Constrained multiple instance learning for ulcerative colitis prediction using histological images

Del Amor R, Meseguer P, Parigi TL, Villanacci V, Colomer A, Launet L, Bazarova A, Tontini GE, Bisschops R, De Hertogh G, Ferraz JG, Goetz M, Gui X, Hayee B, Lazarev M, Panaccione R, Parra-Blanco A, Bhandari P, Pastorelli L, Rath T, Royset ES, Zardo D, Grisan E, Ghosh S, Iacucci M, Naranjo V, Vieth M (2022)

Publication Type: Journal article

Publication year: 2022

Journal

Book Volume: 224

DOI: 10.1016/j.cmpb.2022.107012

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.

Authors with CRIS profile

Involved external institutions

Polytechnic University of Valencia / Universidad Politécnica de Valencia Spain (ES) Università degli Studi di Brescia Italy (IT) Universität zu Köln Germany (DE) Università degli studi di Milano Italy (IT) University Hospital Leuven (UZ) / Universitaire ziekenhuizen Leuven Belgium (BE) University of Calgary Canada (CA) Klinikverbund Südwest (Sindelfingen-Böblingen, Calw, Nagold, Leonberg, Herrenberg) Germany (DE) University of Washington United States (USA) (US) King’s College London United Kingdom (GB) Johns Hopkins Hospital United States (USA) (US) University of Nottingham United Kingdom (GB) Queen Alexandra Hospital United Kingdom (GB) Ospedale San Paolo Italy (IT) NTNU Trondheim - Norwegian University of Science and Technology Norway (NO) Ospedale San Bortolo Italy (IT) University College Cork (UCC) Ireland (IE) Humanitas University Italy (IT) Klinikum Bayreuth Germany (DE)

How to cite

APA:

Del Amor, R., Meseguer, P., Parigi, T.L., Villanacci, V., Colomer, A., Launet, L.,... Vieth, M. (2022). Constrained multiple instance learning for ulcerative colitis prediction using histological images. Computer Methods and Programs in Biomedicine, 224. https://doi.org/10.1016/j.cmpb.2022.107012

MLA:

Del Amor, Rocio, et al. "Constrained multiple instance learning for ulcerative colitis prediction using histological images." Computer Methods and Programs in Biomedicine 224 (2022).

BibTeX: Download