Early Assessment of Renal Transplants Using BOLD-MRI: Promising Results

• Published in: 2019 IEEE International Conference on Image Processing (ICIP) Vol. 2019; pp. 1395 - 1399
• Main Authors: Shehata, M., Keynton, R., El-Baz, A., Shalaby, A., Ghazal, M., El-Ghar, M. Abou, Badawy, M. A., Beache, G., Dwyer, A., El-Melegy, M., Giridharan, G.
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.09.2019
• Subjects: Biopsy; BOLD-MRI; Feature extraction; Image segmentation; Kidney; Machine learning; mean R2; Motion segmentation; pixel-wise R2; Renal transplants; Two dimensional displays
• ISSN: 1522-4880; 2381-8549
• DOI: 10.1109/ICIP.2019.8803042

Non-invasive evaluation of renal transplant function is essential to minimize and manage acute renal rejection (AR). A computer-assisted diagnostic (CAD) system is developed to evaluate kidney function post-transplantation. The developed CAD system utilizes the amount of blood-oxygenation extracted from 3D (2D + time) blood oxygen level-dependent magnetic resonance imaging (BOLD-MRI) to estimate renal function. BOLD-MRI scans were acquired at five different echo-times (2, 7, 12, 17, and 22) ms from 15 transplant patients. The developed CAD system first segments kidneys using the level-sets method followed by estimation of the amount of deoxyhemoglobin, also known as apparent relaxation rate (R2*). These R2* estimates are used as discriminatory features (global features (mean R2*) and local features (pixel-wise R2*)) to train and test state-of-the-art machine learning classifiers to differentiate between non-rejection (NR) and AR. Using a leave-one-out cross-validation approach along with a multi-layer preceptron neural network (MLP-NN) classifier, the CAD system demonstrated 93.3% accuracy, 100% sensitivity, and 90% specificity in distinguishing AR from NR. These preliminary results demonstrate the efficacy of the CAD system to detect renal allograft status non-invasively.