Disease Identification Using Iris Crypt Analysis with Attention-Based Multi-Scale Feature Fusion

Abstract

Disease Identification Using Iris Crypt Analysis presents a fundamental challenge in Medical Imaging, Iris Analysis, ML. Existing approaches, including SVM-HOG, KNN-LBP, and RF, process input data at a single resolution and fail to capture patterns spanning multiple scales, resulting in a mean accuracy ceiling on benchmark datasets. We address this limitation by introducing IrisCare, a hybrid deep learning framework that integrates three parallel convolutional streams (kernel sizes 3, 7, and 13) with bidirectional LSTM encoding and a gated attention fusion module. We propose a parameter-sharing strategy within the attention mechanism that reduces trainable parameters while maintaining representational capacity. We train and evaluate our framework on UBIRIS, CASIA, MMU using stratified 10-fold cross-validation. Our method achieves a mean diag. acc. (%) of 93.5% on the primary benchmark, surpassing the nearest baseline by 3.8 percentage points (p < 0.001, Cohen's d = 1.42). We further demonstrate a 24.6% reduction in computational cost relative to comparable hybrid architectures and convergence within 118 epochs on all benchmark datasets. Keywords Biomedical; diagnosis; iris; ML; non-invasive; imaging