Deep learning analysis of contrast-enhanced spectral mammography to determine histoprognostic factors of malignant breast tumours.

OBJECTIVE: To evaluate if a deep learning model can be used to characterise breast cancers on contrast-enhanced spectral mammography (CESM). METHODS: This retrospective mono-centric study included biopsy-proven invasive cancers with an enhancement on CESM. CESM images include low-energy images (LE) comparable to digital mammography and dual-energy subtracted images (DES) showing tumour angiogenesis. For each lesion, histologic type, tumour grade, estrogen receptor (ER) status, progesterone receptor (PR) status, HER-2 status, Ki-67 proliferation index, and the size of the invasive tumour were retrieved. The deep learning model used was a CheXNet-based model fine-tuned on CESM dataset. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was calculated for the different models: images by images and then by majority voting combining all the incidences for one tumour. RESULTS: In total, 447 invasive breast cancers detected on CESM with pathological evidence, in 389 patients, which represented 2460 images analysed, were included. Concerning the ER, the deep learning model on the DES images had an AUC of 0.83 with the image-by-image analysis and of 0.85 for the majority voting. For the triple-negative analysis, a high AUC was observable for all models, in particularity for the model on LE images with an AUC of 0.90 for the image-by-image analysis and 0.91 for the majority voting. The AUC for the other histoprognostic factors was lower. CONCLUSION: Deep learning analysis on CESM has the potential to determine histoprognostic tumours makers, notably estrogen receptor status, and triple-negative receptor status. KEY POINTS: • A deep learning model developed for chest radiography was adapted by fine-tuning to be used on contrast-enhanced spectral mammography. • The adapted models allowed to determine for invasive breast cancers the status of estrogen receptors and triple-negative receptors. • Such models applied to contrast-enhanced spectral mammography could provide rapid prognostic and predictive information.

Impact of preoperative staging with contrast-enhanced mammography for localized breast cancer management.

OBJECTIVE: A precise evaluation of the disease extent is mandatory before surgery for early breast cancer (EBC). Contrast-enhanced mammography (CEDM) is a recent technique that may help define adequate surgery. METHODS: This retrospective study included consecutive patients referred to a cancer center between November 2016 and July 2017 for biopsy-confirmed invasive EBC management. The primary objective was to evaluate the rate of surgical changes after incorporating the results of the preoperative staging examination, including CEDM. RESULTS: A total of 231 patients were screened for inclusion, and 132 patients were included, corresponding to 134 lesions. The first surgical plan was modified for 33 patients (25%), which represented 34 lesions. For 8 patients (6%), the surgery was cancelled in preference for neoadjuvant chemotherapy; for 16 patients (12.1%), the primary tumor procedure was enlarged; and for 23 patients (17.4%) the lymph node management was modified. Surgery was changed only due to the CEDM results for 24 patients (18.5%) and consisted of a more invasive procedure due to a more extended, multifocal or multicentric lesion than seen on the standard imaging. Anatomopathological surgery piece findings were well correlated with contrast-enhanced mammography results. Overall, there was no increase in the delay between the planned date of surgery and the effective surgical procedure (median 0 days). CONCLUSION: CEDM added to preoperative staging helped define better surgical management without increasing delay in the surgical procedure. ADVANCES IN KNOWLEDGE: CEDM is a reliable technique that should be considered as part of preoperative staging for EBC.