DEXA에서 딥러닝 기반의 척골 및 요골 자동 분할 모델Automated Ulna and Radius Segmentation model based on Deep Learning on DEXA
- Other Titles
- Automated Ulna and Radius Segmentation model based on Deep Learning on DEXA
- Authors
- 김영재; 박성진; 김경래; 김광기
- Issue Date
- Dec-2018
- Publisher
- 한국멀티미디어학회
- Keywords
- DEXA; Deep Learning; Convolutional Neural Network; U-Net; Segmentation
- Citation
- 멀티미디어학회논문지, v.21, no.12, pp.1407 - 1416
- Journal Title
- 멀티미디어학회논문지
- Volume
- 21
- Number
- 12
- Start Page
- 1407
- End Page
- 1416
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/4584
- DOI
- 10.9717/kmms.2018.21.12.1407
- ISSN
- 1229-7771
- Abstract
- The purpose of this study was to train a model for the ulna and radius bone segmentation based on Convolutional Neural Networks and to verify the segmentation model. The data consisted of 840 training data, 210 tuning data, and 200 verification data. The learningmodel for the ulna and radius bone bwas based on U-Net (19 convolutional and 8 maximum pooling) and trained with 8 batch sizes, 0.0001 learning rate, and 200 epochs. As a result, the average sensitivity of the training data was 0.998, the specificity was 0.972, the accuracy was 0.979, and the Dice’s similarity coefficient was 0.968. In the validation data, the average sensitivity was 0.961, specificity was 0.978, accuracy was 0.972, and Dice’s similarity coefficient was 0.961. The performance of deep convolutional neural network based models for the segmentation was good for ulna and radius bone.
- 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/4584)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.