Exploring Generalization Capacity of Artificial Neural Network for Myelin Water Imaging
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Purpose: To understand the effects of datasets with various parameters on pretrained network performance, the generalization capacity of the artificial neural network for myelin water imaging (ANN-MWI) is explored by testing datasets with various scan protocols (i.e., resolution and refocusing RF pulse shape) and types of disorders (i.e., neuromyelitis optica and edema). Materials and Methods: ANN-MWI was trained to generate a T2 distribution, from which the myelin water fraction value was measured. The training and test datasets were acquired from healthy controls and multiple sclerosis patients using a multiecho gradient and spin-echo sequence with the same scan protocols. To test the generalization capacity of ANN-MWI, datasets with different settings were utilized. The datasets were acquired or generated with different resolutions, refocusing pulse shape, and types of disorders. For all datasets, the evaluation was performed in a white matter mask by calculating the normalized root-mean-squared error (NRMSE) between the results from the conventional method and ANN-MWI. Additionally, for the patient datasets, the NRMSE was calculated in each lesion mask. Results: The results of ANN-MWI showed high reliability in generating myelin water fraction maps from the datasets with different resolutions. However, the increased errors were reported for the datasets with different refocusing pulse shapes and disorder types. Specifically, the region of lesions in edema patients reported high NRMSEs. These increased errors indicate the dependency of ANN-MWI on refocusing pulse flip angles and T2 characteristics. Conclusion: This study proposes information about the generalization accuracy of a trained network when applying deep learning to processing myelin water imaging.
Abstract
Purpose: To understand the effects of datasets with various parameters on pretrained network performance, the generalization capacity of the artificial neural network for myelin water imaging (ANN-MWI) is explored by testing datasets with various scan protocols (i.e., resolution and refocusing RF pulse shape) and types of disorders (i.e., neuromyelitis optica and edema). Materials and Methods: ANN-MWI was trained to generate a T2 distribution, from which the myelin water fraction value was measured. The training and test datasets were acquired from healthy controls and multiple sclerosis patients using a multiecho gradient and spin-echo sequence with the same scan protocols. To test the generalization capacity of ANN-MWI, datasets with different settings were utilized. The datasets were acquired or generated with different resolutions, refocusing pulse shape, and types of disorders. For all datasets, the evaluation was performed in a white matter mask by calculating the normalized root-mean-squared error (NRMSE) between the results from the conventional method and ANN-MWI. Additionally, for the patient datasets, the NRMSE was calculated in each lesion mask. Results: The results of ANN-MWI showed high reliability in generating myelin water fraction maps from the datasets with different resolutions. However, the increased errors were reported for the datasets with different refocusing pulse shapes and disorder types. Specifically, the region of lesions in edema patients reported high NRMSEs. These increased errors indicate the dependency of ANN-MWI on refocusing pulse flip angles and T2 characteristics. Conclusion: This study proposes information about the generalization accuracy of a trained network when applying deep learning to processing myelin water imaging.
참고문헌 (36)
- Yoon J, "Quantitative susceptibility mapping using deep neural network : QSMnet", Neuroimage, 179, pp.199~206 (2018)
- Cohen O, "MR fingerprinting Deep RecOnstruction NEtwork(DRONE)", Magn Reson Med, 80, pp.885~894 (2018)
- Kwon K, "A parallel MR imaging method using multilayer perceptron", Med Phys, 44, pp.6209~6224 (2017)
- 이두희, "Deep Learning in MR Image Processing", Investigative Magnetic Resonance Imaging, 23(2), pp.81~99 (2019), 대한자기공명의과학회
- Ben-David S, "Analysis of representations for domain adaptation", Advances in Neural Information Processing Systems (NIPS), pp.137~144 (2006)
- Mårtensson G, "The reliability of a deep learning model in clinical out-of-distribution MRI data : a multicohort study", Med Image Anal, 66, pp.101714~ (2020)
- Jung W, "Exploring linearity of deep neural network trained QSM : QSMnet†", Neuroimage, 211, pp.116619~ (2020)
- Knoll F, "Assessment of the generalization of learned image reconstruction and the potential for transfer learning", Magn Reson Med, 81, pp.116~128 (2019)
- Zhang C, "Understanding deep learning requires rethinking generalization", arXiv preprint arXiv:1611.03530, ~ (2016)
- 윤성원, "Multi-Parametric Quantitative MRI for Measuring Myelin Loss in Hyperglycemia-Induced Hemichorea", Investigative Magnetic Resonance Imaging, 23(2), pp.148~156 (2019), 대한자기공명의과학회
- 서정표, "Mini-Review of Studies Reporting the Repeatability and Reproducibility of Diffusion Tensor Imaging", Investigative Magnetic Resonance Imaging, 23(1), pp.26~33 (2019), 대한자기공명의과학회
- Lee J, "Artificial neural network for myelin water imaging", Magn Reson Med, 83, pp.1875~1883 (2020)
- MacKay A, "In vivo visualization of myelin water in brain by magnetic resonance", Magn Reson Med, 31, pp.673~677 (1994)
- Prasloski T, "Applications of stimulated echo correction to multicomponent T2 analysis", Magn Reson Med, 67, pp.1803~1814 (2012)
- Prasloski T, "Rapid whole cerebrum myelin water imaging using a 3D GRASE sequence", Neuroimage, 63, pp.533~539 (2012)
- Choi JY, "Evaluation of normalappearing white matter in multiple sclerosis using direct visualization of short transverse relaxation time component(ViSTa)myelin water imaging and gradient echo and spin echo(GRASE)myelin water imaging", J Magn Reson Imaging, 49, pp.1091~1098 (2019)
- Jeong IH, "Comparison of myelin water fraction values in periventricular white matter lesions between multiple sclerosis and neuromyelitis optica spectrum disorder", Mult Scler, 22, pp.1616~1620 (2016)
- "IEEE Trans Med Imaging", 1991, 53~65
- Jeong IH, "Normal-appearing white matter demyelination in neuromyelitis optica spectrum disorder", Eur J Neurol, 24, pp.652~658 (2017)
- Borich MR, "Evaluation of white matter myelin water fraction in chronic stroke", Neuroimage Clin, 2, pp.569~580 (2013)
- Dvorak AV, "Rapid myelin water imaging for the assessment of cervical spinal cord myelin damage", Neuroimage Clin, 23, pp.101896~ (2019)
- Baumeister TR, "White matter myelin profiles linked to clinical subtypes of Parkinson's disease", J Magn Reson Imaging, 50, pp.164~174 (2019)
- Lakhani B, "Hemispheric asymmetry in myelin after stroke is related to motor impairment and function", Neuroimage Clin, 14, pp.344~353 (2017)
- Maas AL, "Rectifier nonlinearities improve neural network acoustic models", Proc of the 30th Int Conf Mach Learn (ICML), pp.3~ (2013)
- Kingma DP, "Adam: a method for stochastic optimization", arXiv preprint arXiv:1412.6980, ~ (2014)
- Wilson DR, "The need for small learning rates on large problems", Proc 2001 Int Joint Conf Neural Netw (IJCNN), pp.115~119 (2001)
- Smith SL, "Don't decay the learning rate, increase the batch size", arXiv preprint arXiv:1711.00489, ~ (2017)
- Du YP, "Fast multislice mapping of the myelin water fraction using multicompartment analysis of T2* decay at 3T : a preliminary postmortem study", Magn Reson Med, 58, pp.865~870 (2007)
- Meyers SM, "Reproducibility of myelin water fraction analysis : a comparison of region of interest and voxel-based analysis methods", Magn Reson Imaging, 27, pp.1096~1103 (2009)
- Smith SM, "Fast robust automated brain extraction", Hum Brain Mapp, 17, pp.143~155 (2002)
- Hennig J, "Multiecho imaging sequences with low refocusing flip angles", J Magn Reson, 78, pp.397~407 (1988)
- Wang J, "Factors influencing flip angle mapping in MRI: RF pulse shape, slice-select gradients, off-resonance excitation, and B0inhomogeneities", Magn Reson Med, 56, pp.463~468 (2006)
- Pan SJ, "A survey on transfer learning", IEEE Trans Knowl Data Eng, 22, pp.1345~1359 (2009)
- He H, "Learning from imbalanced data", IEEE Trans Knowl Data Eng, 21, pp.1263~1284 (2009)
- Krawczyk B, "Learning from imbalanced data : open challenges and future directions", Artificial Intelligence, 5, pp.221~232 (2016)
- Lee LE, "Inter-vendor reproducibility of myelin water imaging using a 3D gradient and spin echo sequence", Front Neurosci, 12, pp.854~ (2018)