Please use this identifier to cite or link to this item:

TitleMulti-pathology detection and lesion localization in WCE videos by using the instance segmentation approach
Author(s)Vieira, Pedro Miguel
Freitas, Nuno Renato Azevedo
Lima, Veríssimo B.
Costa, Dalila Amélia Amorim
Rolanda, Carla
Lima, C. S.
KeywordsInstance segmentation
Lesion localization
Multi-pathology detection
Wireless capsule endoscopy
Issue date1-Sep-2021
JournalArtificial Intelligence in Medicine
CitationVieira, P. M., Freitas, N. R., Lima, V. B., Costa, D., Rolanda, C., & Lima, C. S. (2021). Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach. Artificial Intelligence in Medicine, 119, 102141
Abstract(s)The majority of current systems for automatic diagnosis considers the detection of a unique and previously known pathology. Considering specifically the diagnosis of lesions in the small bowel using endoscopic capsule images, very few consider the possible existence of more than one pathology and when they do, they are mainly detection based systems therefore unable to localize the suspected lesions. Such systems do not fully satisfy the medical community, that in fact needs a system that detects any pathology and eventually more than one, when they coexist. In addition, besides the diagnostic capability of these systems, localizing the lesions in the image has been of great interest to the medical community, mainly for training medical personnel purposes. So, nowadays, the inclusion of the lesion location in automatic diagnostic systems is practically mandatory. Multi-pathology detection can be seen as a multi-object detection task and as each frame can contain different instances of the same lesion, instance segmentation seems to be appropriate for the purpose. Consequently, we argue that a multi-pathology system benefits from using the instance segmentation approach, since classification and segmentation modules are both required complementing each other in lesion detection and localization. According to our best knowledge such a system does not yet exist for the detection of WCE pathologies. This paper proposes a multi-pathology system that can be applied to WCE images, which uses the Mask Improved RCNN (MI-RCNN), a new mask subnet scheme which has shown to significantly improve mask predictions of the high performing state-of-the-art Mask-RCNN and PANet systems. A novel training strategy based on the second momentum is also proposed for the first time for training Mask-RCNN and PANet based systems. These approaches were tested using the public database KID, and the included pathologies were bleeding, angioectasias, polyps and inflammatory lesions. Experimental results show significant improvements for the pr
Publisher version
AccessOpen access
Appears in Collections:ICVS - Artigos em revistas internacionais / Papers in international journals
CMEMS - Artigos em revistas internacionais/Papers in international journals

Files in This Item:
File Description SizeFormat 
Manuscript_AIIM_Final_Proofs.pdf522,07 kBAdobe PDFView/Open

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu ORCID