Detection and Weak Segmentation of Masses in Gray-Scale Breast Mammogram Images Using Deep Learning
- Authors
- 김영재; 김광기
- Issue Date
- Jan-2022
- Publisher
- 연세대학교의과대학
- Keywords
- Breast mammogram; detection lesion of mass; deep learning; convolutional neural network; data normalization
- Citation
- Yonsei Medical Journal, v.63, pp.63 - 73
- Journal Title
- Yonsei Medical Journal
- Volume
- 63
- Start Page
- 63
- End Page
- 73
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/83587
- DOI
- 10.3349/ymj.2022.63.S63
- ISSN
- 0513-5796
- Abstract
- Purpose: In this paper, we propose deep-learning methodology with which to enhance the mass differentiation performance of convolutional neural network (CNN)-based architecture.
Materials and Methods: We differentiated breast mass lesions from gray-scale X-ray mammography images based on regions of interest (ROIs). Our dataset comprised breast mammogram images for 150 cases of malignant masses from which we extracted the mass ROI, and we composed a CNN-based deep learning model trained on this dataset to identify ROI mass lesions. The test dataset was created by shifting some of the training data images. Thus, although both datasets were different, they retained a deep structural similarity. We then applied our trained deep-learning model to detect masses on 8-bit mammogram images containing malignant masses. The input images were preprocessed by applying a scaling parameter of intensity before being used to train the CNN model for mass differentiation.
Results: The highest area under the receiver operating characteristic curve was 0.897 (Î 20).
Conclusion: Our results indicated that the proposed patch-wise detection method can be utilized as a mass detection and segmentation tool.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 보건과학대학 > 의용생체공학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/83587)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.