Interactive Joint Feature Extraction for Diabetic Retinopathy Classification using Multiple Instance Neural Symbolic Learning

May 2025
Vol-11, Issue-3
Paper ID: 26500
ISSN: 2395-4396
Downloads: 56
Download PDF

Abstract & Details

Research Area
Sri Venkatesa Perumal College of Engineering & Technology
Keywords
Diabetic retinopathy retinal fundus images multi-class classification deep learning weighted average ensemble.
Abstract
In recent years deep learning (DL) techniques have provided state-of-the-art performance on different medical imaging tasks. However the availability of good quality annotated medical data is very cha lenging due to involved time constraints and the availability of expert annotators e.g. radiologists. In addition DL is data-hungry and their training requires extensive computational resources. Another problem with DL is their black-box nature and lack of transparency on its inner working which inhibits causal understanding and reasoning Automatic classification of diabetic retinopathy from retinal images has been widely studied using deep neural networks with impressive results. However there is a clinical need for estimation of the uncertainty in the classifications a shortcoming of modern neural networks. Recently approximate Bayesian deep learning methods have been proposed for the task but the studies have only considered the binary referable/non-referable diabetic retinopathy classification applied to benchmark datasets. We present novel results by systematica ly investigating a clinical dataset and a clinica ly relevant -class classification scheme in addition to benchmark datasets and the binary classification scheme. Moreover we derive a connection between uncertainty measures and classifier risk from which we develop a new uncertainty measure. We observe that the previously proposed entropy-based uncertainty measure generalizes to the clinical dataset on the binary classification scheme.

Author Information

# Name Institute / Affiliation
1 K Purushotham Sri Venkatesa Perumal College of Engineering & Technology
2 R RADHA Sri Venkatesa Perumal College of Engineering & Technology
3 R YESWANTH Sri Venkatesa Perumal College of Engineering & Technology
4 P Vishnu Vardhan Reddy Sri Venkatesa Perumal College of Engineering & Technology
5 P ANIL KUMAR Sri Venkatesa Perumal College of Engineering & Technology
6 T SAINATH REDDY Sri Venkatesa Perumal College of Engineering & Technology

How to Cite

Use the following formats to cite this article in your research.

APA Style
Purushotham, K, RADHA, R, YESWANTH, R, Reddy, P Vishnu Vardhan, KUMAR, P ANIL, & REDDY, T SAINATH (2025). Interactive Joint Feature Extraction for Diabetic Retinopathy Classification using Multiple Instance Neural Symbolic Learning. International Journal of Advance Research and Innovative Ideas In Education, 11(3), 543-547.
MLA Style
Purushotham, K, et al. "Interactive Joint Feature Extraction for Diabetic Retinopathy Classification using Multiple Instance Neural Symbolic Learning." International Journal of Advance Research and Innovative Ideas In Education, vol. 11, no. 3, 2025, pp. 543-547.
IEEE Style
K Purushotham, R RADHA, R YESWANTH, P Vishnu Vardhan Reddy, P ANIL KUMAR, and T SAINATH REDDY, "Interactive Joint Feature Extraction for Diabetic Retinopathy Classification using Multiple Instance Neural Symbolic Learning," International Journal of Advance Research and Innovative Ideas In Education, vol. 11, no. 3, pp. 543-547, 2025.
Vancouver Style
Purushotham K, RADHA R, YESWANTH R, Reddy P Vishnu Vardhan, KUMAR P ANIL, REDDY T SAINATH. Interactive Joint Feature Extraction for Diabetic Retinopathy Classification using Multiple Instance Neural Symbolic Learning. International Journal of Advance Research and Innovative Ideas In Education. 2025;11(3):543-547.
Harvard Style
Purushotham, K, RADHA, R, YESWANTH, R, Reddy, P Vishnu Vardhan, KUMAR, P ANIL, & REDDY, T SAINATH (2025) 'Interactive Joint Feature Extraction for Diabetic Retinopathy Classification using Multiple Instance Neural Symbolic Learning', International Journal of Advance Research and Innovative Ideas In Education, 11(3), pp. 543-547.
Chicago Style
Purushotham, K, et al. "Interactive Joint Feature Extraction for Diabetic Retinopathy Classification using Multiple Instance Neural Symbolic Learning." International Journal of Advance Research and Innovative Ideas In Education 11, no. 3 (2025): 543-547.
Turabian Style
Purushotham, K, et al. "Interactive Joint Feature Extraction for Diabetic Retinopathy Classification using Multiple Instance Neural Symbolic Learning." International Journal of Advance Research and Innovative Ideas In Education 11, no. 3 (2025): 543-547.

Export Citation

Related Research

AI Powered Autonomous Defence Surveillance Vehicle
SIDDARTH R et al. 2026 Artificial Intelligence, Robotics, Embedded Systems and Autonomous Surveillance
Download PDF
SMART WEARABLE SAFETY PENDANT
Ananya M et al. 2026 Electronics and Communication Engineering, Internet of Things (IoT), Embedded Systems
Download PDF
CARTRAC: A LIGHTWEIGHT IOT-BASED SYSTEM FOR POST-CRASH ACCOUNTABILITY IN HIT-AND-RUN INCIDENTS
prof.Divya k et al. 2026 “Internet of Things (IoT)-Based Intelligent Transportation Systems, with a focus on real-time accident detection, hit-and-run accountability, V2X communication, and smart traffic management.”
Download PDF
Intelligent IoT Healthcare Assistant for Alzheimer's Disease with Fall Detection Airbag
Farzana parveen BA et al. 2026 Internet of Things (IoT) and Artificial Intelligence in Healthcare
Download PDF
MULTIMODAL RASPBERRY PI ROBOT WITH SPEECH, TOUCH, QR CODE AND OBSTACLE DETECTION
Prof Syed Husna et al. 2026 Multimodal Human–Robot Interaction and Autonomous Navigation Using Raspberry Pi
Download PDF
SMART STROKE CARE SYSTEM: INTEGRATING REHABILITATION, HEALTH MONITORING, AND ASSISTIVE AUTOMATION USING AI AND IOT
Prof. Roopa S et al. 2026 Biomedical Engineering and Smart Healthcare, using IoT and embedded systems.
Download PDF