Other search tools

About this data

The publication data currently available has been vetted by Vanderbilt faculty, staff, administrators and trainees. The data itself is retrieved directly from NCBI's PubMed and is automatically updated on a weekly basis to ensure accuracy and completeness.

If you have any questions or comments, please contact us.

Results: 1 to 10 of 433

Publication Record


Distributed deep learning across multisite datasets for generalized CT hemorrhage segmentation.
Remedios SW, Roy S, Bermudez C, Patel MB, Butman JA, Landman BA, Pham DL
(2020) Med Phys 47: 89-98
MeSH Terms: Deep Learning, Hemorrhage, Humans, Image Processing, Computer-Assisted, Tomography, X-Ray Computed
Show Abstract · Added October 30, 2019
PURPOSE - As deep neural networks achieve more success in the wide field of computer vision, greater emphasis is being placed on the generalizations of these models for production deployment. With sufficiently large training datasets, models can typically avoid overfitting their data; however, for medical imaging it is often difficult to obtain enough data from a single site. Sharing data between institutions is also frequently nonviable or prohibited due to security measures and research compliance constraints, enforced to guard protected health information (PHI) and patient anonymity.
METHODS - In this paper, we implement cyclic weight transfer with independent datasets from multiple geographically disparate sites without compromising PHI. We compare results between single-site learning (SSL) and multisite learning (MSL) models on testing data drawn from each of the training sites as well as two other institutions.
RESULTS - The MSL model attains an average dice similarity coefficient (DSC) of 0.690 on the holdout institution datasets with a volume correlation of 0.914, respectively corresponding to a 7% and 5% statistically significant improvement over the average of both SSL models, which attained an average DSC of 0.646 and average correlation of 0.871.
CONCLUSIONS - We show that a neural network can be efficiently trained on data from two physically remote sites without consolidating patient data to a single location. The resulting network improves model generalization and achieves higher average DSCs on external datasets than neural networks trained on data from a single source.
© 2019 American Association of Physicists in Medicine.
0 Communities
1 Members
0 Resources
5 MeSH Terms
Fully automatic liver attenuation estimation combing CNN segmentation and morphological operations.
Huo Y, Terry JG, Wang J, Nair S, Lasko TA, Freedman BI, Carr JJ, Landman BA
(2019) Med Phys 46: 3508-3519
MeSH Terms: Deep Learning, Humans, Image Processing, Computer-Assisted, Liver, Non-alcoholic Fatty Liver Disease, Tomography, X-Ray Computed
Show Abstract · Added July 18, 2019
PURPOSE - Manually tracing regions of interest (ROIs) within the liver is the de facto standard method for measuring liver attenuation on computed tomography (CT) in diagnosing nonalcoholic fatty liver disease (NAFLD). However, manual tracing is resource intensive. To address these limitations and to expand the availability of a quantitative CT measure of hepatic steatosis, we propose the automatic liver attenuation ROI-based measurement (ALARM) method for automated liver attenuation estimation.
METHODS - The ALARM method consists of two major stages: (a) deep convolutional neural network (DCNN)-based liver segmentation and (b) automated ROI extraction. First, liver segmentation was achieved using our previously developed SS-Net. Then, a single central ROI (center-ROI) and three circles ROI (periphery-ROI) were computed based on liver segmentation and morphological operations. The ALARM method is available as an open source Docker container (https://github.com/MASILab/ALARM).
RESULTS - Two hundred and forty-six subjects with 738 abdomen CT scans from the African American-Diabetes Heart Study (AA-DHS) were used for external validation (testing), independent from the training and validation cohort (100 clinically acquired CT abdominal scans). From the correlation analyses, the proposed ALARM method achieved Pearson correlations = 0.94 with manual estimation on liver attenuation estimations. When evaluating the ALARM method for detection of nonalcoholic fatty liver disease (NAFLD) using the traditional cut point of < 40 HU, the center-ROI achieved substantial agreements (Kappa = 0.79) with manual estimation, while the periphery-ROI method achieved "excellent" agreement (Kappa = 0.88) with manual estimation. The automated ALARM method had reduced variability compared to manual measurements as indicated by a smaller standard deviation.
CONCLUSIONS - We propose a fully automated liver attenuation estimation method termed ALARM by combining DCNN and morphological operations, which achieved "excellent" agreement with manual estimation for fatty liver detection. The entire pipeline is implemented as a Docker container which enables users to achieve liver attenuation estimation in five minutes per CT exam.
© 2019 American Association of Physicists in Medicine.
0 Communities
2 Members
0 Resources
6 MeSH Terms
Quantification of DTI in the Pediatric Spinal Cord: Application to Clinical Evaluation in a Healthy Patient Population.
Reynolds BB, By S, Weinberg QR, Witt AA, Newton AT, Feiler HR, Ramkorun B, Clayton DB, Couture P, Martus JE, Adams M, Wellons JC, Smith SA, Bhatia A
(2019) AJNR Am J Neuroradiol 40: 1236-1241
MeSH Terms: Adolescent, Algorithms, Anisotropy, Child, Child, Preschool, Diffusion Tensor Imaging, Female, Humans, Image Processing, Computer-Assisted, Infant, Male, Neurogenesis, Neuroimaging, Retrospective Studies, Spinal Cord
Show Abstract · Added March 30, 2020
BACKGROUND AND PURPOSE - The purpose of the study is to characterize diffusion tensor imaging indices in the developing spinal cord, evaluating differences based on age and cord region. Describing the progression of DTI indices in the pediatric cord increases our understanding of spinal cord development.
MATERIALS AND METHODS - A retrospective analysis was performed on DTI acquired in 121 pediatric patients (mean, 8.6 years; range, 0.3-18.0 years) at Monroe Carell Jr. Children's Hospital at Vanderbilt from 2017 to 2018. Diffusion-weighted images (15 directions; = 750 s/mm; slice thickness, 5 mm; in-plane resolution, 1.0 × 1.0 mm) were acquired on a 3T scanner in the cervicothoracic and/or thoracolumbar cord. Manual whole-cord segmentation was performed. Images were masked and further segmented into cervical, upper thoracic, thoracolumbar, and conus regions. Analyses of covariance were performed for each DTI-derived index to investigate how age affects diffusion across cord regions, and 95% confidence intervals were calculated across age for each derived index and region. Post hoc testing was performed to analyze regional differences.
RESULTS - Analyses of covariance revealed significant correlations of age with axial diffusivity, mean diffusivity, and fractional anisotropy (all, < .001). There were also significant differences among cord regions for axial diffusivity, radial diffusivity, mean diffusivity, and fractional anisotropy (all, < .001).
CONCLUSIONS - This research demonstrates that diffusion evolves in the pediatric spinal cord during development, dependent on both cord region and the diffusion index of interest. Future research could investigate how diffusion may be affected by common pediatric spinal pathologies.
© 2019 by American Journal of Neuroradiology.
0 Communities
1 Members
0 Resources
15 MeSH Terms
Synthesized b0 for diffusion distortion correction (Synb0-DisCo).
Schilling KG, Blaber J, Huo Y, Newton A, Hansen C, Nath V, Shafer AT, Williams O, Resnick SM, Rogers B, Anderson AW, Landman BA
(2019) Magn Reson Imaging 64: 62-70
MeSH Terms: Adult, Aged, Aged, 80 and over, Algorithms, Artifacts, Brain, Diffusion Magnetic Resonance Imaging, Echo-Planar Imaging, Humans, Image Processing, Computer-Assisted, Middle Aged
Show Abstract · Added March 18, 2020
Diffusion magnetic resonance images typically suffer from spatial distortions due to susceptibility induced off-resonance fields, which may affect the geometric fidelity of the reconstructed volume and cause mismatches with anatomical images. State-of-the art susceptibility correction (for example, FSL's TOPUP algorithm) typically requires data acquired twice with reverse phase encoding directions, referred to as blip-up blip-down acquisitions, in order to estimate an undistorted volume. Unfortunately, not all imaging protocols include a blip-up blip-down acquisition, and cannot take advantage of the state-of-the art susceptibility and motion correction capabilities. In this study, we aim to enable TOPUP-like processing with historical and/or limited diffusion imaging data that include only a structural image and single blip diffusion image. We utilize deep learning to synthesize an undistorted non-diffusion weighted image from the structural image, and use the non-distorted synthetic image as an anatomical target for distortion correction. We evaluate the efficacy of this approach (named Synb0-DisCo) and show that our distortion correction process results in better matching of the geometry of undistorted anatomical images, reduces variation in diffusion modeling, and is practically equivalent to having both blip-up and blip-down non-diffusion weighted images.
Copyright © 2019 Elsevier Inc. All rights reserved.
0 Communities
1 Members
0 Resources
11 MeSH Terms
Measurement of T* in the human spinal cord at 3T.
Barry RL, Smith SA
(2019) Magn Reson Med 82: 743-748
MeSH Terms: Adult, Female, Gray Matter, Humans, Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Male, Middle Aged, Neck, Spinal Cord, White Matter, Young Adult
Show Abstract · Added April 10, 2019
PURPOSE - To measure the transverse relaxation time T* in healthy human cervical spinal cord gray matter (GM) and white matter (WM) at 3T.
METHODS - Thirty healthy volunteers were recruited. Axial images were acquired using an averaged multi-echo gradient-echo (mFFE) T*-weighted sequence with 5 echoes. We used the signal equation for an mFFE sequence with constant dephasing gradients after each echo to jointly estimate the spin density and T* for each voxel.
RESULTS - No global difference in T* was observed between all GM (41.3 ± 5.6 ms) and all WM (39.8 ± 5.4 ms). No significant differences were observed between left (43.2 ± 6.8 ms) and right (43.4 ± 5.5 ms) ventral GM, left (38.3 ± 6.1 ms) and right (38.6 ± 6.5 ms) dorsal GM, and left (39.4 ± 5.8 ms) and right (40.3 ± 5.8 ms) lateral WM. However, significant regional differences were observed between ventral (43.4 ± 5.7 ms) and dorsal (38.4 ± 6.0 ms) GM (p < 0.05), as well as between ventral (42.9 ± 6.5 ms) and dorsal (37.9 ± 6.2 ms) WM (p < 0.05). In analyses across slices, inferior T* was longer than superior T* in GM (44.7 ms vs. 40.1 ms; p < 0.01) and in WM (41.8 ms vs. 35.9 ms; p < 0.01).
CONCLUSIONS - Significant differences in T* are observed between ventral and dorsal GM, ventral and dorsal WM, and superior and inferior GM and WM. There is no evidence for bilateral asymmetry in T* in the healthy cord. These values of T* in the spinal cord are notably lower than most reported values of T* in the cortex.
© 2019 International Society for Magnetic Resonance in Medicine.
0 Communities
1 Members
0 Resources
12 MeSH Terms
MR fingerprinting with simultaneous T, T, and fat signal fraction estimation with integrated B correction reduces bias in water T and T estimates.
Ostenson J, Damon BM, Welch EB
(2019) Magn Reson Imaging 60: 7-19
MeSH Terms: Abdomen, Adipose Tissue, Algorithms, Bias, Computer Simulation, Fourier Analysis, Head, Humans, Image Processing, Computer-Assisted, Knee, Magnetic Resonance Imaging, Models, Statistical, Muscle, Skeletal, Phantoms, Imaging, Reproducibility of Results, Signal Processing, Computer-Assisted, Water
Show Abstract · Added March 3, 2020
PURPOSE - MR fingerprinting (MRF) sequences permit efficient T and T estimation in cranial and extracranial regions, but these areas may include substantial fat signals that bias T and T estimates. MRI fat signal fraction estimation is also a topic of active research in itself, but may be complicated by B heterogeneity and blurring during spiral k-space acquisitions, which are commonly used for MRF. An MRF method is proposed that separates fat and water signals, estimates water T and T, and accounts for B effects with spiral blurring correction, in a single sequence.
THEORY AND METHODS - A k-space-based fat-water separation method is further extended to unbalanced steady-state free precession MRF with swept echo time. Repeated application of this k-space fat-water separation to demodulated forms of the measured data allows a B map and correction to be approximated. The method is compared with MRF without fat separation across a broad range of fat signal fractions (FSFs), water Ts and Ts, and under heterogeneous static fields in simulations, phantoms, and in vivo.
RESULTS - The proposed method's FSF estimates had a concordance correlation coefficient of 0.990 with conventional measurements, and reduced biases in the T and T estimates due to fat signal relative to other MRF sequences by several hundred ms. The B correction improved the FSF, T, and T estimation compared to those estimates without correction.
CONCLUSION - The proposed method improves MRF water T and T estimation in the presence of fat and provides accurate FSF estimation with inline B correction.
Copyright © 2019 Elsevier Inc. All rights reserved.
0 Communities
1 Members
0 Resources
MeSH Terms
Registration-based image enhancement improves multi-atlas segmentation of the thalamic nuclei and hippocampal subfields.
Bao S, Bermudez C, Huo Y, Parvathaneni P, Rodriguez W, Resnick SM, D'Haese PF, McHugo M, Heckers S, Dawant BM, Lyu I, Landman BA
(2019) Magn Reson Imaging 59: 143-152
MeSH Terms: Algorithms, Brain Mapping, Hippocampus, Humans, Image Enhancement, Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Temporal Lobe, Thalamic Nuclei
Show Abstract · Added March 26, 2019
Magnetic resonance imaging (MRI) is an important tool for analysis of deep brain grey matter structures. However, analysis of these structures is limited due to low intensity contrast typically found in whole brain imaging protocols. Herein, we propose a big data registration-enhancement (BDRE) technique to augment the contrast of deep brain structures using an efficient large-scale non-rigid registration strategy. Direct validation is problematic given a lack of ground truth data. Rather, we validate the usefulness and impact of BDRE for multi-atlas (MA) segmentation on two sets of structures of clinical interest: the thalamic nuclei and hippocampal subfields. The experimental design compares algorithms using T1-weighted 3 T MRI for both structures (and additional 7 T MRI for the thalamic nuclei) with an algorithm using BDRE. As baseline comparisons, a recent denoising (DN) technique and a super-resolution (SR) method are used to preprocess the original 3 T MRI. The performance of each MA segmentation is evaluated by the Dice similarity coefficient (DSC). BDRE significantly improves mean segmentation accuracy over all methods tested for both thalamic nuclei (3 T imaging: 9.1%; 7 T imaging: 15.6%; DN: 6.9%; SR: 16.2%) and hippocampal subfields (3 T T1 only: 8.7%; DN: 8.4%; SR: 8.6%). We also present DSC performance for each thalamic nucleus and hippocampal subfield and show that BDRE can help MA segmentation for individual thalamic nuclei and hippocampal subfields. This work will enable large-scale analysis of clinically relevant deep brain structures from commonly acquired T1 images.
Copyright © 2019 Elsevier Inc. All rights reserved.
0 Communities
1 Members
0 Resources
9 MeSH Terms
Evaluation of principal component analysis image denoising on multi-exponential MRI relaxometry.
Does MD, Olesen JL, Harkins KD, Serradas-Duarte T, Gochberg DF, Jespersen SN, Shemesh N
(2019) Magn Reson Med 81: 3503-3514
MeSH Terms: Algorithms, Animals, Brain, Computer Simulation, Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Mice, Principal Component Analysis
Show Abstract · Added March 5, 2020
PURPOSE - Multi-exponential relaxometry is a powerful tool for characterizing tissue, but generally requires high image signal-to-noise ratio (SNR). This work evaluates the use of principal-component-analysis (PCA) denoising to mitigate these SNR demands and improve the precision of relaxometry measures.
METHODS - PCA denoising was evaluated using both simulated and experimental MRI data. Bi-exponential transverse relaxation signals were simulated for a wide range of acquisition and sample parameters, and experimental data were acquired from three excised and fixed mouse brains. In both cases, standard relaxometry analysis was performed on both original and denoised image data, and resulting estimated signal parameters were compared.
RESULTS - Denoising reduced the root-mean-square-error of parameters estimated from multi-exponential relaxometry by factors of ≈3×, for typical acquisition and sample parameters. Denoised images and subsequent parameter maps showed little or no signs of spatial artifact or loss of resolution.
CONCLUSION - Experimental studies and simulations demonstrate that PCA denoising of MRI relaxometry data is an effective method of improving parameter precision without sacrificing image resolution. This simple yet important processing step thus paves the way for broader applicability of multi-exponential MRI relaxometry.
© 2019 International Society for Magnetic Resonance in Medicine.
0 Communities
1 Members
0 Resources
8 MeSH Terms
Low-rank plus sparse compressed sensing for accelerated proton resonance frequency shift MR temperature imaging.
Cao Z, Gore JC, Grissom WA
(2019) Magn Reson Med 81: 3555-3566
MeSH Terms: Ablation Techniques, Animals, Brain, Humans, Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Magnetic Resonance Imaging, Interventional, Models, Biological, Phantoms, Imaging, Thalamus, Thermography
Show Abstract · Added March 26, 2019
PURPOSE - To improve multichannel compressed sensing (CS) reconstruction for MR proton resonance frequency (PRF) shift thermography, with application to MRI-induced RF heating evaluation and MR guided high intensity focused ultrasound (MRgFUS) temperature monitoring.
METHODS - A new compressed sensing reconstruction is proposed that enforces joint low rank and sparsity of complex difference domain PRF data between post heating and baseline images. Validations were performed on 4 retrospectively undersampled dynamic data sets in PRF applications, by comparing the proposed method to a previously described L and total variation- (TV-) based CS approach that also operates on complex difference domain data, and to a conventional low rank plus sparse (L+S) separation-based CS reconstruction applied to the original domain data.
RESULTS - In all 4 retrospective validations, the proposed reconstruction method outperformed the conventional L+S and L +TV CS reconstruction methods with a 3.6× acceleration ratio in terms of temperature accuracy with respect to fully sampled data. For RF heating evaluation, the proposed method achieved RMS error of 12%, compared to 19% for the L+S method and 17% for the L +TV method. For in vivo MRgFUS thalamotomy, the peak temperature reconstruction errors were 19%, 31%, and 35%, respectively.
CONCLUSION - The complex difference-based low rank and sparse model enhances compressibility for dynamic PRF temperature imaging applications. The proposed multichannel CS reconstruction method enables high acceleration factors for PRF applications including RF heating evaluation and MRgFUS sonication.
© 2019 International Society for Magnetic Resonance in Medicine.
0 Communities
1 Members
0 Resources
11 MeSH Terms
White matter differences between essential tremor and Parkinson disease.
Juttukonda MR, Franco G, Englot DJ, Lin YC, Petersen KJ, Trujillo P, Hedera P, Landman BA, Kang H, Donahue MJ, Konrad PE, Dawant BM, Claassen DO
(2019) Neurology 92: e30-e39
MeSH Terms: Aged, Anisotropy, Cohort Studies, Diffusion Tensor Imaging, Essential Tremor, Female, Humans, Image Processing, Computer-Assisted, Leukoencephalopathies, Logistic Models, Male, Middle Aged, Parkinson Disease
Show Abstract · Added June 22, 2019
OBJECTIVE - To assess white matter integrity in patients with essential tremor (ET) and Parkinson disease (PD) with moderate to severe motor impairment.
METHODS - Sedated participants with ET (n = 57) or PD (n = 99) underwent diffusion tensor imaging (DTI) and fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity values were computed. White matter tracts were defined using 3 well-described atlases. To determine candidate white matter regions that differ between ET and PD groups, a bootstrapping analysis was applied using the least absolute shrinkage and selection operator. Linear regression was applied to assess magnitude and direction of differences in DTI metrics between ET and PD populations in the candidate regions.
RESULTS - Fractional anisotropy values that differentiate ET from PD localize primarily to thalamic and visual-related pathways, while diffusivity differences localized to the cerebellar peduncles. Patients with ET exhibited lower fractional anisotropy values than patients with PD in the lateral geniculate body ( < 0.01), sagittal stratum ( = 0.01), forceps major ( = 0.02), pontine crossing tract ( = 0.03), and retrolenticular internal capsule ( = 0.04). Patients with ET exhibited greater radial diffusivity values than patients with PD in the superior cerebellar peduncle ( < 0.01), middle cerebellar peduncle ( = 0.05), and inferior cerebellar peduncle ( = 0.05).
CONCLUSIONS - Regionally, distinctive white matter microstructural values in patients with ET localize to the cerebellar peduncles and thalamo-cortical visual pathways. These findings complement recent functional imaging studies in ET but also extend our understanding of putative physiologic features that account for distinctions between ET and PD.
© 2018 American Academy of Neurology.
0 Communities
1 Members
0 Resources
13 MeSH Terms