지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술대회자료
- 저자정보
- 발행연도
- 2024.10
- 수록면
- 71 - 74 (4page)
이용수
초록· 키워드
오류제보하기
Early-stage analysis of various heart diseases can be facilitated by the efficient segmentation and quantification of color variance presence in cardiac histopathology images. This research focuses on examining 4 histopathological whole-slide cardiac images stained with two methods: Masson’s Trichrome (MT) and Sirius Red. K-means clustering algorithms were utilized to segment the tissue components based on the color variances and characteristics of different types of fibrosis present in the images. However, directly applying the K-means clustering algorithm to cardiac image segmentation presents challenges due to the anatomical complexity of heart tissue images. To address this, we utilized morphological methods to refine the shifting of mean thresholds and reduce complexity in post-processing segmented cardiac images. Following the separation and annotation of tissue components, ground truth patches (128×128 pixels) from the three types of fibrosis region (Ischemic, Interstitial, and Replacement), and patches (128×128 pixels) from the original whole slide image (WSIs) are extracted for each stain, preparing them for U-Net-based segmentation. The U-Net architecture incorporates the EfficientNetB3’s encoder path as its backbone to optimize image depth, width, and size. A comprehensive evaluation of accuracy, Dice coefficient (DC), and Jaccard coefficient (JC) analyses is conducted to assess the effectiveness of the models. This study aims to aid pathologists in cardiac disease analysis by providing accurate fibrosis assessment and contributing to advancing future AI-driven segmentation algorithms in digital pathology and medical imaging.
목차
ABSTRACT
Ⅰ. Introduction
Ⅱ. Literature Review
Ⅲ. Materials and Method
Ⅳ. Experimental Results
Ⅴ. Conclusion
References
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Adaptive Image Segmentation Based on Histogram Transition Zone Analysis
INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGENT SYSTEMS
2016 .12
-
영상 분할을 이용한 영상 전송 시스템에 대한 연구
반도체디스플레이기술학회지
2016 .01
-
Simulation of Filter Application for Segmentation of Medical Images
INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING
2018 .06
-
A cux on Transformer-based U-NET models for Medical Image Segmentation
대한전자공학회 학술대회
2024 .06
-
Temporal Difference-based Weighted Instance Segmentation Applied on Consecutive Images for Food Recognition
제어로봇시스템학회 논문지
2023 .12
-
U-Net을 이용한 이미지 내 부식 시편 분할에 관한 연구
한국표면공학회지
2024 .12
-
향상된 세일리언시 맵과 슈퍼픽셀 기반의 효과적인 영상 분할
멀티미디어학회논문지
2016 .07
-
Multi-Level Segmentation of Infrared Images with Region of Interest Extraction
INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGENT SYSTEMS
2016 .12
-
의료 영상 분할을 위한 딥러닝 방법 간의 성능 평가
대한전자공학회 학술대회
2021 .06
-
A Method for Tree Image Segmentation Combined Adaptive Mean Shifting with Image Abstraction
JIPS(Journal of Information Processing Systems)
2020 .01
-
RDIU-Net: Lightweight Medical Image Segmentation Network
제어로봇시스템학회 국제학술대회 논문집
2023 .10
-
딥러닝 성능 향상을 위한 3D 의료 영상 증강법
한국CDE학회 논문집
2021 .06
-
Development of Heart Model Using Cardiac MR Imaging
대한전자공학회 학술대회
2022 .04
-
Multi-Level Transformer-based Segmentation Network for Abnormal Tissue Segmentation in Medical Image
한국정보과학회 학술발표논문집
2021 .06
-
3D UNet-Based Multi-Organ Segmentation of Chest CT Images for Cardiac Digital Twin Model
정보 및 제어 논문집
2024 .10
-
Image Segmentation Method를 활용한 콘크리트-에폭시 파괴면의 정량적 분석
대한토목학회 학술대회
2023 .10
-
Development of HCS Image Algorithm for Cell Segmentation
한국정밀공학회 학술발표대회 논문집
2015 .05
-
정밀 인체 3차원 모델 구현을 위한 Anatomical 3D Segmentation 기술
대한기계학회 춘추학술대회
2022 .04
-
딥러닝기반 Image Segmentation 모델을 이용한 포장표면 균열 검출 방법 연구
대한전자공학회 학술대회
2022 .06
-
주행 이미지의 왜곡에 따른 Semantic segmentation 변화
제어로봇시스템학회 국내학술대회 논문집
2020 .07
이 논문과 함께 이용한 논문
최근 본 자료
댓글(0)
0