Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/122728
Citations
Scopus Web of Science® Altmetric
?
?
Type: Journal article
Title: Pre and post-hoc diagnosis and interpretation of malignancy from breast DCE-MRI
Author: Maicas, G.
Bradley, A.P.
Nascimento, J.C.
Reid, I.
Carneiro, G.
Citation: Medical Image Analysis, 2019; 58:101562-1-101562-14
Publisher: Elsevier
Issue Date: 2019
ISSN: 1361-8415
1361-8423
Statement of
Responsibility: 
Gabriel Maicas, Andrew P. Bradley, Jacinto C. Nascimento, Ian Reid, Gustavo Carneiro
Abstract: We propose a new method for breast cancer screening from DCE-MRI based on a post-hoc approach that is trained using weakly annotated data (i.e., labels are available only at the image level without any lesion delineation). Our proposed post-hoc method automatically diagnosis the whole volume and, for positive cases, it localizes the malignant lesions that led to such diagnosis. Conversely, traditional approaches follow a pre-hoc approach that initially localises suspicious areas that are subsequently classified to establish the breast malignancy - this approach is trained using strongly annotated data (i.e., it needs a delineation and classification of all lesions in an image). We also aim to establish the advantages and disadvantages of both approaches when applied to breast screening from DCE-MRI. Relying on experiments on a breast DCE-MRI dataset that contains scans of 117 patients, our results show that the post-hoc method is more accurate for diagnosing the whole volume per patient, achieving an AUC of 0.91, while the pre-hoc method achieves an AUC of 0.81. However, the performance for localising the malignant lesions remains challenging for the post-hoc method due to the weakly labelled dataset employed during training.
Keywords: Magnetic resonance imaging; breast screening; meta-learning; few-shot learning; weakly supervised learning; strongly supervised learning; model interpretation; lesion detection; deep reinforcement learning
Rights: © 2019 Elsevier B.V. All rights reserved.
RMID: 1000001508
DOI: 10.1016/j.media.2019.101562
Grant ID: http://purl.org/au-research/grants/arc/DP180103232
http://purl.org/au-research/grants/arc/CE140100016
http://purl.org/au-research/grants/arc/FL130100102
Appears in Collections: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.