2023104224 (1).pdf (15.72 MB)
Download file

Diagnostic Performance of Deep Learning Models for Gastric Intestinal Metaplasia Detection in Narrow-band Images

Download (15.72 MB)
posted on 2023-05-11, 01:41 authored by Miguel MartinsMiguel Martins, Maria Pedroso, Diogo Libânio, Mário Dinis-Ribiero, Miguel Coimbra, Francesco Renna

Gastric Intestinal Metaplasia (GIM) is one of the precancerous conditions in the gastric carcinogenesis cascade and its optical diagnosis during endoscopic screening is challenging even for seasoned endoscopists. Several solutions leveraging pre-trained deep neural networks (DNNs) have been recently proposed in order to assist human diagnosis. In this paper, we present a comparative study of these architectures in a new dataset containing GIM and non-GIM Narrow-band imaging still frames. We find that the surveyed DNNs perform remarkably well on average, but still measure sizeable inter- fold variability during cross-validation. An additional ad-hoc analysis suggests that these baseline architectures may not perform equally well at all scales when diagnosing GIM.


Computer Assisted Gastric Cancer Diagnosis

Fundação para a Ciência e Tecnologia

Find out more...

An Artificially Intelligent Diagnostic Assistant for gastric inflammation

European Commission

Find out more...

Deep Learning Algorithms for Anatomical Gastric Landmark Detection

Fundação para a Ciência e Tecnologia

Find out more...


Email Address of Submitting Author

ORCID of Submitting Author


Submitting Author's Institution


Submitting Author's Country

  • Portugal