Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/107614
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Unregistered multiview mammogram analysis with pre-trained deep learning models |
Author: | Carneiro, G. Nascimento, J. Bradley, A. |
Citation: | Lecture Notes in Artificial Intelligence, 2015 / Navab, N., Hornegger, J., Wells, W., Frangi, A. (ed./s), vol.9351, pp.652-660 |
Publisher: | Springer |
Issue Date: | 2015 |
Series/Report no.: | Lecture Notes in Computer Science |
ISBN: | 9783319245737 |
ISSN: | 0302-9743 1611-3349 |
Conference Name: | 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015) (5 Oct 2015 - 9 Oct 2015 : Munich, GERMANY) |
Editor: | Navab, N. Hornegger, J. Wells, W. Frangi, A. |
Statement of Responsibility: | Gustavo Carneiro, Jacinto Nascimento, and Andrew P. Bradley |
Abstract: | We show two important findings on the use of deep convolutional neural networks (CNN) in medical image analysis. First, we show that CNN models that are pre-trained using computer vision databases (e.g., Imagenet) are useful in medical image applications, despite the significant differences in image appearance. Second, we show that multiview classification is possible without the pre-registration of the input images. Rather, we use the high-level features produced by the CNNs trained in each view separately. Focusing on the classification of mammograms using craniocaudal (CC) and mediolateral oblique (MLO) views and their respective mass and micro-calcification segmentations of the same breast, we initially train a separate CNN model for each view and each segmentation map using an Imagenet pre-trained model. Then, using the features learned from each segmentation map and unregistered views, we train a final CNN classifier that estimates the patient's risk of developing breast cancer using the Breast Imaging-Reporting and Data System (BI-RADS) score. We test our methodology in two publicly available datasets (InBreast and DDSM), containing hundreds of cases, and show that it produces a volume under ROC surface of over 0.9 and an area under ROC curve (for a 2-class problem - benign and malignant) of over 0.9. In general, our approach shows state-of-the-art classification results and demonstrates a new comprehensive way of addressing this challenging classification problem. |
Keywords: | Deep learning, mammogram, multiview classification |
Rights: | © Springer International Publishing Switzerland 2015 |
DOI: | 10.1007/978-3-319-24574-4_78 |
Grant ID: | http://purl.org/au-research/grants/arc/DP140102794 http://purl.org/au-research/grants/arc/FT110100623 |
Published version: | http://dx.doi.org/10.1007/978-3-319-24574-4_78 |
Appears in Collections: | Aurora harvest 3 Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
RA_hdl_107614.pdf Restricted Access | Restricted Access | 705.54 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.