On the estimation and correction of bias in local atrophy estimations using example atrophy simulations

Generating Longitudinal Atrophy Evaluation Datasets on Brain Magnetic Resonance Images Using Convolutional Neural Networks and Segmentation Priors

Brain atrophy quantification plays a fundamental role in neuroinformatics since it permits studying brain development and neurological disorders. However, the lack of a ground truth prevents testing the accuracy of longitudinal atrophy quantification methods. We propose a deep learning framework to generate longitudinal datasets by deforming T1-w brain magnetic resonance imaging scans as requested through segmentation maps. Our proposal incorporates a cascaded multi-path U-Net optimised with a multi-objective loss which allows its paths to generate different brain regions accurately. We provided our model with baseline scans and real follow-up segmentation maps from two longitudinal datasets, ADNI and OASIS, and observed that our framework could produce synthetic follow-up scans that matched the real ones (Total scans= 584; Median absolute error: 0.03 ± 0.02; Structural similarity index: 0.98 ± 0.02; Dice similarity coefficient: 0.95 ± 0.02; Percentage of brain volume change: 0.24 ± 0.16; Jacobian integration: 1.13 ± 0.05). Compared to two relevant works generating brain lesions using U-Nets and conditional generative adversarial networks (CGAN), our proposal outperformed them significantly in most cases (p < 0.01), except in the delineation of brain edges where the CGAN took the lead (Jacobian integration: Ours - 1.13 ± 0.05 vs CGAN - 1.00 ± 0.02; p < 0.01). We examined whether changes induced with our framework were detected by FAST, SPM, SIENA, SIENAX, and the Jacobian integration method. We observed that induced and detected changes were highly correlated (Adj. R² > 0.86). Our preliminary results on harmonised datasets showed the potential of our framework to be applied to various data collections without further adjustment.

Agreement of MSmetrix with established methods for measuring cross-sectional and longitudinal brain atrophy

INTRODUCTION

Despite the recognized importance of atrophy in multiple sclerosis (MS), methods for its quantification have been mostly restricted to the research domain. Recently, a CE labelled and FDA approved MS-specific atrophy quantification method, MSmetrix, has become commercially available. Here we perform a validation of MSmetrix against established methods in simulated and in vivo MRI data.

METHODS

Whole-brain and gray matter (GM) volume were measured with the cross-sectional pipeline of MSmetrix and compared to the outcomes of FreeSurfer (cross-sectional pipeline), SIENAX and SPM. For this comparison we investigated 20 simulated brain images, as well as in vivo data from 100 MS patients and 20 matched healthy controls. In fifty of the MS patients a second time point was available. In this subgroup, we additionally analyzed the whole-brain and GM volume change using the longitudinal pipeline of MSmetrix and compared the results with those of FreeSurfer (longitudinal pipeline) and SIENA.

RESULTS

In the simulated data, SIENAX displayed the smallest average deviation compared with the reference whole-brain volume (+ 19.56 ± 10.34 mL), followed by MSmetrix (- 38.15 ± 17.77 mL), SPM (- 42.99 ± 17.12 mL) and FreeSurfer (- 78.51 ± 12.68 mL). A similar pattern was seen in vivo. Among the cross-sectional methods, Deming regression analyses revealed proportional errors particularly in MSmetrix and SPM. The mean difference percentage brain volume change (PBVC) was lowest between longitudinal MSmetrix and SIENA (+ 0.16 ± 0.91%). A strong proportional error was present between longitudinal percentage gray matter volume change (PGVC) measures of MSmetrix and FreeSurfer (slope = 2.48). All longitudinal methods were sensitive to the MRI hardware upgrade that occurred during the time of the study.

CONCLUSION

MSmetrix, FreeSurfer, FSL and SPM show differences in atrophy measurements, even at the whole-brain level, that are large compared to typical atrophy rates observed in MS. Especially striking are the proportional errors between methods. Cross-sectional MSmetrix behaved similarly to SPM, both in terms of mean volume difference as well as proportional error. Longitudinal MSmetrix behaved most similar to SIENA. Our results indicate that brain volume measurement and normalization from T1-weighted images remains an unsolved problem that requires much more attention.

Simulating Longitudinal Brain MRIs with Known Volume Changes and Realistic Variations in Image Intensity

This paper presents a simulator tool that can simulate large databases of visually realistic longitudinal MRIs with known volume changes. The simulator is based on a previously proposed biophysical model of brain deformation due to atrophy in AD. In this work, we propose a novel way of reproducing realistic intensity variation in longitudinal brain MRIs, which is inspired by an approach used for the generation of synthetic cardiac sequence images. This approach combines a deformation field obtained from the biophysical model with a deformation field obtained by a non-rigid registration of two images. The combined deformation field is then used to simulate a new image with specified atrophy from the first image, but with the intensity characteristics of the second image. This allows to generate the realistic variations present in real longitudinal time-series of images, such as the independence of noise between two acquisitions and the potential presence of variable acquisition artifacts. Various options available in the simulator software are briefly explained in this paper. In addition, the software is released as an open-source repository. The availability of the software allows researchers to produce tailored databases of images with ground truth volume changes; we believe this will help developing more robust brain morphometry tools. Additionally, we believe that the scientific community can also use the software to further experiment with the proposed model, and add more complex models of brain deformation and atrophy generation.

A biophysical model of shape changes due to atrophy in the brain with Alzheimer's disease

This paper proposes a model of brain deformation triggered by atrophy in Alzheimer's Disease (AD). We introduce a macroscopic biophysical model assuming that the density of the brain remains constant, hence its volume shrinks when neurons die in AD. The deformation in the brain parenchyma minimizes the elastic strain energy with the prescribed local volume loss. The cerebrospinal fluid (CSF) is modelled differently to allow for fluid readjustments occuring at a much faster time-scale. PDEs describing the model is discretized in staggered grid and solved using Finite Difference Method. We illustrate the power of the model by showing different deformation patterns obtained for the same global atrophy but prescribed in gray matter (GM) or white matter (WM) on a generic atlas MRI, and with a realistic AD simulation on a subject MRI. This well-grounded forward model opens a way to study different hypotheses about the distribution of brain atrophy, and to study its impact on the observed changes in MR images.

Simulating neurodegeneration through longitudinal population analysis of structural and diffusion weighted MRI data

Neuroimaging biomarkers play a prominent role for disease diagnosis or tracking neurodegenerative processes. Multiple methods have been proposed by the community to extract robust disease specific markers from various imaging modalities. Evaluating the accuracy and robustness of developed methods is difficult due to the lack of a biologically realistic ground truth. We propose a proof-of-concept method for a patient- and disease-specific brain neurodegeneration simulator. The proposed scheme, based on longitudinal multi-modal data, has been applied to a population of normal controls and patients diagnosed with Alzheimer's disease or frontotemporal dementia. We simulated follow-up images from baseline scans and compared them to real repeat images. Additionally, simulated maps of volume change are generated, which can be compared to maps estimated from real longitudinal data. The results indicate that the proposed simulator reproduces realistic patient-specific patterns of longitudinal brain change for the given populations.