후두내시경 영상에서의 라디오믹스에 의한 병변 분류 연구Research on the Lesion Classification by Radiomics in Laryngoscopy Image
- Other Titles
- Research on the Lesion Classification by Radiomics in Laryngoscopy Image
- Authors
- 박준하; 김영재; 우주현; 김광기
- Issue Date
- Oct-2022
- Publisher
- 대한의용생체공학회
- Keywords
- Radiomics; Machine learning; Laryngoscopy; Laryngeal disease; Quantitative
- Citation
- 의공학회지, v.43, no.5, pp.353 - 360
- Journal Title
- 의공학회지
- Volume
- 43
- Number
- 5
- Start Page
- 353
- End Page
- 360
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/86044
- ISSN
- 1229-0807
- Abstract
- Laryngeal disease harms quality of life, and laryngoscopy is critical in identifying causative lesions. This study extracts and analyzes using radiomics quantitative features from the lesion in laryngoscopy images and will fit and validate a classifier for finding meaningful features. Searching the region of interest for lesions not classified by the YOLOv5 model, features are extracted with radionics. Selected the extracted features are through a com- bination of three feature selectors, and three estimator models. Through the selected features, trained and verified two classification models, Random Forest and Gradient Boosting, and found meaningful features. The combination of SFS, LASSO, and RF shows the highest performance with an accuracy of 0.90 and AUROC 0.96. Model using fea- tures to select by SFM, or RIDGE was low lower performance than other things. Classification of larynx lesions through radiomics looks effective. But it should use various feature selection methods and minimize data loss as los- ing color data.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 의과대학 > 의학과 > 1. Journal Articles
- 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/86044)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.