Mostrar el registro sencillo del ítem

A Deep Attention-Multiple Instance Learning Framework to Predict Survival of Soft-Tissue Sarcoma from Whole Slide Images

hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
hal.structure.identifierBoRdeaux Institute in onCology [Inserm U1312 - BRIC]
hal.structure.identifierInstitut Bergonié [Bordeaux]
hal.structure.identifierModélisation Mathématique pour l'Oncologie [MONC]
dc.contributor.authorLE, Van-Linh
hal.structure.identifierBoRdeaux Institute in onCology [Inserm U1312 - BRIC]
hal.structure.identifierInstitut Bergonié [Bordeaux]
dc.contributor.authorMICHOT, Audrey
hal.structure.identifierModélisation Mathématique pour l'Oncologie [MONC]
hal.structure.identifierHôpital Pellegrin
dc.contributor.authorCROMBÉ, Amandine
hal.structure.identifierInstitut Gustave Roussy [IGR]
hal.structure.identifierDépartement de biologie et pathologie médicales [Gustave Roussy]
dc.contributor.authorNGO, Carine
hal.structure.identifierInstitut Gustave Roussy [IGR]
hal.structure.identifierPôle chirurgical et interventionnel [Gustave Roussy]
dc.contributor.authorHONORÉ, Charles
hal.structure.identifierInstitut Bergonié [Bordeaux]
dc.contributor.authorCOINDRE, Jean-Michel
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
hal.structure.identifierCentre National de la Recherche Scientifique [CNRS]
hal.structure.identifierModélisation Mathématique pour l'Oncologie [MONC]
dc.contributor.authorSAUT, Olivier
hal.structure.identifierBoRdeaux Institute in onCology [Inserm U1312 - BRIC]
hal.structure.identifierUniversité de Bordeaux [UB]
hal.structure.identifierInstitut Bergonié [Bordeaux]
dc.contributor.authorLE-LOARER, Francois
dc.date.accessioned2024-04-04T02:32:04Z
dc.date.available2024-04-04T02:32:04Z
dc.date.issued2023-10-07
dc.date.conference2023-10-12
dc.identifier.isbn978-3-031-45350-2
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/190353
dc.description.abstractEnSoft-tissue sarcomas are heterogeneous cancers of the mesenchymal lineage that can develop anywhere in the body. A precise prediction of sarcomas patients’ prognosis is critical for clinicians to define an adequate treatment plan. In this paper, we proposed an end-to-end Deep learning framework via Multiple Instance Learning (MIL), Deep Attention-MIL framework, for the survival predictions: Overall survival (OS), Metastasis-free survival (MFS), and Local-recurrence free survival (LRFS) of sarcomas patients, by studying the features from Whole Slide Images (WSIs) of their tumors. The Deep Attention-MIL framework consists of three steps: tiles selection from the WSIs to choose the relevant tiles for the study; tiles feature extraction by using a pre-trained deep learning model; and a Deep Attention-MIL model to predict the risk score for each patient via MIL approach. The risk scores outputted from the Deep Attention-MIL model are used to divide the patients into low/high-risk groups and predict survival time. The framework was trained and validated on a local dataset including 220 patients, then it was used to predict the survival for 48 patients in an external validation dataset. The experiments showed the proposed framework yielded satisfactory and promising results and contributed to accurate cancer survival predictions on both the validation and external testing datasets: By using the WSIs feature only, we obtained an average C-index (of 5-fold cross-validation) of 0.6901, 0.7179, and 0.6211 for OS, MFS, and LRFS tasks on the validation dataset, respectively. On the external testing dataset, these scores are 0.6294, 0.682, and 0.76 for the three tasks (OS, MFS, LRFS), respectively. By adding the clinical features, these scores have been improved both on validation and external testing datasets. We obtained an average C-index of 0.7835/0.6378, 0.7389/0.6885, and 0.6883/0.7272 for the three tasks (OS, MFS, LRFS) on validation/external testing datasets.
dc.language.isoen
dc.publisherSpringer Nature Switzerland
dc.publisher.locationCham
dc.rights.urihttp://creativecommons.org/licenses/by/
dc.source.titleLecture Notes in Computer Science
dc.subject.enMultiple Instance Learning
dc.subject.enDeep Attention model
dc.subject.enSurvival prediction
dc.subject.enSoft-tissue sarcoma
dc.subject.enWhole Slide Image
dc.title.enA Deep Attention-Multiple Instance Learning Framework to Predict Survival of Soft-Tissue Sarcoma from Whole Slide Images
dc.typeCommunication dans un congrès
dc.identifier.doi10.1007/978-3-031-45350-2_1
dc.subject.halInformatique [cs]
bordeaux.page3-16
bordeaux.volumeLNCS-14295
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.conference.titleMICCAI 2023 - CaPTion Workshop on Cancer Prevention through early detecTion
bordeaux.countryCA
bordeaux.title.proceedingLecture Notes in Computer Science
bordeaux.conference.cityVancouver
bordeaux.peerReviewedoui
hal.identifierhal-04235077
hal.version1
hal.invitednon
hal.proceedingsoui
hal.conference.organizerMICCAI
hal.conference.end2023-10-12
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-04235077v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.btitle=Lecture%20Notes%20in%20Computer%20Science&rft.date=2023-10-07&rft.volume=LNCS-14295&rft.spage=3-16&rft.epage=3-16&rft.au=LE,%20Van-Linh&MICHOT,%20Audrey&CROMB%C3%89,%20Amandine&NGO,%20Carine&HONOR%C3%89,%20Charles&rft.isbn=978-3-031-45350-2&rft.genre=unknown


Archivos en el ítem

ArchivosTamañoFormatoVer

No hay archivos asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem