AI 评分 10 的间隔性癌症被归类为假阴性、微小征象显著/非特异性或真阴性。
所有筛查检出癌症和 AI 评分 10 的 78%（93/120）的间隔性癌症均被 AI 系统正确定位。AI 标记在头尾位和内外斜位上与 79%（100/126）的筛查检出癌症和 22%（26/120）的间隔性癌症相匹配。对于 AI 评分 10 的间隔性癌症，11%（13/120）被正确定位并归类为假阴性，10%（12/120）为微小征象显著，26%（31/120）为微小征象非特异性，31%（37/120）为真阴性。
AI 标记与所有筛查检出癌症和 AI 评分高的 78%的间隔性癌症的癌症位置相对应，这表明有可能减少间隔性癌症的数量。然而，尚不确定在真正的筛查环境中，只有一个视图中存在细微表现的间隔性癌症是否可以进行召回。
在这项研究中，AI 标记在高比例的病例中与癌症的位置相对应，这表明 AI 系统在高 AI 评分的乳房 X 光片中准确地识别了癌症的位置。
所有筛查检出的癌症和高 AI 风险评分（AI 评分 10）的 78%的间隔性癌症在一个或两个视图中具有与诊断图像上癌症位置相对应的 AI 标记。
在所有 120 例 AI 评分 10 的间隔性癌症中，21%（25/120）被归类为假阴性或微小征象显著，并且具有与癌症位置相匹配的 AI 标记，这表明它们可能在前一次筛查中可见。
大多数正确定位的间隔性癌症仅在一个视图中匹配，且大多数被归类为真阴性或微小征象非特异性，这表明在实际的筛查环境中，它们被更早检测到的可能性较低。
