Shape Learning of 3D Surfaces of the Knee using different Image Segmentation Techniques
Field of medical image analysis is evolving at a rapid pace. New advancements have introduced big challenges in analysis and information extraction from the generated images. Usually the scale of input data is so immense that it needs very efficient and smart algorithms to process intended outcomes. Magnetic Resonance Images (MRI) is one of the primary sources for morphometric analysis. Frequently used techniques for this kind of analysis are Principal Component analysis (PCA) and a more robust Incremental Principal Component Analysis (IPCA). Both these techniques apply complex algorithms for producing statistical shape models which ultimately show variance in clinical images. Variance is primarily detected and measured in the articular cartilage. Statistical assessment of cartilage volume and surface area estimation gives an indication of osteoarthritis severity. This research paper proposes an agile framework for segmentation of images of the knee by using Active contour model. Image texture information is merged in the model with the help of effective mathematical functions. Vector valued geodesic was used during segmentation and also to detect and measure variance in the image at pixel level. By use of efficient algorithms and mathematical tools this technique showed promising results in handling noise and nonuniform intensities within the image. The algorithm effectively provided a quantitative cartilage assessment which could help physicians in classifying osteoarthritis stages.