Maximizing AUC with Deep Learning for Classification of Imbalanced Mammogram Datasets

Simple item page
dc.contributor.authorSulam, Jeremiasen_US
dc.contributor.authorBen-Ari, Ramien_US
dc.contributor.authorKisilev, Pavelen_US
dc.contributor.editorStefan Bruckner and Anja Hennemuth and Bernhard Kainz and Ingrid Hotz and Dorit Merhof and Christian Riederen_US
dc.date.accessioned2017-09-06T07:12:42Z
dc.date.available2017-09-06T07:12:42Z
dc.date.issued2017
dc.description.abstractBreast cancer is the second most common cause of death in women. Computer-aided diagnosis typically demand for carefully annotated data, precise tumor allocation and delineation of the boundaries, which is rarely available in the medical system. In this paper we present a new deep learning approach for classification of mammograms that requires only a global binary label. Traditional deep learning methods typically employ classification error losses, which are highly biased by class imbalance - a situation that naturally arises in medical classification problems.We hereby suggest a novel loss measure that directly maximizes the Area Under the ROC Curve (AUC), providing an unbiased loss. We validate the proposed model on two mammogram datasets: IMG, comprising of 796 patients, 80 positive (164 images) and 716 negative (1869 images), and the publicly available dataset INbreast. Our results are encouraging, as the proposed scheme achieves an AUC of 0.76 and 0.65 for IMG and INbreast, respectively.en_US
dc.description.sectionheadersShort Papers
dc.description.seriesinformationEurographics Workshop on Visual Computing for Biology and Medicine
dc.identifier.doi10.2312/vcbm.20171246
dc.identifier.isbn978-3-03868-036-9
dc.identifier.issn2070-5786
dc.identifier.pages131-135
dc.identifier.urihttps://doi.org/10.2312/vcbm.20171246
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/vcbm20171246
dc.publisherThe Eurographics Associationen_US
dc.titleMaximizing AUC with Deep Learning for Classification of Imbalanced Mammogram Datasetsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
131-135.pdf
Size:
541.34 KB
Format:
Adobe Portable Document Format
Download
Collections
VCBM 17: Eurographics Workshop on Visual Computing for Biology and Medicine