Pub Date : 2021-01-01DOI: 10.13104/imri.2021.25.4.218
Jong-ryul Choi, S. Oh
optics can be integrated with magnetic resonance imaging (MRI) diagnostic systems to acquire valuable information on biological tissues and organs based on a magnetic field. In this article, we explored the combination of MRI and optical sensing/imaging techniques by classifying them into the following topics: 1) functional near-infrared spectroscopy with functional MRI for brain studies and brain disease diagnoses, 2) integration of fiber-optic molecular imaging and optogenetic stimulation with MRI, and 3) optical therapeutic applications with an MRI guidance system. Through these investigations, we believe that a combination of MRI and optical sensing/imaging techniques can be employed as both research methods for multidisciplinary studies and clinical diagnostic/therapeutic devices. oxygenated hemoglobin dynamics captured by fNIRS and BOLD fMRI in this experiment. ΔHbO-BOLD indicates a correlation between changes in BOLD fMRI signals and oxygenated hemoglobin measured by fNIRS. ΔHbR-BOLD indicates a correlation between changes in BOLD fMRI signals and deoxygenated hemoglobin measured by fNIRS. Deriving the relationship between hemodynamics measured by fNIRS and BOLD fMRI signals and acquiring a highly relevant brain region for the specific brain functions could be utilized to analyze brain activities and functions in more various scenarios compared with using MRI only. Reprint of figures in (32) is permitted by Springer Nature under the terms of the Creative Commons CC BY license.
{"title":"Magnetic Resonance Imaging Meets Fiber Optics: a Brief Investigation of Multimodal Studies on Fiber Optics-Based Diagnostic / Therapeutic Techniques and Magnetic Resonance Imaging","authors":"Jong-ryul Choi, S. Oh","doi":"10.13104/imri.2021.25.4.218","DOIUrl":"https://doi.org/10.13104/imri.2021.25.4.218","url":null,"abstract":"optics can be integrated with magnetic resonance imaging (MRI) diagnostic systems to acquire valuable information on biological tissues and organs based on a magnetic field. In this article, we explored the combination of MRI and optical sensing/imaging techniques by classifying them into the following topics: 1) functional near-infrared spectroscopy with functional MRI for brain studies and brain disease diagnoses, 2) integration of fiber-optic molecular imaging and optogenetic stimulation with MRI, and 3) optical therapeutic applications with an MRI guidance system. Through these investigations, we believe that a combination of MRI and optical sensing/imaging techniques can be employed as both research methods for multidisciplinary studies and clinical diagnostic/therapeutic devices. oxygenated hemoglobin dynamics captured by fNIRS and BOLD fMRI in this experiment. ΔHbO-BOLD indicates a correlation between changes in BOLD fMRI signals and oxygenated hemoglobin measured by fNIRS. ΔHbR-BOLD indicates a correlation between changes in BOLD fMRI signals and deoxygenated hemoglobin measured by fNIRS. Deriving the relationship between hemodynamics measured by fNIRS and BOLD fMRI signals and acquiring a highly relevant brain region for the specific brain functions could be utilized to analyze brain activities and functions in more various scenarios compared with using MRI only. Reprint of figures in (32) is permitted by Springer Nature under the terms of the Creative Commons CC BY license.","PeriodicalId":73505,"journal":{"name":"Investigative magnetic resonance imaging","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66633005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.13104/imri.2021.25.4.229
X. Yin, Nan Li, Seng Jia, Xiaoliang Zhang, Ye Li
Arteriosclerosis is the leading cause of stroke, with a fatality rate surpassing that of ischemic heart disease. High-resolution vessel wall magnetic resonance imaging is generally recognized as a non-invasive and panoramic method for the evaluation of arterial plaque; however, this method requires improved signal-to-noise ratio and scanning speed. Recent advances in high-density head and neck coil arrays are characterized by broad coverage, multiple channels, and close-fitting designs. This review analyzes fast magnetic resonance imaging from the perspective of accelerated algorithms for vessel wall imaging and demonstrates the need for effective algorithms for signal acquisition using advanced radiofrequency system. We summarize different phased-array structures under various experimental objectives and equipment conditions, introduce current research results, and propose prospective research studies in the future.
{"title":"Advances in Fast Vessel-Wall Magnetic Resonance Imaging Using High-Density Coil Arrays","authors":"X. Yin, Nan Li, Seng Jia, Xiaoliang Zhang, Ye Li","doi":"10.13104/imri.2021.25.4.229","DOIUrl":"https://doi.org/10.13104/imri.2021.25.4.229","url":null,"abstract":"Arteriosclerosis is the leading cause of stroke, with a fatality rate surpassing that of ischemic heart disease. High-resolution vessel wall magnetic resonance imaging is generally recognized as a non-invasive and panoramic method for the evaluation of arterial plaque; however, this method requires improved signal-to-noise ratio and scanning speed. Recent advances in high-density head and neck coil arrays are characterized by broad coverage, multiple channels, and close-fitting designs. This review analyzes fast magnetic resonance imaging from the perspective of accelerated algorithms for vessel wall imaging and demonstrates the need for effective algorithms for signal acquisition using advanced radiofrequency system. We summarize different phased-array structures under various experimental objectives and equipment conditions, introduce current research results, and propose prospective research studies in the future.","PeriodicalId":73505,"journal":{"name":"Investigative magnetic resonance imaging","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66633023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.13104/imri.2021.25.4.338
J. Kim, Min Seon Kim, K. Lee, L. Kim
Case Report Solitary fibrous tumors (SFT) are rare mesenchymal tumors that most commonly develop in the pleura; they rarely involve the diaphragm. MRI has not been widely used to evaluate SFTs of the thoracic cavity, though it may be highly useful in assessing local invasion, predicting malignant potential, and helping in the differential diagnosis. However, MRI findings of malignant SFTs of the diaphragmatic pleura have been described in only two cases. We report a rare case of a malignant solitary fibrous tumor of the diaphragmatic pleura in an 82-year-old man. We describe the clinical and characteristic imaging features, including computed tomography, conventional MRI, and diffusion-weighted imaging. Contrast-enhanced MRI is more accurate than is CT in identifying the origin of SFTs, predicting whether they ae benign or malignant, and assessing local invasion. This imaging modality proved helpful in deciding on the treatment strategy for these rare tumors.
{"title":"MRI Findings of a Malignant Solitary Fibrous Tumor of the Diaphragmatic Pleura: a Case Report","authors":"J. Kim, Min Seon Kim, K. Lee, L. Kim","doi":"10.13104/imri.2021.25.4.338","DOIUrl":"https://doi.org/10.13104/imri.2021.25.4.338","url":null,"abstract":"Case Report Solitary fibrous tumors (SFT) are rare mesenchymal tumors that most commonly develop in the pleura; they rarely involve the diaphragm. MRI has not been widely used to evaluate SFTs of the thoracic cavity, though it may be highly useful in assessing local invasion, predicting malignant potential, and helping in the differential diagnosis. However, MRI findings of malignant SFTs of the diaphragmatic pleura have been described in only two cases. We report a rare case of a malignant solitary fibrous tumor of the diaphragmatic pleura in an 82-year-old man. We describe the clinical and characteristic imaging features, including computed tomography, conventional MRI, and diffusion-weighted imaging. Contrast-enhanced MRI is more accurate than is CT in identifying the origin of SFTs, predicting whether they ae benign or malignant, and assessing local invasion. This imaging modality proved helpful in deciding on the treatment strategy for these rare tumors.","PeriodicalId":73505,"journal":{"name":"Investigative magnetic resonance imaging","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66633408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.13104/imri.2021.25.4.323
Sukjoon Lim, Nam Hyeok Kim, Hyo-Sung Kwak, S. Hwang, G. Chung
Purpose: To investigate the diagnostic criteria of T1-weighted imaging (T1W) and time-of-flight (TOF) imaging for detecting intraplaque hemorrhage (IPH) of a vertebrobasilar artery (VBA) compared with simultaneous non-contrast angiography and intraplaque hemorrhage (SNAP) imaging. Materials and Methods: Eighty-seven patients with VBA atherosclerosis who underwent high resolution MR imaging for evaluation of VBA plaque were reviewed. The presence and location of VBA plaque and IPH on SNAP were determined. The signal intensity (SI) of the VBA plaque on T1W and TOF imaging was manually measured and the SI ratio against adjacent muscles was calculated. The receiveroperating characteristic (ROC) curve was used to compare the diagnostic accuracy for detecting VBA IPH. Results: Of 87 patients, 67 had IPH and 20 had no IPH on SNAP. The SI ratio between VBA IPH and temporalis muscle on T1W was significantly higher than that in the noIPH group (235.9 ± 16.8 vs. 120.0 ± 5.1, P < 0.001). The SI ratio between IPH and temporalis muscle on TOF was also significantly higher than that in the no-IPH group (236.8 ± 13.3 vs. 112.8 ± 7.4, P < 0.001). Diagnostic efficacies of SI ratios on TOF and TIW were excellent (AUC: 0.976 on TOF and 0.964 on T1W; cutoff value: 136.7% for TOF imaging and 135.1% for T1W imaging). Conclusion: Compared with SNAP, cutoff levels of the SI ratio between VBA plaque and temporalis muscle on T1W and TOF imaging for detecting IPH were approximately 1.35 times.
{"title":"Diagnostic Criteria of T1-Weighted Imaging for Detecting Intraplaque Hemorrhage of Vertebrobasilar Artery Based on Simultaneous Non-Contrast Angiography and Intraplaque Hemorrhage Imaging","authors":"Sukjoon Lim, Nam Hyeok Kim, Hyo-Sung Kwak, S. Hwang, G. Chung","doi":"10.13104/imri.2021.25.4.323","DOIUrl":"https://doi.org/10.13104/imri.2021.25.4.323","url":null,"abstract":"Purpose: To investigate the diagnostic criteria of T1-weighted imaging (T1W) and time-of-flight (TOF) imaging for detecting intraplaque hemorrhage (IPH) of a vertebrobasilar artery (VBA) compared with simultaneous non-contrast angiography and intraplaque hemorrhage (SNAP) imaging. Materials and Methods: Eighty-seven patients with VBA atherosclerosis who underwent high resolution MR imaging for evaluation of VBA plaque were reviewed. The presence and location of VBA plaque and IPH on SNAP were determined. The signal intensity (SI) of the VBA plaque on T1W and TOF imaging was manually measured and the SI ratio against adjacent muscles was calculated. The receiveroperating characteristic (ROC) curve was used to compare the diagnostic accuracy for detecting VBA IPH. Results: Of 87 patients, 67 had IPH and 20 had no IPH on SNAP. The SI ratio between VBA IPH and temporalis muscle on T1W was significantly higher than that in the noIPH group (235.9 ± 16.8 vs. 120.0 ± 5.1, P < 0.001). The SI ratio between IPH and temporalis muscle on TOF was also significantly higher than that in the no-IPH group (236.8 ± 13.3 vs. 112.8 ± 7.4, P < 0.001). Diagnostic efficacies of SI ratios on TOF and TIW were excellent (AUC: 0.976 on TOF and 0.964 on T1W; cutoff value: 136.7% for TOF imaging and 135.1% for T1W imaging). Conclusion: Compared with SNAP, cutoff levels of the SI ratio between VBA plaque and temporalis muscle on T1W and TOF imaging for detecting IPH were approximately 1.35 times.","PeriodicalId":73505,"journal":{"name":"Investigative magnetic resonance imaging","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66633663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.13104/imri.2021.25.4.281
Ji Ye Lee, Hye Min Park, Boeun Lee, Ji-hoon Kim
{"title":"Cranial Nerve Disorders: Clinical Application of High-Resolution Magnetic Resonance Imaging Techniques","authors":"Ji Ye Lee, Hye Min Park, Boeun Lee, Ji-hoon Kim","doi":"10.13104/imri.2021.25.4.281","DOIUrl":"https://doi.org/10.13104/imri.2021.25.4.281","url":null,"abstract":"","PeriodicalId":73505,"journal":{"name":"Investigative magnetic resonance imaging","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66632920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.13104/imri.2021.25.4.266
Y. Park, Narae Lee, S. Ahn, Jong-Hee Chang, Seung-Koo Lee
Advances in radiomics and deep learning (DL) hold great potential to be at the forefront of precision medicine for the treatment of patients with brain metastases. Radiomics and DL can aid clinical decision-making by enabling accurate diagnosis, facilitating the identification of molecular markers, providing accurate prognoses, and monitoring treatment response. In this review, we summarize the clinical background, unmet needs, and current state of research of radiomics and DL for the treatment of brain metastases. The promises, pitfalls, and future roadmap of radiomics and DL in brain metastases are addressed as well.
{"title":"Radiomics and Deep Learning in Brain Metastases: Current Trends and Roadmap to Future Applications","authors":"Y. Park, Narae Lee, S. Ahn, Jong-Hee Chang, Seung-Koo Lee","doi":"10.13104/imri.2021.25.4.266","DOIUrl":"https://doi.org/10.13104/imri.2021.25.4.266","url":null,"abstract":"Advances in radiomics and deep learning (DL) hold great potential to be at the forefront of precision medicine for the treatment of patients with brain metastases. Radiomics and DL can aid clinical decision-making by enabling accurate diagnosis, facilitating the identification of molecular markers, providing accurate prognoses, and monitoring treatment response. In this review, we summarize the clinical background, unmet needs, and current state of research of radiomics and DL for the treatment of brain metastases. The promises, pitfalls, and future roadmap of radiomics and DL in brain metastases are addressed as well.","PeriodicalId":73505,"journal":{"name":"Investigative magnetic resonance imaging","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66633307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.13104/imri.2021.25.4.332
E. Choi, Min Sun Kim, H. Koo, Jae-Kwan Song, Joon Seon Song, Joon-Won Kang, D. Yang
or pathological findings diagnostic of Behçet’s disease. Cardiac involvement is rare but might present as endocarditis, myocarditis, pericarditis, or intracardiac thrombosis. This report presents a case of Behçet’s disease involving the heart in a 22-year-old man with unusual manifestations of right ventricular fibrosis and intracardiac thrombosis. Cardiac magnetic resonance imaging revealed multiple intracardiac thrombi and delayed diffuse subendocardial enhancement involving the right ventricle. No peripheral eosinophilia was detected. Endomyocardial biopsy showed mixed inflammatory cell infiltrates. Based on the patient’s clinical history of oral ulcer and arthritis, a diagnosis of Behçet’s disease was made considering the clinical, radiological, and histological findings. Intracardiac thrombi and endomyocardial fibrosis are rare manifestations of Behçet’s disease, and the diagnosis is often a clinical challenge. Early diagnosis is important for appropriate management. Behçet’s disease should be considered in the differential diagnosis of patients with intracardiac thrombosis and endomyocardial fibrosis of the right chamber.
{"title":"Cardiac Behçet's Disease Presenting with Right Ventricular Endomyocardial Fibrosis and Intracardiac Thrombosis: a Case Report","authors":"E. Choi, Min Sun Kim, H. Koo, Jae-Kwan Song, Joon Seon Song, Joon-Won Kang, D. Yang","doi":"10.13104/imri.2021.25.4.332","DOIUrl":"https://doi.org/10.13104/imri.2021.25.4.332","url":null,"abstract":"or pathological findings diagnostic of Behçet’s disease. Cardiac involvement is rare but might present as endocarditis, myocarditis, pericarditis, or intracardiac thrombosis. This report presents a case of Behçet’s disease involving the heart in a 22-year-old man with unusual manifestations of right ventricular fibrosis and intracardiac thrombosis. Cardiac magnetic resonance imaging revealed multiple intracardiac thrombi and delayed diffuse subendocardial enhancement involving the right ventricle. No peripheral eosinophilia was detected. Endomyocardial biopsy showed mixed inflammatory cell infiltrates. Based on the patient’s clinical history of oral ulcer and arthritis, a diagnosis of Behçet’s disease was made considering the clinical, radiological, and histological findings. Intracardiac thrombi and endomyocardial fibrosis are rare manifestations of Behçet’s disease, and the diagnosis is often a clinical challenge. Early diagnosis is important for appropriate management. Behçet’s disease should be considered in the differential diagnosis of patients with intracardiac thrombosis and endomyocardial fibrosis of the right chamber.","PeriodicalId":73505,"journal":{"name":"Investigative magnetic resonance imaging","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66633801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.13104/imri.2021.25.4.300
Jing Cheng, Yuanyuan Liu, Yanjie Zhu, Dong Liang
magnetic resonance (MR) parametric mapping to reduce scan time. However, the relatively long reconstruction time restricts its widespread applications in the clinic. Recently, deep learning-based methods have shown great potential in accelerating reconstruction time and improving imaging quality in fast MR imaging, although their adaptation to parametric mapping is still in an early stage. In this paper, we proposed a novel deep learning-based framework DEMO for fast and robust MR parametric mapping. Different from current deep learning-based methods, DEMO trains the network in an unsupervised way, which is more practical given that it is difficult to acquire large fully sampled training data of parametric-weighted images. Specifically, a CS-based loss function is used in DEMO to avoid the necessity of using fully sampled k-space data as the label, thus making it an unsupervised learning approach. DEMO reconstructs parametric weighted images and generates a parametric map simultaneously by unrolling an interaction approach in conventional fast MR parametric mapping, which enables multi-tasking learning. Experimental results showed promising performance of the proposed DEMO framework in quantitative MR T1 ρ mapping.
{"title":"DEMO: Deep MR Parametric Mapping with Unsupervised Multi-Tasking Framework","authors":"Jing Cheng, Yuanyuan Liu, Yanjie Zhu, Dong Liang","doi":"10.13104/imri.2021.25.4.300","DOIUrl":"https://doi.org/10.13104/imri.2021.25.4.300","url":null,"abstract":"magnetic resonance (MR) parametric mapping to reduce scan time. However, the relatively long reconstruction time restricts its widespread applications in the clinic. Recently, deep learning-based methods have shown great potential in accelerating reconstruction time and improving imaging quality in fast MR imaging, although their adaptation to parametric mapping is still in an early stage. In this paper, we proposed a novel deep learning-based framework DEMO for fast and robust MR parametric mapping. Different from current deep learning-based methods, DEMO trains the network in an unsupervised way, which is more practical given that it is difficult to acquire large fully sampled training data of parametric-weighted images. Specifically, a CS-based loss function is used in DEMO to avoid the necessity of using fully sampled k-space data as the label, thus making it an unsupervised learning approach. DEMO reconstructs parametric weighted images and generates a parametric map simultaneously by unrolling an interaction approach in conventional fast MR parametric mapping, which enables multi-tasking learning. Experimental results showed promising performance of the proposed DEMO framework in quantitative MR T1 ρ mapping.","PeriodicalId":73505,"journal":{"name":"Investigative magnetic resonance imaging","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66633454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.13104/imri.2021.25.4.209
T. Shin
{"title":"Principles of Magnetic Resonance Angiography Techniques","authors":"T. Shin","doi":"10.13104/imri.2021.25.4.209","DOIUrl":"https://doi.org/10.13104/imri.2021.25.4.209","url":null,"abstract":"","PeriodicalId":73505,"journal":{"name":"Investigative magnetic resonance imaging","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"66632951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-01DOI: 10.13104/IMRI.2020.24.4.207
Jieun Lee, J. Choi, Dongmyung Shin, E. Kim, S. Oh, Jongho Lee
Purpose: To understand the effects of datasets with various parameters on pre-trained 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 T 2 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 T 2 characteristics. Conclusion: This study proposes information about the generalization accuracy of a trained network when applying deep learning to processing myelin water imaging.
{"title":"Exploring Generalization Capacity of Artificial Neural Network for Myelin Water Imaging","authors":"Jieun Lee, J. Choi, Dongmyung Shin, E. Kim, S. Oh, Jongho Lee","doi":"10.13104/IMRI.2020.24.4.207","DOIUrl":"https://doi.org/10.13104/IMRI.2020.24.4.207","url":null,"abstract":"Purpose: To understand the effects of datasets with various parameters on pre-trained 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 T 2 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 T 2 characteristics. Conclusion: This study proposes information about the generalization accuracy of a trained network when applying deep learning to processing myelin water imaging.","PeriodicalId":73505,"journal":{"name":"Investigative magnetic resonance imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45362528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：