Real-time prediction of segmentation quality

File Description SizeFormat 
robinson2018miccai.pdfFile embargoed until 01 January 10000722.66 kBAdobe PDF    Request a copy
Title: Real-time prediction of segmentation quality
Authors: Robinson, R
Oktay, O
Bai, W
Valindria, V
Sanghvi, MM
Aung, N
Paiva, JM
Zemrak, F
Fung, K
Lukaschuk, E
Lee, AM
Carapella, V
Kim, YJ
Kainz, B
Piechnik, SK
Neubauer, S
Petersen, SE
Page, C
Rueckert, D
Glocker, B
Item Type: Conference Paper
Abstract: Recent advances in deep learning based image segmentation methods have enabled real-time performance with human-level accuracy. However, occasionally even the best method fails due to low image qual- ity, artifacts or unexpected behaviour of black box algorithms. Being able to predict segmentation quality in the absence of ground truth is of paramount importance in clinical practice, but also in large-scale studies to avoid the inclusion of invalid data in subsequent analysis. In this work, we propose two approaches of real-time automated quality control for cardiovascular MR segmentations using deep learning. First, we train a neural network on 12,880 samples to predict Dice Similarity Coefficients (DSC) on a per-case basis. We report a mean average error (MAE) of 0.03 on 1,610 test samples and 97% binary classification accu- racy for separating low and high quality segmentations. Secondly, in the scenario where no manually annotated data is available, we train a net- work to predict DSC scores from estimated quality obtained via a reverse testing strategy. We report an MAE = 0.14 and 91% binary classifica- tion accuracy for this case. Predictions are obtained in real-time which, when combined with real-time segmentation methods, enables instant feedback on whether an acquired scan is analysable while the patient is still in the scanner. This further enables new applications of optimising image acquisition towards best possible analysis results.
Issue Date: 31-Dec-2018
Date of Acceptance: 25-May-2018
URI: http://hdl.handle.net/10044/1/60750
ISSN: 0302-9743
Publisher: Springer Verlag
Journal / Book Title: Lecture Notes in Computer Science
Copyright Statement: This paper is embargoed until publication.
Sponsor/Funder: GlaxoSmithKline
Engineering & Physical Science Research Council (EPSRC)
Commission of the European Communities
Funder's Grant Number: EP/P001009/1
H2020 - 757173
Conference Name: International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)
Keywords: cs.CV
08 Information And Computing Sciences
Artificial Intelligence & Image Processing
Publication Status: Accepted
Start Date: 2018-09-16
Finish Date: 2018-09-20
Conference Place: Granada, Spain
Embargo Date: publication subject to indefinite embargo
Appears in Collections:Faculty of Engineering
Computing
Faculty of Medicine



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

Creative Commons