딥러닝과 의미론적 분할 기법을 이용한 각막궤양 영역 검출
Corneal Ulcer Region Detection With Semantic Segmentation Using Deep Learning
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
안과 환자의 질병을 판단하기 위해서는 특수 촬영 장비를 통해 찍은 안구영상을 이용한 안과의사의주관적 판단의 개입이 전통적으로 활용되고 있다. 본 연구에서는 안과 의료진이 질병을 판단할 때보조적 도움이 될 수 있도록 객관적 진단결과를 제시해주는 각막궤양 의미론적 분할방법에 대하여제안하였다. 이를 위해 DeepLab 모델을 활용하였고 그 중 Backbone network으로 Xception과 ResNet 네트워크를 이용하였다. 실험결과를 나타내기 위한 평가지표로 다이스 유사계수와 IoU 값을 이용하였고ResNet101 네트워크를 사용하였을 때 ‘crop & resized’ 이미지에 대해 최대 평균 정확도 93%의 다이스유사계수 값을 보였다. 본 연구는 객체 검출을 위한 의미론적 분할모델 또한 안구의 각막궤양 부분과같은 불규칙하고 특이한 모양을 추출하고 분류하는데 뛰어난 결과를 도출할 수 있는 성능을 보유하고있음을 보여주었다. 향후 학습용 Dataset을 양적으로 보강하여 실험결과의 정확도를 제고할 수 있도록하고 실제 의료진단 환경에서 구현되어 사용되어 질 수 있도록 할 계획이다.
Abstract
Traditional methods of measuring corneal ulcers were difficult to present objective basis for diagnosis because of the subjective judgment of the medical staff through photographs taken with special equipment. In this paper, we propose a method to detect the ulcer area on a pixel basis in corneal ulcer images using a semantic segmentation model. In order to solve this problem, we performed the experiment to detect the ulcer area based on the DeepLab model which has the highest performance in semantic segmentation model. For the experiment, the training and test data were selected and the backbone network of DeepLab model which set as Xception and ResNet, respectively were evaluated and compared the performances. We used Dice similarity coefficient and IoU value as an indicator to evaluate the performances. Experimental results show that when ‘crop & resized’ images are added to the dataset, it segment the ulcer area with an average accuracy about 93% of Dice similarity coefficient on the DeepLab model with ResNet101 as the backbone network. This study shows that the semantic segmentation model used for object detection also has an ability to make significant results when classifying objects with irregular shapes such as corneal ulcers. Ultimately, we will perform the extension of datasets and experiment with adaptive learning methods through future studies so that they can be implemented in real medical diagnosis environment.
참고문헌 (27)
- Y. Tsai, "Learning to adapt structured output space for semantic segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.7472~7481 (2018)
- Z. Wang, "Outline Objects using Deep Reinforcement Learning", ~ (2018)
- S. Zheng, "Conditional random fields as recurrent neural networks", Proceedings of the IEEE international conference on computer vision, pp.1529~1537 (2015)
- Y. Chu, "Adaptive Global Sliding-Mode Control for Dynamic Systems Using Double Hidden Layer Recurrent Neural Network Structure", IEEE Trans. on Neural Networks and Learning Systems, 31(4), pp.1297~1309 (2020)[DOI]
- V. Iglovikov, "Satellite imagery feature detection using deep convolutional neural network: A kaggle competition", ~ (2017)
- X. Du, "Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection", 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp.953~961 (2017)
- L. Tai, "Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation", IEEE, 2017, 31~36
- M. Teichmann, "Multinet: Real-time joint semantic reasoning for autonomous driving", 2018 IEEE Intelligent Vehicles Symposium (IV), pp.1013~1020 (2018)
- J. Long, "Fully Convolutional Networks for Semantic Segmentation", The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.3431~3440 (2015)
- D. Wang, "SSRNet: In-Field Counting Wheat Ears Using Multi-Stage Convolutional Neural Network", IEEE Trans. on Geoscience and Remote Sensing, 60, pp.1~11 (2022)[DOI]
- H. Noh, "Learning Deconvolution Network for Semantic Segmentation", The IEEE Conference on Computer Vision (ICCV), pp.1520~1528 (2015)
- C. Peng, "Cross Fusion Net: A Fast Semantic Segmentation Network for Small-Scale Semantic Information Capturing in Aerial Scenes", IEEE Trans. on Geoscience and Remote Sensing, 60, pp.1~13 (2022)[DOI]
- F. Yu, "Multi-Scale Context Aggregation By Dilated Convolutions", IEEE Trans. on Parallel and Distributed Systems, 16(3), pp.219~232 (2005)
- Y. -J. Ma, "Spatiotemporal Dilated Convolution With Uncertain Matching for Video-Based Crowd Estimation", IEEE Trans. on Multimedia, 24, pp.261~273 (2022)[DOI]
- H. Fu, "Retinal Vessel Segmentation via Deep Learning Network And Fully-connected Conditional Random Fields", 2016 IEEE 13th International Symposium on Biomedical Imaging(ISBI), pp.698~701 (2016)
- C. Chen, "Retinal Vessel Segmentation Using Deep Learning: A Review", IEEE Access, 9, pp.111985~112004 (2021)[DOI]
- H. Lee, "Pixel-level deep segmentation: artificial intelligence quantifies muscle on computed tomography for body morphometric analysis", Journal of digital imaging, 30(4), pp.487~498 (2017)
- Y. Yuan, "Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks With Jaccard Distance", IEEE Trans. on Medical Imaging, 36(9), pp.1876~1886 (2017)
- G. Wang, "Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning", IEEE Trans. on Medical Imaging, 37(7), pp.1562~1573 (2018)
- D. Lin, "ScribbleSup:Scribble-Supervised Convolutional Networks for Semantic Segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.3159~3167 (2016)
- N. A. T. Otoum, "Medical Iamge Processing : applications in ophthalmology and total hip replacement", pp.2012
- Y. Ma, "Structure and Illumination Constrained GAN for Medical Image Enhancement", IEEE Trans. on Medical Imaging, 40(12), pp.3955~3967 (2021)[DOI]
- T. F. Chen, "Active Contours Without Edges", IEEE Trans. on Image Processing, 10(2), pp.266~277 (2001)
- T. P. Patel, "Novel Image Based Analysis for Reduction of Clinician-Dependent Varability in Measurement of the Corneal Ulcer Size", Clinical Science, pp.331~339 (2018)
- Q. Sun, "Fetal, Infant and Ophthalmic Medical Image Analysis", pp.101~108 (2017), Springer, Cham
- L. Chen, "Semantic Image Segmentation With Deep Convolutional Nets and Fully Connected CRFs", ~ (2014)
- G. Lenczner, "DIAL: Deep Interactive and Active Learning for Semantic Segmentation in Remote Sensing", IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, pp.3376~3389 (2022)[DOI]