Intracranial Hemorrhage Segmentation Using Deep Convolutional Model

TL;DR

This paper presents a deep learning approach using a U-Net model to automatically segment intracranial hemorrhage regions in CT scans, aiming to assist radiologists in timely diagnosis.

Contribution

The study introduces a new dataset of 82 annotated CT scans and applies a U-Net model for ICH segmentation, providing a baseline for future research.

Findings

Achieved a Dice coefficient of 0.31 for ICH segmentation.

Created a publicly available dataset of 82 CT scans.

Demonstrated the feasibility of automated ICH detection using deep learning.

Abstract

Traumatic brain injuries could cause intracranial hemorrhage (ICH). ICH could lead to disability or death if it is not accurately diagnosed and treated in a time-sensitive procedure. The current clinical protocol to diagnose ICH is examining Computerized Tomography (CT) scans by radiologists to detect ICH and localize its regions. However, this process relies heavily on the availability of an experienced radiologist. In this paper, we designed a study protocol to collect a dataset of 82 CT scans of subjects with traumatic brain injury. Later, the ICH regions were manually delineated in each slice by a consensus decision of two radiologists. Recently, fully convolutional networks (FCN) have shown to be successful in medical image segmentation. We developed a deep FCN, called U-Net, to segment the ICH regions from the CT scans in a fully automated manner. The method achieved a Dice coefficient of 0.31 for the ICH segmentation based on 5-fold cross-validation. The dataset is publicly available online at PhysioNet repository for future analysis and comparison.