A new non-invasive approach for early classification of renal rejection types using diffusion-weighted MRI

• Published in: Proceedings - International Conference on Image Processing pp. 136 - 140
• Main Authors: Shehata, Mohamed, Khalifa, Fahmi, Hollis, Elizabeth, Soliman, Ahmed, Hosseini-Asl, Ehsan, Abou El-Ghar, Mohamed, El-Baz, Maryam, Dwyer, Amy C., El-Baz, Ayman, Keynton, Robert
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2016
• Subjects: ADC; ARTR types; Blood; Deep learning; Design automation; DW-MRI; Image segmentation; Kidney; Magnetic resonance imaging; Motion segmentation; Three-dimensional displays
• ISSN: 2381-8549
• DOI: 10.1109/ICIP.2016.7532334

Although renal biopsy remains the gold standard for diagnosing the type of renal rejection, it is not preferred due to its invasiveness, recovery time (1-2 weeks), and potential for complications, e.g., bleeding and/or infection. Therefore, there is an urgent need to explore a non-invasive technique that can early classify renal rejection types. In this paper, we develop a computer-aided diagnostic (CAD) system that can classify acute renal transplant rejection (ARTR) types early via the analysis of apparent diffusion coefficients (ADCs) extracted from diffusion-weighted (DW) MRI data acquired at low-(accounting for perfusion) and high-(accounting for diffusion) b-values. The developed framework mainly consists of three steps: (i) data co-alignment using a 3D B-spline-based approach (to handle local deviations due to breathing and heart beat motions) and segmentation of kidney tissue with an evolving geometric (level-set based) deformable model guided by a voxel-wise stochastic speed function, which follows a joint kidney-background Markov-Gibbs random field model accounting for an adaptive kidney shape prior and visual kidney-background appearances of DW-MRI data (image intensities and spatial interactions); (ii) construction of a cumulative empirical distribution of ADC at low and high b-values of the segmented kidney accounting for blood perfusion and water diffusion, respectively, to be our discriminatory ARTR types feature; and (iii) classification of ARTR types (acute tubular necrosis (ATN) anti-body- and T-cell-mediated rejection) based on deep learning of a non-negative constrained stacked autoencoder. Results show that 98% of the subjects were correctly classified in our "leave-one-subject-out" experiments on 39 subjects (namely, 8 out of 8 of the ATN group and 30 out of 31 of the T-cell group). Thus, the proposed approach holds promise as a reliable non-invasive diagnostic tool.