Adversarial Pseudo Healthy Synthesis Needs Pathology Factorization

Tian Xia, Agisilaos Chartsias, Sotirios Tsaftaris

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Pseudo healthy synthesis, i.e. the creation of a subject-specific `healthy' image from a pathological one, could be helpful in tasks such as anomaly detection, understanding changes induced by pathology and disease or even as data augmentation. We treat this task as a factor decomposition problem: we aim to separate what appears to be healthy and where disease is (as a map). The two factors are then recombined (by a network) to reconstruct the input disease image. We train our models in an adversarial way using either paired or unpaired settings, where we pair disease images and maps (as segmentation masks) when available. We quantitatively evaluate the quality of pseudo healthy images. We show in a series of experiments, performed in ISLES and BraTS datasets, that our method is better than conditional GAN and CycleGAN, highlighting challenges in using adversarial methods in the image translation task of pseudo healthy image generation.
Original languageEnglish
Title of host publicationProceedings of Machine Learning Research
Subtitle of host publicationMedical Imaging Deep Learning
Volume102
Publication statusPublished - 10 Jul 2019
EventInternational Conference on Medical Imaging with Deep Learning - London, United Kingdom
Duration: 8 Jul 201910 Jul 2019
https://2019.midl.io/

Conference

ConferenceInternational Conference on Medical Imaging with Deep Learning
Abbreviated titleMIDL 2019
CountryUnited Kingdom
CityLondon
Period8/07/1910/07/19
Internet address

Fingerprint Dive into the research topics of 'Adversarial Pseudo Healthy Synthesis Needs Pathology Factorization'. Together they form a unique fingerprint.

Cite this