RESUMO
OBJECTIVES: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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. CLINICAL RELEVANCE STATEMENT: 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. KEY POINTS: ⢠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.
RESUMO
This study aimed to assess variation between radiologists evaluating the quality of multi-detector computed tomography enterography. For 40 consecutive examinations, three experienced radiologists independently rated the following quality variables: % length of adequately filled bowel, bowel lumen diameters, bowel wall delineation, superior mesenteric vein, and bowel wall enhancement, artefacts, and total quality. We calculated the mean difference between observers with standard deviation (SD) for continuous variables and % total agreement, exact Fleiss kappa, and P-values (McNemar's test) for categorical variables. Depending on bowel segment (duodenum distal to bulb, jejunum, ileum, terminal ileum), mean difference between observers ranged from two to 33 (SD from 11 to 32) for % length of adequately filled bowel judged subjectively, 0-2 (SD 0-3) mm for smallest bowel lumen diameter and 0-4 (SD 3-7) mm for largest bowel lumen diameter. Agreement on bowel wall delineation was 80%/kappa 0.50 in duodenum, 90%/kappa 0.57 in jejunum, 75%/kappa 0.14 in ileum and 88%/kappa 0.17 in terminal ileum, where ratings differed between observers (P < 0.04). Agreement was 65%/kappa 0.18 for bowel wall enhancement judged subjectively. For contrast enhancement measured in Hounsfield Units, mean difference between observers ranged from two to 11 (SD 12-15) in normal jejunum wall and zero to one (SD 4-5) in the superior mesenteric vein depending on observer pair. Agreement was 78%/kappa 0.12 for image artefacts. Rating of total examination quality (good/optimal versus poor/very poor) differed between observers (P < 0.01); agreement was 60%/kappa 0.41. Many subjective evaluations varied between observers. We believe that measurements of bowel lumen diameters and contrast enhancement may be preferable.