Search

Purpose: The purpose of this study was to evaluate an artificial intelligence (AI) software that automatically detects and quantifies breast arterial calcifications (BAC)., Materials and Methods: Women who underwent both mammography and thoracic computed tomography (CT) from 2009 to 2018 were retrospectively included in this single-center study. Deep learning-based software was used to automatically detect and quantify BAC with a BAC AI score ranging from 0 to 10-points. Results were compared using Spearman correlation test with a previously described BAC manual score based on radiologists' visual quantification of BAC on the mammogram. Coronary artery calcification (CAC) score was manually scored using a 12-point scale on CT. The diagnostic performance of the marked BAC AI score (defined as BAC AI score ≥ 5) for the detection of marked CAC (CAC score ≥ 4) was analyzed in terms of sensitivity, specificity, accuracy and area under the receiver operating characteristic curve (AUC)., Results: A total of 502 women with a median age of 62 years (age range: 42-96 years) were included. The BAC AI score showed a very strong correlation with the BAC manual score (r = 0.83). Marked BAC AI score had 32.7 % sensitivity (37/113; 95 % confidence interval [CI]: 24.2-42.2), 96.1 % specificity (374/389; 95 % CI: 93.7-97.8), 71.2 % positive predictive value (37/52; 95 % CI: 56.9-82.9), 83.1 % negative predictive value (374/450; 95 % CI: 79.3-86.5), and 81.9 % accuracy (411/502; 95 % CI: 78.2-85.1) for the diagnosis of marked CAC. The AUC of the marked BAC AI score for the diagnosis of marked CAC was 0.64 (95 % CI: 0.60-0.69)., Conclusion: The automated BAC AI score shows a very strong correlation with manual BAC scoring in this external validation cohort. The automated BAC AI score may be a useful tool to promote the integration of BAC into mammography reports and to improve awareness of a woman's cardiovascular risk status., Competing Interests: Declaration of competing interest The deep learning software have been developed by iCAD. No financial support was received to conduct the study. A research agreement for the use of the software was signed prior to the study. Data collection and data analysis were performed by the authors. The final version of the submitted manuscript was read by iCAD representatives before submission, to ensure that it did not contain any confidential information., (Copyright © 2024. Published by Elsevier Masson SAS.)

Purpose: To assess the incidence and presentation of ipsilateral cancer recurrences (ICR) after deep inferior epigastric perforator (DIEP) flap reconstruction for breast cancer., Patients and Methods: Data of 247 consecutive women with DIEP flap reconstruction after breast cancer in our institution between 1997 and 2009 were retrospectively reviewed., Results: Mean follow-up time was 4.1years±3.2 (SD) (median: 3years; range: 1month - 14years). Thirty-one patients (12.5%, 95%CI: =8.7-17.3) presented 34 relapses, in average 4.1years±2.6 after mastectomy: 14 (41%) were ipsilateral, 6 (18%) contralateral and 14 (41%) metastatic. ICRs occurred earlier (3.9 vs. 5.8years; P<0.05) than non-ICRs. Most ICRs (10/14, 71%) involved the periphery of the flap and presented as palpable nodules. The remaining (4/14, 29%) involved the axilla and 3/4 (75%) were palpable. Imaging procedures detected infra-clinical ICRs in 3 of 10 imaged patients (30%)., Conclusion: ICRs after DIEP flap reconstruction are more frequent than contralateral recurrences suggesting the need for imaging follow-up of the reconstructed breast., (Copyright © 2015 Éditions françaises de radiologie. Published by Elsevier Masson SAS. All rights reserved.)

Purpose: To evaluate using phantom study the average glandular dose (AGD) and image quality in breast tomosynthesis., Materials and Methods: The study was performed with a full-field digital mammography system (Mammomat Inspiration(®), Siemens, Erlangen, Germany) combined with tomosynthesis equipment (3D). For AGD evaluation, polymethyl methacrylate (PMMA) plates and a dosimeter were used to directly measure the absorbed doses in 2D and in 3D. The doses were then compared to the doses displayed on the equipment using the Mann-Whitney test. Three phantoms, accredited for 2D digital mammography (MTM 100, ACR RMI 156, BR3D), were imaged three times in 2D then in 3D. For each acquisition, the AGD was recorded. For image quality assessment, scores, defined by the rate of visible inserts, obtained for each acquisition both in 2D and in 3D, and for each phantom, were compared (Kruskall-Wallis and post-hoc Dunn tests)., Results: There was no significant difference between the measured and displayed AGD, both in 2D and in 3D imaging (P>0.05). With identical acquisition parameters, AGD were significantly greater in 3D than in 2D P<0.01). For phantoms MTM 100 and ACR RMI 156, there was no significant difference between the rate of visible inserts in 2D and in 3D (P=0.06 and P=0.36, respectively). However for phantom BR3D, the rate was significantly higher in 3D than in 2D (P<0.0001)., Conclusion: Doses are significantly greater in 3D than in 2D. With tomosynthesis, out of the three phantoms tested, only phantom BR3D showed a higher rate of visible inserts., (Copyright © 2015 Éditions françaises de radiologie. Published by Elsevier Masson SAS. All rights reserved.)