ICAM: Interpretable Classification via Disentangled Representations and Feature Attribution Mapping

by   Cher Bass, et al.

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 behaviours, 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 .


page 2

page 8

page 15

page 19

page 20

page 21

page 22


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

An important goal of medical imaging is to be able to precisely detect p...

Evaluating Feature Attribution Methods in the Image Domain

Feature attribution maps are a popular approach to highlight the most im...

Disentangled representations: towards interpretation of sex determination from hip bone

By highlighting the regions of the input image that contribute the most ...

RepMix: Representation Mixing for Robust Attribution of Synthesized Images

Rapid advances in Generative Adversarial Networks (GANs) raise new chall...

SepVAE: a contrastive VAE to separate pathological patterns from healthy ones

Contrastive Analysis VAE (CA-VAEs) is a family of Variational auto-encod...

Keep CALM and Improve Visual Feature Attribution

The class activation mapping, or CAM, has been the cornerstone of featur...

Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings

We study the effects of constrained optimization formulations and Frank-...

Please sign up or login with your details

Forgot password? Click here to reset