딥 러닝 기반의 악성흑색종 분류를 위한 컴퓨터 보조진단 알고리즘
A Computer Aided Diagnosis Algorithm for Classification of Malignant Melanoma based on Deep Learning
2
조회
0
다운로드
7
인용
0
참고문헌
키워드
초록
The malignant melanoma accounts for about 1 to 3% of the total malignant tumor in the West, especially in the US, it is a disease that causes more than 9,000 deaths each year. Generally, skin lesions are difficult to detect the features through photography. In this paper, we propose a computer-aided diagnosis algorithm based on deep learning for classification of malignant melanoma and benign skin tumor in RGB channel skin images. The proposed deep learning model configures the tumor lesion segmentation model and a classification model of malignant melanoma. First, U-Net was used to segment a skin lesion area in the dermoscopic image. We could implement algorithms to classify malignant melanoma and benign tumor using skin lesion image and results of expert’s labeling in ResNet. The U-Net model obtained a dice similarity coefficient of 83.45% compared with results of expert’s labeling. The classification accuracy of malignant melanoma obtained the 83.06%. As the result, it is expected that the proposed artificial intelligence algorithm will utilize as a computer-aided diagnosis algorithm and help to detect malignant melanoma at an early stage.
Abstract
The malignant melanoma accounts for about 1 to 3% of the total malignant tumor in the West, especially in the US, it is a disease that causes more than 9,000 deaths each year. Generally, skin lesions are difficult to detect the features through photography. In this paper, we propose a computer-aided diagnosis algorithm based on deep learning for classification of malignant melanoma and benign skin tumor in RGB channel skin images. The proposed deep learning model configures the tumor lesion segmentation model and a classification model of malignant melanoma. First, U-Net was used to segment a skin lesion area in the dermoscopic image. We could implement algorithms to classify malignant melanoma and benign tumor using skin lesion image and results of expert’s labeling in ResNet. The U-Net model obtained a dice similarity coefficient of 83.45% compared with results of expert’s labeling. The classification accuracy of malignant melanoma obtained the 83.06%. As the result, it is expected that the proposed artificial intelligence algorithm will utilize as a computer-aided diagnosis algorithm and help to detect malignant melanoma at an early stage.
참고문헌 (18)
- 송계용, "악성 흑색종의 임상 및 병리조직학적 고찰", 대한병리학회지, 124(6), pp.566~573 (1997)
- "ISIC Archive"[URL]
- Jerant, A. F., "Early detection and treatment of skin cancer", Am Fam Physician, 62(2), pp.357~368 (2000)
- Yuexuang, L., "Skin Lesion Analysis Towards Melanoma Detection Using Deep Learning Network", Sensors, 18(2), pp.1~4 (2017)
- Wiebke, S., "Initial misdiagnosis of melanoma located on the foot is associated with poorer prognosis", Medicine, 95(29), pp.4332~ (2016)
- Krige, J. E. J., "Delay in the diagnosis of cutaneous malignant melanoma, A prospective study in 250 patients", Cancer, 68(9), pp.2064~2072 (1991)
- Metzger, S., "Extent and consequences of physician delay in the diagnosis of acral melanoma", Melanoma research, 8(2), pp.181~186 (1998)
- Grin, C. M., "Dermoscopy: a review", Dermatologic clinics, pp.641~646 (2002)
- 조영석, "IOT를 이용한 DB기반 농작물 자동재배에 관한 연구", (사)디지털산업정보학회 논문지, 13(4), pp.25~31 (2017), (사)디지털산업정보학회[DOI]
- 문원식, "실시간 분산 시스템에서 heartbeat 시그널을 이용한 장애 검출", (사)디지털산업정보학회 논문지, 14(3), pp.39~44 (2018), (사)디지털산업정보학회[DOI]
- Rigel, Darrell S., "ABCDE—an evolving concept in the early detection of melanoma", Archives of dermatology, 141(8), pp.1032~1036 (2016)
- Yann, L., "Deep learning", nature, 521, pp.436~444 (2015)
- Kevin, P. M., "Machine Learning: A Probabilistic Perspective" (2012), MIT
- Alex, K, "Imagenet classification with deep convolutional neural networks", ACM, 60(6), pp.84~90 (2017)
- Olaf, R., "U-net: Convolutional networks for biomedical image segmentation", International Conference on Medical Image Computing and Computer- Assisted Intervention, pp.234~241 (2015)
- An overview of current evaluation methods used in medical image segmentation, "Yeghiazaryan, V.", Department of Computer Science, University of Oxford, ~, pp.Tech. Rep. CS-RR-15-08 (2015)
- Kaiming, H., "Deep residual learning for image recognition", Proceedings of the IEEE conference on computer vision and pattern recognition (2016)
- Kaiming, H., "Identity mappings in deep residual networks", European conference on computer vision (2016), Springer