AI-Powered Intracranial Hemorrhage Detection: A Co-Scale Convolutional Attention Model with Uncertainty-Based Fuzzy Integral Operator and Feature Screening

TL;DR

This paper presents a novel AI model for intracranial hemorrhage detection using a co-scale convolutional attention architecture, feature selection, and an uncertainty-based fuzzy integral operator to enhance accuracy and explainability.

Contribution

It introduces a new two-layer model combining feature screening, an explainable AI approach, and a fuzzy integral operator for improved ICH detection from CT scans.

Findings

Enhanced detection accuracy with the fuzzy integral operator.

Effective feature selection improves model interpretability.

Novel architecture combining attention, feature screening, and uncertainty modeling.

Abstract

Intracranial hemorrhage (ICH) refers to the leakage or accumulation of blood within the skull, which occurs due to the rupture of blood vessels in or around the brain. If this condition is not diagnosed in a timely manner and appropriately treated, it can lead to serious complications such as decreased consciousness, permanent neurological disabilities, or even death.The primary aim of this study is to detect the occurrence or non-occurrence of ICH, followed by determining the type of subdural hemorrhage (SDH). These tasks are framed as two separate binary classification problems. By adding two layers to the co-scale convolutional attention (CCA) classifier architecture, we introduce a novel approach for ICH detection. In the first layer, after extracting features from different slices of computed tomography (CT) scan images, we combine these features and select the 50 components that capture the highest variance in the data, considering them as informative features. We then assess the discriminative power of these features using the bootstrap forest algorithm, discarding those that lack sufficient discriminative ability between different classes. This algorithm explicitly determines the contribution of each feature to the final prediction, assisting us in developing an explainable AI model. The features feed into a boosting neural network as a latent feature space. In the second layer, we introduce a novel uncertainty-based fuzzy integral operator to fuse information from different CT scan slices. This operator, by accounting for the dependencies between consecutive slices, significantly improves detection accuracy.