ICAM-reg: Interpretable Classification and Regression with Feature Attribution for Mapping Neurological Phenotypes in Individual Scans

@article{Bass2021ICAMregIC,
  title={ICAM-reg: Interpretable Classification and Regression with Feature Attribution for Mapping Neurological Phenotypes in Individual Scans},
  author={Cher Bass and Mariana da Silva and Carole Helene Sudre and Logan Z. J. Williams and Petru-Daniel Tudosiu and Fidel Alfaro-Almagro and Sean P. Fitzgibbon and Matthew F. Glasser and Stephen M. Smith and Emma Claire Robinson},
  journal={IEEE transactions on medical imaging},
  year={2021},
  volume={PP}
}
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 on image registration, 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… 

Voxel-level Importance Maps for Interpretable Brain Age Estimation

This study focuses on the task of brain age regression from 3D brain MR images using a Convolutional Neural Network, termed prediction model, and interpret its predictions by extracting importance maps, which discover the parts of the brain that are the most important for brain age.

Benchmarking Geometric Deep Learning for Cortical Segmentation and Neurodevelopmental Phenotype Prediction

This paper benchmarks a collection of geometric and traditional deep learning models on phenotype prediction and segmentation of sphericalised neonatal cortical surface data, from the publicly available Developing Human Connectome Project (dHCP).

Towards better Interpretable and Generalizable AD detection using Collective Artificial Intelligence

NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants

Experimental results on the public dHCP benchmark suggest that Neuro Explainer led to quantitatively reliable explanation results that are qualitatively consistent with representative neuroimaging studies.

A Deep Generative Model of Neonatal Cortical Surface Development

A surface-based CycleGAN using mixture model CNNs (MoNet) to translate spher-icalised neonatal cortical surface features (curvature and T1w/T2w cortical myelin) between different stages of cortical maturity and is able to reliably predict changes in individual patterns of cortical organisation at later stages of gestation.

Multiscale Metamorphic VAE for 3D Brain MRI Synthesis

This work proposes to address the challenge of generative modeling of 3D brain MRIs with composable, multiscale morphological transformations in a variational autoencoder (VAE) framework, equipping the model with strong anatomical inductive biases.

The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study

The result indicated that the utilisation of optimizers such as SGD and Adam improved the accuracy in training, testing, and validation stages and was crucial to analyse and summarise optimization techniques methodically from a machine learning standpoint.

References

SHOWING 1-10 OF 62 REFERENCES

ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping

This work proposes the use of a VAE-GAN to explicitly disentangle class relevance from background features for improved interpretability properties, which results in meaningful FA maps that outperform baseline FA methods when validated against ground truth.

Visual Feature Attribution Using Wasserstein GANs

This paper develops a novel feature attribution technique based on Wasserstein Generative Adversarial Networks (WGAN), which performs substantially better than the state-of-the-art for visual attribution on a synthetic dataset and on real 3D neuroimaging data from patients with mild cognitive impairment and Alzheimer's disease.

Testing the robustness of attribution methods for convolutional neural networks in MRI-based Alzheimer's disease classification

It is shown that visual comparison is not sufficient and that some widely used attribution methods produce highly inconsistent outcomes, including gradient*input, guided backpropagation, layer-wise relevance propagation and occlusion.

Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification

It is concluded that LRP might have a high potential to assist clinicians in explaining neural network decisions for diagnosing AD (and potentially other diseases) based on structural MRI data.

Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images

This work shows that deep spatial autoencoding models can be efficiently used to capture normal anatomical variability of entire 2D brain MR images and shows that constraints on the latent space and adversarial training can further improve the segmentation performance over standard deep representation learning.

A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain.

A deep learning algorithm developed for early prediction of Alzheimer disease achieved 82% specificity at 100% sensitivity, an average of 75.8 months prior to the final diagnosis, which in ROC space outperformed reader performance.

VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images

A brief history of voxel-based grey matter analysis in Alzheimer's disease.

The hypothesis that VBM can sensitively detect hippocampal atrophy, but is relatively insensitive to changes in the cortical ribbon, is tested, by contrasting VBM with FreeSurfer cortical thickness measurements and highlighting a bias that V BM has toward detecting mesial temporal lobe atrophy.

Multimodal population brain imaging in the UK Biobank prospective epidemiological study

UK Biobank brain imaging is described and results derived from the first 5,000 participants' data release are presented, which have already yielded a rich range of associations between brain imaging and other measures collected by UK Biobanks.
...