Biomechanical modeling of tissue deformation can be used to simulate different scenarios of longitudinal brain evolution. In this work,we present a deep learning framework for hyper-elastic strain modelling of brain atrophy, during healthy ageing and
in Alzheimers Disease. The framework directly models the effects of age, disease status, and scan interval to regress regional patterns of atrophy, from which a strain-based model estimates deformations. This model is trained and validated using 3D structural magnetic resonance imaging data from the ADNI cohort. Results show that the framework can estimate realistic deformations, following the known course of Alzheimers disease, that clearly differentiate between healthy and demented patterns of ageing. This suggests the framework has potential to be incorporated into explainable models of disease, for the exploration of interventions and counterfactual examples.
An important goal of medical imaging is to be able to precisely detect patterns of disease specific to individual scans; however, this is challenged in brain imaging by the degree of heterogeneity of shape and appearance. Traditional methods, based o
n image registration to a global template, historically fail to detect variable features of disease, as they utilise population-based analyses, suited primarily to studying group-average effects. In this paper we therefore take advantage of recent developments in generative deep learning to develop a method for simultaneous classification, or regression, and feature attribution (FA). Specifically, we explore the use of a VAE-GAN translation network called ICAM, to explicitly disentangle class relevant features from background confounds for improved interpretability and regression of neurological phenotypes. We validate our method on the tasks of Mini-Mental State Examination (MMSE) cognitive test score prediction for the Alzheimers Disease Neuroimaging Initiative (ADNI) cohort, as well as brain age prediction, for both neurodevelopment and neurodegeneration, using the developing Human Connectome Project (dHCP) and UK Biobank datasets. We show that the generated FA maps can be used to explain outlier predictions and demonstrate that the inclusion of a regression module improves the disentanglement of the latent space. Our code is freely available on Github https://github.com/CherBass/ICAM.
We present a proof-of-concept, deep learning (DL) based, differentiable biomechanical model of realistic brain deformations. Using prescribed maps of local atrophy and growth as input, the network learns to deform images according to a Neo-Hookean mo
del of tissue deformation. The tool is validated using longitudinal brain atrophy data from the Alzheimers Disease Neuroimaging Initiative (ADNI) dataset, and we demonstrate that the trained model is capable of rapidly simulating new brain deformations with minimal residuals. This method has the potential to be used in data augmentation or for the exploration of different causal hypotheses reflecting brain growth and atrophy.
Feature attribution (FA), or the assignment of class-relevance to different locations in an image, is important for many classification problems but is particularly crucial within the neuroscience domain, where accurate mechanistic models of behaviou
rs, or disease, require knowledge of all features discriminative of a trait. At the same time, predicting class relevance from brain images is challenging as phenotypes are typically heterogeneous, and changes occur against a background of significant natural variation. Here, we present a novel framework for creating class specific FA maps through image-to-image translation. We propose the use of a VAE-GAN to explicitly disentangle class relevance from background features for improved interpretability properties, which results in meaningful FA maps. We validate our method on 2D and 3D brain image datasets of dementia (ADNI dataset), ageing (UK Biobank), and (simulated) lesion detection. We show that FA maps generated by our method outperform baseline FA methods when validated against ground truth. More significantly, our approach is the first to use latent space sampling to support exploration of phenotype variation. Our code will be available online at https://github.com/CherBass/ICAM.
Management of discarded tires is a compelling environmental issue worldwide. Although several approaches have been developed to recycle waste tire rubbers, their application in solid-state cooling is still unexplored. Considering the high barocaloric
potential verified for elastomers, the use of waste tire rubber (WTR) as refrigerant in solid-state cooling devices is very promising. Here, we investigated the barocaloric effects in WTR and polymer blends made of vulcanized natural rubber (VNR) and WTR, in order to evaluate its feasibility for solid-state cooling technologies. The adiabatic temperature change and the isothermal entropy change reach giant values, as well as the performance parameters, being comparable or even better than most barocaloric materials in literature. Moreover, pure WTR and WTR-based samples also present a faster thermal exchange than VNR, consisting in an additional advantage of using these discarded materials. Thus, the present findings evidence the encouraging perspectives of employing waste rubbers in solid-state cooling based on barocaloric effect, contributing in both the recycling of polymers and the sustainable energy technology field.
