Share Email Print
cover

Proceedings Paper

A novel exponential loss function for pathological lymph node image classification
Author(s): Guoping Xu; Hanqiang Cao; Jayaram K. Udupa; Chunyi Yue; Youli Dong; Li Cao; Drew A. Torigian
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Recent progress in deep learning, especially deep convolutional neural networks (DCNNs), has led to significant improvement in natural image classification. However, research is still ongoing in the domain of medical image analysis in part due to the shortage of annotated data sets for training DCNNs, the imbalanced number of positive and negative samples, and the difference between medical images and natural images. In this paper, two strategies are proposed to train a DCNN for pathological lymph node image classification. Firstly, the transfer learning strategy is used to deal with the shortage of training samples. Second, a novel exponential loss function is presented for the imbalance in training samples. Four state-of-the-art DCNNs (GoogleNet, ResNet101, Xception, and MobileNetv2) are tested. The experiments demonstrate that the two strategies are effective to improve the performance of pathological lymph node image classification in terms of accuracy and sensitivity with a mean of 0.13% and 1.50%, respectively, for the four DCNNs. In particular, the proposed exponential loss function improved the sensitivity by 3.9% and 4.0% for Xception and ResNet101, respectively.

Paper Details

Date Published: 14 February 2020
PDF: 7 pages
Proc. SPIE 11431, MIPPR 2019: Parallel Processing of Images and Optimization Techniques; and Medical Imaging, 114310A (14 February 2020); doi: 10.1117/12.2537004
Show Author Affiliations
Guoping Xu, Huazhong Univ. of Science and Technology (China)
Univ. of Pennsylvania (United States)
Hanqiang Cao, Huazhong Univ. of Science and Technology (China)
Jayaram K. Udupa, Univ. of Pennsylvania (United States)
Chunyi Yue, Huazhong Univ. of Science and Technology (China)
Youli Dong, Huazhong Univ. of Science and Technology (China)
Li Cao, Huazhong Univ. of Science and Technology (China)
Drew A. Torigian, Univ. of Pennsylvania (United States)


Published in SPIE Proceedings Vol. 11431:
MIPPR 2019: Parallel Processing of Images and Optimization Techniques; and Medical Imaging
Hong Sun; Bruce Hirsch; Chao Cai, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray