Domain Adaption for Homogenizing CT Scans using Auto-Encoders for Cross-Dataset Medical Image Analysis

Mohammadreza Amirian, Javier A. Montoya-Zegarra, Ahmet Selman Bozkir, Marco Calandri, Friedhelm Schwenker, Thilo Stadelmann

Keywords: Adaptive preprocessing, domain adaptation, auto-encoder

TL;DR: This paper proposes an architecture to unify several CT scan datasets concerning varying image acquisition circumstances through a trainable preprocessing network and presents promising preliminary experimental results on two public datasets.

Abstract: Medical imaging research profits from data unification and homogenization methods to merge global datasets in order to reduce annotation effort and improve generalization of trained models to unseen datasets. In this paper, we explicitly address dataset variability using two public datasets and propose an architecture that aims at erasing the differences in CT scans from different sources while simultaneously introducing only minimal changes through leveraging the idea of deep auto-encoders. The proposed trainable prepossessing architecture (PrepNet) (i) is jointly trained on the SARS-COVID-2 and UCSD COVID-CT datasets and (ii) maintains discriminant features for downstream diagnosis.

Paper Type: both

Primary Subject Area: Transfer Learning and Domain Adaptation

Secondary Subject Area: Detection and Diagnosis

Paper Status: original work, not submitted yet

Source Code Url: To be published after further developments.

Data Set Url: Public datasets are available in the references.

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.