Baichen Liu
ABSTRACT
Pathologic myopia (PM) is a common retinal degenerative disease that carries the risk of blindness.In recent years, given the latest developments of Artificial Intelligence (AI) technology in the field of computer-aided disease diagnosis and treatment, multiple disease domains have begun to focus on applying this technology to disease diagnosis and treatment. However, only a few studies specifically target Pathological Myopia (PM). In this paper, based on pathologic myopia classification technology is studied. Based on the mainstream deep learning model EfficientNet, the PM classification model shuffle-efficientNet is established. First, the images from the Pathological Myopia dataset (PALM) are preprocessed, then enter them into the ShuffleBlock and MBConv layers for training, and then enter the training results into the full connection layer, calculate the loss function to obtain the prediction result. Finally, we compare this model with EfficientNet, EfficientNetV2, and other traditional models. The experimental result show that the accuracy of Shuffle-EfficientNet reaches 98.1%, slightly higher than EfficientNetV2 at 97.6%, indicating better classification performance.
- Kyoko Ohno-Matsui, Pei-Chang Wu.et al. IMI Pathologic Myopia. Invest. Ophthalmol. Vis. Sci. 2021;62(5)Ohno-Matsui K, Lai TY, Lai CC, Cheung CM. Updates of pathologic myopia. Prog Retin Eye Res. 2016; 52:156–187.Google Scholar
- Percival, S. Redefinition of high myopia: the relationship of axial length measurement to myopic pathology and its relevance to cataract surgery. Dev. ophthalmology 14, 42–46 (1987).Google ScholarCross Ref
- Orlando, J. I. Refuge challenge: A unified framework for evaluating automated methods for glaucoma assessment from fundus photographs. Med. image analysis 59, 101570 (2020).Google Scholar
- Sengupta, S., Singh, A., Leopold, H. A., Gulati, T. Lakshminarayanan, V. Ophthalmic diagnosis using deep learning with fundusGoogle Scholar
- images–a critical review. Artif. Intell. Medicine 102, 101758 (2020).Google ScholarDigital Library
- Hemelings, R. Pathological myopia classification with simultaneous lesion segmentation using deep learning. Comput. Methods Programs Biomed. 199, 105920 (2021).Google ScholarCross Ref
- Kittipat Sriwong, Kittisak Kerdprasop, Nittaya Kerdprasop. The Study of Noise Effect on CNN-Based Deep Learning from Medical Images[J]. International Journal of Machine Learning and Computing, 2021, 11(3)Google Scholar
- Du, R. Deep learning approach for automated detection of myopic maculopathy and pathologic myopia in fundus images. Ophthalmol. Retin. 5, 1235–1244 (2021)Google ScholarCross Ref
- Babaqi T, Jaradat M, Yildirim A E, Eye Disease Classification Using Deep Learning Techniques[J]. arXiv preprint arXiv:2307.10501, 2023.Google Scholar
- Jolly, Vedant, Eye Disease Detection using MobiNet. 2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS). IEEE, 2023.Google Scholar
- Rebolleda G, Diez-Alvarez L, Casado A, OCT: new perspectives in neuro-ophthalmology[J]. Saudi Journal of Ophthalmology, 2015, 29(1): 9-25.Google ScholarCross Ref
- Fang H, Li F, Wu J, PALM: Open Fundus Photograph Dataset with Pathologic Myopia Recognition and Anatomical Structure Annotation[J]. arXiv preprint arXiv:2305.07816, 2023.Google Scholar
- Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks [C.International conference on machine learning. PMLR, 2019: 6105-6114.Google Scholar
- Howard A, Sandler M, Chu G, Searching for mobilenetv3[C]. Proceedings of the IEEE/CVF international conference on computer vision. 2019: 1314-1324.Google Scholar
- Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.Google Scholar
- Tan M, Le Q. Efficientnetv2: Smaller models and faster training[C]. International conference on machine learning. PMLR, 2021: 10096-10106.Google Scholar
- Zhang X, Zhou X, Lin M, Shufflenet: An extremely efficient convolutional neural network for mobile devices[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 6848-6856.Google Scholar
- He K, Zhang X, Ren S, Deep residual learning for image recognition[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.Google Scholar
Index Terms
- Pathologic Myopia Classification based on Shuffle-EfficientNet Model
Recommendations
Deep-Learning-Based Early Detection of Diabetic Retinopathy on Fundus Photography Using EfficientNet
ICIAI '20: Proceedings of the 2020 the 4th International Conference on Innovation in Artificial IntelligenceDiabetic retinopathy, which is the leading cause of blindness among working aged adults, is a serious health problem worldwide. As millions of people suffer from diabetic retinopathy, the need for an automated method of diabetic retinopathy detection to ...
A real time cloud-based framework for glaucoma screening using EfficientNet
AbstractThese days one of the major causes of partial or complete blindness that has affected a majority of people all around the world is glaucoma. Glaucoma is caused as a result of increased fluid pressure inside the optic nerves called intra ocular ...
A robust framework for glaucoma detection using CLAHE and EfficientNet
AbstractGlaucoma disease is affecting a large community worldwide. It gradually affects the optic nerve and may cause partial or complete vision loss. Glaucoma happens due to an increase in the fluid pressure inside the optic nerve, which is also known as ...
Comments