Hung P Do1, Yi Guo1, Andrew J Yoon2, Krishna S Nayak1. 1. Ming Hsieh Department of Electrical and Computer Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, California. 2. Long Beach Memorial Medical Center, University of California Irvine, Irvine, California.
Abstract
PURPOSE: To apply deep convolution neural network to the segmentation task in myocardial arterial spin labeled perfusion imaging and to develop methods that measure uncertainty and that adapt the convolution neural network model to a specific false-positive versus false-negative tradeoff. METHODS: The Monte Carlo dropout U-Net was trained on data from 22 subjects and tested on data from 6 heart transplant recipients. Manual segmentation and regional myocardial blood flow were available for comparison. We consider 2 global uncertainty measures, named "Dice uncertainty" and "Monte Carlo dropout uncertainty," which were calculated with and without the use of manual segmentation, respectively. Tversky loss function with a hyperparameter β was used to adapt the model to a specific false-positive versus false-negative tradeoff. RESULTS: The Monte Carlo dropout U-Net achieved a Dice coefficient of 0.91 ± 0.04 on the test set. Myocardial blood flow measured using automatic segmentations was highly correlated to that measured using the manual segmentation (R2 = 0.96). Dice uncertainty and Monte Carlo dropout uncertainty were in good agreement (R2 = 0.64). As β increased, the false-positive rate systematically decreased and false-negative rate systematically increased. CONCLUSION: We demonstrate the feasibility of deep convolution neural network for automatic segmentation of myocardial arterial spin labeling, with good accuracy. We also introduce 2 simple methods for assessing model uncertainty. Finally, we demonstrate the ability to adapt the convolution neural network model to a specific false-positive versus false-negative tradeoff. These findings are directly relevant to automatic segmentation in quantitative cardiac MRI and are broadly applicable to automatic segmentation problems in diagnostic imaging.
PURPOSE: To apply deep convolution neural network to the segmentation task in myocardial arterial spin labeled perfusion imaging and to develop methods that measure uncertainty and that adapt the convolution neural network model to a specific false-positive versus false-negative tradeoff. METHODS: The Monte Carlo dropout U-Net was trained on data from 22 subjects and tested on data from 6 heart transplant recipients. Manual segmentation and regional myocardial blood flow were available for comparison. We consider 2 global uncertainty measures, named "Dice uncertainty" and "Monte Carlo dropout uncertainty," which were calculated with and without the use of manual segmentation, respectively. Tversky loss function with a hyperparameter β was used to adapt the model to a specific false-positive versus false-negative tradeoff. RESULTS: The Monte Carlo dropout U-Net achieved a Dice coefficient of 0.91 ± 0.04 on the test set. Myocardial blood flow measured using automatic segmentations was highly correlated to that measured using the manual segmentation (R2 = 0.96). Dice uncertainty and Monte Carlo dropout uncertainty were in good agreement (R2 = 0.64). As β increased, the false-positive rate systematically decreased and false-negative rate systematically increased. CONCLUSION: We demonstrate the feasibility of deep convolution neural network for automatic segmentation of myocardial arterial spin labeling, with good accuracy. We also introduce 2 simple methods for assessing model uncertainty. Finally, we demonstrate the ability to adapt the convolution neural network model to a specific false-positive versus false-negative tradeoff. These findings are directly relevant to automatic segmentation in quantitative cardiac MRI and are broadly applicable to automatic segmentation problems in diagnostic imaging.
Keywords:
Bayesian; Monte Carlo dropout; automatic segmentation; deep convolutional neural network; false-positive and false-negative tradeoff; uncertainty measure
Authors: Hung Phi Do; Andrew J Yoon; Michael W Fong; Farhood Saremi; Mark L Barr; Krishna S Nayak Journal: Magn Reson Med Date: 2016-05-30 Impact factor: 4.668
Authors: K K Kwong; D A Chesler; R M Weisskoff; K M Donahue; T L Davis; L Ostergaard; T A Campbell; B R Rosen Journal: Magn Reson Med Date: 1995-12 Impact factor: 4.668
Authors: Konstantinos Kamnitsas; Christian Ledig; Virginia F J Newcombe; Joanna P Simpson; Andrew D Kane; David K Menon; Daniel Rueckert; Ben Glocker Journal: Med Image Anal Date: 2016-10-29 Impact factor: 8.545
Authors: Heerajnarain Bulluck; Stefania Rosmini; Amna Abdel-Gadir; Steven K White; Anish N Bhuva; Thomas A Treibel; Marianna Fontana; Esther Gonzalez-Lopez; Patricia Reant; Manish Ramlall; Ashraf Hamarneh; Alex Sirker; Anna S Herrey; Charlotte Manisty; Derek M Yellon; Peter Kellman; James C Moon; Derek J Hausenloy Journal: J Am Heart Assoc Date: 2016-07-11 Impact factor: 5.501