Deep learning and capsule endoscopy: automatic panendoscopic detection of protruding lesions
This study aims to address a gap in artificial intelligence (AI)-enhanced capsule panendoscopy by reporting the development of the first CNN for the detection of protruding lesions across the GI tract. AI's improvement of CE's diagnostic accuracy, along with the growing interest in minimally invasive procedures, may contribute to increasing access to this diagnostic tool. Further multicentric and prospective studies are needed to validate our preliminary results to ultimately introduce deep learning models into clinical practice.
Authors
- Francisco Mendes (ORCID: https://orcid.org/0000-0001-8504-8676)
- Maria João Almeida (ORCID: https://orcid.org/0000-0003-4061-8924)
- Guilherme Macedo (ORCID: https://orcid.org/0000-0002-9878-4901)
- Pedro Cardoso (ORCID: https://orcid.org/0000-0001-9427-5635)
- Miguel A. Martins (ORCID: https://orcid.org/0000-0002-7294-6204)
- Miguel Mascarenhas (ORCID: https://orcid.org/0000-0002-0340-0830)
- Hélder Cardoso (ORCID: https://orcid.org/0000-0002-7013-6216)
- Tiago Ribeiro (ORCID: https://orcid.org/0000-0002-4307-8671)
- Joana Mota (ORCID: https://orcid.org/0000-0002-8835-852X)
- João Afonso (ORCID: https://orcid.org/0000-0003-2088-2525)
- João Canas Ferreira (ORCID: https://orcid.org/0000-0001-7471-3888)
- Ana Patrícia Andrade
Institutions
- Universidade do Porto (PT)
- Hospital de São João (PT)
- Institute of Mechanical Engineering and Industrial Mangement (PT)
Publication Details
- Journal
- BMJ Open Gastroenterology
- Published
- 2025-09-01
- DOI
- https://doi.org/10.1136/bmjgast-2024-001655
- Citations
- 1
- Primary Topic
- Gastrointestinal Bleeding Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 1.81