A Deep Learning-Based Segmentation Technique for Automatic Detection of Conjunctivitis from Conjunctival Eye Images
Madhusudhan S1, Anitha S2
1Prof. Madhusudhan S, Assistant Professor, Department of Electronics and Communication Engineering, Amruta Institute of Engineering and Management Sciences, Bidadi, Bengaluru, Visvesvaraya Technological University, Belagavi (Karnataka), India.
2Dr. Anitha S, Professor, Department of Bio-Medical Engineering, Research Centre: ACS College of Engineering, Bengaluru, Visvesvaraya Technological University, Belagavi (Karnataka), India.
Manuscript received on 02 April 2026 | Revised Manuscript received on 09 April 2026 | Manuscript Accepted on 15 April 2026 | Manuscript published on 30 April 2026 | PP: 18-21 | Volume-15 Issue-5, April 2026 | Retrieval Number: 100.1/ijitee.E125515060526 | DOI: 10.35940/ijitee.E1255.15050426
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Eye diseases are becoming common in day-to-day life and affecting all age groups of people. The ratio of ophthalmologists to patients suggests the need for an automated technique to detect eye diseases. Conjunctivitis is of many types, including adenoviral conjunctivitis, ocular drug toxic conjunctivitis, pollen-allergic conjunctivitis, bacterial conjunctivitis, and many others. Conjunctivitis can be automatically detected using conventional image processing techniques, but with lower accuracy and precision, and more computational time is required compared to deep learning and AI techniques. This paper presents a novel deep-learning-assisted segmentation technique for the automatic detection of conjunctivitis that overcomes the limitations of conventional methods. The proposed method uses Attention-U-Net++ with Transformer Encoder (Global Context), Swin / ViT CNN +, Transformer Monte-Carlo Dropout Layer Enabled at inference time, Uncertainty-aware and Segmentation Mask + Uncertainty Map, which provides better results with Accuracy= 90.3%, sensitivity= 0.87, specificity= 0.93, precision=0.88, recall=0.87, F1-Score= 0.89, ROC-Auc=0.96.
Keywords: Pollen Allergic Conjunctivitis, Ocular Drug Toxicity, U-Net++, swin/ViT, CNN, ROC
Scope of the Article: Biomedical Engineering