Hercules: Deep Hierarchical Attentive Multilevel Fusion Model With Uncertainty Quantification for Medical Image Classification

The automatic and accurate analysis of medical images (e.g., segmentation,detection, classification) are prerequisites for modern disease diagnosis and prognosis. Computer-aided diagnosis (CAD) systems empower accurate and effective detection of various diseases and timely treatment decisions. The past decade witnessed a spur in deep learning (DL)-based CADs showing outstanding performance across many health care applications. Medical imaging is hindered by multiple sources of uncertainty ranging fromnteasurement (aleatoric) errors, physiological variability, and limited medical knowledge (epistemic errors). However, uncertainty quantification (UQ) in most existing DL methods is insufficiently investigated, particularly in medical image analysis. Therefore, to address this gap, in this article, we propose a simple yet novel hierarchical attentive multilevel feature fusion model with an uncertainty-aware module for medical image classification coined Hercules. This approach is tested on several real medical image classification challenges. The proposed Hercules model consists of two main feature fusion blocks, where the former concentrates on attention-based fusion with uncertainty quantification module and the latter uses the raw features. Hercules was evaluated across three medical imaging datasets, i.e., retinal OCT, lung CT, and chest X-ray. Hercules produced the best classification accuracy in retinal OCT (94.21%), lung CT (99.59%), and chest X-ray (96.50%) datasets, respectively, against other state-of-the-art medical image classification methods.

I. Introduction

Machine learning (ML) and deep learning (DL) techniques have proven effective across many problems and diverse benchmark datasets. ML and DL methods extract hidden information from raw data and make predictions utilizing these models [1]. The performance of predictive models can be hindered by the uncertainty in input data and modeling priors. Imprecise or noisy data and limiting or wrong model assumptions are sources of uncertainty. Handling uncertainties effectively is crucial for trustworthy machine learning, particularly in safety-critical applications like health care. Uncertainty quantification plays, thus, an important role in ML [2], [3].