Weakly Supervised Breast Lesion Detection in Dynamic Contrast-Enhanced MRI
- 30 May 2023
- journal article
- research article
- Published by Springer Nature in Journal of Digital Imaging
- Vol. 36 (4) , 1553-1564
Abstract
Currently, obtaining accurate medical annotations requires high labor and time effort, which largely limits the development of supervised learning-based tumor detection tasks. In this work, we investigated a weakly supervised learning model for detecting breast lesions in dynamic contrast-enhanced MRI (DCE-MRI) with only image-level labels. Two hundred fifty-four normal and 398 abnormal cases with pathologically confirmed lesions were retrospectively enrolled into the breast dataset, which was divided into the training set (80%), validation set (10%), and testing set (10%) at the patient level. First, the second image series S2 after the injection of a contrast agent was acquired from the 3.0-T, T1-weighted dynamic enhanced MR imaging sequences. Second, a feature pyramid network (FPN) with convolutional block attention module (CBAM) was proposed to extract multi-scale feature maps of the modified classification network VGG16. Then, initial location information was obtained from the heatmaps generated using the layer class activation mapping algorithm (Layer-CAM). Finally, the detection results of breast lesion were refined by the conditional random field (CRF). Accuracy, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC) were utilized for evaluation of image-level classification. Average precision (AP) was estimated for breast lesion localization. Delong's test was used to compare the AUCs of different models for significance. The proposed model was effective with accuracy of 95.2%, sensitivity of 91.6%, specificity of 99.2%, and AUC of 0.986. The AP for breast lesion detection was 84.1% using weakly supervised learning. Weakly supervised learning based on FPN combined with Layer-CAM facilitated automatic detection of breast lesion.Keywords
Funding Information
- National Natural Science Foundation of China (81830052)
- Science and Technology Innovation Plan Of Shanghai Science and Technology Commission (18441900500)
- Natural Science Foundation of Shanghai Municipality (20ZR1438300)
- Shanghai Key Laboratory of Molecular Imaging (18DZ2260400)
This publication has 38 references indexed in Scilit:
- An Investigation of Deep Learning for Lesions Malignancy Classification in Breast DCE-MRI2017
- Hybrid Mass Detection in Breast MRI Combining Unsupervised Saliency Analysis and Deep Learning2017
- Feature Pyramid Networks for Object Detection2017
- MR Imaging Radiomics Signatures for Predicting the Risk of Breast Cancer Recurrence as Given by Research Versions of MammaPrint, Oncotype DX, and PAM50 Gene AssaysRadiology, 2016
- Self-Transfer Learning for Weakly Supervised Lesion Localization2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Learning Deep Features for Discriminative Localization2016
- Automated detection of breast tumor in MRI and comparison of kinetic features for assessing tumor response to chemotherapy2015
- Performance of a fully automatic lesion detection system for breast DCE‐MRIJournal of Magnetic Resonance Imaging, 2011
- Receiver Operating Characteristic Curves and Their Use in RadiologyRadiology, 2003