Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

피부병변 영상 분할의 성능향상을 위한 VmCUnetVmCUnet for Improving the Performance of Skin lesion Image Segmentation

Other Titles
VmCUnet for Improving the Performance of Skin lesion Image Segmentation
Authors
김홍진이태희황우성최명렬
Issue Date
Sep-2024
Publisher
한국전기전자학회
Keywords
CNN; U-net; Medical Image Segmentation; Vmamba; VM-Unet; VM-UnetV2
Citation
전기전자학회논문지, v.28, no.3, pp 405 - 411
Pages
7
Indexed
KCI
Journal Title
전기전자학회논문지
Volume
28
Number
3
Start Page
405
End Page
411
URI
https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/121307
DOI
10.7471/ikeee.2024.28.3.405
ISSN
1226-7244
2288-243X
Abstract
본 논문에서는 피부병변 영상에서 이미지 분할 성능을 향상시키기 위해 설계된 딥러닝 모델인 VmCUnet을 제안한다. VmCUnet은 Vm-UnetV2와 CIM(Cross-Scale Interaction Module)을 결합하여 인코더의 각 계층에서 추출한 특징들을 CIM으로 통합하여다양한 패턴과 경계를 정확하게 인식할 수 있다. VmCUnet은 ISIC-2017와 ISIC-2018 데이터 세트를 사용하여 피부 병변의 이미지 분할을 수행하였고 Unet, TransUnet, SwinUnet Vm-Unet, Vm-UnetV2와 비교하여 성능 지표인 IoU, Dice Score에서 더높은 성능을 보였다. 향후 작업에서는 다양한 의료 영상 데이터 세트에 대한 추가 실험을 수행하여 VmCUnet 모델의 일반화 성능을 검증할 예정이다
In this paper, we have proposed VmCUnet, a deep learning model designed to enhance image segmentationperformance in skin lesion image. VmCUnet has combined Vm-UnetV2 with the CIM(Cross-Scale InteractionModule), and the features extracted from each layer of the encoder have been integrated through CIM toaccurately recognize the boundaries of various patterns and objects. VmCUnet has performed image segmentationof skin lesions using ISIC-2017 and ISIC-2018 datasets and has outperformed Unet, TransUnet, SwinUnet,Vm-Unet, and Vm-UnetV2 on the performance metrics IoU and Dice Score. In future work, we will conductadditional experiments on different medical imaging datasets to validate the generalization performance of theVmCUnet model
Files in This Item
Go to Link
Appears in
Collections
COLLEGE OF ENGINEERING SCIENCES > SCHOOL OF ELECTRICAL ENGINEERING > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher CHOI, MYUNG RYUL photo

CHOI, MYUNG RYUL
ERICA 공학대학 (SCHOOL OF ELECTRICAL ENGINEERING)
Read more

Altmetrics

Total Views & Downloads

BROWSE