PMID- 36342640
OWN - NLM
STAT- MEDLINE
DCOM- 20230301
LR  - 20230301
IS  - 1865-0341 (Electronic)
IS  - 1865-0333 (Linking)
VI  - 16
IP  - 1
DP  - 2023 Mar
TI  - Deep learning model for breast cancer diagnosis based on bilateral asymmetrical 
      detection (BilAD) in digital breast tomosynthesis images.
PG  - 20-27
LID - 10.1007/s12194-022-00686-y [doi]
AB  - The purpose of this study was to develop a deep learning model to diagnose breast 
      cancer by embedding a diagnostic algorithm that examines the asymmetry of 
      bilateral breast tissue. This retrospective study was approved by the 
      institutional review board. A total of 115 patients who underwent breast surgery 
      and had pathologically confirmed breast cancer were enrolled in this study. Two 
      image pairs [230 pairs of bilateral breast digital breast tomosynthesis (DBT) 
      images with 115 malignant tumors and contralateral tissue (M/N), and 115 
      bilateral normal areas (N/N)] were generated from each patient enrolled in this 
      study. The proposed deep learning model is called bilateral asymmetrical 
      detection (BilAD), which is a modified convolutional neural network (CNN) model 
      of Xception with two-dimensional tensors for bilateral breast images. BilAD was 
      trained to classify the differences between pairs of M/N and N/N datasets. The 
      results of the BilAD model were compared to those of the unilateral control CNN 
      model (uCNN). The results of BilAD and the uCNN were as follows: accuracy, 0.84 
      and 0.75; sensitivity, 0.73 and 0.58; and specificity, 0.93 and 0.92, 
      respectively. The mean area under the receiver operating characteristic curve of 
      BilAD was significantly higher than that of the uCNN (p = 0.02): 0.90 and 0.84, 
      respectively. The proposed deep learning model trained by embedding a diagnostic 
      algorithm to examine the asymmetry of bilateral breast tissue improves the 
      diagnostic accuracy for breast cancer.
CI  - (c) 2022. The Author(s), under exclusive licence to Japanese Society of 
      Radiological Technology and Japan Society of Medical Physics.
FAU - Shimokawa, Daiki
AU  - Shimokawa D
AD  - Department of Clinical Imaging, Tohoku University Graduate School of Medicine, 
      2-1 Seiryo-Machi, Aoba-Ku, Sendai, Miyagi, 980-8575, Japan.
FAU - Takahashi, Kengo
AU  - Takahashi K
AD  - Department of Clinical Imaging, Tohoku University Graduate School of Medicine, 
      2-1 Seiryo-Machi, Aoba-Ku, Sendai, Miyagi, 980-8575, Japan.
FAU - Kurosawa, Daiya
AU  - Kurosawa D
AD  - Department of Clinical Imaging, Tohoku University Graduate School of Medicine, 
      2-1 Seiryo-Machi, Aoba-Ku, Sendai, Miyagi, 980-8575, Japan.
FAU - Takaya, Eichi
AU  - Takaya E
AD  - AI Lab, Tohoku University Hospital, 1-1 Seiryo-Machi, Aoba-Ku, Sendai, Miyagi, 
      980-8574, Japan.
FAU - Oba, Ken
AU  - Oba K
AD  - Department of Radiology, St. Luke's International Hospital, 9-1, Akashi-Cho, 
      Chuo-Ku, Tokyo, Tokyo, 104-8560, Japan.
FAU - Yagishita, Kazuyo
AU  - Yagishita K
AD  - Department of Radiology, St. Luke's International Hospital, 9-1, Akashi-Cho, 
      Chuo-Ku, Tokyo, Tokyo, 104-8560, Japan.
FAU - Fukuda, Toshinori
AU  - Fukuda T
AD  - Department of Radiology, St. Luke's International Hospital, 9-1, Akashi-Cho, 
      Chuo-Ku, Tokyo, Tokyo, 104-8560, Japan.
FAU - Tsunoda, Hiroko
AU  - Tsunoda H
AD  - Department of Radiology, St. Luke's International Hospital, 9-1, Akashi-Cho, 
      Chuo-Ku, Tokyo, Tokyo, 104-8560, Japan.
FAU - Ueda, Takuya
AU  - Ueda T
AUID- ORCID: 0000-0002-0913-5791
AD  - Department of Clinical Imaging, Tohoku University Graduate School of Medicine, 
      2-1 Seiryo-Machi, Aoba-Ku, Sendai, Miyagi, 980-8575, Japan. 
      takuya.ueda.d3@tohoku.ac.jp.
AD  - AI Lab, Tohoku University Hospital, 1-1 Seiryo-Machi, Aoba-Ku, Sendai, Miyagi, 
      980-8574, Japan. takuya.ueda.d3@tohoku.ac.jp.
LA  - eng
GR  - JPMJCR15D1/Core Research for Evolutional Science and Technology/
PT  - Journal Article
DEP - 20221107
PL  - Japan
TA  - Radiol Phys Technol
JT  - Radiological physics and technology
JID - 101467995
SB  - IM
MH  - Humans
MH  - Female
MH  - *Breast Neoplasms/diagnostic imaging
MH  - *Deep Learning
MH  - Retrospective Studies
MH  - Mammography/methods
MH  - Breast/diagnostic imaging
OTO - NOTNLM
OT  - Artificial intelligence
OT  - Breast cancer
OT  - Deep learning
OT  - Digital breast tomosynthesis
OT  - Mammography
EDAT- 2022/11/08 06:00
MHDA- 2023/03/03 06:00
CRDT- 2022/11/07 11:19
PHST- 2022/06/06 00:00 [received]
PHST- 2022/10/25 00:00 [accepted]
PHST- 2022/10/23 00:00 [revised]
PHST- 2022/11/08 06:00 [pubmed]
PHST- 2023/03/03 06:00 [medline]
PHST- 2022/11/07 11:19 [entrez]
AID - 10.1007/s12194-022-00686-y [pii]
AID - 10.1007/s12194-022-00686-y [doi]
PST - ppublish
SO  - Radiol Phys Technol. 2023 Mar;16(1):20-27. doi: 10.1007/s12194-022-00686-y. Epub 
      2022 Nov 7.