Bridging the Gap Between Paired and Unpaired Medical Image Translation

Pauliina Paavilainen*, Saad Ullah Akram, Juho Kannala

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

4 Citations (Scopus)

Abstract

Medical image translation has the potential to reduce the imaging workload, by removing the need to capture some sequences, and to reduce the annotation burden for developing machine learning methods. GANs have been used successfully to translate images from one domain to another, such as MR to CT. At present, paired data (registered MR and CT images) or extra supervision (e.g. segmentation masks) is needed to learn good translation models. Registering multiple modalities or annotating structures within each of them is a tedious and laborious task. Thus, there is a need to develop improved translation methods for unpaired data. Here, we introduce modified pix2pix models for tasks CT → MR and MR → CT, trained with unpaired CT and MR data, and MRCAT pairs generated from the MR scans. The proposed modifications utilize the paired MR and MRCAT images to ensure good alignment between input and translated images, and unpaired CT images ensure the MR → CT model produces realistic-looking CT and CT → MR model works well with real CT as input. The proposed pix2pix variants outperform baseline pix2pix, pix2pixHD and CycleGAN in terms of FID and KID, and generate more realistic looking CT and MR translations.

Original languageEnglish
Title of host publicationDeep Generative Models, and Data Augmentation, Labelling, and Imperfections
Subtitle of host publicationFirst Workshop, DGM4MICCAI 2021, and First Workshop, DALI 2021, Held in Conjunction with MICCAI 2021, Proceedings
EditorsSandy Engelhardt, Ilkay Oksuz, Dajiang Zhu, Yixuan Yuan, Anirban Mukhopadhyay, Nicholas Heller, Sharon Xiaolei Huang, Hien Nguyen, Raphael Sznitman, Yuan Xue
PublisherSpringer
Pages35-44
Number of pages10
ISBN (Electronic)9783030882105
ISBN (Print)9783030882099
DOIs
Publication statusPublished - 25 Sept 2021
MoE publication typeA4 Conference publication
EventInternational Conference on Medical Image Computing and Computer Assisted Intervention - Virtual, Online
Duration: 27 Sept 20211 Oct 2021
https://www.miccai2021.org/

Publication series

NameLecture Notes in Computer Science
Volume13003 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceInternational Conference on Medical Image Computing and Computer Assisted Intervention
Abbreviated titleMICCAI
CityVirtual, Online
Period27/09/202101/10/2021
Internet address

Keywords

  • Generative adversarial network
  • Medical image translation

Fingerprint

Dive into the research topics of 'Bridging the Gap Between Paired and Unpaired Medical Image Translation'. Together they form a unique fingerprint.

Cite this