Quantifiable brain atrophy synthesis for benchmarking of cortical thickness estimation methods

Rusak, Filip; Cruz, Rodrigo Santa; Lebrat, Léo; Hlinka, Ondrej; Fripp, Jürgen; Smith, Elliot; Fookes, Clinton; Bradley, Andrew P.; Bourgeat, Pierrick

doi:10.1016/j.media.2022.102576

Cited by 15 publications

(25 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our findings of smaller error bars when using DL+-DiReCT instead of FreeSurfer together with larger group separation capabilities strongly suggest DL-based input for SCN estimation as an alternative. Enhanced robustness of DL+DiReCT compared to Free-Surfer has been reported before (Rebsamen et al, 2020(Rebsamen et al, , 2022Rusak et al, 2022). SCN analysis revealed clear separation between the two subgroups of MS, with DL+DiReCT from both non-enhanced and CE images.…”

Section: Structural Covariance Network (Scn)supporting

confidence: 61%

Reliable brain morphometry from contrast‐enhanced T1w‐MRI in patients with multiple sclerosis

Rebsamen

McKinley

Radojewski

et al. 2022

Human Brain Mapping

View full text Add to dashboard Cite

Brain morphometry is usually based on non-enhanced (pre-contrast) T1-weighted MRI. However, such dedicated protocols are sometimes missing in clinical examinations. Instead, an image with a contrast agent is often available. Existing tools such as FreeSurfer yield unreliable results when applied to contrast-enhanced (CE) images.Consequently, these acquisitions are excluded from retrospective morphometry studies, which reduces the sample size. We hypothesize that deep learning (DL)-based morphometry methods can extract morphometric measures also from contrastenhanced MRI. We have extended DL+DiReCT to cope with contrast-enhanced MRI. Training data for our DL-based model were enriched with non-enhanced and CE image pairs from the same session. The segmentations were derived with Free-Surfer from the non-enhanced image and used as ground truth for the coregistered CE image. A longitudinal dataset of patients with multiple sclerosis (MS), comprising relapsing remitting (RRMS) and primary progressive (PPMS) subgroups, was used for the evaluation. Global and regional cortical thickness derived from non-enhanced and CE images were contrasted to results from FreeSurfer. Correlation coefficients of global mean cortical thickness between non-enhanced and CE images were significantly larger with DL+DiReCT (r = 0.92) than with FreeSurfer (r = 0.75). When comparing the longitudinal atrophy rates between the two MS subgroups, the effect sizes between PPMS and RRMS were higher with DL+DiReCT both for non-enhanced (d = À0.304) and CE images (d = À0.169) than for FreeSurfer (non-enhanced d = À0.111, CE d = 0.085). In conclusion, brain morphometry can be derived reliably from contrast-enhanced MRI using DL-based morphometry tools, making additional cases available for analysis and potential future diagnostic morphometry tools.

show abstract

Section: Structural Covariance Network (Scn)supporting

confidence: 61%

Reliable brain morphometry from contrast‐enhanced T1w‐MRI in patients with multiple sclerosis

Rebsamen

McKinley

Radojewski

et al. 2022

Human Brain Mapping

View full text Add to dashboard Cite

show abstract

“…We additionally applied the UKB-trained algorithm to a synthetic dataset of global neocortical thinning from Rusak et al (2022). The authors simulated neocortical thickness loss from 0 to 0.1 mm in steps of 0.01 mm per time point.…”

Section: Resultsmentioning

confidence: 99%

“…To further validate the model, we used a synthetic global neocortical atrophy dataset by Rusak et al (2022), which was derived from ADNI baseline scans of 20 subjects without AD ( n = 20; M Age = 70.65±5.39) and used to simulate neocortical thinning, progressing from 0 to 0.1 mm or 1 mm thickness loss, with steps of 0.01 mm or 0.1 mm between the time points, respectively, resulting in total of 400 synthetic images.…”

Section: Methodsmentioning

confidence: 99%

“…ADNI dataset is publicly available at https://ida.loni.usc.edu/login.jsp?project=ADNI and IXI at https://brain-development.org/ixi-dataset/. The synthetic dataset from Rusak et al (2022) is available at the CSIRO data access portal .…”

Section: Data Availability Statementmentioning

confidence: 99%

“…In addition, the simulated images were only provided in MNI space which can also affect BrainAGE prediction as a general offset but not the slope. Despite the artificial character of simulated atrophy pattern, the dataset allows for testing specific structural changes (Aubert-Broche et al, 2006, Lerch et al, 2005, Rusak et al 2022) and their interaction with the brain age algorithms. Simulated datasets can serve as an alternative approach to explainable AI by providing information on the influence of anatomical characteristics on brain age prediction.…”

Section: Generalisability and Validitymentioning

confidence: 99%

See 2 more Smart Citations

BrainAGE: Revisited and reframed machine learning workflow

Kalc

Dahnke

Hoffstaedter

et al. 2022

Preprint

View full text Add to dashboard Cite

Since the introduction of the BrainAGE method (Franke et al., 2010), novel machine learning methods of brain age prediction have continued to emerge. The idea of estimating the chronological age from (different modalities of) magnetic resonance images proved to be an interesting field of research due to the simplicity of its interpretation and its potential use as a biomarker of brain health. With the advancement of deep learning methods that are starting to dominate the field, it may seem like standard machine learning methods are not competitive anymore. Here we present our revised BrainAGE framework that combines multiple weighted BrainAGE models. We employed the analyses on a sample of 36840 T1-weighted images from the UK Biobank. The most accurate prediction with a mean absolute error (MAE) of 2.02 years was obtained by relevance vector regression weighted model combination. Our results are comparable to those of deep learning methods. We additionally tested the relation of different BrainAGE models and white matter hyperintensities as markers of ageing brain and found no differences in association to biomedical data between models of differing accuracies.

show abstract

BrainAGE: Revisited and reframed machine learning workflow

Kalc,

Dahnke,

Hoffstaedter

et al. 2024

Human Brain Mapping

View full text Add to dashboard Cite

Since the introduction of the BrainAGE method, novel machine learning methods for brain age prediction have continued to emerge. The idea of estimating the chronological age from magnetic resonance images proved to be an interesting field of research due to the relative simplicity of its interpretation and its potential use as a biomarker of brain health. We revised our previous BrainAGE approach, originally utilising relevance vector regression (RVR), and substituted it with Gaussian process regression (GPR), which enables more stable processing of larger datasets, such as the UK Biobank (UKB). In addition, we extended the global BrainAGE approach to regional BrainAGE, providing spatially specific scores for five brain lobes per hemisphere. We tested the performance of the new algorithms under several different conditions and investigated their validity on the ADNI and schizophrenia samples, as well as on a synthetic dataset of neocortical thinning. The results show an improved performance of the reframed global model on the UKB sample with a mean absolute error (MAE) of less than 2 years and a significant difference in BrainAGE between healthy participants and patients with Alzheimer's disease and schizophrenia. Moreover, the workings of the algorithm show meaningful effects for a simulated neocortical atrophy dataset. The regional BrainAGE model performed well on two clinical samples, showing disease‐specific patterns for different levels of impairment. The results demonstrate that the new improved algorithms provide reliable and valid brain age estimations.

show abstract

Quantifiable brain atrophy synthesis for benchmarking of cortical thickness estimation methods

Cited by 15 publications

References 40 publications

Reliable brain morphometry from contrast‐enhanced T1w‐MRI in patients with multiple sclerosis

Reliable brain morphometry from contrast‐enhanced T1w‐MRI in patients with multiple sclerosis

BrainAGE: Revisited and reframed machine learning workflow

BrainAGE: Revisited and reframed machine learning workflow

Contact Info

Product

Resources

About