1
|
Sirucek L, Zoelch N, Schweinhardt P. Improving magnetic resonance spectroscopy in the brainstem periaqueductal gray using spectral registration. Magn Reson Med 2024; 91:28-38. [PMID: 37800387 DOI: 10.1002/mrm.29832] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2023] [Revised: 07/08/2023] [Accepted: 07/31/2023] [Indexed: 10/07/2023]
Abstract
PURPOSE Functional understanding of the periaqueductal gray (PAG), a clinically relevant brainstem region, can be advanced using 1 H-MRS. However, the PAG's small size and high levels of physiological noise are methodologically challenging. This study aimed to (1) improve 1 H-MRS quality in the PAG using spectral registration for frequency and phase error correction; (2) investigate whether spectral registration is particularly useful in cases of greater head motion; and (3) examine metabolite quantification using literature-based or individual-based water relaxation times. METHODS Spectra were acquired in 33 healthy volunteers (50.1 years, SD = 17.19, 18 females) on a 3 T Philipps MR system using a point-resolved spectroscopy (PRESS) sequence optimized with very selective saturation pulses (OVERPRESS) and voxel-based flip angle calibration (effective volume of interest size: 8.8 × 10.2 × 12.2 mm3 ). Spectra were fitted using LCModel and SNR, NAA peak linewidths and Cramér-Rao lower bounds (CRLBs) were measured after spectral registration and after minimal frequency alignment. RESULTS Spectral registration improved SNR by 5% (p = 0.026, median value post-correction: 18.0) and spectral linewidth by 23% (p < 0.001, 4.3 Hz), and reduced the metabolites' CRLBs by 1% to 15% (p < 0.026). Correlational analyses revealed smaller SNR improvements with greater head motion (p = 0.010) recorded using a markerless motion tracking system. Higher metabolite concentrations were detected using individual-based compared to literature-based water relaxation times (p < 0.001). CONCLUSION This study demonstrates high-quality 1 H-MRS acquisition in the PAG using spectral registration. This shows promise for future 1 H-MRS studies in the PAG and possibly other clinically relevant brain regions with similar methodological challenges.
Collapse
Affiliation(s)
- Laura Sirucek
- Department of Chiropractic Medicine, Integrative Spinal Research Group, Balgrist University Hospital, University of Zurich, Zurich, Switzerland
- Neuroscience Center Zurich, University of Zurich, Zurich, Switzerland
| | - Niklaus Zoelch
- Department of Forensic Medicine and Imaging, Institute of Forensic Medicine, University of Zurich, Zurich, Switzerland
- Department of Psychiatry, Psychotherapy, and Psychosomatics, Psychiatric University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Petra Schweinhardt
- Department of Chiropractic Medicine, Integrative Spinal Research Group, Balgrist University Hospital, University of Zurich, Zurich, Switzerland
- Neuroscience Center Zurich, University of Zurich, Zurich, Switzerland
| |
Collapse
|
2
|
Roy A, Reich BJ, Guinness J, Shinohara RT, Staicu AM. Spatial Shrinkage Via the Product Independent Gaussian Process Prior. J Comput Graph Stat 2021. [DOI: 10.1080/10618600.2021.1923512] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
Affiliation(s)
- Arkaprava Roy
- Department of Biostatistics, University of Florida, Gainesville, FL
| | - Brian J. Reich
- Department of Statistics, North Carolina State University, Raleigh, NC
| | - Joseph Guinness
- Department of Statistics and Data Science, Cornell University, Ithaca, NY
| | | | - Ana-Maria Staicu
- Department of Statistics, North Carolina State University, Raleigh, NC
| |
Collapse
|
3
|
Hu M, Schindler MK, Dewey BE, Reich DS, Shinohara RT, Eloyan A. Experimental design and sample size considerations in longitudinal magnetic resonance imaging-based biomarker detection for multiple sclerosis. Stat Methods Med Res 2020; 29:2617-2628. [PMID: 32070238 PMCID: PMC8244615 DOI: 10.1177/0962280220904392] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Several modeling approaches have been developed to quantify differences in multiple sclerosis lesion evolution on magnetic resonance imaging to identify the effect of treatment on disease progression. These studies have limited clinical applicability due to onerous scan frequency and lengthy study duration. Efficient methods are needed to reduce the required sample size, study duration, and sampling frequency in longitudinal magnetic resonance imaging studies. We develop a data-driven approach to identify parameters of study design for evaluation of longitudinal magnetic resonance imaging biomarkers of multiple sclerosis lesion evolution. Our design strategies are considerably shorter than those described in previous studies, thus having the potential to lower costs of clinical trials. From a dataset of 36 multiple sclerosis patients with at least six monthly magnetic resonance imagings, we extracted new lesions and performed principal component analysis to estimate a biomarker that recapitulated lesion recovery. We tested the effect of multiple sclerosis disease modifying therapy on the lesion evolution index in three experimental designs and calculated sample sizes needed to appropriately power studies. Our proposed methods can be used to calculate required sample size and scan frequency in observational studies of multiple sclerosis disease progression as well as in designing clinical trials to find effects of treatment on multiple sclerosis lesion evolution.
Collapse
Affiliation(s)
- Menghan Hu
- Department of Biostatistics, Brown University School of Public Health, Providence, RI 02903, USA
| | - Matthew K. Schindler
- Translational Neuroradiology Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD 20892, USA
| | - Blake E. Dewey
- Translational Neuroradiology Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD 20892, USA
- Department of Electrical and Computer Engineering, Johns Hopkins Whiting School of Engineering, Baltimore, MD 21205, USA
| | - Daniel S. Reich
- Translational Neuroradiology Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD 20892, USA
- Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD 21205, USA
| | - Russell T. Shinohara
- Penn Statistics in Imaging and Visualization Center, Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, USA
| | - Ani Eloyan
- Department of Biostatistics, Brown University School of Public Health, Providence, RI 02903, USA
| |
Collapse
|
4
|
Deep learning segmentation of orbital fat to calibrate conventional MRI for longitudinal studies. Neuroimage 2020; 208:116442. [DOI: 10.1016/j.neuroimage.2019.116442] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2018] [Revised: 11/04/2019] [Accepted: 12/03/2019] [Indexed: 01/21/2023] Open
|
5
|
Hazra A, Reich BJ, Reich DS, Shinohara RT, Staicu AM. A Spatio-Temporal Model for Longitudinal Image-on-Image Regression. STATISTICS IN BIOSCIENCES 2019; 11:22-46. [PMID: 31156722 PMCID: PMC6537615] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
Neurologists and radiologists often use magnetic resonance imaging (MRI) in the management of subjects with multiple sclerosis (MS) because it is sensitive to inflammatory and demyelinative changes in the white matter of the brain and spinal cord. Two conventional modalities used for identifying lesions are T1-weighted (T1) and T2-weighted fluid-attenuated inversion recovery (FLAIR) imaging, which are used clinically and in research studies. Magnetization transfer ratio (MTR), which is available only in research settings, is an advanced MRI modality that has been used extensively for measuring disease-related demyelination both in white matter lesions as well across normal-appearing white matter. Acquiring MTR is not standard in clinical practice, due to the increased scan time and cost. Hence, prediction of MTR based on the modalities T1 and FLAIR could have great impact on the availability of these promising measures for improved patient management. We propose a spatio-temporal regression model for image response and image predictors that are acquired longitudinally, with images being co-registered within the subject but not across subjects. The model is additive, with the response at a voxel being dependent on the available covariates not only through the current voxel but also on the imaging information from the voxels within a neighboring spatial region as well as their temporal gradients. We propose a dynamic Bayesian estimation procedure that updates the parameters of the subject-specific regression model as data accummulates. To bypass the computational challenges associated with a Bayesian approach for high-dimensional imaging data, we propose an approximate Bayesian inference technique. We assess the model fitting and the prediction performance using longitudinally acquired MRI images from 46 MS patients.
Collapse
Affiliation(s)
- Arnab Hazra
- North Carolina State University, Raleigh, NC, USA
| | | | - Daniel S Reich
- National Institute of Neurological Disorders and Stroke, Bethesda, MD, USA
| | | | | |
Collapse
|
6
|
McPhee KC, Wilman AH. T
1
and T
2
quantification from standard turbo spin echo images. Magn Reson Med 2018; 81:2052-2063. [DOI: 10.1002/mrm.27495] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2018] [Revised: 07/10/2018] [Accepted: 07/23/2018] [Indexed: 11/10/2022]
Affiliation(s)
- Kelly C. McPhee
- Department of Physics University of Alberta Edmonton Alberta Canada
- Department of Biomedical Engineering University of Alberta Edmonton Alberta Canada
| | - Alan H. Wilman
- Department of Physics University of Alberta Edmonton Alberta Canada
- Department of Biomedical Engineering University of Alberta Edmonton Alberta Canada
| |
Collapse
|
7
|
Valcarcel AM, Linn KA, Vandekar SN, Satterthwaite TD, Muschelli J, Calabresi PA, Pham DL, Martin ML, Shinohara RT. MIMoSA: An Automated Method for Intermodal Segmentation Analysis of Multiple Sclerosis Brain Lesions. J Neuroimaging 2018. [PMID: 29516669 DOI: 10.1111/jon.12506] [Citation(s) in RCA: 29] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/17/2023] Open
Abstract
BACKGROUND AND PURPOSE Magnetic resonance imaging (MRI) is crucial for in vivo detection and characterization of white matter lesions (WMLs) in multiple sclerosis. While WMLs have been studied for over two decades using MRI, automated segmentation remains challenging. Although the majority of statistical techniques for the automated segmentation of WMLs are based on single imaging modalities, recent advances have used multimodal techniques for identifying WMLs. Complementary modalities emphasize different tissue properties, which help identify interrelated features of lesions. METHODS Method for Inter-Modal Segmentation Analysis (MIMoSA), a fully automatic lesion segmentation algorithm that utilizes novel covariance features from intermodal coupling regression in addition to mean structure to model the probability lesion is contained in each voxel, is proposed. MIMoSA was validated by comparison with both expert manual and other automated segmentation methods in two datasets. The first included 98 subjects imaged at Johns Hopkins Hospital in which bootstrap cross-validation was used to compare the performance of MIMoSA against OASIS and LesionTOADS, two popular automatic segmentation approaches. For a secondary validation, a publicly available data from a segmentation challenge were used for performance benchmarking. RESULTS In the Johns Hopkins study, MIMoSA yielded average Sørensen-Dice coefficient (DSC) of .57 and partial AUC of .68 calculated with false positive rates up to 1%. This was superior to performance using OASIS and LesionTOADS. The proposed method also performed competitively in the segmentation challenge dataset. CONCLUSION MIMoSA resulted in statistically significant improvements in lesion segmentation performance compared with LesionTOADS and OASIS, and performed competitively in an additional validation study.
Collapse
Affiliation(s)
- Alessandra M Valcarcel
- Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
| | - Kristin A Linn
- Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
| | - Simon N Vandekar
- Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
| | - Theodore D Satterthwaite
- Department of Psychiatry, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
| | - John Muschelli
- Department of Biostatistics, The Johns Hopkins University Bloomberg School of Public Health, Baltimore, MD
| | - Peter A Calabresi
- Department of Neurology, The Johns Hopkins University School of Medicine, Baltimore, MD
| | - Dzung L Pham
- Henry M. Jackson Foundation for the Advancement of Military Medicine, Bethesda, MD
| | - Melissa Lynne Martin
- Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
| | - Russell T Shinohara
- Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA
| |
Collapse
|
8
|
Fleishman GM, Valcarcel A, Pham DL, Roy S, Calabresi PA, Yushkevich P, Shinohara RT, Oguz I. Joint Intensity Fusion Image Synthesis Applied to Multiple Sclerosis Lesion Segmentation. BRAINLESION : GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES. BRAINLES (WORKSHOP) 2018; 10670:43-54. [PMID: 29714357 PMCID: PMC5920684] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
We propose a new approach to Multiple Sclerosis lesion segmentation that utilizes synthesized images. A new method of image synthesis is considered: joint intensity fusion (JIF). JIF synthesizes an image from a library of deformably registered and intensity normalized atlases. Each location in the synthesized image is a weighted average of the registered atlases; atlas weights vary spatially. The weights are determined using the joint label fusion (JLF) framework. The primary methodological contribution is the application of JLF to MRI signal directly rather than labels. Synthesized images are then used as additional features in a lesion segmentation task using the OASIS classifier, a logistic regression model on intensities from multiple modalities. The addition of JIF synthesized images improved the Dice-Sorensen coefficient (relative to manually drawn gold standards) of lesion segmentations over the standard model segmentations by 0.0462 ± 0.0050 (mean ± standard deviation) at optimal threshold over all subjects and 10 separate training/testing folds.
Collapse
Affiliation(s)
- Greg M Fleishman
- Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Alessandra Valcarcel
- Department of Biostatistics and Epidemiology, University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Dzung L Pham
- CNRM, The Henry M. Jackson Foundation for the Advancement of Military Medicine, Bethesda, MD 20817, USA
| | - Snehashis Roy
- CNRM, The Henry M. Jackson Foundation for the Advancement of Military Medicine, Bethesda, MD 20817, USA
| | - Peter A Calabresi
- Department of Neurology, The Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA
| | - Paul Yushkevich
- Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Russell T Shinohara
- Department of Biostatistics and Epidemiology, University of Pennsylvania, Philadelphia, PA 19104, USA
| | - Ipek Oguz
- Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA
| |
Collapse
|
9
|
Hazra A, Reich BJ, Reich DS, Shinohara RT, Staicu AM. A Spatio-Temporal Model for Longitudinal Image-on-Image Regression. STATISTICS IN BIOSCIENCES 2017. [DOI: 10.1007/s12561-017-9206-z] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/31/2022]
|
10
|
Pomann GM, Staicu AM, Lobaton EJ, Mejia AF, Dewey BE, Reich DS, Sweeney EM, Shinohara RT. A LAG FUNCTIONAL LINEAR MODEL FOR PREDICTION OF MAGNETIZATION TRANSFER RATIO IN MULTIPLE SCLEROSIS LESIONS. Ann Appl Stat 2016; 10:2325-2348. [PMID: 35791328 PMCID: PMC9252322 DOI: 10.1214/16-aoas981] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/14/2023]
Abstract
We propose a lag functional linear model to predict a response using multiple functional predictors observed at discrete grids with noise. Two procedures are proposed to estimate the regression parameter functions: (1) an approach that ensures smoothness for each value of time using generalized cross-validation; and (2) a global smoothing approach using a restricted maximum likelihood framework. Numerical studies are presented to analyze predictive accuracy in many realistic scenarios. The methods are employed to estimate a magnetic resonance imaging (MRI)-based measure of tissue damage (the magnetization transfer ratio, or MTR) in multiple sclerosis (MS) lesions, a disease that causes damage to the myelin sheaths around axons in the central nervous system. Our method of estimation of MTR within lesions is useful retrospectively in research applications where MTR was not acquired, as well as in clinical practice settings where acquiring MTR is not currently part of the standard of care. The model facilitates the use of commonly acquired imaging modalities to estimate MTR within lesions, and outperforms cross-sectional models that do not account for temporal patterns of lesion development and repair.
Collapse
Affiliation(s)
- Gina-Maria Pomann
- Department of Biostatistics and Bioinformatics, Duke University, Durham, North Carolina 27710, USA
| | - Ana-Maria Staicu
- Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695, USA
| | - Edgar J Lobaton
- Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, North Carolina 27695, USA
| | - Amanda F Mejia
- Department of Statistics, Indiana University Bloomington, Bloomington, Indiana 47405, USA
| | - Blake E Dewey
- National Institute of Neurological Disorders and Stroke NIH, Bethesda, Maryland 20892, USA
| | - Daniel S Reich
- National Institute of Neurological Disorders and Stroke NIH, Bethesda, Maryland 20892, USA
| | | | - Russell T Shinohara
- Department of Biostatistics and Epidemiology, Center for Clinical Epidemiology and Biostatisti Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania 19104, USA
| |
Collapse
|
11
|
Suttner LH, Mejia A, Dewey B, Sati P, Reich DS, Shinohara RT. Statistical estimation of white matter microstructure from conventional MRI. Neuroimage Clin 2016; 12:615-623. [PMID: 27722085 PMCID: PMC5048084 DOI: 10.1016/j.nicl.2016.09.010] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2016] [Revised: 08/29/2016] [Accepted: 09/10/2016] [Indexed: 12/11/2022]
Abstract
Diffusion tensor imaging (DTI) has become the predominant modality for studying white matter integrity in multiple sclerosis (MS) and other neurological disorders. Unfortunately, the use of DTI-based biomarkers in large multi-center studies is hindered by systematic biases that confound the study of disease-related changes. Furthermore, the site-to-site variability in multi-center studies is significantly higher for DTI than that for conventional MRI-based markers. In our study, we apply the Quantitative MR Estimation Employing Normalization (QuEEN) model to estimate the four DTI measures: MD, FA, RD, and AD. QuEEN uses a voxel-wise generalized additive regression model to relate the normalized intensities of one or more conventional MRI modalities to a quantitative modality, such as DTI. We assess the accuracy of the models by comparing the prediction error of estimated DTI images to the scan-rescan error in subjects with two sets of scans. Across the four DTI measures, the performance of the models is not consistent: Both MD and RD estimations appear to be quite accurate, while AD estimation is less accurate than MD and RD; the accuracy of FA estimation is poor. Thus, in some cases when assessing white matter integrity, it may be sufficient to acquire conventional MRI sequences alone.
Collapse
Affiliation(s)
- Leah H Suttner
- Department of Biostatistics and Epidemiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, United States
| | - Amanda Mejia
- Department of Biostatistics, The Johns Hopkins University, Baltimore, MD 21205, United States
| | - Blake Dewey
- Translational Neuroradiology Unit, Division of Neuroimmunology and Neurovirology, National Institute of Neurological Disease and Stroke, National Institute of Health, Bethesda, MD 20892, United States
| | - Pascal Sati
- Translational Neuroradiology Unit, Division of Neuroimmunology and Neurovirology, National Institute of Neurological Disease and Stroke, National Institute of Health, Bethesda, MD 20892, United States
| | - Daniel S Reich
- Department of Biostatistics, The Johns Hopkins University, Baltimore, MD 21205, United States
- Translational Neuroradiology Unit, Division of Neuroimmunology and Neurovirology, National Institute of Neurological Disease and Stroke, National Institute of Health, Bethesda, MD 20892, United States
| | - Russell T Shinohara
- Department of Biostatistics and Epidemiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, United States
| |
Collapse
|
12
|
Dworkin JD, Sweeney EM, Schindler MK, Chahin S, Reich DS, Shinohara RT. PREVAIL: Predicting Recovery through Estimation and Visualization of Active and Incident Lesions. NEUROIMAGE-CLINICAL 2016; 12:293-9. [PMID: 27551666 PMCID: PMC4983640 DOI: 10.1016/j.nicl.2016.07.015] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/24/2016] [Revised: 07/21/2016] [Accepted: 07/30/2016] [Indexed: 12/02/2022]
Abstract
Objective The goal of this study was to develop a model that integrates imaging and clinical information observed at lesion incidence for predicting the recovery of white matter lesions in multiple sclerosis (MS) patients. Methods Demographic, clinical, and magnetic resonance imaging (MRI) data were obtained from 60 subjects with MS as part of a natural history study at the National Institute of Neurological Disorders and Stroke. A total of 401 lesions met the inclusion criteria and were used in the study. Imaging features were extracted from the intensity-normalized T1-weighted (T1w) and T2-weighted sequences as well as magnetization transfer ratio (MTR) sequence acquired at lesion incidence. T1w and MTR signatures were also extracted from images acquired one-year post-incidence. Imaging features were integrated with clinical and demographic data observed at lesion incidence to create statistical prediction models for long-term damage within the lesion. Validation The performance of the T1w and MTR predictions was assessed in two ways: first, the predictive accuracy was measured quantitatively using leave-one-lesion-out cross-validated (CV) mean-squared predictive error. Then, to assess the prediction performance from the perspective of expert clinicians, three board-certified MS clinicians were asked to individually score how similar the CV model-predicted one-year appearance was to the true one-year appearance for a random sample of 100 lesions. Results The cross-validated root-mean-square predictive error was 0.95 for normalized T1w and 0.064 for MTR, compared to the estimated measurement errors of 0.48 and 0.078 respectively. The three expert raters agreed that T1w and MTR predictions closely resembled the true one-year follow-up appearance of the lesions in both degree and pattern of recovery within lesions. Conclusion This study demonstrates that by using only information from a single visit at incidence, we can predict how a new lesion will recover using relatively simple statistical techniques. The potential to visualize the likely course of recovery has implications for clinical decision-making, as well as trial enrichment. A model for predicting degree and pattern of MS lesion tissue recovery is proposed. The model relies solely on MR images at lesion incidence and patient information. Predictions performed well when rated for accuracy by expert MS clinicians.
Collapse
Affiliation(s)
- Jordan D Dworkin
- Department of Biostatistics and Epidemiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, United States
| | - Elizabeth M Sweeney
- Department of Biostatistics, The Johns Hopkins University Bloomberg School of Public Health, Baltimore, MD 21205, United States
| | - Matthew K Schindler
- Translational Neuroradiology Unit, Division of Neuroimmunology and Neurovirology, National Institute of Neurological Disease and Stroke, National Institute of Health, Bethesda, MD 20892, United States
| | - Salim Chahin
- Multiple Sclerosis Division of the Department of Neurology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, United States
| | - Daniel S Reich
- Department of Biostatistics, The Johns Hopkins University Bloomberg School of Public Health, Baltimore, MD 21205, United States; Translational Neuroradiology Unit, Division of Neuroimmunology and Neurovirology, National Institute of Neurological Disease and Stroke, National Institute of Health, Bethesda, MD 20892, United States
| | - Russell T Shinohara
- Department of Biostatistics and Epidemiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, United States
| |
Collapse
|