A Comparison Between a Deep Convolutional Neural Network and Radiologists for Classifying Regions of Interest in Mammography

被引：32

作者：

Kooi, Thijs ^{[1
]}

Gubern-Merida, Albert ^{[1
]}

Mordang, Jan-Jurre ^{[1
]}

Mann, Ritse ^{[1
]}

Pijnappel, Ruud ^{[2
]}

Schuur, Klaas ^{[2
]}

den Heeten, Ard ^{[3
]}

Karssemeijer, Nico ^{[1
]}

机构：

[1] Radboud Univ Nijmegen, Med Ctr, Dept Radiol, Nijmegen, Netherlands

[2] Dutch Reference Ctr Screening, Nijmegen, Netherlands

[3] Univ Amsterdam, Dept Radiol, Amsterdam, Netherlands

来源：

BREAST IMAGING, IWDM 2016 | 2016年 / 9699卷

关键词：

D O I：

10.1007/978-3-319-41546-8_7

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

In this paper, we employ a deep Convolutional Neural Network (CNN) for the classification of regions of interest of malignant soft tissue lesions in mammography and show that it performs on par to experienced radiologists. The CNN was applied to 398 regions of 5x5 cm, half of which contained a malignant lesion and the other half depicted suspicious regions in normal mammograms detected by a traditional CAD system. Four radiologists participated in the study. ROC analysis was used for evaluating results. The AUC of CNN was 0.87, which was higher than the mean AUC of the radiologists (0.84), though the difference was not significant.

引用

页码：51 / 56

页数：6

共 12 条

[1]

[Anonymous], ARXIV150201852V1

[2] Random forests [J].

Breiman, L .

MACHINE LEARNING, 2001, 45 (01) :5-32

[3]

Dauphin Y. N., 2015, ADV NEURAL INFORM PR, P1504

[4] Effectiveness of Computer-Aided Detection in Community Mammography Practice [J].

Fenton, Joshua J. ;

Abraham, Linn ;

Taplin, Stephen H. ;

Geller, Berta M. ;

Carney, Patricia A. ;

D'Orsi, Carl ;

Elmore, Joann G. ;

Barlow, William E. .

JOURNAL OF THE NATIONAL CANCER INSTITUTE, 2011, 103 (15) :1152-1161

[5] Recent developments in the Dorfman-Berbaum-Metz procedure for multireader ROC study analysis [J].

Hillis, Stephen L. ;

Berbaum, Kevin S. ;

Metz, Charles E. .

ACADEMIC RADIOLOGY, 2008, 15 (05) :647-661

[6] Detection of stellate distortions in mammograms [J].

Karssemeijer, N ;

teBrake, GM .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 1996, 15 (05) :611-619

[7] ImageNet Classification with Deep Convolutional Neural Networks [J].

Krizhevsky, Alex ;

Sutskever, Ilya ;

Hinton, Geoffrey E. .

COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90

[8] Human-level control through deep reinforcement learning [J].

Mnih, Volodymyr ;

Kavukcuoglu, Koray ;

Silver, David ;

Rusu, Andrei A. ;

Veness, Joel ;

Bellemare, Marc G. ;

Graves, Alex ;

Riedmiller, Martin ;

Fidjeland, Andreas K. ;

Ostrovski, Georg ;

Petersen, Stig ;

Beattie, Charles ;

Sadik, Amir ;

Antonoglou, Ioannis ;

King, Helen ;

Kumaran, Dharshan ;

Wierstra, Daan ;

Legg, Shane ;

Hassabis, Demis .

NATURE, 2015, 518 (7540) :529-533

[9] Deep learning [J].

Rusk, Nicole .

NATURE METHODS, 2016, 13 (01) :35-35

[10] Mastering the game of Go with deep neural networks and tree search [J].

Silver, David ;

Huang, Aja ;

Maddison, Chris J. ;

Guez, Arthur ;

Sifre, Laurent ;

van den Driessche, George ;

Schrittwieser, Julian ;

Antonoglou, Ioannis ;

Panneershelvam, Veda ;

Lanctot, Marc ;

Dieleman, Sander ;

Grewe, Dominik ;

Nham, John ;

Kalchbrenner, Nal ;

Sutskever, Ilya ;

Lillicrap, Timothy ;

Leach, Madeleine ;

Kavukcuoglu, Koray ;

Graepel, Thore ;

Hassabis, Demis .

NATURE, 2016, 529 (7587) :484-+

← 1 2 →