Publications by authors named "Jerry L Prince"

316 Publications

Autoencoder based self-supervised test-time adaptation for medical image analysis.

Med Image Anal 2021 08 19;72:102136. Epub 2021 Jun 19.

Dept. of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA.

Deep neural networks have been successfully applied to medical image analysis tasks like segmentation and synthesis. However, even if a network is trained on a large dataset from the source domain, its performance on unseen test domains is not guaranteed. The performance drop on data obtained differently from the network's training data is a major problem (known as domain shift) in deploying deep learning in clinical practice. Existing work focuses on retraining the model with data from the test domain, or harmonizing the test domain's data to the network training data. A common practice is to distribute a carefully-trained model to multiple users (e.g., clinical centers), and then each user uses the model to process their own data, which may have a domain shift (e.g., varying imaging parameters and machines). However, the lack of availability of the source training data and the cost of training a new model often prevents the use of known methods to solve user-specific domain shifts. Here, we ask whether we can design a model that, once distributed to users, can quickly adapt itself to each new site without expensive retraining or access to the source training data? In this paper, we propose a model that can adapt based on a single test subject during inference. The model consists of three parts, which are all neural networks: a task model (T) which performs the image analysis task like segmentation; a set of autoencoders (AEs); and a set of adaptors (As). The task model and autoencoders are trained on the source dataset and can be computationally expensive. In the deployment stage, the adaptors are trained to transform the test image and its features to minimize the domain shift as measured by the autoencoders' reconstruction loss. Only the adaptors are optimized during the testing stage with a single test subject thus is computationally efficient. The method was validated on both retinal optical coherence tomography (OCT) image segmentation and magnetic resonance imaging (MRI) T1-weighted to T2-weighted image synthesis. Our method, with its short optimization time for the adaptors (10 iterations on a single test subject) and its additional required disk space for the autoencoders (around 15 MB), can achieve significant performance improvement. Our code is publicly available at: https://github.com/YufanHe/self-domain-adapted-network.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2021.102136DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8316425PMC
August 2021

MR Imaging of Human Brain Mechanics In Vivo: New Measurements to Facilitate the Development of Computational Models of Brain Injury.

Ann Biomed Eng 2021 Jul 1. Epub 2021 Jul 1.

Department of Biomedical Engineering, University of Delaware, Newark, DE, USA.

Computational models of the brain and its biomechanical response to skull accelerations are important tools for understanding and predicting traumatic brain injuries (TBIs). However, most models have been developed using experimental data collected on animal models and cadaveric specimens, both of which differ from the living human brain. Here we describe efforts to noninvasively measure the biomechanical response of the human brain with MRI-at non-injurious strain levels-and generate data that can be used to develop, calibrate, and evaluate computational brain biomechanics models. Specifically, this paper reports on a project supported by the National Institute of Neurological Disorders and Stroke to comprehensively image brain anatomy and geometry, mechanical properties, and brain deformations that arise from impulsive and harmonic skull loadings. The outcome of this work will be a publicly available dataset ( http://www.nitrc.org/projects/bbir ) that includes measurements on both males and females across an age range from adolescence to older adulthood. This article describes the rationale and approach for this study, the data available, and how these data may be used to develop new computational models and augment existing approaches; it will serve as a reference to researchers interested in using these data.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s10439-021-02820-0DOI Listing
July 2021

A deep joint sparse non-negative matrix factorization framework for identifying the common and subject-specific functional units of tongue motion during speech.

Med Image Anal 2021 08 12;72:102131. Epub 2021 Jun 12.

Gordon Center for Medical Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA.

Intelligible speech is produced by creating varying internal local muscle groupings-i.e., functional units-that are generated in a systematic and coordinated manner. There are two major challenges in characterizing and analyzing functional units. First, due to the complex and convoluted nature of tongue structure and function, it is of great importance to develop a method that can accurately decode complex muscle coordination patterns during speech. Second, it is challenging to keep identified functional units across subjects comparable due to their substantial variability. In this work, to address these challenges, we develop a new deep learning framework to identify common and subject-specific functional units of tongue motion during speech. Our framework hinges on joint deep graph-regularized sparse non-negative matrix factorization (NMF) using motion quantities derived from displacements by tagged Magnetic Resonance Imaging. More specifically, we transform NMF with sparse and graph regularizations into modular architectures akin to deep neural networks by means of unfolding the Iterative Shrinkage-Thresholding Algorithm to learn interpretable building blocks and associated weighting map. We then apply spectral clustering to common and subject-specific weighting maps from which we jointly determine the common and subject-specific functional units. Experiments carried out with simulated datasets show that the proposed method achieved on par or better clustering performance over the comparison methods.Experiments carried out with in vivo tongue motion data show that the proposed method can determine the common and subject-specific functional units with increased interpretability and decreased size variability.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2021.102131DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8316408PMC
August 2021

Group characterization of impact-induced, human brain kinematics.

J R Soc Interface 2021 06 23;18(179):20210251. Epub 2021 Jun 23.

Center for Neuroscience and Regenerative Medicine, Henry M Jackson Foundation for the Advancement of Military Medicine Inc, Bethesda, MD, USA.

Brain movement during an impact can elicit a traumatic brain injury, but tissue kinematics vary from person to person and knowledge regarding this variability is limited. This study examines spatio-temporal brain-skull displacement and brain tissue deformation across groups of subjects during a mild impact . The heads of two groups of participants were imaged while subjected to a mild (less than 350 rad s) impact during neck extension (NE, = 10) and neck rotation (NR, = 9). A kinematic atlas of displacement and strain fields averaged across all participants was constructed and compared against individual participant data. The atlas-derived mean displacement magnitude was 0.26 ± 0.13 mm for NE and 0.40 ± 0.26 mm for NR, which is comparable to the displacement magnitudes from individual participants. The strain tensor from the atlas displacement field exhibited maximum shear strain (MSS) of 0.011 ± 0.006 for NE and 0.017 ± 0.009 for NR and was lower than the individual MSS averaged across participants. The atlas illustrates common patterns, containing some blurring but visible relationships between anatomy and kinematics. Conversely, the direction of the impact, brain size, and fluid motion appear to underlie kinematic variability. These findings demonstrate the biomechanical roles of key anatomical features and illustrate common features of brain response for model evaluation.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1098/rsif.2021.0251DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8220272PMC
June 2021

Optic Neuritis-Independent Retinal Atrophy in Neuromyelitis Optica Spectrum Disorder.

J Neuroophthalmol 2021 May 17. Epub 2021 May 17.

Department of Neurology (AGF, ESV, KCF, GK, JL, MAM, EMM, SS, PAC, ESS), Johns Hopkins University School of Medicine, Baltimore, Maryland; Department of Electrical and Computer Engineering (YH, YL, JLP), Johns Hopkins University, Baltimore, Maryland; Viela Bio (MAM), Gaithersburg, Maryland; and Department of Neurology (ML), Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts.

Background: A limited number of studies have investigated the presence of ongoing disease activity independent of clinical relapses in neuromyelitis optica spectrum disorder (NMOSD), and data are conflicting. The objective of our study was to examine whether patients with aquaporin-4 (AQP4)-IgG seropositive NMOSD exhibit progressive retinal neuroaxonal loss, independently of optic neuritis (ON) attacks.

Methods: In this single-center, longitudinal study, 32 AQP4-IgG+ NMOSD patients and 48 healthy controls (HC) were followed with serial spectral-domain optical coherence tomography and visual acuity (VA) assessments. NMOSD patients with ON less than 6 months before baseline were excluded, whereas data from patients with ON during follow-up were censored at the last visit before ON. VA worsening was defined as a decrease in monocular letter acuity ≥5 letters for high-contrast VA and ≥7 letters for low-contrast VA. Analyses were performed with mixed-effects linear regression models adjusted for age, sex, and race.

Results: The median follow-up duration was 4.2 years (interquartile range: 1.8-7.5). Relative to HC, NMOSD eyes had faster peripapillary retinal nerve fiber layer (pRNFL) (β = -0.25 µm/year faster, 95% confidence interval [CI]: -0.45 to -0.05, P = 0.014) and GCIPL thinning (β = -0.09 µm/year faster, 95% CI: -0.17 to 0, P = 0.05). This difference seemed to be driven by faster pRNFL and GCIPL thinning in NMOSD eyes without a history of ON compared with HC (GCIPL: β = -0.15 µm/year faster; P = 0.005; pRNFL: β = -0.43 µm/year faster, P < 0.001), whereas rates of pRNFL (β: -0.07 µm/year, P = 0.53) and GCIPL (β = -0.01 µm/year, P = 0.90) thinning did not differ between NMOSD-ON and HC eyes. Nine NMOSD eyes had VA worsening during follow-up.

Conclusions: In this longitudinal study, we observed progressive pRNFL and GCIPL atrophy in AQP4-IgG+ NMOSD eyes unaffected by ON. These results support that subclinical involvement of the anterior visual pathway may occur in AQP4-IgG+ NMOSD.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1097/WNO.0000000000001282DOI Listing
May 2021

Floor-of-the-Mouth Muscle Function Analysis Using Dynamic Magnetic Resonance Imaging.

Proc SPIE Int Soc Opt Eng 2021 Feb 15;11596. Epub 2021 Feb 15.

Gordon Center for Medical Imaging, Department of Radiology, Massachusetts General Hospital/Harvard Medical School, Boston, MA, US 02114.

To advance our understanding of speech motor control, it is essential to image and assess dynamic functional patterns of internal structures caused by the complex muscle anatomy inside the human tongue. Speech pathologists are investigating into new tools that help assessment of internal tongue muscle's cooperative mechanics on top of their anatomical differences. Previous studies using dynamic magnetic resonance imaging (MRI) of the tongue revealed that tongue muscles tend to function in different groups during speech, especially the floor-of-the-mouth (FOM) muscles. In this work, we developed a method that analyzed the unique functional pattern of the FOM muscles in speech. First, four-dimensional motion fields of the whole tongue were computed using tagged MRI. Meanwhile, a statistical atlas of the tongue was constructed to form a common space for subject comparison, while a manually delineated mask of internal tongue muscles was used to separate individual muscle's motion. Then we computed four-dimensional motion correlation between each muscle and the FOM muscle group. Finally, dynamic correlation of different muscle groups was compared and evaluated. We used data from a study group of nineteen subjects including both healthy controls and oral cancer patients. Results revealed that most internal tongue muscles coordinated in a similar pattern in speech while the FOM muscles followed a unique pattern that helped supporting the tongue body and pivoting its rotation. The proposed method can help provide further interpretation of clinical observations and speech motor control from an imaging point of view.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1117/12.2581484DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8130842PMC
February 2021

In vivo estimates of axonal stretch and 3D brain deformation during mild head impact.

Brain Multiphys 2020 Nov 3;1. Epub 2020 Sep 3.

Center for Neuroscience and Regenerative Medicine, The Henry M. Jackson Foundation for the Advancement of Military Medicine, Bethesda, Maryland, USA.

The rapid deformation of brain tissue in response to head impact can lead to traumatic brain injury. In vivo measurements of brain deformation during non-injurious head impacts are necessary to understand the underlying mechanisms of traumatic brain injury and compare to computational models of brain biomechanics. Using tagged magnetic resonance imaging (MRI), we obtained measurements of three-dimensional strain tensors that resulted from a mild head impact after neck rotation or neck extension. Measurements of maximum principal strain (MPS) peaked shortly after impact, with maximal values of 0.019-0.053 that correlated strongly with peak angular velocity. Subject-specific patterns of MPS were spatially heterogeneous and consistent across subjects for the same motion, though regions of high deformation differed between motions. The largest MPS values were seen in the cortical gray matter and cerebral white matter for neck rotation and the brainstem and cerebellum for neck extension. Axonal fiber strain (Ef) was estimated by combining the strain tensor with diffusion tensor imaging data. As with MPS, patterns of Ef varied spatially within subjects, were similar across subjects within each motion, and showed group differences between motions. Values were highest and most strongly correlated with peak angular velocity in the corpus callosum for neck rotation and in the brainstem for neck extension. The different patterns of brain deformation between head motions highlight potential areas of greater risk of injury between motions at higher loading conditions. Additionally, these experimental measurements can be directly compared to predictions of generic or subject-specific computational models of traumatic brain injury.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.brain.2020.100015DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8049176PMC
November 2020

Modulation of Retinal Atrophy With Rituximab in Multiple Sclerosis.

Neurology 2021 05 7;96(20):e2525-e2533. Epub 2021 Apr 7.

From the Department of Neurology (J.L., H.R., A.G.F., O.C.M., E.S.S., H.E., E.O., N.P., B.T., N.J.L., S.D., N.F., O.K., P.A.C., K.C.F., S.S.), Johns Hopkins University School of Medicine; and Department of Electrical and Computer Engineering (J.L.P.), Johns Hopkins University, Baltimore, MD.

Objective: To investigate the effects of rituximab on retinal atrophy in patients with relapsing-remitting multiple sclerosis (RRMS), we performed serial optical coherence tomography (OCT) scans among a cohort of patients with RRMS on rituximab and compared rates of ganglion cell + inner plexiform layer (GCIPL) atrophy to those observed among age- and sex-matched glatiramer acetate (GA)-and natalizumab-treated patients with RRMS and healthy controls (HCs).

Methods: In this observational study, patients with RRMS treated with a single disease-modifying therapy and HCs were followed with serial OCT for a median duration of 2.8 years. Participants with uncontrolled hypertension, diabetes mellitus, or glaucoma, and eyes with optic neuritis ≤6 months prior to baseline OCT, or during follow-up, were excluded. Statistical analyses were performed using linear mixed-effects regression.

Results: During the overall follow-up period, rates of GCIPL atrophy were -0.28 ± 0.11 µm/y among rituximab-treated patients with RRMS (n = 35). This was similar to GA-treated (n = 49; -0.33 ± 0.05 µm/y; = 0.69) and natalizumab-treated patients (n = 88; -0.17 ± 0.10 µm/y; = 0.13) and faster than HCs (n = 78; -0.15 ± 0.03 µm/y; = 0.006). Rituximab-treated patients exhibited 0.55 ± 0.23 µm/y faster rates of GCIPL atrophy during the first 12 months of treatment, relative to afterwards (n = 25; = 0.02), during which period GCIPL atrophy rates were -0.14 ± 0.13 µm/y.

Conclusions: Retinal atrophy in RRMS is modulated by rituximab. Greater attenuation of retinal atrophy may occur after 12 months of rituximab treatment, following which time GCIPL atrophy rates are similar to those observed among natalizumab-treated patients with RRMS and HCs. Our findings raise the possibility that the neuroprotective therapeutic response with rituximab in RRMS may take up to 12 months, which should be confirmed by larger studies.

Classification Of Evidence: This study provides Class IV evidence on the difference in rate of change of the GCIPL thickness in patients with RRMS comparing rituximab to other disease-modifying therapies.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1212/WNL.0000000000011933DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8205480PMC
May 2021

Early Stage Longitudinal Subcortical Volumetric Changes following Mild Traumatic Brain Injury.

Brain Inj 2021 May 6;35(6):725-733. Epub 2021 Apr 6.

Center for Advanced Imaging Research, Department of Diagnostic Radiology & Nuclear Medicine, University of Maryland School of Medicine, Baltimore, Maryland, USA.

: To investigate early brain volumetric changes from acute to 6 months following mild traumatic brain injury (mTBI) in deep gray matter regions and their association with patient 6-month outcome.: Fifty-six patients with mTBI underwent MRI and behavioral evaluation at acute (<10 days) and approximately 1 and 6 months post injury. Regional volume changes were investigated in key gray matter regions: thalamus, hippocampus, putamen, caudate, pallidum, and amygdala, and compared with volumes from 34 healthy control subjects. In patients with mTBI, we further assessed associations between longitudinal regional volume changes with patient outcome measures at 6 months including post-concussive symptoms, cognitive performance, and overall satisfaction with life.: Reduction in thalamic and hippocampal volumes was observed at 1 month among patients with mTBI. Such volume reduction persisted in the thalamus until 6 months. Changes in thalamic volumes also correlated with multiple symptom and functional outcome measures in patients at 6 months.: Our results indicate that the thalamus may be differentially affected among patients with mTBI, resulting in both structural and functional deficits with subsequent post-concussive sequelae and may serve as a biomarker for the assessment of efficacy of novel therapeutic interventions.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1080/02699052.2021.1906445DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8207827PMC
May 2021

Prospective motion detection and re-acquisition in diffusion MRI using a phase image-based method-Application to brain and tongue imaging.

Magn Reson Med 2021 08 4;86(2):725-737. Epub 2021 Mar 4.

Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, Maryland, USA.

Purpose: To develop an image-based motion-robust diffusion MRI (dMRI) acquisition framework that is able to minimize motion artifacts caused by rigid and nonrigid motion, applicable to both brain and tongue dMRI.

Methods: We developed a novel prospective motion-correction technique in dMRI using a phase image-based real-time motion-detection method (PITA-MDD) with re-acquisition of motion-corrupted images. The prospective PITA-MDD acquisition technique was tested in the brains and tongues of volunteers. The subjects were instructed to move their heads or swallow, to induce motion. Motion-detection efficacy was validated against visual inspection as the gold standard. The effect of the PITA-MDD technique on diffusion-parameter estimates was evaluated by comparing reconstructed fiber tracts using tractography with and without re-acquisition.

Results: The prospective PITA-MDD technique was able to effectively and accurately detect motion-corrupted data as compared with visual inspection. Tractography results demonstrated that PITA-MDD motion detection followed by re-acquisition helps in recovering lost and misshaped fiber tracts in the brain and tongue that would otherwise be corrupted by motion and yield erroneous estimates of the diffusion tensor.

Conclusion: A prospective PITA-MDD technique was developed for dMRI acquisition, providing improved dMRI image quality and motion-robust diffusion estimation of the brain and tongue.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/mrm.28729DOI Listing
August 2021

Association of Spectral-Domain OCT With Long-term Disability Worsening in Multiple Sclerosis.

Neurology 2021 04 2;96(16):e2058-e2069. Epub 2021 Mar 2.

From the Department of Neurology (J.L., K.C.F., O.C.M., A.G.F., E.S.S., G.K., E.V., N.P., E.O., B.T., N.J.L., S.D., N.F., O.K., H.R., S.D.N., E.M.M., S.S., P.A.C.), Johns Hopkins University School of Medicine; and Departments of Biostatistics (C.M.C.) and Electrical and Computer Engineering (J.L.P.), Johns Hopkins University, Baltimore, MD.

Objective: To evaluate whether a retinal spectral-domain optical coherence tomography (SD-OCT) assessment at baseline is associated with long-term disability worsening in people with multiple sclerosis (PwMS), we performed SD-OCT and Expanded Disability Status Scale (EDSS) assessments among 132 PwMS at baseline and at a median of 10 years later.

Methods: In this prospective, longitudinal study, participants underwent SD-OCT, EDSS, and visual acuity (VA) assessments at baseline and at follow-up. Statistical analyses were performed using generalized linear regression models, adjusted for age, sex, race, multiple sclerosis (MS) subtype, and baseline disability. We defined clinically meaningful EDSS worsening as an increase of ≥2.0 if baseline EDSS score was <6.0 or an increase of ≥1.0 if baseline EDSS score was ≥6.0.

Results: A total of 132 PwMS (mean age 43 years; 106 patients with relapsing-remitting MS) were included in analyses. Median duration of follow-up was 10.4 years. In multivariable models excluding eyes with prior optic neuritis, relative to patients with an average baseline ganglion cell + inner plexiform layer (GCIPL) thickness ≥70 µm (the mean GCIPL thickness of all eyes at baseline), an average baseline GCIPL thickness <70 µm was associated with a 4-fold increased odds of meaningful EDSS worsening (adjusted odds ratio [OR] 3.97, 95% confidence interval [CI] 1.24-12.70; = 0.02) and an almost 3-fold increased odds of low-contrast VA worsening (adjusted OR 2.93, 95% CI 1.40-6.13; = 0.04).

Conclusions: Lower baseline GCIPL thickness on SD-OCT is independently associated with long-term disability worsening in MS. Accordingly, SD-OCT at a single time point may help guide therapeutic decision-making among individual PwMS.

Classification Of Evidence: This study provides Class I evidence that lower baseline GCIPL thickness on SD-OCT is independently associated with long-term disability worsening in MS.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1212/WNL.0000000000011788DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8166450PMC
April 2021

Optical Coherence Tomography and Optical Coherence Tomography Angiography Findings After Optic Neuritis in Multiple Sclerosis.

Front Neurol 2020 15;11:618879. Epub 2020 Dec 15.

Division of Neuroimmunology and Neurological Infections, Department of Neurology, Johns Hopkins Hospital, Baltimore, MD, United States.

In people with multiple sclerosis (MS), optic neuritis (ON) results in inner retinal layer thinning, and reduced density of the retinal microvasculature. To compare inter-eye differences (IEDs) in macular optical coherence tomography (OCT) and OCT angiography (OCTA) measures in MS patients with a history of unilateral ON (MS ON) vs. MS patients with no history of ON (MS non-ON), and to assess how these measures correlate with visual function outcomes after ON. In this cross-sectional study, people with MS underwent OCT and OCTA. Superficial vascular plexus (SVP) density of each eye was quantified using a deep neural network. IEDs were calculated with respect to the ON eye in MS ON patients, and with respect to the right eye in MS non-ON patients. Statistical analyses used mixed-effect regression models accounting for intra-subject correlations. We included 43 MS ON patients (with 92 discrete OCT/OCTA visits) and 14 MS non-ON patients (with 24 OCT/OCTA visits). Across the cohorts, mean IED in SVP density was -2.69% (SD 3.23) in MS ON patients, as compared to 0.17% (SD 2.39) in MS non-ON patients ( = 0.002). When the MS ON patients were further stratified according to time from ON and compared to MS non-ON patients with multiple cross-sectional analyses, we identified that IED in SVP density was significantly increased in MS ON patients at 1-3 years ( = < 0.001) and >3 years post-ON ( < 0.001), but not at <3 months ( = 0.21) or 3-12 months post-ON ( = 0.07), while IED in ganglion cell + inner plexiform layer (GCIPL) thickness was significantly increased in MS ON patients at all time points post-ON ( ≦ 0.01 for all). IED in SVP density and IED in GCIPL thickness demonstrated significant relationships with IEDs in 100% contrast, 2.5% contrast, and 1.25% contrast letter acuity in MS ON patients ( < 0.001 for all). Our findings suggest that increased IED in SVP density can be detected after ON in MS using OCTA, and detectable changes in SVP density after ON may occur after changes in GCIPL thickness. IED in SVP density and IED in GCIPL thickness correlate well with visual function outcomes in MS ON patients.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fneur.2020.618879DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7769949PMC
December 2020

Serum ceramide levels are altered in multiple sclerosis.

Mult Scler 2020 Dec 14:1352458520971816. Epub 2020 Dec 14.

Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, USA.

Background: Sphingolipids are myelin components and inflammatory signaling intermediates. Sphingolipid metabolism may be altered in people with multiple sclerosis (PwMS), but existing studies are limited by small sample sizes.

Objectives: To compare the levels of serum ceramides between PwMS and healthy controls (HCs) and to determine whether ceramide levels correlate with disability status, as well as optical coherence tomography (OCT)-derived rates of retinal layer atrophy.

Methods: We performed targeted lipidomics analyses for 45 ceramides in PwMS ( = 251) and HCs ( = 68). For a subset of PwMS, baseline and 5-year Expanded Disability Status Scale (EDSS) assessments ( = 185), or baseline and serial spectral-domain OCT ( = 180) were assessed.

Results: Several ceramides, including hexosylceramides, lactosylceramides, and dihydroceramides, were altered in PwMS compared with HCs. Higher levels of Cer16:0 were associated with higher odds of EDSS worsening at 5 years in univariable (odds ratio (OR) = 3.84, 95% confidence interval (CI) = 1.41-10.43) and multivariable analyses accounting for age, sex, and race (OR = 2.97, 95% CI = 1.03-8.59). Each 1 ng/mL higher concentration of Hex-Cer22:0 and DH-HexCer22:0 was associated with accelerated rates (μm/year) of ganglion cell + inner plexiform layer (-0.138 ± 0.053,  = 0.01; -0.158 ± 0.053,  = 0.003, respectively) and peripapillary retinal nerve fiber layer thinning (-0.305 ± 0.107,  = 0.004; -0.358 ± 0.106,  = 0.001, respectively).

Conclusion: Ceramide levels are altered in PwMS and may be associated with retinal neurodegeneration and physical disability.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1177/1352458520971816DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8200368PMC
December 2020

Evidence of subclinical quantitative retinal layer abnormalities in AQP4-IgG seropositive NMOSD.

Mult Scler 2020 Dec 14:1352458520977771. Epub 2020 Dec 14.

Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, USA.

Background: Prior studies have suggested that subclinical retinal abnormalities may be present in aquaporin-4 immunoglobulin G (AQP4-IgG) seropositive neuromyelitis optica spectrum disorder (NMOSD), in the absence of a clinical history of optic neuritis (ON).

Objective: Our aim was to compare retinal layer thicknesses at the fovea and surrounding macula between AQP4-IgG+ NMOSD eyes without a history of ON (AQP4-nonON) and healthy controls (HC).

Methods: In this single-center cross-sectional study, 83 AQP4-nonON and 154 HC eyes were studied with spectral-domain optical coherence tomography (OCT).

Results: Total foveal thickness did not differ between AQP4-nonON and HC eyes. AQP4-nonON eyes exhibited lower outer nuclear layer (ONL) and inner photoreceptor segment (IS) thickness at the fovea (ONL: -4.01 ± 2.03 μm,  = 0.049; IS: -0.32 ± 0.14 μm,  = 0.029) and surrounding macula (ONL: -1.98 ± 0.95 μm,  = 0.037; IS: -0.16 ± 0.07 μm,  = 0.023), compared to HC. Macular retinal nerve fiber layer (RNFL: -1.34 ± 0.51 μm,  = 0.009) and ganglion cell + inner plexiform layer (GCIPL: -2.44 ± 0.93 μm,  = 0.009) thicknesses were also lower in AQP4-nonON compared to HC eyes. Results were similar in sensitivity analyses restricted to AQP4-IgG+ patients who had never experienced ON in either eye.

Conclusions: AQP4-nonON eyes exhibit evidence of subclinical retinal ganglion cell neuronal and axonal loss, as well as structural evidence of photoreceptor layer involvement. These findings support that subclinical anterior visual pathway involvement may occur in AQP4-IgG+ NMOSD.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1177/1352458520977771DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8200372PMC
December 2020

Structured layer surface segmentation for retina OCT using fully convolutional regression networks.

Med Image Anal 2021 02 14;68:101856. Epub 2020 Oct 14.

Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA; Department of Computer Science, The Johns Hopkins University, Baltimore, MD 21218, USA.

Optical coherence tomography (OCT) is a noninvasive imaging modality with micrometer resolution which has been widely used for scanning the retina. Retinal layers are important biomarkers for many diseases. Accurate automated algorithms for segmenting smooth continuous layer surfaces with correct hierarchy (topology) are important for automated retinal thickness and surface shape analysis. State-of-the-art methods typically use a two step process. Firstly, a trained classifier is used to label each pixel into either background and layers or boundaries and non-boundaries. Secondly, the desired smooth surfaces with the correct topology are extracted by graph methods (e.g., graph cut). Data driven methods like deep networks have shown great ability for the pixel classification step, but to date have not been able to extract structured smooth continuous surfaces with topological constraints in the second step. In this paper, we combine these two steps into a unified deep learning framework by directly modeling the distribution of the surface positions. Smooth, continuous, and topologically correct surfaces are obtained in a single feed forward operation. The proposed method was evaluated on two publicly available data sets of healthy controls and subjects with either multiple sclerosis or diabetic macular edema, and is shown to achieve state-of-the art performance with sub-pixel accuracy.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2020.101856DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7855873PMC
February 2021

SMORE: A Self-Supervised Anti-Aliasing and Super-Resolution Algorithm for MRI Using Deep Learning.

IEEE Trans Med Imaging 2021 03 2;40(3):805-817. Epub 2021 Mar 2.

High resolution magnetic resonance (MR) images are desired in many clinical and research applications. Acquiring such images with high signal-to-noise (SNR), however, can require a long scan duration, which is difficult for patient comfort, is more costly, and makes the images susceptible to motion artifacts. A very common practical compromise for both 2D and 3D MR imaging protocols is to acquire volumetric MR images with high in-plane resolution, but lower through-plane resolution. In addition to having poor resolution in one orientation, 2D MRI acquisitions will also have aliasing artifacts, which further degrade the appearance of these images. This paper presents an approach SMORE1 based on convolutional neural networks (CNNs) that restores image quality by improving resolution and reducing aliasing in MR images.2 This approach is self-supervised, which requires no external training data because the high-resolution and low-resolution data that are present in the image itself are used for training. For 3D MRI, the method consists of only one self-supervised super-resolution (SSR) deep CNN that is trained from the volumetric image data. For 2D MRI, there is a self-supervised anti-aliasing (SAA) deep CNN that precedes the SSR CNN, also trained from the volumetric image data. Both methods were evaluated on a broad collection of MR data, including filtered and downsampled images so that quantitative metrics could be computed and compared, and actual acquired low resolution images for which visual and sharpness measures could be computed and compared. The super-resolution method is shown to be visually and quantitatively superior to previously reported methods.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2020.3037187DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8053388PMC
March 2021

Unsupervised MR-to-CT Synthesis Using Structure-Constrained CycleGAN.

IEEE Trans Med Imaging 2020 12 30;39(12):4249-4261. Epub 2020 Nov 30.

Synthesizing a CT image from an available MR image has recently emerged as a key goal in radiotherapy treatment planning for cancer patients. CycleGANs have achieved promising results on unsupervised MR-to-CT image synthesis; however, because they have no direct constraints between input and synthetic images, cycleGANs do not guarantee structural consistency between these two images. This means that anatomical geometry can be shifted in the synthetic CT images, clearly a highly undesirable outcome in the given application. In this paper, we propose a structure-constrained cycleGAN for unsupervised MR-to-CT synthesis by defining an extra structure-consistency loss based on the modality independent neighborhood descriptor. We also utilize a spectral normalization technique to stabilize the training process and a self-attention module to model the long-range spatial dependencies in the synthetic images. Results on unpaired brain and abdomen MR-to-CT image synthesis show that our method produces better synthetic CT images in both accuracy and visual quality as compared to other unsupervised synthesis methods. We also show that an approximate affine pre-registration for unpaired training data can improve synthesis results.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2020.3015379DOI Listing
December 2020

Longitudinal analysis of regional cerebellum volumes during normal aging.

Neuroimage 2020 10 25;220:117062. Epub 2020 Jun 25.

Laboratory of Behavioral Neuroscience, National Institute on Aging, National Institutes of Health, Baltimore, MD, 20892, USA.

Some cross-sectional studies suggest reduced cerebellar volumes with aging, but there have been few longitudinal studies of age changes in cerebellar subregions in cognitively healthy older adults. In this work, 2,023 magnetic resonance (MR) images of 822 cognitively normal participants from the Baltimore Longitudinal Study of Aging (BLSA) were analyzed. Participants ranged in age from 50 to 95 years (mean 70.7 years) at the baseline assessment. Follow-up intervals were 1-9 years (mean 3.7 years) for participants with two or more visits. We used a recently developed cerebellum parcellation algorithm based on convolutional neural networks to divide the cerebellum into 28 subregions. Linear mixed effects models were applied to the volume of each cerebellar subregion to investigate cross-sectional and longitudinal age effects, as well as effects of sex and their interactions, after adjusting for intracranial volume. Our findings suggest spatially varying atrophy patterns across the cerebellum with respect to age and sex both cross-sectionally and longitudinally.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.neuroimage.2020.117062DOI Listing
October 2020

Identifying the Common and Subject-specific Functional Units of Speech Movements via a Joint Sparse Non-negative Matrix Factorization Framework.

Proc SPIE Int Soc Opt Eng 2020 Feb 10;11313. Epub 2020 Mar 10.

Gordon Center for Medical Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USA.

The tongue is capable of producing intelligible speech because of successful orchestration of muscle groupings-i.e., functional units-of the highly complex muscles over time. Due to the different motions that tongues produce, functional units are transitional structures which transform muscle activity to surface tongue geometry and they vary significantly from one subject to another. In order to compare and contrast the location and size of functional units in the presence of such substantial inter-person variability, it is essential to study both common and subject-specific functional units in a group of people carrying out the same speech task. In this work, a new normalization technique is presented to simultaneously identify the common and subject-specific functional units defined in the tongue when tracked by tagged magnetic resonance imaging. To achieve our goal, a joint sparse non-negative matrix factorization framework is used, which learns a set of building blocks and subject-specific as well as common weighting matrices from motion quantities extracted from displacements. A spectral clustering technique is then applied to the subject-specific and common weighting matrices to determine the subject-specific functional units for each subject and the common functional units across subjects. Our experimental results using tongue motion data show that our approach is able to identify the common and subject-specific functional units with reduced size variability of tongue motion during speech.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7243345PMC
February 2020

Automatic cerebellum anatomical parcellation using U-Net with locally constrained optimization.

Neuroimage 2020 09 11;218:116819. Epub 2020 May 11.

Department of Biomedical Engineering, The Johns Hopkins University, Baltimore, MD, 21218, USA; Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD, 21218, USA; Department of Computer Science, The Johns Hopkins University, Baltimore, MD, 21218, USA.

The cerebellum plays a central role in sensory input, voluntary motor action, and many neuropsychological functions and is involved in many brain diseases and neurological disorders. Cerebellar parcellation from magnetic resonance images provides a way to study regional cerebellar atrophy and also provides an anatomical map for functional imaging. In a recent comparison, a multi-atlas approach proved to be superior to other parcellation methods including some based on convolutional neural networks (CNNs) which have a considerable speed advantage. In this work, we developed an alternative CNN design for cerebellar parcellation, yielding a method that achieves the leading performance to date. The proposed method was evaluated on multiple data sets to show its broad applicability, and a Singularity container has been made publicly available.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.neuroimage.2020.116819DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7416473PMC
September 2020

Evaluating White Matter Lesion Segmentations with Refined Sørensen-Dice Analysis.

Sci Rep 2020 05 19;10(1):8242. Epub 2020 May 19.

Department of Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN, 37203, USA.

The Sørensen-Dice index (SDI) is a widely used measure for evaluating medical image segmentation algorithms. It offers a standardized measure of segmentation accuracy which has proven useful. However, it offers diminishing insight when the number of objects is unknown, such as in white matter lesion segmentation of multiple sclerosis (MS) patients. We present a refinement for finer grained parsing of SDI results in situations where the number of objects is unknown. We explore these ideas with two case studies showing what can be learned from our two presented studies. Our first study explores an inter-rater comparison, showing that smaller lesions cannot be reliably identified. In our second case study, we demonstrate fusing multiple MS lesion segmentation algorithms based on the insights into the algorithms provided by our analysis to generate a segmentation that exhibits improved performance. This work demonstrates the wealth of information that can be learned from refined analysis of medical image segmentations.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-020-64803-wDOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7237671PMC
May 2020

Hierarchical Parcellation of the Cerebellum.

Med Image Comput Comput Assist Interv 2019 Oct 10;11766:484-491. Epub 2019 Oct 10.

Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA.

Parcellation of the cerebellum in an MR image has been used to study regional associations with both motion and cognitive functions. Despite the fact that the division of the cerebellum is defined hierarchically-i.e., the cerebellum can be divided into lobes and the lobes can be further divided into lobules-previous automatic methods to parcellate the cerebellum do not utilize this information. In this work, we propose a method based on convolutional neural networks (CNNs) to explicitly incorporate the hierarchical organization of the cerebellum. The network is constructed in a tree structure with each node representing a cerebellar region and having child nodes that further subdivide the region into finer substructures. Thus, our CNN is aware of the hierarchical organization of the cerebellum. Furthermore, by selecting tree nodes to represent the hierarchical properties of a given training sample, our network can be trained with heterogeneous training data that are labeled to different hierarchical depths. The proposed method was compared with a state-of-the-art cerebellum parcellation network. Our approach shows promising results as a first parcellation method to take the cerebellar hierarchical organization into consideration.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-030-32248-9_54DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7217559PMC
October 2019

Association of body mass index with longitudinal rates of retinal atrophy in multiple sclerosis.

Mult Scler 2020 06 16;26(7):843-854. Epub 2020 Apr 16.

Division of Neuroimmunology and Neurological Infections, Department of Neurology, The Johns Hopkins University School of Medicine, Baltimore, MD, USA.

Background: Studies evaluating associations between body mass index (BMI) and optical coherence tomography (OCT) measures in multiple sclerosis (MS) are lacking.

Objective: To assess whether elevated BMI is associated with accelerated retinal atrophy.

Methods: In this observational study, 513 MS patients were followed with serial spectral-domain OCT for a median of 4.4 years. Participants were categorized as normal weight (BMI: 18.5-24.9 kg/m), overweight (BMI: 25-29.9 kg/m), and obese (BMI: ⩾30 kg/m). Participants with diabetes mellitus or uncontrolled hypertension and eyes with optic neuritis (ON) ⩽6 months prior to baseline OCT or during follow-up were excluded. Statistical analyses were performed with mixed-effects linear regression.

Results: Obese patients ( = 146) exhibited accelerated rates of ganglion cell + inner plexiform layer (GCIPL) atrophy relative to normal weight patients ( = 214; -0.57%/year (95% confidence interval (CI): -0.65% to -0.48%) versus -0.42%/year (95% CI: -0.49% to -0.35%);  = 0.012). GCIPL atrophy rate did not differ between overweight ( = 153) and normal weight patients (-0.47%/year vs -0.42%/year;  = 0.41). Each 1 kg/m higher BMI was associated with accelerated GCIPL (-0.011%/year; 95% CI: -0.019% to -0.004%;  = 0.003) atrophy. Multivariable analyses accounting for age, sex, race, MS subtype, and ON history did not alter the above findings.

Conclusions: Elevated BMI, in the absence of overt metabolic comorbidities, may be associated with accelerated GCIPL atrophy. Obesity, a modifiable risk factor, may be associated with accelerated neurodegeneration in MS.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1177/1352458519900942DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7293552PMC
June 2020

Progressive Multiple Sclerosis Is Associated with Faster and Specific Retinal Layer Atrophy.

Ann Neurol 2020 06 28;87(6):885-896. Epub 2020 Apr 28.

Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, USA.

Objective: Therapeutic development in progressive multiple sclerosis (PMS) has been hampered by a lack of reliable biomarkers to monitor neurodegeneration. Optical coherence tomography (OCT)-derived retinal measures have been proposed as promising biomarkers to fulfill this role. However, it is unclear whether retinal atrophy persists in PMS, exceeds normal aging, or can be distinguished from relapsing-remitting multiple sclerosis (RRMS).

Methods: 178 RRMS, 186 PMS, and 66 control participants were followed with serial OCT for a median follow-up of 3.7 years.

Results: The estimated proportion of peripapillary retinal nerve fiber layer (pRNFL) and macular ganglion cell + inner plexiform layer (GCIPL) thinning in multiple sclerosis (MS) attributable to normal aging increased from 42.7% and 16.7% respectively at age 25 years, to 83.7% and 81.1% at age 65 years. However, independent of age, PMS was associated with faster pRNFL (-0.34 ± 0.09%/yr, p < 0.001) and GCIPL (-0.27 ± 0.07%/yr, p < 0.001) thinning, as compared to RRMS. In both MS and controls, higher baseline age was associated with faster inner nuclear layer (INL) and outer nuclear layer (ONL) thinning. INL and ONL thinning were independently faster in PMS, as compared to controls (INL:-0.09 ± 0.04%/yr, p = 0.03; ONL:-0.12 ± 0.06%/yr, p = 0.04), and RRMS (INL:-0.10 ± 0.04%/yr, p = 0.01; ONL:-0.13 ± 0.05%/yr, p = 0.01), whereas they were similar in RRMS and controls. Unlike RRMS, disease-modifying therapies (DMTs) did not impact rates of retinal layer atrophy in PMS.

Interpretation: PMS is associated with faster retinal atrophy independent of age. INL and ONL measures may be novel biomarkers of neurodegeneration in PMS that appear to be unaffected by conventional DMTs. The effects of aging on rates of retinal layer atrophy should be considered in clinical trials incorporating OCT outcomes. ANN NEUROL 2020;87:885-896.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/ana.25738DOI Listing
June 2020

Analysis of fiber strain in the human tongue during speech.

Comput Methods Biomech Biomed Engin 2020 Jun 7;23(8):312-322. Epub 2020 Feb 7.

Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA.

This study investigates mechanical cooperation among tongue muscles. Five volunteers were imaged using tagged magnetic resonance imaging to quantify spatiotemporal kinematics while speaking. Waveforms of strain in the line of action of fibers (SLAF) were estimated by projecting strain tensors onto a model of fiber directionality. SLAF waveforms were temporally aligned to determine consistency across subjects and correlation across muscles. The cohort exhibited consistent patterns of SLAF, and muscular extension-contraction was correlated. Volume-preserving tongue movement in speech generation can be achieved through multiple paths, but the study reveals similarities in motion patterns and muscular action-despite anatomical (and other) dissimilarities.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1080/10255842.2020.1722808DOI Listing
June 2020

Fully Convolutional Boundary Regression for Retina OCT Segmentation.

Med Image Comput Comput Assist Interv 2019 Oct 10;11764:120-128. Epub 2019 Oct 10.

Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA.

A major goal of analyzing retinal optical coherence tomography (OCT) images is retinal layer segmentation. Accurate automated algorithms for segmenting smooth continuous layer surfaces, with correct hierarchy (topology) are desired for monitoring disease progression. State-of-the-art methods use a trained classifier to label each pixel into background, layer, or surface pixels. The final step of extracting the desired smooth surfaces with correct topology are mostly performed by graph methods (e.g. shortest path, graph cut). However, manually building a graph with varying constraints by retinal region and pathology and solving the minimization with specialized algorithms will degrade the flexibility and time efficiency of the whole framework. In this paper, we directly model the distribution of surface positions using a deep network with a fully differentiable soft argmax to obtain smooth, continuous surfaces in a single feed forward operation. A special topology module is used in the deep network both in the training and testing stages to guarantee the surface topology. An extra deep network output branch is also used for predicting lesion and layers in a pixel-wise labeling scheme. The proposed method was evaluated on two publicly available data sets of healthy controls, subjects with multiple sclerosis, and diabetic macular edema; it achieves state-of-the art sub-pixel results.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-030-32239-7_14DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6918831PMC
October 2019

Deep learning based topology guaranteed surface and MME segmentation of multiple sclerosis subjects from retinal OCT.

Biomed Opt Express 2019 Oct 12;10(10):5042-5058. Epub 2019 Sep 12.

Deptartment of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA.

Optical coherence tomography (OCT) is a noninvasive imaging modality that can be used to obtain depth images of the retina. Patients with multiple sclerosis (MS) have thinning retinal nerve fiber and ganglion cell layers, and approximately 5% of MS patients will develop microcystic macular edema (MME) within the retina. Segmentation of both the retinal layers and MME can provide important information to help monitor MS progression. Graph-based segmentation with machine learning preprocessing is the leading method for retinal layer segmentation, providing accurate surface delineations with the correct topological ordering. However, graph methods are time-consuming and they do not optimally incorporate joint MME segmentation. This paper presents a deep network that extracts continuous, smooth, and topology-guaranteed surfaces and MMEs. The network learns shape priors automatically during training rather than being hard-coded as in graph methods. In this new approach, retinal surfaces and MMEs are segmented together with two cascaded deep networks in a single feed forward propagation. The proposed framework obtains retinal surfaces (separating the layers) with sub-pixel surface accuracy comparable to the best existing graph methods and MMEs with better accuracy than the state-of-the-art method. The full segmentation operation takes only ten seconds for a 3D volume.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1364/BOE.10.005042DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6788619PMC
October 2019

Evaluating the Impact of Intensity Normalization on MR Image Synthesis.

Proc SPIE Int Soc Opt Eng 2019 Mar;10949

Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA 21218.

Image synthesis learns a transformation from the intensity features of an input image to yield a different tissue contrast of the output image. This process has been shown to have application in many medical image analysis tasks including imputation, registration, and segmentation. To carry out synthesis, the intensities of the input images are typically scaled-i.e., normalized-both in training to learn the transformation and in testing when applying the transformation, but it is not presently known what type of input scaling is optimal. In this paper, we consider seven different intensity normalization algorithms and three different synthesis methods to evaluate the impact of normalization. Our experiments demonstrate that intensity normalization as a preprocessing step improves the synthesis results across all investigated synthesis algorithms. Furthermore, we show evidence that suggests intensity normalization is vital for successful deep learning-based MR image synthesis.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1117/12.2513089DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6758567PMC
March 2019

Quantifying Tongue Tip Shape in Apical and Laminal /s/: Contributions of Palate Shape.

J Speech Lang Hear Res 2019 09 29;62(9):3149-3159. Epub 2019 Aug 29.

Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD.

Purpose Anterior tongue shape during /s/ production is often described as "tip-up" or apical, versus "tip-down" or laminal. Typically, this is determined by observing the shape of the anterior midline tongue. The purpose of this study was to identify methods of curvature calculation that quantify the observed shape differences and to examine whether the shape differences were affected by palate shape. Previous work shows that palate height has some effect (Grimm et al., 2017). Method Four curvature-based measures were applied to a series of points selected along the tongue surface in midsagittal cine magnetic resonance images during speech. The measures were minimal curvature, averaged largest curvature (ALC), normalized ALC, and interpolated normalized ALC. These measures were compared to visual judgments of apical and laminal /s/. Anterior palate shape was measured from dental casts. Results The apical /s/ contained a flat or concave region in the anterior tongue, while the laminal /s/ had a convex shape along the entire tongue. Thus, the laminal shape was less complex than the apical. The last 2 metrics, based on averages of multiple normalized curvatures, captured this complexity difference. Subjects with a more steeply sloped anterior palate tended to use laminal /s/. Conclusions The tongue shape for the 2 /s/ types was best defined by complexity of the shape, rather than local anterior shape. Statistical quantities that measured curvature in multiple locations, and normalized across subjects, were best at distinguishing the 2 /s/ shapes. Interpolating additional points between the manually selected ones did not improve the method. Supplemental Material https://doi.org/10.23641/asha.9733709.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1044/2019_JSLHR-S-19-0114DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6808342PMC
September 2019

Aquaporin-4 IgG seropositivity is associated with worse visual outcomes after optic neuritis than MOG-IgG seropositivity and multiple sclerosis, independent of macular ganglion cell layer thinning.

Mult Scler 2020 10 31;26(11):1360-1371. Epub 2019 Jul 31.

Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, MD, USA.

Background: Comparative studies of characteristics of optic neuritis (ON) associated with myelin oligodendrocyte glycoprotein-IgG (MOG-ON) and aquaporin-4-IgG (AQP4-ON) seropositivity are limited.

Objective: To compare visual and optical coherence tomography (OCT) measures following AQP4-ON, MOG-ON, and multiple sclerosis associated ON (MS-ON).

Methods: In this cross-sectional study, 48 AQP4-ON, 16 MOG-ON, 40 MS-ON, and 31 healthy control participants underwent monocular letter-acuity assessment and spectral-domain OCT. Eyes with a history of ON >3 months prior to evaluation were analyzed.

Results: AQP4-ON eyes exhibited worse high-contrast letter acuity (HCLA) compared to MOG-ON (-22.3 ± 3.9 letters;  < 0.001) and MS-ON eyes (-21.7 ± 4.0 letters;  < 0.001). Macular ganglion cell + inner plexiform layer (GCIPL) thickness was lower, as compared to MS-ON, in AQP4-ON (-9.1 ± 2.0 µm;  < 0.001) and MOG-ON (-7.6 ± 2.2 µm;  = 0.001) eyes. Lower GCIPL thickness was associated with worse HCLA in AQP4-ON (-16.5 ± 1.5 letters per 10 µm decrease;  < 0.001) and MS-ON eyes (-8.5 ± 2.3 letters per 10 µm decrease;  < 0.001), but not in MOG-ON eyes (-5.2 ± 3.8 letters per 10 µm decrease;  = 0.17), and these relationships differed between the AQP4-ON and other ON groups ( < 0.01 for interaction).

Conclusion: AQP4-IgG seropositivity is associated with worse visual outcomes after ON compared with MOG-ON and MS-ON, even with similar severity of macular GCIPL thinning.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1177/1352458519864928DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6992495PMC
October 2020
-->