Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{179802,
        author = {P Gopinathan  M.E., and V Sundhararaj  M.E., and S Vinoth Kumar  M.E., and S Ravichandran and R Dhanasekaran and G Yugan},
        title = {Automated Retinal Multi-Disease Detection with Explainability using Raspberry Pi},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {8216-8220},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179802},
        abstract = {Organized illnesses such as diabetic retinopathy, glaucoma and age-related macular degeneration are one of the world's driving but avoidable causes of visual disability. Early location and conclusion are greatly critical, particularly in regions with lacking administrations where get to uncommon eye care isn't limited. This extend presents an inventive, reasonable and versatile framework for auto-detecting a few retinal conditions. It is worked by a profound learning show utilizing the Raspberry PI5. The framework employments collapsing systems (CNNs) prepared with freely accessible save finance picture information records to appropriately recognize different network-like add up to active activity natures. To extend the interpretability and unwavering quality of the comes about, the gadget coordinating informative AI strategies such as actuation task (GRAD-CAM) and locally interpretable demonstrate tag portrayals (LIME). These devices contribute to demonstrate choices, back both wellbeing proficient individuals and conclusion clients, and offer assistance get it the results. This compact gadget forms fundus pictures in close genuine time, appearing      both symptomatic comes about and visual depiction cards on a 3.5-inch show. The framework illustrates solid exactness and commonsense execution, making it perfect for utilize in wellbeing programs, mobile-Aiden Camps, and clinics with constrained framework. By filling the hole between AI advance and down to earth utilize, this approach underpins early conclusion and progresses understanding care results.},
        keywords = {Retinal malady detainment, raspberry-PI, profound learning, CNN, therapeutic picture investigation, logical AI, Grad-CAM, LIME, diabetic retinopathy, glaucoma,},
        month = {May},
        }