MULTIPARAMETRIC IMAGE FUSION AND SEGMENTATION
Multiparametric Magnetic Resonance Imaging (MRI) produces large amounts of high dimensional data for radiologists to read. Currently, radiologists integrate multiparametric MRI data visually to identify meaningful structures within the data. In this project, we developed different novel visualization and clustering techniques based on manifold learning and deep learning for integration of multidimensional radiological data. The algorithms developed in this project include Consensus Similarity Mapping (CSM) and multiparametric deep network (MPDN). We demonstrate the performance of our algorithms on well-known synthetic datasets as well as multiparametric magnetic resonance imaging (MRI) data.
- V. S. Parekh, M. A. Jacobs. “Consensus Similarity Mapping System (CSMS): Computer Aided Detection/Diagnosis system for
advanced segmentation and visualization of different pathologies/objects using variable input data.” (D13500, 2015)
- V. S. Parekh, J. R. Jacobs, and M. A. Jacobs. "Unsupervised nonlinear dimensionality reduction machine learning
methods applied to multiparametric MRI in cerebral ischemia: preliminary results." SPIE Medical Imaging. International
Society for Optics and Photonics, 2014.
- V. Parekh and M. A. Jacobs, “A multidimensional data visualization and clustering method: Consensus similarity mapping.”
2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI) pp. 420-423.