Dual-Task Vision Transformer for Rapid and Accurate Intracerebral Hemorrhage CT Image Classification

TL;DR

This paper introduces DTViT, a dual-task vision transformer model that rapidly and accurately classifies intracerebral hemorrhage types from CT images, aiding early diagnosis with high performance.

Contribution

The paper proposes a novel dual-task vision transformer architecture that simultaneously detects ICH presence and classifies hemorrhage location, improving diagnostic efficiency and accuracy.

Findings

DTViT achieves high accuracy on real-world ICH dataset.

The model effectively distinguishes between ICH and normal cases.

It accurately classifies hemorrhage locations into Deep, Subcortical, and Lobar.

Abstract

Intracerebral hemorrhage (ICH) is a severe and sudden medical condition caused by the rupture of blood vessels in the brain, leading to permanent damage to brain tissue and often resulting in functional disabilities or death in patients. Diagnosis and analysis of ICH typically rely on brain CT imaging. Given the urgency of ICH conditions, early treatment is crucial, necessitating rapid analysis of CT images to formulate tailored treatment plans. However, the complexity of ICH CT images and the frequent scarcity of specialist radiologists pose significant challenges. Therefore, we collect a dataset from the real world for ICH and normal classification and three types of ICH image classification based on the hemorrhage location, i.e., Deep, Subcortical, and Lobar. In addition, we propose a neural network structure, dual-task vision transformer (DTViT), for the automated classification and diagnosis of ICH images. The DTViT deploys the encoder from the Vision Transformer (ViT), employing attention mechanisms for feature extraction from CT images. The proposed DTViT framework also incorporates two multilayer perception (MLP)-based decoders to simultaneously identify the presence of ICH and classify the three types of hemorrhage locations. Experimental results demonstrate that DTViT performs well on the real-world test dataset. The code and newly collected dataset for this work are available at: https://github.com/jfan1997/DTViT.