Rohini Gaikar1, Fatemeh Zabihollahy2, Mohamed W Elfaal3, Azar Azad4, Nicola Schieda5, Eranga Ukwatta1. 1. University of Guelph, School of Engineering, Biomedical Engineering, Guelph, Ontario, Canada. 2. Johns Hopkins University School of Medicine, Department of Radiation Oncology and Molecular Radiation Sciences, Baltimore, Maryland, United States. 3. University of Alberta, Department of Radiology, Edmonton, Alberta, Canada. 4. A.I. VALI Inc., Toronto, Ontario, Canada. 5. University of Ottawa, Department of Radiology, Ottawa, Ontario, Canada.
Abstract
Purpose: Multiparametric magnetic resonance imaging (mp-MRI) is being investigated for kidney cancer because of better soft tissue contrast ability. The necessity of manual labels makes the development of supervised kidney segmentation algorithms challenging for each mp-MRI protocol. Here, we developed a transfer learning-based approach to improve kidney segmentation on a small dataset of five other mp-MRI sequences. Approach: We proposed a fully automated two-dimensional (2D) attention U-Net model for kidney segmentation on T1 weighted-nephrographic phase contrast enhanced (CE)-MRI (T1W-NG) dataset ( N = 108 ). The pretrained weights of T1W-NG kidney segmentation model transferred to five other distinct mp-MRI sequences model (T2W, T1W-in-phase (T1W-IP), T1W-out-of-phase (T1W-OP), T1W precontrast (T1W-PRE), and T1W-corticomedullary-CE (T1W-CM), N = 50 ) and fine-tuned by unfreezing the layers. The individual model performances were evaluated with and without transfer-learning fivefold cross-validation on average Dice similarity coefficient (DSC), absolute volume difference, Hausdorff distance (HD), and center-of-mass distance (CD) between algorithm generated and manually segmented kidneys. Results: The developed 2D attention U-Net model for T1W-NG produced kidney segmentation DSC of 89.34 ± 5.31 % . Compared with randomly initialized weight models, the transfer learning-based models of five mp-MRI sequences showed average increase of 2.96% in DSC of kidney segmentation ( p = 0.001 to 0.006). Specifically, the transfer-learning approach increased average DSC on T2W from 87.19% to 89.90%, T1W-IP from 83.64% to 85.42%, T1W-OP from 79.35% to 83.66%, T1W-PRE from 82.05% to 85.94%, and T1W-CM from 85.65% to 87.64%. Conclusions: We demonstrate that a pretrained model for automated kidney segmentation of one mp-MRI sequence improved automated kidney segmentation on five other additional sequences.
Purpose: Multiparametric magnetic resonance imaging (mp-MRI) is being investigated for kidney cancer because of better soft tissue contrast ability. The necessity of manual labels makes the development of supervised kidney segmentation algorithms challenging for each mp-MRI protocol. Here, we developed a transfer learning-based approach to improve kidney segmentation on a small dataset of five other mp-MRI sequences. Approach: We proposed a fully automated two-dimensional (2D) attention U-Net model for kidney segmentation on T1 weighted-nephrographic phase contrast enhanced (CE)-MRI (T1W-NG) dataset ( N = 108 ). The pretrained weights of T1W-NG kidney segmentation model transferred to five other distinct mp-MRI sequences model (T2W, T1W-in-phase (T1W-IP), T1W-out-of-phase (T1W-OP), T1W precontrast (T1W-PRE), and T1W-corticomedullary-CE (T1W-CM), N = 50 ) and fine-tuned by unfreezing the layers. The individual model performances were evaluated with and without transfer-learning fivefold cross-validation on average Dice similarity coefficient (DSC), absolute volume difference, Hausdorff distance (HD), and center-of-mass distance (CD) between algorithm generated and manually segmented kidneys. Results: The developed 2D attention U-Net model for T1W-NG produced kidney segmentation DSC of 89.34 ± 5.31 % . Compared with randomly initialized weight models, the transfer learning-based models of five mp-MRI sequences showed average increase of 2.96% in DSC of kidney segmentation ( p = 0.001 to 0.006). Specifically, the transfer-learning approach increased average DSC on T2W from 87.19% to 89.90%, T1W-IP from 83.64% to 85.42%, T1W-OP from 79.35% to 83.66%, T1W-PRE from 82.05% to 85.94%, and T1W-CM from 85.65% to 87.64%. Conclusions: We demonstrate that a pretrained model for automated kidney segmentation of one mp-MRI sequence improved automated kidney segmentation on five other additional sequences.
Authors: Alberto Diaz de Leon; Matthew S Davenport; Stuart G Silverman; Nicola Schieda; Jeffrey A Cadeddu; Ivan Pedrosa Journal: AJR Am J Roentgenol Date: 2019-04-17 Impact factor: 3.959
Authors: Noah E Canvasser; Fernando U Kay; Yin Xi; Daniella F Pinho; Daniel Costa; Alberto Diaz de Leon; Gaurav Khatri; John R Leyendecker; Takeshi Yokoo; Aaron Lay; Nicholas Kavoussi; Ersin Koseoglu; Jeffrey A Cadeddu; Ivan Pedrosa Journal: J Urol Date: 2017-04-28 Impact factor: 7.450
Authors: Alessandro Volpe; Tony Panzarella; Ricardo A Rendon; Masoom A Haider; Filippos I Kondylis; Michael A S Jewett Journal: Cancer Date: 2004-02-15 Impact factor: 6.860