Dataset Information

BrainLossNet: a fast, accurate and robust method to estimate brain volume loss from longitudinal MRI.

ABSTRACT:

Purpose

MRI-derived brain volume loss (BVL) is widely used as neurodegeneration marker. SIENA is state-of-the-art for BVL measurement, but limited by long computation time. Here we propose "BrainLossNet", a convolutional neural network (CNN)-based method for BVL-estimation.

Methods

BrainLossNet uses CNN-based non-linear registration of baseline(BL)/follow-up(FU) 3D-T1w-MRI pairs. BVL is computed by non-linear registration of brain parenchyma masks segmented in the BL/FU scans. The BVL estimate is corrected for image distortions using the apparent volume change of the total intracranial volume. BrainLossNet was trained on 1525 BL/FU pairs from 83 scanners. Agreement between BrainLossNet and SIENA was assessed in 225 BL/FU pairs from 94 MS patients acquired with a single scanner and 268 BL/FU pairs from 52 scanners acquired for various indications. Robustness to short-term variability of 3D-T1w-MRI was compared in 354 BL/FU pairs from a single healthy men acquired in the same session without repositioning with 116 scanners (Frequently-Traveling-Human-Phantom dataset, FTHP).

Results

Processing time of BrainLossNet was 2-3 min. The median [interquartile range] of the SIENA-BrainLossNet BVL difference was 0.10% [- 0.18%, 0.35%] in the MS dataset, 0.08% [- 0.14%, 0.28%] in the various indications dataset. The distribution of apparent BVL in the FTHP dataset was narrower with BrainLossNet (p = 0.036; 95th percentile: 0.20% vs 0.32%).

Conclusion

BrainLossNet on average provides the same BVL estimates as SIENA, but it is significantly more robust, probably due to its built-in distortion correction. Processing time of 2-3 min makes BrainLossNet suitable for clinical routine. This can pave the way for widespread clinical use of BVL estimation from intra-scanner BL/FU pairs.

SUBMITTER: Opfer R

PROVIDER: S-EPMC11365843 | biostudies-literature | 2024 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

BrainLossNet: a fast, accurate and robust method to estimate brain volume loss from longitudinal MRI.

Opfer Roland R Krüger Julia J Buddenkotte Thomas T Spies Lothar L Behrendt Finn F Schippling Sven S Buchert Ralph R

International journal of computer assisted radiology and surgery 20240616 9

<h4>Purpose</h4>MRI-derived brain volume loss (BVL) is widely used as neurodegeneration marker. SIENA is state-of-the-art for BVL measurement, but limited by long computation time. Here we propose "BrainLossNet", a convolutional neural network (CNN)-based method for BVL-estimation.<h4>Methods</h4>BrainLossNet uses CNN-based non-linear registration of baseline(BL)/follow-up(FU) 3D-T1w-MRI pairs. BVL is computed by non-linear registration of brain parenchyma masks segmented in the BL/FU scans. The ...[more]

PMID: 38879844

Similar Datasets

Project description:Advances in biophysical multi-compartment modeling for diffusion MRI (dMRI) have gained popularity because of greater specificity than DTI in relating the dMRI signal to underlying cellular microstructure. A large range of these diffusion microstructure models have been developed and each of the popular models comes with its own, often different, optimization algorithm, noise model and initialization strategy to estimate its parameter maps. Since data fit, accuracy and precision is hard to verify, this creates additional challenges to comparability and generalization of results from diffusion microstructure models. In addition, non-linear optimization is computationally expensive leading to very long run times, which can be prohibitive in large group or population studies. In this technical note we investigate the performance of several optimization algorithms and initialization strategies over a few of the most popular diffusion microstructure models, including NODDI and CHARMED. We evaluate whether a single well performing optimization approach exists that could be applied to many models and would equate both run time and fit aspects. All models, algorithms and strategies were implemented on the Graphics Processing Unit (GPU) to remove run time constraints, with which we achieve whole brain dataset fits in seconds to minutes. We then evaluated fit, accuracy, precision and run time for different models of differing complexity against three common optimization algorithms and three parameter initialization strategies. Variability of the achieved quality of fit in actual data was evaluated on ten subjects of each of two population studies with a different acquisition protocol. We find that optimization algorithms and multi-step optimization approaches have a considerable influence on performance and stability over subjects and over acquisition protocols. The gradient-free Powell conjugate-direction algorithm was found to outperform other common algorithms in terms of run time, fit, accuracy and precision. Parameter initialization approaches were found to be relevant especially for more complex models, such as those involving several fiber orientations per voxel. For these, a fitting cascade initializing or fixing parameter values in a later optimization step from simpler models in an earlier optimization step further improved run time, fit, accuracy and precision compared to a single step fit. This establishes and makes available standards by which robust fit and accuracy can be achieved in shorter run times. This is especially relevant for the use of diffusion microstructure modeling in large group or population studies and in combining microstructure parameter maps with tractography results.

Project description:BackgroundMeasurement of muscle mass is important in the diagnosis of sarcopenia. Current measurement equipment are neither cost-effective nor standardized and cannot be used in a variety of medical settings. Some simple measurement tools have been proposed that are subjective and unvalidated. We aimed to develop and validate a new estimation equation in a more objective and standardized way, based on current proven variables that accurately reflect muscle mass.MethodsCross-sectional analysis with The National Health and Nutrition Examination Survey database for equation development and validation. Overall, 9875 participants were included for development (6913 participants) and validation (2962 participants), for whom the database included demographic data, physical measurements, and main biochemical indicators. Appendicular skeletal muscle mass (ASM) was estimated by dual-energy x-ray absorptiometry (DXA) and low muscle mass was defined by reference to five international diagnostic criteria. Linear regression was used to estimate the logarithm of the actual ASM from demographic data, physical measurements, and biochemical indicators.ResultsThis study of 9875 participants comprised 4492 females (49.0%), with a weighted mean (SE) age of 41.83 (0.36) years and range of 12 to 85 years. The estimated ASM equations performed well in the validation data set. The variability in estimated ASM was low compared with the actual ASM (R2 : Equation 1 = 0.91, Equation 4 = 0.89), with low bias (median difference: Equation 1 = -0.64, Equation 4 = 0.07; root mean square error: Equation 1 = 1.70 [1.69-1.70], Equation 4 = 1.85 [1.84-1.86]), high precision (interquartile range of the differences: Equation 1 = 1.87, Equation 4 = 2.17), and high efficacy in diagnosing low muscle mass (area under the curve: Equation 1 = 0.91 to 0.95, Equation 4 = 0.90 to 0.94).ConclusionsThe estimated ASM equations are accurate and simple and can be routinely applied clinically to estimate ASM and thus assess sarcopenia.

Project description:To investigate longitudinal changes in global and regional brain volume in patients 1 year after mild traumatic brain injury (MTBI) and to correlate such changes with clinical and neurocognitive metrics.This institutional review board-approved study was HIPAA compliant. Twenty-eight patients with MTBI (with 19 followed up at 1 year) with posttraumatic symptoms after injury and 22 matched control subjects (with 12 followed up at 1 year) were enrolled. Automated segmentation of brain regions to compute regional gray matter (GM) and white matter (WM) volumes was performed by using three-dimensional T1-weighted 3.0-T magnetic resonance imaging, and results were correlated with clinical metrics. Pearson and Spearman rank correlation coefficients were computed between longitudinal brain volume and neurocognitive scores, as well as clinical metrics, over the course of the follow-up period.One year after MTBI, there was measurable global brain atrophy, larger than that in control subjects. The anterior cingulate WM bilaterally and the left cingulate gyrus isthmus WM, as well as the right precuneal GM, showed significant decreases in regional volume in patients with MTBI over the 1st year after injury (corrected P < .05); this was confirmed by means of cross-sectional comparison with data in control subjects (corrected P < .05). Left and right rostral anterior cingulum WM volume loss correlated with changes in neurocognitive measures of memory (r = 0.65, P = .005) and attention (r = 0.60, P = .01). At 1-year follow-up, WM volume in the left cingulate gyrus isthmus correlated with clinical scores of anxiety (Spearman rank correlation r = -0.68, P = .007) and postconcussive symptoms (Spearman rank correlation r = -0.65, P = .01).These observations demonstrate structural changes to the brain 1 year after injury after a single concussive episode. Regional brain atrophy is not exclusive to moderate and severe traumatic brain injury but may be seen after mild injury. In particular, the anterior part of the cingulum and the cingulate gyrus isthmus, as well as the precuneal GM, may be distinctively vulnerable 1 year after MTBI.

Dataset Information

BrainLossNet: a fast, accurate and robust method to estimate brain volume loss from longitudinal MRI.

Purpose

Methods

Results

Conclusion

Publications

BrainLossNet: a fast, accurate and robust method to estimate brain volume loss from longitudinal MRI.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets