Artificial intelligence, capsule endoscopy, databases, and the Sword of Damocles
| Autor: | Thomas de Lange, Xavier Dray, Ervin Toth, Anastasio Koulaouzidis |
|---|---|
| Přispěvatelé: | Centre d'Endoscopie Digestive [CHU Saint-Antoine], CHU Saint-Antoine [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), Skane University Hospital [Malmo], Lund University [Lund], Sahlgrenska University Hospital [Gothenburg], Pomeranian Medical University [Szczecin, Poland] (PMU) |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
business.industry
RC799-869 Diseases of the digestive system. Gastroenterology law.invention World Wide Web 03 medical and health sciences 0302 clinical medicine Capsule endoscopy law 030220 oncology & carcinogenesis Medicine Letter to the editor 030211 gastroenterology & hepatology Pharmacology (medical) SWORD business [SDV.MHEP]Life Sciences [q-bio]/Human health and pathology |
| Zdroj: | Endoscopy International Open Endoscopy International Open, Georg Thieme Verlag KG, 2021, 09 (11), pp.E1754-E1755. ⟨10.1055/a-1521-4882⟩ Endoscopy International Open, Vol 09, Iss 11, Pp E1754-E1755 (2021) |
| ISSN: | 2196-9736 2364-3722 |
| DOI: | 10.1055/a-1521-4882⟩ |
| Popis: | International audience; We read with interest the editorial by Hassan et al [1] entitled “AI everywhere in endoscopy, not only for detection and characterization,” prompted by the recent paper of Hansen et al. on “Novel artificial intelligence (AI)-driven software significantly shortens the time required for annotation in computer vision projects” [2]. As Hassan et al. point out, unlike classic machine learning methods (MLM), the new kid on the block’s (i. e., deep learning [DL]) main advantage is its capability to automatically extract image features so that computers can use them to characterize their content [3]. This, essentially, means that the accuracy of this unsupervised approach depends primarily on the aptness and quality of the training data provided. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|