End-to-end autoencoding architecture for the simultaneous generation of medical images and corresponding segmentation masks

Despite the increasing use of deep learning in medical image segmentation, acquiring sufficient training data remains a challenge in the medical field. In response, data augmentation techniques have been proposed; however, the generation of diverse and realistic medical images and their correspondin...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org
Main Authors: Aghiles Kebaili, Lapuyade-Lahorgue, Jérôme, Vera, Pierre, Ruan, Su
Format: Paper
Language:English
Published: Ithaca Cornell University Library, arXiv.org 17.11.2023
Subjects:
Data acquisition
Data augmentation
Image acquisition
Image processing
Image quality
Image segmentation
Machine learning
Masks
Medical imaging
Tumors
ISSN:2331-8422
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Despite the increasing use of deep learning in medical image segmentation, acquiring sufficient training data remains a challenge in the medical field. In response, data augmentation techniques have been proposed; however, the generation of diverse and realistic medical images and their corresponding masks remains a difficult task, especially when working with insufficient training sets. To address these limitations, we present an end-to-end architecture based on the Hamiltonian Variational Autoencoder (HVAE). This approach yields an improved posterior distribution approximation compared to traditional Variational Autoencoders (VAE), resulting in higher image generation quality. Our method outperforms generative adversarial architectures under data-scarce conditions, showcasing enhancements in image quality and precise tumor mask synthesis. We conduct experiments on two publicly available datasets, MICCAI's Brain Tumor Segmentation Challenge (BRATS), and Head and Neck Tumor Segmentation Challenge (HECKTOR), demonstrating the effectiveness of our method on different medical imaging modalities.
Bibliography:SourceType-Working Papers-1
ObjectType-Working Paper/Pre-Print-1
content type line 50
ISSN:2331-8422
DOI:10.48550/arxiv.2311.10472