# Improved ICH classification using task-dependent learning

## TL;DR

BloodNet is a deep learning model that improves intracranial hemorrhage detection in head CT scans by integrating segmentation and classification tasks, leading to faster and more accurate triaging in emergency settings.

## Contribution

This paper introduces BloodNet, a novel task-dependent deep learning architecture that enhances ICH classification by modeling dependencies between segmentation and classification tasks.

## Key findings

- Achieved high AUCs of 0.9493 and 0.9566 on diverse datasets.
- Outperformed previous models with fewer annotated studies.
- Demonstrated effectiveness across multiple hospitals.

## Abstract

Head CT is one of the most commonly performed imaging studied in the Emergency Department setting and Intracranial hemorrhage (ICH) is among the most critical and timesensitive findings to be detected on Head CT. We present BloodNet, a deep learning architecture designed for optimal triaging of Head CTs, with the goal of decreasing the time from CT acquisition to accurate ICH detection. The BloodNet architecture incorporates dependency between the otherwise independent tasks of segmentation and classification, achieving improved classification results. AUCs of 0.9493 and 0.9566 are reported on held out positive-enriched and randomly sampled sets comprised of over 1400 studies acquired from over 10 different hospitals. These results are comparable to previously reported results with smaller number of tagged studies.