Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Training medical image analysis systems like radiologists
Author: Maicas Suso, G.
Bradley, A.
Nascimento, J.
Reid, I.
Carneiro, G.
Citation: Lecture Notes in Artificial Intelligence, 2018 / Frangi, A., Schnabel, J., Davatzikos, C., Alberola-Lopez, C., Fichtinger, G. (ed./s), vol.11070 LNCS, pp.546-554
Publisher: Springer
Issue Date: 2018
Series/Report no.: Lecture notes in computer science; 11070
ISBN: 9783030009274
ISSN: 0302-9743
Conference Name: 21st International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2018) (16 Sep 2018 - 20 Sep 2018 : Granada)
Editor: Frangi, A.
Schnabel, J.
Davatzikos, C.
Alberola-Lopez, C.
Fichtinger, G.
Statement of
Gabriel Maicas, Andrew P. Bradley, Jacinto C. Nascimento, Ian Reid, and Gustavo Carneiro
Abstract: The training of medical image analysis systems using machine learning approaches follows a common script: collect and annotate a large dataset, train the classifier on the training set, and test it on a hold-out test set. This process bears no direct resemblance with radiologist training, which is based on solving a series of tasks of increasing difficulty, where each task involves the use of significantly smaller datasets than those used in machine learning. In this paper, we propose a novel training approach inspired by how radiologists are trained. In particular, we explore the use of meta-training that models a classifier based on a series of tasks. Tasks are selected using teacher-student curriculum learning, where each task consists of simple classification problems containing small training sets. We hypothesize that our proposed meta-training approach can be used to pre-train medical image analysis models. This hypothesis is tested on the automatic breast screening classification from DCE-MRI trained with weakly labeled datasets. The classification performance achieved by our approach is shown to be the best in the field for that application, compared to state of art baseline approaches: DenseNet, multiple instance learning and multi-task learning.
Keywords: Meta-learning; curriculum learning; multi-task training; breast image analysis; breast screening; magnetic resonance imaging
Rights: © Springer Nature Switzerland AG 2018
DOI: 10.1007/978-3-030-00928-1_62
Grant ID:
Appears in Collections:Aurora harvest 3
Australian Institute for Machine Learning publications
Computer Science publications

Files in This Item:
There are no files associated with this item.

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