• K.Saiteja
• Dr.K.Satyanarayana Raju
• D.Karthik
• P.Stave Flaming
• Sk.Mansoor

Millions of people worldwide suffer from knee pain, which is a common and incapacitating symptom that frequently indicates underlying illnesses such arthritis, rheumatoid arthritis, and osteoarthritis (OA). For planning therapy and patient care management to be successful, accurate diagnosis of these disorders is essential. Medical imaging is essential to the diagnosis process since it gives doctors detailed information on joint abnormalities and structures, especially when it comes to X-ray imaging of the knees. Deep learning approaches have transformed medical image analysis in recent years, bringing up a paradigm shift in the way medical practitioners interpret diagnostic images. Deep learning algorithms have proven to be exceptionally effective in automating image interpretation activities, which improves the efficiency and accuracy of diagnosis. Inspired by deep learning's potential in medical image processing using CNN’s, this study offers a novel approach for classifying knee pain using X-ray pictures. More specifically, Grade 0, Grade 1, Grade 2, Grade 3, and Grade 4 are the five different diagnostic groups into which our approach attempts to classify knee X-ray pictures. We achieve this by utilizing power pretrained models, such as VGG12, ResNet50, DenseNet, and EfficientNet, which are well-known for their efficacy in picture classification tasks.

OA, arthritis, deep learning, CNN.

"DEEP LEARNING BASED KNEE PAIN CLASSIFICATION X-RAY USING IMAGES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.e272-e278, April-2024, Available :http://www.jetir.org/papers/JETIR2404432.pdf

"DEEP LEARNING BASED KNEE PAIN CLASSIFICATION X-RAY USING IMAGES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppe272-e278, April-2024, Available at : http://www.jetir.org/papers/JETIR2404432.pdf