Database Restricted Access

Computed Tomography Images for Intracranial Hemorrhage Detection and Segmentation

Murtadha Hssayeni

Published: March 10, 2020. Version: 1.3.1


When using this resource, please cite: (show more options)
Hssayeni, M. (2020). Computed Tomography Images for Intracranial Hemorrhage Detection and Segmentation (version 1.3.1). PhysioNet. https://doi.org/10.13026/4nae-zg36.

Additionally, please cite the original publication:

Hssayeni, M. D., Croock, M. S., Salman, A. D., Al-khafaji, H. F., Yahya, Z. A., & Ghoraani, B. (2020). Intracranial Hemorrhage Segmentation Using A Deep Convolutional Model. Data, 5(1), 14.

Please include the standard citation for PhysioNet: (show more options)
Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220.

Abstract

After traumatic brain injury (TBI), intracranial hemorrhage (ICH) may occur that could lead to death or disability if it is not accurately diagnosed and treated in a time-sensitive procedure. Currently, Computerized Tomography (CT) scans are examined by radiologists to diagnose intracranial hemorrhage to localize affected regions. In this work, we collected a dataset of 82 CT scans of patients with traumatic brain injury. Intracranial hemorrhage regions in these scans were delineated in each slice by two radiologists. The radiologists also annotated each CT slice for the presence of different types of intracranial hemorrhage and fracture. The CT scans of 75 subjects in NIfTI format are made public in this dataset.


Background

Traumatic brain injury (TBI) is a major cause of death and disability in the United States, contributing to about 30% of all injury deaths as of 2013 [1]. After accidents that involve TBI, extra-axial intracranial lesions may present, such as intracranial hemorrhage (ICH). An ICH is a critical medical lesion that is associated with a high rate of mortality [2]. ICH is considered to be clinically dangerous because of its high risk of turning into a secondary brain insult that may lead to paralysis and death if it is not treated appropriately. Hemorrhages can be classified based upon their location in the brain: Intraventricular (IVH), Intraparenchymal (IPH), Subarachnoid (SAH), Epidural (EDH) and Subdural (SDH).

Computerized Tomography (CT) scans are commonly used in the emergency evaluation of patients with TBI to diagnose intracranial hemorrhage by capturing multiple layers of the brain [3]. The availability of CT scans and their rapid acquisition time makes CT a preferred diagnostic tool over Magnetic Resonance Imaging (MRI) for initial hemorrhage assessment. CT scans generate a sequence of images using X-ray beams where brain tissues are captured with different intensities depending on the amount of X-ray absorbency of the tissue. CT scans are displayed using a windowing method, which converts Hounsfield units (HU) into grayscale values ([0, 255]) using two parameters: window level (WL) and window width (WW). Different windows allow different features of tissues to be displayed in a grayscale image (e.g., brain window, stroke window, or a bone window) [4]. In CT scans using brain windows, hemorrhages appear as hyper intense regions with relatively undefined structure. CT images are examined by senior radiologists to determine whether a hemorrhage has occurred and if so, to detect the type and its region. However, this process can be lengthy, and subspecialty-trained neuroradiologists may not always be available to make an assessment.

Convolutional neural networks (CNN) have been shown to have excellent performance in automating multiple image classification and segmentation tasks [5,6]. We hypothesized that deep learning algorithms have the potential to automate the diagnosing procedure of segmenting the ICH regions and detecting skull fracture, reducing the time taken for the ICH diagnosis and potentially improving its accuracy. An automated ICH screen tool could be used to assist radiologists with less experience in detecting hemorrhage types, or when experts are not immediately available in the emergency room, which is especially prevalent in developing countries or remote areas.


Methods

A retrospective study was designed to collect head CT scans of subjects with TBI and it was approved by the research and ethics board in the Iraqi Ministry of Health, Babil Office (approval #1369). The inclusion criteria were any subject who was admitted to the hospital emergency unit with a TBI, and a CT scan was performed to him/her. CT scans were collected between February and August 2018 from Al Hilla Teaching Hospital, Iraq. Sensitive information for each patient was anonymized, and the subjects' faces were de-identified in the CT scans.


Data Description

A dataset of 82 CT scans was collected, including 36 scans for patients diagnosed with intracranial hemorrhage with the following types: Intraventricular, Intraparenchymal, Subarachnoid, Epidural and Subdural. Each CT scan for each patient includes about 30 slices with 5 mm slice-thickness. The mean and std of patients' age were 27.8 and 19.5, respectively. 46 of the patients were males and 36 of them were females. Each slice of the non-contrast CT scans was by two radiologists who recorded hemorrhage types if hemorrhage occurred or if a fracture occurred. The radiologists also delineated the ICH regions in each slice. There was a consensus between the radiologists. Radiologists did not have access to clinical history of the patients.

During data collection, syngo by Siemens Medical Solutions was first used to read the CT DICOM files and save two videos (avi format) using brain (level=40, width=120) and bone (level=700, width=3200) windows, respectively. Second, a custom tool was implemented in Matlab and used to read the avi files and perform the annotation. Also, the generated masks were mapped and saved to NIfTI files for 75 subjects. 

Files and folders in the dataset are:

  1. patient_demographics.csv contains the patient #, age and gender and the labels (the ICH subtypes if ICH was diagnosed, and a skull fracture if it was diagnosed) for each CT scan.
  2. hemorrhage_diagnosis_raw_ct.csv contains the patient #, slice # and the labels (the ICH subtypes if ICH was diagnosed, and a skull fracture if it was diagnosed) for each slice in the NIfTI CT scans.
  3. ct_scans folder contains the NIfTI scans for the patients in the patient demographics file except for subject #59 to 65 which are missing. The names of the NIfTI mask files match the patients numbers in the patient demographics file (patient_demographics.csv and hemorrhage_diagnosis_raw_ct.csv).
  4. masks folder contains the ICH segmentation of each of the CT slices in NIfTI file format. The names of the NIfTI mask files match the patients numbers in the patient demographics file.

Usage Notes

split_raw_data.py is provided to load the NIfTI CT scans and window them using a brain window, and also to load the NIfTI masks. An environment file is provided, ct_ich.yml, which specifies the virtual environment that was used to execute the code. The virtual environment can be recreated using conda as follows:

conda env create -f ct_ich.yml

This will create the ct_ich python virtual environment for running the code.


Release Notes

In this release, only the CT scans in the NIfTI format were included, and the subjects' faces in these CT scans were de-identified by blurring them and adding random noise. 


Conflicts of Interest

The authors declare no conflict of interest.


References

  1. Taylor, C. A., Bell, J. M., Breiding, M. J., & Xu, L. (2017). Traumatic brain injury–related emergency department visits, hospitalizations, and deaths—United States, 2007 and 2013. MMWR Surveillance Summaries, 66(9), 1.
  2. van Asch, C. J., Luitse, M. J., Rinkel, G. J., van der Tweel, I., Algra, A., & Klijn, C. J. (2010). Incidence, case fatality, and functional outcome of intracerebral haemorrhage over time, according to age, sex, and ethnic origin: a systematic review and meta-analysis. The Lancet Neurology, 9(2), 167-176.
  3. Currie, S., Saleem, N., Straiton, J. A., Macmullen-Price, J., Warren, D. J., & Craven, I. J. (2016). Imaging assessment of traumatic brain injury. Postgraduate medical journal, 92(1083), 41-50.
  4. Xue, Z., Antani, S., Long, L. R., Demner-Fushman, D., & Thoma, G. R. (2012). Window classification of brain CT images in biomedical articles. In AMIA Annual Symposium Proceedings (Vol. 2012, p. 1023). American Medical Informatics Association.
  5. Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., ... & Sánchez, C. I. (2017). A survey on deep learning in medical image analysis. Medical image analysis, 42, 60-88.
  6. Chilamkurthy, S., Ghosh, R., Tanamala, S., Biviji, M., Campeau, N. G., Venugopal, V. K., ... & Warier, P. (2018). Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. The Lancet, 392(10162), 2388-2396.

Share
Access

Access Policy:
Only logged in users who sign the specified data use agreement can access the files.

License (for files):
PhysioNet Restricted Health Data License 1.5.0

Corresponding Author
You must be logged in to view the contact information.
Versions

Files