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
- 학술저널
- 저자정보
- 발행연도
- 2024.11
- 수록면
- 1,268 - 1,288 (21page)
- DOI
- 10.9717/kmms.2024.27.11.1268
이용수
초록· 키워드
오류제보하기
Today, the appropriate utilization of colors in histopathology tissue images is a major research area in the fields of medical imaging and digital pathology, particularly when cancerous tissues are examined.
This research intends to concentrate on experiments and analyzes the different color/stain normalization methods including histogram equalization, Reinhard, Macenko, Zheng, Gray world, and Vahadane that may impact and enhance the accuracy of computer-aided cancer diagnosis. The study additionally experi- ments with several pre- and post-processing steps with normalization approaches that aid the enhance- ment of image quality. In this study, 300 cancerous histopathology tissue images (256 × 256 pixels) were selected from different datasets on prostate, breast, and colon cancer. To allow quantitative comparison of the various approaches, several statistical measures were computed, including the Bhattacharyya dis- tance, mean square error (MSE), structural similarity index metric (SSIM), standard deviation (SD) and coefficient of variation (CV) of the normalized median intensity (NMI), and the weighted sum. The Reinhard method was the most effective for all three datasets in combination with bilateral filter, CLAHE, and gamma correction. The ultimate objective is to find out the best-fitted normalization method and suitable pre-and post-processing methods for three types of cancer datasets. Our comparative research study will greatly aid the future development of new strategies in the fields of digital pathology and medical imaging.
This research intends to concentrate on experiments and analyzes the different color/stain normalization methods including histogram equalization, Reinhard, Macenko, Zheng, Gray world, and Vahadane that may impact and enhance the accuracy of computer-aided cancer diagnosis. The study additionally experi- ments with several pre- and post-processing steps with normalization approaches that aid the enhance- ment of image quality. In this study, 300 cancerous histopathology tissue images (256 × 256 pixels) were selected from different datasets on prostate, breast, and colon cancer. To allow quantitative comparison of the various approaches, several statistical measures were computed, including the Bhattacharyya dis- tance, mean square error (MSE), structural similarity index metric (SSIM), standard deviation (SD) and coefficient of variation (CV) of the normalized median intensity (NMI), and the weighted sum. The Reinhard method was the most effective for all three datasets in combination with bilateral filter, CLAHE, and gamma correction. The ultimate objective is to find out the best-fitted normalization method and suitable pre-and post-processing methods for three types of cancer datasets. Our comparative research study will greatly aid the future development of new strategies in the fields of digital pathology and medical imaging.
목차
ABSTRACT
1. INTRODUCTION
2. RELATED WORKS
3. MATERIALS AND METHODS
4. RESULT AND DISCUSSION
5. CONCLUSION
REFERENCE
참고문헌 (51)
참고문헌 신청
M.Z. Hoque, A. Keskinarkaus, P. Nyberg, and T. Seppänen “Stain Normalization Methods for Histopathology Image Analysis: A Comprehensive Review and Experimental Comparison,” Information Fusion, Vol. 102, No. C, pp. 1-22, 2023.
F. Ghaznavi, A. Evans, A. Madabhushi, and M. Feldman, “Digital Imaging in Pathology: Whole-Slide Imaging and Beyond,” Annual Review of Pathology: Mechanisms of Disease, Vol. 8, No. 1, pp. 331-359, 2013.
M.Z. Hoque, A. Keskinarkaus, P. Nyberg, and T. Seppänen, “Retinex Model Based Stain Normalization Technique for Whole Slide Image Analysis,” Computerized Medical Imaging and Graphics, Vol. 90, 101901, 2021.
S.A.‐Janabi, A. Huisman, and P.J. Van Diest, “Digital Pathology: Current Status and Future Perspectives,” Histopathology, Vol. 61, No. 1, pp. 1–9, 2012.
Y. Zheng, Z. Jiang, H. Zhang, F. Xie, J. Shi, and C. Xue, “Adaptive Color Deconvolution for Histological WSI Normalization,” Computer Methods and Programs in Biomedicine, Vol. 170, pp. 107-120, 2019.
F. Ghaznavi, A. Evans, A. Madabhushi, and M. Feldman, “Digital Imaging in Pathology: Whole-Slide Imaging and Beyond,” Annual Review of Pathology: Mechanisms of Disease, Vol. 8, No. 1, pp. 331-359, 2013.
M.Z. Hoque, A. Keskinarkaus, P. Nyberg, and T. Seppänen, “Retinex Model Based Stain Normalization Technique for Whole Slide Image Analysis,” Computerized Medical Imaging and Graphics, Vol. 90, 101901, 2021.
S.A.‐Janabi, A. Huisman, and P.J. Van Diest, “Digital Pathology: Current Status and Future Perspectives,” Histopathology, Vol. 61, No. 1, pp. 1–9, 2012.
Y. Zheng, Z. Jiang, H. Zhang, F. Xie, J. Shi, and C. Xue, “Adaptive Color Deconvolution for Histological WSI Normalization,” Computer Methods and Programs in Biomedicine, Vol. 170, pp. 107-120, 2019.
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Stain Normalization을 활용한 현업 적용 현미경 세포 양성 예측 모델
한국정보과학회 학술발표논문집
2024 .06
-
LED 열화 데이터에 대한 정규화 방법에 대한 연구
신뢰성응용연구
2018 .03
-
다양한 정규화 방법에 따른 평일 단기 전력수요예측 정확도 분석
조명·전기설비학회논문지
2018 .06
-
초분광 영상의 조명 불변성을 위한 분광 정규화 기법 비교 분석
제어로봇시스템학회 국내학술대회 논문집
2015 .05
-
Super-resolution in Music Score Images by Instance Normalization
스마트미디어저널
2019 .01
-
주기 일관성 생성 적대적 네트워크를 사용한 조직병리 슬라이드 이미지의 색상 정규화
한국정밀공학회 학술발표대회 논문집
2022 .05
-
Single batch training 환경에서 normalization 방식에 따른 성능 비교
대한전자공학회 학술대회
2023 .06
-
Ensemble Normalization for Stable Training
한국통신학회 학술대회논문집
2020 .02
-
MNIST 데이터셋 상에서 Batch Normalization을 사용한 정확도 분석에 관한 연구
한국통신학회 인공지능 학술대회 논문집
2023 .09
-
Magnetic Resonance Brain Image Contrast Enhancement Using Histogram Equalization Techniques
한국컴퓨터정보학회 학술발표논문집
2019 .01
-
Local-Based Iterative Histogram Matching for Relative Radiometric Normalization
한국측량학회지
2019 .10
-
다양한 이미지 향상 기법을 사용한 전립선 병리영상 딥러닝 이진 분류 연구
멀티미디어학회논문지
2020 .04
-
광학 밀도 기반 이미지 정규화를 이용한 장기간 부식 시편 이미지 분석
한국표면공학회지
2024 .12
-
AI-based Multi Stain Cardiac Image Segmentation Using U-Net-Based Architecture with EfficientNetB3
한국정보통신학회 종합학술대회 논문집
2024 .10
-
강인한 음성인식을 위한 극점 필터링 및 스케일 정규화를 이용한 켑스트럼 특징 정규화 방식
한국음향학회지
2015 .01
-
Comparative Study of Compressive Sensing Approach in T1, T2, and Proton Density-based MRI Images
IEIE Transactions on Smart Processing & Computing
2021 .06
-
Tumor Detection in Breast Histopathology Images via modified Faster-RCNN
제어로봇시스템학회 국내학술대회 논문집
2021 .06
-
Adaptive Layer-Instance Normalization 기법을 활용한 Few-shot 비지도 방식 이미지 변환
한국통신학회 학술대회논문집
2019 .11
-
선명도에 따른 조직 이미지 분류: 딥러닝 모델과 이미지 품질 측정 기법의 성능 비교
대한전자공학회 학술대회
2024 .06
-
MNIST 데이터셋에 Batch Normalization을 적용한 CNN의 정확도 향상에 관한 연구
한국통신학회 인공지능 학술대회 논문집
2024 .09
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-151-25-02-091188303