Share Email Print
cover

Proceedings Paper • new

Generalization error analysis: deep convolutional neural network in mammography
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We conducted a study to gain understanding of the generalizability of deep convolutional neural networks (DCNNs) given their inherent capability to memorize data. We examined empirically a specific DCNN trained for classification of masses on mammograms. Using a data set of 2,454 lesions from 2,242 mammographic views, a DCNN was trained to classify masses into malignant and benign classes using transfer learning from ImageNet LSVRC-2010. We performed experiments with varying amounts of label corruption and types of pixel randomization to analyze the generalization error for the DCNN. Performance was evaluated using the area under the receiver operating characteristic curve (AUC) with an N-fold cross validation. Comparisons were made between the convergence times, the inference AUCs for both the training set and the test set of the original image patches without corruption, and the root-mean-squared difference (RMSD) in the layer weights of the DCNN trained with different amounts and methods of corruption. Our experiments observed trends which revealed that the DCNN overfitted by memorizing corrupted data. More importantly, this study improved our understanding of DCNN weight updates when learning new patterns or new labels. Although we used a specific classification task with the ImageNet as example, similar methods may be useful for analysis of the DCNN learning processes, especially those that employ transfer learning for medical image analysis where sample size is limited and overfitting risk is high.

Paper Details

Date Published: 27 February 2018
PDF: 9 pages
Proc. SPIE 10575, Medical Imaging 2018: Computer-Aided Diagnosis, 1057520 (27 February 2018); doi: 10.1117/12.2292921
Show Author Affiliations
Caleb D. Richter, Univ. of Michigan (United States)
Ravi K. Samala, Univ. of Michigan (United States)
Heang-Ping Chan, Univ. of Michigan (United States)
Lubomir Hadjiiski, Univ. of Michigan (United States)
Kenny Cha, Univ. of Michigan (United States)


Published in SPIE Proceedings Vol. 10575:
Medical Imaging 2018: Computer-Aided Diagnosis
Nicholas Petrick; Kensaku Mori, Editor(s)

© SPIE. Terms of Use
Back to Top