Fully-Automated Semantic Segmentation of Wireless Capsule Endoscopy Abnormalities
| Autor: | Chandra Sekhar Seelamantula, Sukriti Paul, Hanitha Devi Gundabattula, V.R. Mujeeb, A.S. Prasad |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Gastrointestinal tract
Endoscope business.industry Computer science 0206 medical engineering 02 engineering and technology 020601 biomedical engineering law.invention 03 medical and health sciences 0302 clinical medicine Fully automated Capsule endoscopy law Wireless Segmentation Digestive tract Computer vision Artificial intelligence business 030217 neurology & neurosurgery Minimally invasive procedures |
| Zdroj: | ISBI |
| DOI: | 10.1109/isbi45749.2020.9098634 |
| Popis: | Wireless capsule endoscopy (WCE) is a minimally invasive procedure performed with a tiny swallowable optical endoscope that allows exploration of the human digestive tract. The medical device transmits tens of thousands of colour images, which are manually reviewed by a medical expert. This paper highlights the significance of using inputs from multiple colour spaces to train a classical U-Net model for automated semantic segmentation of eight WCE abnormalities. We also present a novel approach of grouping similar abnormalities during the training phase. Experimental results on the KID datasets demonstrate that a U-Net with 4-channel inputs outperforms the single-channel U-Net providing state-of-the-art semantic segmentation of WCE abnormalities. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|