TITLE:
Using Cross Entropy as a Performance Metric for Quantifying Uncertainty in DNN Image Classifiers: An Application to Classification of Lung Cancer on CT Images
AUTHORS:
Eri Matsuyama, Masayuki Nishiki, Noriyuki Takahashi, Haruyuki Watanabe
KEYWORDS:
Cross Entropy, Performance Metrics, DNN Image Classifiers, Lung Cancer, Prediction Uncertainty
JOURNAL NAME:
Journal of Biomedical Science and Engineering,
Vol.17 No.1,
January
17,
2024
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.