Knee Osteoarthritis Severity Grading Using Optimized Deep Learning and LLM-Driven Intelligent AI on Computationally Limited Systems
Summary
This paper presents an automated diagnostic system for grading knee osteoarthritis severity using an optimized ResNet-18 model deployed on edge devices via TensorFlow Lite. It integrates an LLM interface using Gemini 2.0 Flash to provide structured interpretive findings while maintaining offline capability for resource-constrained environments.
View Cached Full Text
Cached at: 05/08/26, 08:42 AM
# Knee Osteoarthritis Severity Grading Using Optimized Deep Learning and LLM-Driven Intelligent AI on Computationally Limited Systems Source: [https://arxiv.org/abs/2605.05731](https://arxiv.org/abs/2605.05731) [View PDF](https://arxiv.org/pdf/2605.05731) > Abstract:Knee osteoarthritis \(KOA\) is among the musculoskeletal disorders that considerably restrict joint mobility, cause severe chronic pain and impact negatively on quality life\. It is one of the persistent health issues worldwide\. Generally, subjectivity and inter\-observer variability undermine conventional practices and evaluation process that are adopted to address such health issues\. Hence precise and timely diagnosis would be one of the effective ways for the assessment of its severity\. This paper proposes an automated diagnostic approach for severity grading of KOA by blending a deep learning convolutional neural network \(CNN\) with a device\-based inference platform powered by TensorFlow Lite\. It proposes a model based on the ResNet\-18 convolutional neural network\. The designed model is trained on publicly available database\. Through a transfer learning approach obtained knee images are first classified into five Kellgren\-Lawrence \(KL\) grades\. Further the developed model is optimised\. During the training of the model test accuracy of 94\.48% with stable convergence has been achieved\. Subsequently the optimised model transformed into a lightweight TensorFlow Lite format, facilitating seamless deployment on resource\-constrained devices\. The designed model is capable enough to operate in the environment having no continuous internet connectivity\. Also, an auxiliary Large Language Model \(Gemini\-2\.0\-flash\) is applied to generate structured interpretive findings like potential symptoms, risk factors, and preventive majors etc\. The LLM component functions as interface without influencing the classification process\. The proposed model articulates the feasibility of an on\-device, interpretable decision\-support tools for early diagnosis and improve accessibility to Artificial Intelligence \(AI\)\-assisted knee screening tool\. ## Submission history From: Dayam Nadeem \[[view email](https://arxiv.org/show-email/fd4be269/2605.05731)\] **\[v1\]**Thu, 7 May 2026 06:24:04 UTC \(1,471 KB\)
Similar Articles
An Agentic AI Framework Overcomes Fundamental Limitations of Large Language Models for Glaucoma Detection from Fundus Photography
This arXiv paper presents an agentic AI framework that integrates LLMs with specialized deep learning tools for glaucoma detection from fundus images, improving accuracy by 16-47 percentage points and reducing run-to-run variability compared to LLM-alone approaches.
DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs
The DeepLens Diagnosis Agent uses a five-stage agentic workflow with a small medical reasoning model (7B) to achieve 60.14% diagnostic accuracy on a 915-case benchmark, outperforming frontier LLMs like Claude Sonnet 4.5 and Gemini 3.1 Pro at lower cost. The workflow design alone yields a 36-point gain over the base model, demonstrating that structured process constraints are key for diagnostic reasoning.
Evidence-Grounded AI for Musculoskeletal Care
This paper presents an evidence-grounded AI framework for diagnosing and treating musculoskeletal conditions, leveraging clinical data and orthopedic knowledge.
A specialized reasoning large language model for accelerating rare disease diagnosis: a randomized AI physician assistance trial
This paper presents RaDaR, a 32B open-source reasoning LLM trained on public and synthetic rare disease cases, which outperforms larger models like DeepSeek-R1 in diagnosis benchmarks and improves physician accuracy by 21.44 percentage points in a randomized trial.
Lightweight Multimodal LLM-Enabled Cost-Effective Defect Grading of Power Transmission Equipment
This paper introduces a lightweight multimodal LLM-based framework for cost-effective defect grading of power transmission equipment, using in-context learning and chain-of-thought to generate training data and fine-tuning Qwen3-VL-8B for state-of-the-art performance.