EUVIMEDEUVIMED entdecken
Crossref

Weakly supervised breast lesion detection in DCE‐MRI using self‐transfer learning

Rong Sun, Xiaobing Zhang, Yuanzhong Xie, Shengdong Nie

Medical Physics · 2023-08 · 50 (8) · 4960-4972

DOI: 10.1002/mp.16296 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, 2023-03. Verfasst von Rong Sun und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China. Hauptthemen laut MEDLINE: Breast Neoplasms. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shanghai Science and Technology Support Project, Natural Science Foundation of Shanghai.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Breast cancer is a typically diagnosed and life‐threatening cancer in women. Thus, dynamic contrast‐enhanced magnetic resonance imaging (DCE‐MRI) is increasingly used for breast lesion detection and diagnosis because of the high resolution of soft tissues. Moreover, supervised detection methods have been implemented for breast lesion detection. However, these methods require substantial time and specialized staff to develop the labeled training samples.

Purpose

To investigate the potential of weakly supervised deep learning models for breast lesion detection.

Methods

A total of 1003 breast DCE‐MRI studies were collected, including 603 abnormal cases with 770 breast lesions and 400 normal subjects. The proposed model was trained using breast DCE‐MRI considering only the image‐level labels (normal and abnormal) and optimized for classification and detection sub‐tasks simultaneously. Ablation experiments were performed to evaluate different convolutional neural network (CNN) backbones (VGG19 and ResNet50) as shared convolutional layers, as well as to evaluate the effect of the preprocessing methods.

Results

Our weakly supervised model performed better with VGG19 than with ResNet50 ( p < 0.05). The average precision (AP) of the classification sub‐task was 91.7% for abnormal cases and 88.0% for normal samples. The area under the receiver operating characteristic (ROC) curve (AUC) was 0.939 (95% confidence interval [CI]: 0.920–0.941). The weakly supervised detection task AP was 85.7%, and the correct location (CorLoc) was 90.2%. A sensitivity of 84.0% at two‐false positives per image was assessed based on free‐response ROC (FROC) curve.

Conclusions

The results confirm that a weakly supervised CNN based on self‐transfer learning is an effective and promising auxiliary tool for detecting breast lesions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsHumansFemaleBreastMagnetic Resonance ImagingNeural Networks, ComputerMachine Learning

Stichwörter der Autor:innen

DCE-MRIbreast tumorlesion detectionself-transfer learningweakly supervised learning

Autor:innen und Institutionen

  • School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China.
  • Department of Radiology, Ruijin Hospital Affiliated to Shanghai Jiaotong University School of Medicine, Shanghai, China.
  • Medical Imaging Center, Taian Center Hospital, Shandong, China.

Förderung

  • National Natural Science Foundation of China
  • Shanghai Science and Technology Support Project
  • Natural Science Foundation of Shanghai

Zitieren

APA

Sun, R., Zhang, X., Xie, Y., & Nie, S. (2023). Weakly supervised breast lesion detection in DCE‐MRI using self‐transfer learning. Medical Physics, 50(8), 4960-4972. https://doi.org/10.1002/mp.16296

Vancouver

Sun R, Zhang X, Xie Y, Nie S. Weakly supervised breast lesion detection in DCE‐MRI using self‐transfer learning. Medical Physics. 2023;50(8):4960-4972. doi:10.1002/mp.16296

BibTeX
@article{Sun2023,
  author = {Sun, Rong and Zhang, Xiaobing and Xie, Yuanzhong and Nie, Shengdong},
  title = {Weakly supervised breast lesion detection in DCE‐MRI using self‐transfer learning},
  journal = {Medical Physics},
  year = {2023},
  volume = {50},
  number = {8},
  pages = {4960--4972},
  doi = {10.1002/mp.16296}
}
Kostenlos starten →