A multi-centre polyp detection and segmentation dataset for generalisability assessment
<p>Polyps in the colon are widely known cancer precursors identified by colonoscopy. Whilst most polyps are benign, the polyp’s number, size and surface structure are linked to the risk of colon cancer. Several methods have been developed to automate polyp detection and segmentation. However,...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Journal article |
| Idioma: | English |
| Publicado: |
Springer Nature
2023
|
| _version_ | 1826310256654811136 |
|---|---|
| author | Ali, S Jha, D Ghatwary, N Realdon, S Cannizzaro, R Salem, OE Lamarque, D Daul, C Riegler, MA Anonsen, KV Petlund, A Halvorsen, P Rittscher, J de Lange, T East, JE |
| author_facet | Ali, S Jha, D Ghatwary, N Realdon, S Cannizzaro, R Salem, OE Lamarque, D Daul, C Riegler, MA Anonsen, KV Petlund, A Halvorsen, P Rittscher, J de Lange, T East, JE |
| author_sort | Ali, S |
| collection | OXFORD |
| description | <p>Polyps in the colon are widely known cancer precursors identified by colonoscopy. Whilst most polyps are benign, the polyp’s number, size and surface structure are linked to the risk of colon cancer. Several methods have been developed to automate polyp detection and segmentation. However, the main issue is that they are not tested rigorously on a large multicentre purpose-built dataset, one reason being the lack of a comprehensive public dataset. As a result, the developed methods may not generalise to different population datasets. To this extent, we have curated a dataset from six unique centres incorporating more than 300 patients. The dataset includes both single frame and sequence data with 3762 annotated polyp labels with precise delineation of polyp boundaries verified by six senior gastroenterologists. To our knowledge, this is the most comprehensive detection and pixel-level segmentation dataset (referred to as <em>PolypGen</em>) curated by a team of computational scientists and expert gastroenterologists. The paper provides insight into data construction and annotation strategies, quality assurance, and technical validation.</p> |
| first_indexed | 2024-03-07T07:47:43Z |
| format | Journal article |
| id | oxford-uuid:f071b791-3b20-43db-b793-f8745da4352f |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:47:43Z |
| publishDate | 2023 |
| publisher | Springer Nature |
| record_format | dspace |
| spelling | oxford-uuid:f071b791-3b20-43db-b793-f8745da4352f2023-06-19T14:37:13ZA multi-centre polyp detection and segmentation dataset for generalisability assessmentJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:f071b791-3b20-43db-b793-f8745da4352fEnglishSymplectic ElementsSpringer Nature2023Ali, SJha, DGhatwary, NRealdon, SCannizzaro, RSalem, OELamarque, DDaul, CRiegler, MAAnonsen, KVPetlund, AHalvorsen, PRittscher, Jde Lange, TEast, JE<p>Polyps in the colon are widely known cancer precursors identified by colonoscopy. Whilst most polyps are benign, the polyp’s number, size and surface structure are linked to the risk of colon cancer. Several methods have been developed to automate polyp detection and segmentation. However, the main issue is that they are not tested rigorously on a large multicentre purpose-built dataset, one reason being the lack of a comprehensive public dataset. As a result, the developed methods may not generalise to different population datasets. To this extent, we have curated a dataset from six unique centres incorporating more than 300 patients. The dataset includes both single frame and sequence data with 3762 annotated polyp labels with precise delineation of polyp boundaries verified by six senior gastroenterologists. To our knowledge, this is the most comprehensive detection and pixel-level segmentation dataset (referred to as <em>PolypGen</em>) curated by a team of computational scientists and expert gastroenterologists. The paper provides insight into data construction and annotation strategies, quality assurance, and technical validation.</p> |
| spellingShingle | Ali, S Jha, D Ghatwary, N Realdon, S Cannizzaro, R Salem, OE Lamarque, D Daul, C Riegler, MA Anonsen, KV Petlund, A Halvorsen, P Rittscher, J de Lange, T East, JE A multi-centre polyp detection and segmentation dataset for generalisability assessment |
| title | A multi-centre polyp detection and segmentation dataset for generalisability assessment |
| title_full | A multi-centre polyp detection and segmentation dataset for generalisability assessment |
| title_fullStr | A multi-centre polyp detection and segmentation dataset for generalisability assessment |
| title_full_unstemmed | A multi-centre polyp detection and segmentation dataset for generalisability assessment |
| title_short | A multi-centre polyp detection and segmentation dataset for generalisability assessment |
| title_sort | multi centre polyp detection and segmentation dataset for generalisability assessment |
| work_keys_str_mv | AT alis amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT jhad amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT ghatwaryn amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT realdons amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT cannizzaror amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT salemoe amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT lamarqued amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT daulc amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT rieglerma amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT anonsenkv amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT petlunda amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT halvorsenp amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT rittscherj amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT delanget amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT eastje amulticentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT alis multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT jhad multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT ghatwaryn multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT realdons multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT cannizzaror multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT salemoe multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT lamarqued multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT daulc multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT rieglerma multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT anonsenkv multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT petlunda multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT halvorsenp multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT rittscherj multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT delanget multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment AT eastje multicentrepolypdetectionandsegmentationdatasetforgeneralisabilityassessment |