Aim To assess the generalisability of a deep learning (DL) system for screening mammography developed at New York University (NYU), USA (1,2) in a South Australian (SA) dataset. Methods and Materials Clients with pathology-proven lesions (n=3,160) and age-matched controls (n=3,240) were selected from women screened at BreastScreen SA from January 2010 to December 2016 (n clients=207,691) and split into training, validation and test subsets (70\%, 15\%, 15\% respectively). The primary outcome was area under the curve (AUC), in the SA Test Set 1 (SATS1), differentiating invasive breast cancer or ductal carcinoma in situ (n=469) from age-matched controls (n=490) and benign lesions (n=44). The NYU system was tested statically, after training without transfer learning (TL), after retraining with TL and without (NYU1) and with (NYU2) heatmaps. Results The static NYU1 model AUCs in the NYU test set (NYTS) and SATS1 were 83.0\%(95\%CI=82.4\%-83.6\%)(2) and 75.8\%(95\%CI=72.6\%-78.8\%), respectively. Static NYU2 AUCs in the NYTS and SATS1 were 88.6\%(95\%CI=88.3\%-88.9\%)(2) and 84.5\%(95\%CI=81.9\%-86.8\%), respectively. Training of NYU1 and NYU2 without TL achieved AUCs in the SATS1 of 65.8\% (95\%CI=62.2\%-69.1\%) and 85.9\%(95\%CI=83.5\%-88.2\%), respectively. Retraining of NYU1 and NYU2 with TL resulted in AUCs of 82.4\%(95\%CI=79.7-84.9\%) and 86.3\%(95\%CI=84.0-88.5\%) respectively. Conclusion We did not fully reproduce the reported performance of NYU on a local dataset; local retraining with TL approximated this level of performance. Optimising models for local clinical environments may improve performance. The generalisation of DL systems to new environments may be challenging.

Supplemental Digital Content is available in the text.

Background: Wire-guided localisation (WGL) is the most widely used approach to excise impalpable breast lesions in breast conserving surgery (BCS). There are several disadvantages to this technique. There are a variety of methods available, each with its own imperfections, therefore a superior approach is much desired. Here we report the efficacy of carbon-track localisation (CL) as an adjunct to hookwire in terms of margins, complications and operating time. Methods: A consecutive series of patients with impalpable breast lesions undergoing either CL combined with WGL or just WGL alone from 2016 to 2017 were evaluated in this retrospective cohort study. Of 57 patients, 27 CLs with WGL and 30 WGLs alone were performed. Results: All breast lesions were successfully localised pre-operatively and excised in both groups. Involved margins for invasive or in-situ disease were found in 14% in the CL group and 24% in the WGL group (p = 0.70). Close margins of <1 mm were found in 29% of the CL group and 48% in the WGL group (p = 0.34). The median operating time were 26 min and 37 min for the CL and WGL groups respectively (p = 0.002). Complications were noted to be 7.4% with CL and 16.7% with WGL (p = 0.43). Conclusion: Carbon-track as an adjunct to hookwire localisation can be easily adopted and has a short learning curve with improved surgical outcomes. Although requiring further validation from larger studies to demonstrate statistical significance, the outcomes reported here are promising. Highlights:

Objective: To examine the screening-treatment-mortality pathway among women with invasive breast cancer in 2006-2014 using linked data.Methods: BreastScreen histories of South Australian women diagnosed with breast cancer (n = 8453) were investigated. Treatments recorded within 12 months from diagnosis were obtained from linked registry and administrative data. Associations of screening history with treatment were investigated using logistic regression and with cancer mortality outcomes using competing risk analyses, adjusting for sociodemographic, cancer and comorbidity characteristics. Results and conclusion:For screening ages of 50-69 years, 70% had participated in BreastScreen SA ≤ 5 years and 53% ≤ 2 years of diagnosis. Five-year disease-specific survival post-diagnosis was 90%. Compared with those not screened ≤5 years, women screened ≤2 years had higher odds, adjusted for socio-demographic, cancer and comorbidity characteristics, and diagnostic period, of breast-conserving surgery (aOR 2.5, 95% CI 1.9-3.2) and radiotherapy (aOR 1.2, 95% CI 1.1-1.3). These women had a lower unadjusted risk of post-diagnostic cancer mortality (SHR 0.33, 95% CI 0.27-0.41), partly mediated by stage (aSHR 0.65, 95% CI 0.51-0.81), and less breast surgery (aSHR 0.78, 95% CI 0.62-0.99). Screening ≤2 years and conserving surgery

No abstract