TY - JOUR
T1 - Applying Data-driven Imaging Biomarker in Mammography for Breast Cancer Screening
T2 - Preliminary Study
AU - Kim, Eun Kyung
AU - Kim, Hyo Eun
AU - Han, Kyunghwa
AU - Kang, Bong Joo
AU - Sohn, Yu Mee
AU - Woo, Ok Hee
AU - Lee, Chan Wha
N1 - Publisher Copyright:
© 2018, The Author(s).
PY - 2018/12/1
Y1 - 2018/12/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85054190424&partnerID=8YFLogxK
U2 - 10.1038/s41598-018-21215-1
DO - 10.1038/s41598-018-21215-1
M3 - Article
C2 - 29426948
AN - SCOPUS:85054190424
SN - 2045-2322
VL - 8
JO - Scientific reports
JF - Scientific reports
IS - 1
M1 - 2762
ER -
