Explanation and Use of Uncertainty Quantified by Bayesian Neural NetworkClassifiers for Breast Histopathology Images

Abstract

Convolutional neural network (CNN) based classification models have been successfully used on histopathological images for the detection of diseases. Despite its success, CNN may yield erroneous or overfitted results when the data is not sufficiently large or is biased. To overcome these limitations of CNN and to provide uncertainty quantification Bayesian CNN is recently proposed. However, we show that Bayesian-CNN still suffers from inaccuracies, especially in negative predictions. In the present work, we extend the Bayesian-CNN to improve accuracy and the rate of convergence. The proposed model is called modified Bayesian-CNN. The novelty of the proposed model lies in an adaptive activation function that contains a learnable parameter for each of the neurons. This adaptive activation function dynamically changes the loss function thereby providing faster convergence and better accuracy. The uncertainties associated with the predictions are obtained since the model learns a probability distribution on the network parameters. It reduces overfitting through an ensemble averaging over networks, which in turn improves accuracy on the unknown data. The proposed model demonstrates significant improvement by nearly eliminating overfitting and remarkably reducing (about 38%) the number of false-negative predictions. We found that the proposed model predicts higher uncertainty for images having features of both the classes. The uncertainty in the predictions of individual images can be used to decide when further human-expert intervention is needed. These findings have the potential to advance the state-of-the-art machine learning-based automatic classification for histopathological images.

On the Use of Uncertainty in Classifying Aedes Albopictus Mosquitoes

“…By incorporating a learnable parameter, Khairnar et al [20] proposed a Bayesian CNN with an adaptive activation function to dynamically adjust the loss function, increasing the accuracy and convergence rate in breast histopathology image classification. Dropout-based Bayesian uncertainty measure was evaluated by Leibig et al [24] for estimating diabetic retinopathy from fundus images.…”