Go to main content
Toward automatic tumor-stroma ratio assessment for survival analysis in colorectal cancer
Abbet, Christian; Studer, Linda; Zlobec, Inti; Thiran, Jean-Philippe
2022
Télécharger
Formats
Format
BibTeX
MARCXML
TextMARC
MARC
DublinCore
EndNote
NLM
RefWorks
RIS

Résumé

In this paper, we present a fully automated system for tumor-stroma ratio (TSR) scoring in line with current recommendations for pathologists, based on tumor and tumor-adjacent stroma tissue detection. In order to evaluate the scoring system, we perform survival analysis on 221 whole slide image from colorectal cancer patients. We find that the whole slide image-level and region of interest-level TSR are statistically significant predictors of overall survival.

Détails

Titre
Toward automatic tumor-stroma ratio assessment for survival analysis in colorectal cancer
Auteur(s)/ trice(s)
Abbet, Christian (EPFL, Lausanne, Switzerland ; University of Bern, Bern, Switzerland)
Studer, Linda (University of Bern, Bern, Switzerland ; University of Fribourg, Fribourg, Switzerland ; School of Engineering and Architecture (HEIA-FR), HES-SO University of Applied Sciences Western Switzerland)
Zlobec, Inti (University of Bern, Bern, Switzerland)
Thiran, Jean-Philippe (EPFL, Lausanne, Switzerland ; Center for Biomedical Imaging (CIBM), Switzerland ; CHUV, University of Lausanne, Lausanne, Switzerland)
Date
2022-07
Publié dans
Proceedings of Medical Imaging with Deep Learning Zürich, 6 – 8 July 2022, Zurich, Switzerland
Publié par
Zurich, Switzerland, 6-8 July 2022
Pagination & équivalents
3 p.
Présenté à
Medical Imaging with Deep Learning Zürich, Zurich, Switzerland, 2022-07-06, 2022-07-08
Mots-clés (libres)
computational pathology ; tumor-stroma ratio ; colorectal cancer
Type de papier
short paper
Domaine
Ingénierie et Architecture
Ecole
HEIA-FR
Institut
iCoSys- Institut d’intelligence artificielle et systèmes complexes
Le document apparaît dans
Documents de conférences
Global
Ressource(s) externe(s)
Online proceedings

Actions

PDF