Domain adaptation for MRI organ segmentation using reverse classification accuracy

File Description SizeFormat 
1806.00363v1.pdfAccepted version1.43 MBAdobe PDFView/Open
Title: Domain adaptation for MRI organ segmentation using reverse classification accuracy
Authors: Valindria, VV
Lavdas, I
Bai, W
Kamnitsas, K
Aboagye, EO
Rockall, AG
Rueckert, D
Glocker, B
Item Type: Conference Paper
Abstract: The variations in multi-center data in medical imaging studies have brought the necessity of domain adaptation. Despite the advancement of machine learning in automatic segmentation, performance often degrades when algorithms are applied on new data acquired from different scanners or sequences than the training data. Manual annotation is costly and time consuming if it has to be carried out for every new target domain. In this work, we investigate automatic selection of suitable subjects to be annotated for supervised domain adaptation using the concept of reverse classification accuracy (RCA). RCA predicts the performance of a trained model on data from the new domain and different strategies of selecting subjects to be included in the adaptation via transfer learning are evaluated. We perform experiments on a two-center MR database for the task of organ segmentation. We show that subject selection via RCA can reduce the burden of annotation of new data for the target domain.
Issue Date: 4-Jul-2018
Date of Acceptance: 15-May-2018
Copyright Statement: © 2018 The Author(s)
Sponsor/Funder: Commission of the European Communities
Funder's Grant Number: H2020 - 757173
Conference Name: International Conference on Medical Imaging with Deep Learning (MIDL)
Keywords: cs.CV
Notes: Accepted at the International Conference on Medical Imaging with Deep Learning (MIDL) 2018
Publication Status: Published
Start Date: 2018-07-04
Finish Date: 2018-07-06
Conference Place: Amsterdam, The Netherlands
Appears in Collections:Faculty of Engineering
Division of Surgery
Division of Cancer
Faculty of Medicine

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx