Course Contents
Imaging Modalities: Brief survey of major modalities for medical imaging: Ultrasound, X-ray, CT, MRI, PET, and SPECT.
Objectives of biomedical image analysis – Computer aided diagnosis, Removal of artifacts – Image Enhancement – Gray level transforms – Histogram transformation.
Spatial domain filters – Frequency domain filters – Morphological image processing – Binary morphological operations and properties – Morphological algorithms – Medical Image Segmentation, Thresholding – Region growing – Region splitting and merging – Edge detection.
Analysis of shape and texture – Representation of shapes and contours – Shape factors – Models for generation of texture – Statistical analysis of texture – Fractal analysis – Fourier domain analysis of texture – Applications – Contrast enhancement of mammograms – Detection of calcifications by region growing – Shape and texture analysis of tumours.
Reconstruction Techniques, Classification and Clustering, Examples of Image Classification for Diagnostic/Assistive Technologies, Case studies.
Image processing practical exercises:
- Basic operations on images
- Image enhancement using point operations
- Image enhancement using spatial domain filters
- Histogram processing of images
- Image enhancement using frequency domain filters
- Denoising of medical images
- Medical image segmentation using edge and region-based methods
- Extraction of shape and texture features from a medical image
- Design of pattern classification system for biomedical images
- Performance metrics in bioimages
Recommended Tools MATLAB, Python