EUVIMEDEUVIMED entdecken
Crossref

Artificial Intelligence and Minimally Invasive Endoscopy – Panendoscopic Detection of Pleomorphic Lesions

M. Mascarenhas, J. P. Afonso, T. Ribeiro, C. Pedro, M. Francisco, C. Hélder, A. Patrícia, P. F. João, M. Guilherme

Endoscopy · 01.04.2024 · 56 (S 02 S 02) · S410

DOI: 10.1055/s-0044-1783725 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Endoscopy, erschienen am 01.04.2024. Verfasst von M. Mascarenhas und 8 weiteren Autor:innen. Die Arbeit nennt 3 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aims

Capsule endoscopy (CE) is a minimally invasive exam suitable of panendoscopicevaluation of the gastrointestinal tract. Nevertheless, CE is time-consuming withsuboptimal diagnostic yield in the upper GI tract. Convolutional neural networks (CNN) are human brain architecture-based models suitable for image analysis. However, there is no study about their role in capsule panendoscopy.

Methods

Our group developed an artificial intelligence (AI) model for panendoscopic automaticdetection of pleomorphic lesions (namely vascular lesions, protuberant lesions,hematic residues, ulcers and erosions). 355110 images (6977 esophageal, 12918 gastric, 258443 small bowel, 76772 colonic) from eight different CE and colon CE(CCE) devices were divided in a training and validation dataset in a patient split design.The model classification was compared to three CE experts’ classification. The model’s performance was evaluated by its sensitivity, specificity, accuracy, positive predictive value, negative predictive value, and area under the precision-recall curve.

Results

The binary esophagus CNN had a diagnostic accuracy for pleomorphic lesions of 95.7%. The binary gastric CNN identified pleomorphic lesions with a 96.9% accuracy.The undenary small bowel CNN distinguished pleomorphic lesions with differenthemorrhagic potential with 98.9% accuracy. The trinary colonic CNN (detection and differentiation of normal mucosa, pleomorphic lesions and hematic residues) had 96.8% global accuracy. [ 1 ] [ 2 ] [ 3 ] [ 4 ]

Conclusions

Our group developed the first AI model for panendoscopic automatic detection of pleomorphic lesions in both CE and colon CE from multiple brands, solving a critical interoperability technological challenge. Deep learning-based tools may change the landscape ofminimally invasive capsule panendoscopy. Publication History Article published online: 15 April 2024 © 2024. European Society of Gastrointestinal Endoscopy. All rights reserved. Georg Thieme Verlag KG Rüdigerstraße 14, 70469 Stuttgart, Germany

Zitieren

APA

Mascarenhas, M., Afonso, J. P., Ribeiro, T., Pedro, C., Francisco, M., Hélder, C., Patrícia, A., João, P. F., & Guilherme, M. (2024). Artificial Intelligence and Minimally Invasive Endoscopy – Panendoscopic Detection of Pleomorphic Lesions. Endoscopy, 56(S 02 S 02), S410. https://doi.org/10.1055/s-0044-1783725

Vancouver

Mascarenhas M, Afonso JP, Ribeiro T, Pedro C, Francisco M, Hélder C, et al. Artificial Intelligence and Minimally Invasive Endoscopy – Panendoscopic Detection of Pleomorphic Lesions. Endoscopy. 2024;56(S 02 S 02):S410. doi:10.1055/s-0044-1783725

BibTeX
@article{Mascarenhas2024,
  author = {Mascarenhas, M. and Afonso, J. P. and Ribeiro, T. and Pedro, C. and Francisco, M. and Hélder, C. and Patrícia, A. and João, P. F. and Guilherme, M.},
  title = {Artificial Intelligence and Minimally Invasive Endoscopy – Panendoscopic Detection of Pleomorphic Lesions},
  journal = {Endoscopy},
  year = {2024},
  volume = {56},
  number = {S 02 S 02},
  pages = {S410},
  doi = {10.1055/s-0044-1783725}
}
Kostenlos starten →