Eye Melanoma Diagnosis System using Statistical Texture Feature Extraction and Soft Computing Techniques

Abstract

Background: Eye melanoma is deforming in the eye, growing and developing in tissues inside the middle layer of an eyeball, resulting in dark spots in the iris section of the eye, changes in size, the shape of the pupil, and vision. Objective: The current study aims to diagnose eye melanoma using a gray level co-occurrence matrix (GLCM) for texture extraction and soft computing techniques, leading to the disease diagnosis faster, time-saving, and prevention of misdiagnosis resulting from the physician’s manual approach. Material and Methods: In this experimental study, two models are proposed for the diagnosis of eye melanoma, including backpropagation neural networks (BPNN) and radial basis functions network (RBFN). The images used for training and validating were obtained from the eye-cancer database. Results: Based on our experiments, our proposed models achieve 92.31% and 94.70% recognition rates for GLCM+BPNN and GLCM+RBFN, respectively. Conclusion: Based on the comparison of our models with the others, the models used in the current study outperform other proposed models.

Clinical Applications of Machine Learning in the Management of Intraocular Cancers: A Narrative Review

“…Methods to work around this issue include leveraging synthetic data enhancement with imaging data using techniques similar to those seen in Santos-Bustos et al. 28 and Olaniyi et al., 27 collaborating with ocular oncology centers of excellence that have large in-house data repositories, and adopting “low-shot” ML algorithms that can be trained with relatively small training datasets. 93 Regardless of sample size, the studies analyzed in this review demonstrated strong performance.…”

“…Other image-based diagnostic methods using CNN, artificial neural networks, and radial basis function networks have achieved similar results. 27 , 28 Although iris nevi are not cancerous, 8% can transform into melanoma over 15 years, 29 making proper diagnosis important. This study highlights the usefulness of CNNs in augmenting the confidence of visual diagnosis by ophthalmologists.…”