A Modified AUC for Training Convolutional Neural Networks: Taking Confidence into Account

TL;DR

This paper introduces a modified AUC metric that incorporates model confidence into the training process of CNNs, aiming to improve binary classification performance.

Contribution

It proposes a novel confidence-aware AUC modification integrated into the BCE loss for CNN training, validated on multiple datasets.

Findings

Improved classification metrics on MNIST, prostate MRI, and brain MRI datasets.

Published a Python library for conventional and modified AUC calculations.

Enhanced model performance by considering confidence in AUC during training.

Abstract

Receiver operating characteristic (ROC) curve is an informative tool in binary classification and Area Under ROC Curve (AUC) is a popular metric for reporting performance of binary classifiers. In this paper, first we present a comprehensive review of ROC curve and AUC metric. Next, we propose a modified version of AUC that takes confidence of the model into account and at the same time, incorporates AUC into Binary Cross Entropy (BCE) loss used for training a Convolutional neural Network for classification tasks. We demonstrate this on three datasets: MNIST, prostate MRI, and brain MRI. Furthermore, we have published GenuineAI, a new python library, which provides the functions for conventional AUC and the proposed modified AUC along with metrics including sensitivity, specificity, recall, precision, and F1 for each point of the ROC curve.