• Sanskar Masirkar
• Prof. R. B. Khule
• Shrikrishna Bawankule

: Knee osteoarthritis (OA) is a degenerative joint disorder affecting mobility and quality of life, especially in older adults. Early detection and accurate severity grading are crucial for effective management. This study compares deep learning models for automating knee OA severity grading using X-ray images. The dataset underwent preprocessing techniques such as resizing, normalization, and augmentation to enhance model robustness. Seven deep learning architectures—CNN, DenseNet121, ResNet50, Xception, VGG16, VGG19, MobileNet, and AlexNet—were evaluated using accuracy, precision, recall, F1 score, and confusion matrices. DenseNet121 outperformed others with 98.55% accuracy due to its efficient feature reuse. ResNet50 followed with 97.92%, leveraging residual connections. Xception (97.45%) and MobileNet (96.87%) provided computational efficiency for resource-limited environments. VGG16 and VGG19 achieved moderate accuracies, while AlexNet performed the lowest at 93.47%. The study highlights DenseNet121 as the best model for OA severity grading, demonstrating deep learning's potential in medical diagnostics. Future work may explore ensemble models and explainable AI to improve robustness and clinical adoption.

Convolutional Neural Networks (CNNs), DenseNet121, Image Processing, Xception, ResNet50V2, VGG16, VGG19, Automated Diagnosis.

"KNEE OSTEOARTHRITIS SEVERITY GRADING USING MACHINE LEARNING LIBRARIES AND DEEP LEARNING MODELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.i199-i207, March-2025, Available :http://www.jetir.org/papers/JETIR2503827.pdf

"KNEE OSTEOARTHRITIS SEVERITY GRADING USING MACHINE LEARNING LIBRARIES AND DEEP LEARNING MODELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppi199-i207, March-2025, Available at : http://www.jetir.org/papers/JETIR2503827.pdf