Skip to Main content Skip to Navigation
Conference papers

A Gaussian Process Model Based Generative Framework for Data Augmentation of Multi-modal 3D Image Volumes

Abstract : Medical imaging protocols routinely employ more than one image modality for diagnosis or treatment. To reduce healthcare costs in such scenarios, research is ongoing on synthetically generating images of one modality from another. Machine learning has shown great potential for such synthesis but performance suffers from scarcity of high quality, co-registered, balanced, and paired multi-modal data required for the training. While methods that do not depend on paired data have been reported, image quality limitations persist including image blurriness. We propose a framework to synthetically generate co-registered and paired 3D volume data using Gaussian process morphable models constructed from a single matching pair of multi-modal 3D image volumes. We demonstrate the application of the framework for matching pairs of CT and MR 3D image volume data with our main contributions being: 1) A generative process for synthesising valid, realistic, and co-registered pairs of CT and MR 3D image volumes, 2) Evaluation of the consistency of the coupling between the generated image volume pairs. Our experiments show that the proposed method is a viable approach to data augmentation that could be used in resource limited environments.
Document type :
Conference papers
Complete list of metadata

https://hal-imt-atlantique.archives-ouvertes.fr/hal-03384418
Contributor : Valérie Burdin Connect in order to contact the contributor
Submitted on : Monday, October 18, 2021 - 10:20:36 PM
Last modification on : Wednesday, November 3, 2021 - 10:01:59 AM

Identifiers

Citation

Nicolas Nbonsou Tegang, Jean-Rassaire Fouefack, Bhushan Borotikar, Valérie Burdin, Tania Douglas, et al.. A Gaussian Process Model Based Generative Framework for Data Augmentation of Multi-modal 3D Image Volumes. SASHIMI 2020: Simulation and Synthesis in Medical Imaging, Oct 2020, Lima, Peru. pp.90-100, ⟨10.1007/978-3-030-59520-3_10⟩. ⟨hal-03384418⟩

Share

Metrics

Record views

25