Translational Lung Imaging Analysis Through Disentangled Representations

Pedro M. Gordaliza, Juan José Vaquero, Arrate Munoz-Barrutia

Abstract:

The development of new treatments often requires clinical trials with translational animal models using (pre)-clinical imaging to characterize inter-species pathological processes. Deep Learning (DL) models are commonly used to automate the extraction of relevant information from the images. The DL models are usually specific for each animal model. This is due to their typical low generalizability and explainability as a product of their entangled design. Consequently, it is not possible to take advantage of the high capacity
of DL to discover statistical relationships from inter-species images. To alleviate this problem, in this work, we present a model capable of extracting disentangled information from images of different animal models, as well as the mechanisms that generate the images. Our method is located at the intersection between deep generative models, disentanglement and causal representation learning. It is optimized from images of pathological lung infected by Tuberculosis and is able: a) from an input slice, infer its position in a volume, the animal model to which it belongs, the damage present and even more, generate its mask (similar overlap measures to the nnU-Net), b) generate realistic lung images by setting the above variables and c) generate counterfactual images. Namely, healthy versions of a damaged input slice.

Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.

Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.

Paper Type: methodological development

Primary Subject Area: Unsupervised Learning and Representation Learning

Secondary Subject Area: Integration of Imaging and Clinical Data

Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/translational-lung-imaging-analysis-through/code)