Using Cross Entropy as a Performance Metric for Quantifying Uncertainty in DNN Image Classifiers: An Application to Classification of Lung Cancer on CT Images ()
Affiliation(s)
1Faculty of Informatics, University of Fukuchiyama, Kyoto, Japan.
2Graduate School of Radiological Sciences,
International University of Health and Welfare, Tochigi, Japan.
3School of Health Sciences, Fukushima Medical
University, Fukushima, Japan.
4School of Radiological Technology, Gunma Prefectural College of Health Sciences, Gunma, Japan.
ABSTRACT
Cross entropy is a measure in machine
learning and deep learning that assesses the difference between predicted and
actual probability distributions. In this study, we propose cross entropy as a
performance evaluation metric for image classifier models and apply it to the
CT image classification of lung cancer. A convolutional neural network is
employed as the deep neural network (DNN) image classifier, with the residual
network (ResNet) 50 chosen as the DNN archi-tecture. The image data used
comprise a lung CT image set. Two classification models are built from datasets
with varying amounts of data, and lung cancer is categorized into four classes
using 10-fold cross-validation. Furthermore, we employ t-distributed stochastic
neighbor embedding to visually explain the data distribution after
classification. Experimental results demonstrate that cross en-tropy is a
highly useful metric for evaluating the reliability of image classifier models.
It is noted that for a more comprehensive evaluation of model perfor-mance,
combining with other evaluation metrics is considered essential.
Share and Cite:
Matsuyama, E. , Nishiki, M. , Takahashi, N. and Watanabe, H. (2024) Using Cross Entropy as a Performance Metric for Quantifying Uncertainty in DNN Image Classifiers: An Application to Classification of Lung Cancer on CT Images.
Journal of Biomedical Science and Engineering,
17, 1-12. doi:
10.4236/jbise.2024.171001.
Cited by
No relevant information.