Prospective Analysis Using a Novel CNN Algorithm to Distinguish Atypical Ductal Hyperplasia From Ductal Carcinoma in Situ in Breast.

INTRODUCTION: We previously developed a convolutional neural networks (CNN)-based algorithm to distinguish atypical ductal hyperplasia (ADH) from ductal carcinoma in situ (DCIS) using a mammographic dataset. The purpose of this study is to further validate our CNN algorithm by prospectively analyzing an unseen new dataset to evaluate the diagnostic performance of our algorithm. MATERIALS AND METHODS: In this institutional review board-approved study, a new dataset composed of 280 unique mammographic images from 140 patients was used to test our CNN algorithm. All patients underwent stereotactic-guided biopsy of calcifications and underwent surgical excision with available final pathology. The ADH group consisted of 122 images from 61 patients with the highest pathology diagnosis of ADH. The DCIS group consisted of 158 images from 79 patients with the highest pathology diagnosis of DCIS. Two standard mammographic magnification views (craniocaudal and mediolateral/lateromedial) of the calcifications were used for analysis. Calcifications were segmented using an open source software platform 3D slicer and resized to fit a 128 × 128 pixel bounding box. Our previously developed CNN algorithm was used. Briefly, a 15 hidden layer topology was used. The network architecture contained 5 residual layers and dropout of 0.25 after each convolution. Diagnostic performance metrics were analyzed including sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve. The "positive class" was defined as the pure ADH group in this study and thus specificity represents minimizing the amount of falsely labeled pure ADH cases. RESULTS: Area under the receiver operating characteristic curve was 0.90 (95% confidence interval, ± 0.04). Diagnostic accuracy, sensitivity, and specificity was 80.7%, 63.9%, and 93.7%, respectively. CONCLUSION: Prospectively tested on new unseen data, our CNN algorithm distinguished pure ADH from DCIS using mammographic images with high specificity.

Development of a New Patient-reported Outcome Instrument to Evaluate Treatments for Scars: The SCAR-Q.

BACKGROUND: Every year millions of individuals acquire scars. A literature review of patient-reported outcome (PRO) instruments identified content limitations in existing scar-specific measures. The aim of this study was to develop a new PRO instrument called SCAR-Q for children and adults with surgical, traumatic, and burn scars. METHODS: We performed a secondary analysis of the qualitative datasets used in the development of PRO instruments for plastic and reconstructive surgery, that is, BREAST-Q, FACE-Q, BODY-Q, and CLEFT-Q. The keyword "scar*" was used to extract scar-specific text. Data were analyzed to identify concepts of interest and to form a comprehensive item pool. Scales were developed and refined through multiple rounds of cognitive interviews with patients and with input from international clinical experts between July 2015 and December 2016. RESULTS: A total of 52 children and 192 adults from the qualitative datasets provided between 1 and 34 scar-specific codes (n = 1,227). The analysis led to the identification of 3 key domains for which scales were developed: scar appearance (eg, size, color, contour), scar symptoms (eg, painful, tight, itchy), and psychosocial impact (eg, feeling self-conscious, bothered by scar). Cognitive interviews with 25 adults and 20 pediatric participants with scars, plus feedback from 27 clinical experts, led to rewording and removal of items, and new items added. These steps ensured content validity for SCAR-Q in a broad range of scars. CONCLUSIONS: The SCAR-Q is now being field-tested. Once completed, we anticipate SCAR-Q will be used in clinical practice and in clinical trials to test different scar therapies.