All You Need Is a Few Dots to Label CT Images for Organ Segmentationopen access
- Authors
- Ju, Mingeon; Lee, Moonhyun; Lee, Jaeyoung; Yang, Jaewoo; Yoon, Seunghan; Kim, Younghoon
- Issue Date
- Feb-2022
- Publisher
- MDPI
- Keywords
- medical image segmentation; CT image segmentation; deep learning; kernel density; semi-automated labeling tool
- Citation
- Applied Sciences-basel, v.12, no.3, pp 1 - 13
- Pages
- 13
- Indexed
- SCIE
SCOPUS
- Journal Title
- Applied Sciences-basel
- Volume
- 12
- Number
- 3
- Start Page
- 1
- End Page
- 13
- URI
- https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/107964
- DOI
- 10.3390/app12031328
- ISSN
- 2076-3417
- Abstract
- Image segmentation is used to analyze medical images quantitatively for diagnosis and treatment planning. Since manual segmentation requires considerable time and effort from experts, research to automatically perform segmentation is in progress. Recent studies using deep learning have improved performance but need many labeled data. Although there are public datasets for research, manual labeling is required in an area where labeling is not performed to train a model. We propose a deep-learning-based tool that can easily create training data to alleviate this inconvenience. The proposed tool receives a CT image and the pixels of organs the user wants to segment as inputs and extract the features of the CT image using a deep learning network. Then, pixels that have similar features are classified to the identical organ. The advantage of the proposed tool is that it can be trained with a small number of labeled data. After training with 25 labeled CT images, our tool shows competitive results when it is compared to the state-of-the-art segmentation algorithms, such as UNet and DeepNetV3.
- Files in This Item
-
Go to Link
- Appears in
Collections - COLLEGE OF COMPUTING > DEPARTMENT OF ARTIFICIAL INTELLIGENCE > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/107964)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.