119 145

Cited 6 times in

Applying Data-driven Imaging Biomarker in Mammography for Breast Cancer Screening: Preliminary Study

Authors
 Eun-Kyung Kim  ;  Hyo-Eun Kim  ;  Kyunghwa Han  ;  Bong Joo Kang  ;  Yu-Mee Sohn  ;  Ok Hee Woo  ;  Chan Wha Lee 
Citation
 SCIENTIFIC REPORTS, Vol.8(1) : 2762, 2018 
Journal Title
 SCIENTIFIC REPORTS 
Issue Date
2018
Abstract
We assessed the feasibility of a data-driven imaging biomarker based on weakly supervised learning (DIB; an imaging biomarker derived from large-scale medical image data with deep learning technology) in mammography (DIB-MG). A total of 29,107 digital mammograms from five institutions (4,339 cancer cases and 24,768 normal cases) were included. After matching patients' age, breast density, and equipment, 1,238 and 1,238 cases were chosen as validation and test sets, respectively, and the remainder were used for training. The core algorithm of DIB-MG is a deep convolutional neural network; a deep learning algorithm specialized for images. Each sample (case) is an exam composed of 4-view images (RCC, RMLO, LCC, and LMLO). For each case in a training set, the cancer probability inferred from DIB-MG is compared with the per-case ground-truth label. Then the model parameters in DIB-MG are updated based on the error between the prediction and the ground-truth. At the operating point (threshold) of 0.5, sensitivity was 75.6% and 76.1% when specificity was 90.2% and 88.5%, and AUC was 0.903 and 0.906 for the validation and test sets, respectively. This research showed the potential of DIB-MG as a screening tool for breast cancer.
Files in This Item:
T201800488.pdf Download
DOI
10.1038/s41598-018-21215-1
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Radiology (영상의학교실) > 1. Journal Papers
Yonsei Authors
Kim, Eun-Kyung(김은경) ORCID logo https://orcid.org/0000-0002-3368-5013
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/162014
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse