A Novel Method to Predict Knee Osteoarthritis using Deep Learning
A Novel Method to Predict Knee Osteoarthritis using Deep Learning
PROJECT ABSTRACT:
Osteoarthritis (OA), particularly knee OA, is the most common type of arthritis, and it causes major disability in patients all over the world. One of the most common degenerative musculoskeletal illnesses is osteoarthritis (OA). Almost 5% of the world’s population is affected by this disease. The most frequent joint affected by OA is the knee, which is marked by permanent deterioration of the articular cartilage at the ends of the bones.
Knee osteoarthritis (OA) is a condition that affects the entire knee joint and progresses over time. Manual diagnosis, segmentation, and annotating of knee joints are still used in clinical practise to diagnose OA, despite the fact that they are time-consuming and sensitive to user variance. As a result, we built the proposed system employing the VGG16 model to increase the clinical workflow efficiency and overcome the constraints of the generally used method.
Clinical examination and plain radiography are presently used to diagnose knee osteoarthritis (OA). However, one clinically relevant challenge to address in OA is the prediction of its progression as well as the detection of early changes. Imaging-based diagnostic methods can be enhanced using novel quantitative methods, but one clinically relevant challenge to address in OA is the prediction of its progression as well as the detection of early changes.
We introduce a novel Deep Learning (DL)-based technique for predicting OA progression from knee X-ray images in this work. In this system, we compile the model and use the fit function to apply it. The batch size will be limited to six. The graphs for accuracy and loss will then be plotted. The average validation accuracy was 87%, and the average training accuracy was 95%.
PROJECT OUTPUT VIDEO:
ALGORITHM / MODEL USED:
VGG16 Model.
SYSTEM REQUIREMENTS:
HARDWARE REQUIREMENTS:
- System : Pentium i3 Processor.
- Hard Disk : 500 GB.
- Monitor : 15’’ LED
- Input Devices : Keyboard, Mouse
- Ram : 4 GB
SOFTWARE REQUIREMENTS:
- Operating System : Windows 10 / 11.
- Coding Language : Python 3.8.
- Web Framework : Flask.
- Frontend : HTML, CSS, JavaScript.