Enhancing Knee Osteoarthritis severity level classification using diffusion augmented images

TL;DR

This study demonstrates that combining diffusion-based data augmentation, advanced CNN models, and attention visualization techniques significantly improves the accuracy and interpretability of knee osteoarthritis severity classification.

Contribution

It introduces the use of diffusion models for data augmentation and applies attention visualization to enhance model interpretability in knee OA classification.

Findings

Augmentation with diffusion models improves accuracy to 84%.

Preprocessing with CLAHE enhances model performance.

Attention maps provide better understanding of model focus.

Abstract

This research paper explores the classification of knee osteoarthritis (OA) severity levels using advanced computer vision models and augmentation techniques. The study investigates the effectiveness of data preprocessing, including Contrast-Limited Adaptive Histogram Equalization (CLAHE), and data augmentation using diffusion models. Three experiments were conducted: training models on the original dataset, training models on the preprocessed dataset, and training models on the augmented dataset. The results show that data preprocessing and augmentation significantly improve the accuracy of the models. The EfficientNetB3 model achieved the highest accuracy of 84\% on the augmented dataset. Additionally, attention visualization techniques, such as Grad-CAM, are utilized to provide detailed attention maps, enhancing the understanding and trustworthiness of the models. These findings highlight the potential of combining advanced models with augmented data and attention visualization for accurate knee OA severity classification.