Clinical evaluation of medical image synthesis: a case study in wireless capsule endoscopy.
Authors
Affiliations (15)
Affiliations (15)
- Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece.
- Department of Clinical Research, University of Southern Denmark, Odense, Denmark.
- Department of Gastroenterology, Pomeranian Medical University, Szczecin, Poland.
- Department of Gastroenterology, Clínica Universidad de Navarra, Pamplona, Spain.
- Gastroenterology Department, Mater Dei Hospital, Msida, MSD 2090, Malta.
- Gastroenterology and Endoscopy Unit, University Hospital of Parma, University of Parma, Parma, Italy.
- Department of Gastroenterology, Hospital Clínic i Provincial de Barcelona, Barcelona, Spain.
- Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas, Madrid, Spain.
- Department of Gastroenterology, S Maria della Croci Hosp, Ravenna, Italy.
- The Centre for Liver and Digestive Disorders, Royal Infirmary of Edinburgh, Edinburgh, UK.
- Department of Digestive Diseases, University Hospitals of Leicester NHS Trust, Leicester, UK.
- Gastroenterology Department, Hospital da Senhora da Oliveira, Guimarães, Portugal.
- Department of Gastroenterology, Skåne University Hospital, Lund University, Malmö, Sweden.
- Department of Clinical Sciences, Lund University, Lund, Sweden.
- Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece. [email protected].
Abstract
Synthetic Data Generation (SDG) based on Artificial Intelligence (AI) can transform the way clinical medicine is delivered by overcoming privacy barriers that currently render clinical data sharing difficult. This is the key to accelerating the development of digital tools contributing to enhanced patient safety. Such tools include robust data-driven clinical decision support systems, and example-based digital training tools that will enable healthcare professionals to improve their diagnostic performance for enhanced patient safety. This study focuses on the clinical evaluation of medical SDG, with a proof-of-concept investigation on diagnosing Inflammatory Bowel Disease (IBD) using Wireless Capsule Endoscopy (WCE) images. Its scientific contributions include (a) a novel protocol for the systematic Clinical Evaluation of Medical Image Synthesis (CEMIS); (b) a novel variational autoencoder-based model, named TIDE-II, which enhances its predecessor model, TIDE (This Intestine Does not Exist), for the generation of high-resolution synthetic WCE images; and (c) a comprehensive evaluation of the synthetic images using the CEMIS protocol by 10 international WCE specialists, in terms of image quality, diversity, and realism, as well as their utility for clinical decision-making. The results show that TIDE-II generates clinically plausible, very realistic WCE images, of improved quality compared to relevant state-of-the-art generative models. Concludingly, CEMIS can serve as a reference for future research on medical image-generation techniques, while the adaptation/extension of the architecture of TIDE-II to other imaging domains can be promising.