BHSD: A 3D Multi-Class Brain Hemorrhage Segmentation Dataset

TL;DR

This paper introduces BHSD, a comprehensive 3D multi-class brain hemorrhage dataset with detailed annotations, enabling improved deep learning segmentation models for clinical diagnosis.

Contribution

The paper presents a novel large-scale multi-class ICH dataset with detailed annotations, filling a gap in existing public datasets for advanced segmentation research.

Findings

State-of-the-art models establish baseline performance on BHSD.

The dataset supports supervised and semi-supervised ICH segmentation tasks.

Benchmark results facilitate future model development and evaluation.

Abstract

Intracranial hemorrhage (ICH) is a pathological condition characterized by bleeding inside the skull or brain, which can be attributed to various factors. Identifying, localizing and quantifying ICH has important clinical implications, in a bleed-dependent manner. While deep learning techniques are widely used in medical image segmentation and have been applied to the ICH segmentation task, existing public ICH datasets do not support the multi-class segmentation problem. To address this, we develop the Brain Hemorrhage Segmentation Dataset (BHSD), which provides a 3D multi-class ICH dataset containing 192 volumes with pixel-level annotations and 2200 volumes with slice-level annotations across five categories of ICH. To demonstrate the utility of the dataset, we formulate a series of supervised and semi-supervised ICH segmentation tasks. We provide experimental results with state-of-the-art models as reference benchmarks for further model developments and evaluations on this dataset.