del Amor, Rocio, Meseguer, Pablo, Parigi, Tommaso Lorenzo ORCID: 0000-0002-3398-0231, Villanacci, Vincenzo, Colomer, Adrian, Launet, Laetitia ORCID: 0000-0003-4230-0987, Bazarova, Alina, Tontini, Gian Eugenio, Bisschops, Raf ORCID: 0000-0002-9994-8226, de Hertogh, Gert, Ferraz, Jose G., Goetz, Martin, Gui, Xianyong, Hayee, Bu'Hussain, Lazarev, Mark, Panaccione, Remo, Parra-Blanco, Adolfo, Bhandari, Pradeep, Pastorelli, Luca ORCID: 0000-0002-2810-9951, Rath, Timo ORCID: 0000-0002-7728-9338, Royset, Elin Synnove, Vieth, Michael, Zardo, Davide, Grisan, Enrico ORCID: 0000-0002-7365-5652, Ghosh, Subrata, Iacucci, Marietta and Naranjo, Valery (2022). Constrained multiple instance learning for ulcerative colitis prediction using histological images. Comput. Meth. Programs Biomed., 224. CLARE: ELSEVIER IRELAND LTD. ISSN 1872-7565

Full text not available from this repository.

Abstract

Background and Objective: Ulcerative colitis (UC) is an inflammatory bowel disease (IBD) affecting the colon and the rectum characterized by a remitting-relapsing course. To detect mucosal inflammation as-sociated with UC, histology is considered the most stringent criteria. In turn, histologic remission (HR) correlates with improved clinical outcomes and has been recently recognized as a desirable treatment target. The leading biomarker for assessing histologic remission is the presence or absence of neutrophils. Therefore, the finding of this cell in specific colon structures indicates that the patient has UC activity. However, no previous studies based on deep learning have been developed to identify UC based on neu-trophils detection using whole-slide images (WSI). Methods: The methodological core of this work is a novel multiple instance learning (MIL) framework with location constraints able to determine the presence of UC activity using WSI. In particular, we put forward an effective way to introduce constraints about positive instances to effectively explore additional weakly supervised information that is easy to obtain and enjoy a significant boost to the learning process. In addition, we propose a new weighted embedding to enlarge the relevance of the positive instances. Results: Extensive experiments on a multi-center dataset of colon and rectum WSIs, PICASSO-MIL, demon-strate that using the location information we can improve considerably the results at WSI-level. In com-parison with prior MIL settings, our method allows for 10% improvements in bag-level accuracy. Conclusion : Our model, which introduces a new form of constraints, surpass the results achieved from current state-of-the-art methods that focus on the MIL paradigm. Our method can be applied to other histological concerns where the morphological features determining a positive WSI are tiny and similar to others in the image. (c) 2022 Elsevier B.V. All rights reserved.

Item Type: Journal Article
Creators:
CreatorsEmailORCIDORCID Put Code
del Amor, RocioUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Meseguer, PabloUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Parigi, Tommaso LorenzoUNSPECIFIEDorcid.org/0000-0002-3398-0231UNSPECIFIED
Villanacci, VincenzoUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Colomer, AdrianUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Launet, LaetitiaUNSPECIFIEDorcid.org/0000-0003-4230-0987UNSPECIFIED
Bazarova, AlinaUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Tontini, Gian EugenioUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Bisschops, RafUNSPECIFIEDorcid.org/0000-0002-9994-8226UNSPECIFIED
de Hertogh, GertUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Ferraz, Jose G.UNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Goetz, MartinUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Gui, XianyongUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Hayee, Bu'HussainUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Lazarev, MarkUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Panaccione, RemoUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Parra-Blanco, AdolfoUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Bhandari, PradeepUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Pastorelli, LucaUNSPECIFIEDorcid.org/0000-0002-2810-9951UNSPECIFIED
Rath, TimoUNSPECIFIEDorcid.org/0000-0002-7728-9338UNSPECIFIED
Royset, Elin SynnoveUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Vieth, MichaelUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Zardo, DavideUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Grisan, EnricoUNSPECIFIEDorcid.org/0000-0002-7365-5652UNSPECIFIED
Ghosh, SubrataUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Iacucci, MariettaUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Naranjo, ValeryUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
URN: urn:nbn:de:hbz:38-697234
DOI: 10.1016/j.cmpb.2022.107012
Journal or Publication Title: Comput. Meth. Programs Biomed.
Volume: 224
Date: 2022
Publisher: ELSEVIER IRELAND LTD
Place of Publication: CLARE
ISSN: 1872-7565
Language: English
Faculty: Unspecified
Divisions: Unspecified
Subjects: no entry
Uncontrolled Keywords:
KeywordsLanguage
DISEASE-ACTIVITY; HISTOPATHOLOGY; REMISSIONMultiple languages
Computer Science, Interdisciplinary Applications; Computer Science, Theory & Methods; Engineering, Biomedical; Medical InformaticsMultiple languages
URI: http://kups.ub.uni-koeln.de/id/eprint/69723

Downloads

Downloads per month over past year

Altmetric

Export

Actions (login required)

View Item View Item