@article{Khalvati_Zhang_Baig_Haider_Wong_2016, title={Sparse Correlated Diffusion Imaging: A New Computational Diffusion MRI Modality for Prostate Cancer Detection}, volume={2}, url={https://openjournals.uwaterloo.ca/index.php/vsl/article/view/107}, DOI={10.15353/vsnl.v2i1.107}, abstractNote={<p>Diffusion weighted imaging (DWI) is a promising magnetic resonance<br />imaging (MRI) modality with wide applications in diagnosis<br />of different types of diseases such as prostate cancer. DWI provides<br />a large amount of imaging data which often makes it difficult<br />to interpret accurately, mainly due to the fact that much of information<br />in diffusion imaging cannot be deciphered by human experts<br />alone. Computational diffusion MRI (CD-MRI) aims to leverage<br />computational means to generate imagery from diffusion signals<br />which are easier to interpret by human experts. Recently, a<br />new CD-MRI modality called correlated diffusion imaging (CDI) has<br />been proposed which takes advantage of the joint correlation of diffusion<br />signal attenuation across multiple gradient pulse strengths<br />and timings to improve the separability of cancerous and healthy<br />tissues. In this paper, we propose a new CD-MRI modality called<br />Sparse CDI (sCDI) where an optimally sparse subset of diffusion<br />signals contributes to the formation of the final diffusion signal leading<br />to further separation of cancerous and healthy tissue in prostate<br />gland compared to CDI and conventional DWI.</p>}, number={1}, journal={Journal of Computational Vision and Imaging Systems}, author={Khalvati, Farzad and Zhang, Junjie and Baig, Sameer and Haider, Masoom A. and Wong, Alexander}, year={2016}, month={Oct.} }