Related Experiment Video
Updated: May 30, 2026
State of the Art Cranial Ultrasound Imaging in Neonates
Published on: February 2, 2015
A robust method for ventriculomegaly detection from neonatal brain ultrasound images
Prasenjit Mondal1, Jayanta Mukhopadhyay, Shamik Sural
1Department of Computer Science and Engineering, Indian Institute of Technology, Kharagpur, India. prasenjitm@cse.iitkgp.ernet.in
Insights
We developed an automated image processing method to detect ventriculomegaly, a common neonatal brain abnormality, by measuring the anterior horn width in ultrasound images. This technique shows promising accuracy for early diagnosis.
Area of Science:
- Medical Imaging
- Neonatal Neurology
- Image Processing
Background:
- Ventriculomegaly, characterized by dilated brain ventricles, is a frequent neonatal abnormality.
- It can lead to increased intracranial pressure, head enlargement, and potentially severe neurological deficits or death.
- Early detection of ventriculomegaly is crucial for timely intervention and improved outcomes.
Purpose of the Study:
- To propose and evaluate an automated image processing approach for identifying ventriculomegaly in neonatal brain ultrasound images.
- To measure the anterior horn width of lateral ventricles as a key indicator for ventriculomegaly detection.
- To conduct cross-sectional and longitudinal studies on anterior horn width in neonates.
Main Methods:
- Utilizing neonatal brain ultrasound images in the midline coronal view.
- Implementing an automated image processing technique to measure the anterior horn width at the widest point.
- Analyzing images from 96 neonates with gestational ages from 26 to 39 weeks.
Main Results:
- The automated method accurately measures anterior horn width, a critical parameter for ventriculomegaly detection.
- Experimental results demonstrate promising accuracy when compared against physician-verified ground truth.
- The study provides both cross-sectional and longitudinal data on anterior horn width in neonates.
Conclusions:
- The proposed automated image processing method offers a promising tool for the early and accurate detection of ventriculomegaly in neonates.
- Measuring anterior horn width via this automated approach can aid in the diagnosis and monitoring of neonatal brain conditions.
- This technique has the potential to improve clinical management and outcomes for affected infants.
Abstract:
Ventriculomegaly is the most commonly detected abnormality in neonatal brain. It can be defined as a condition when the human brain ventricle system becomes dilated. This in turn increases the intracranial pressure inside the skull resulting in progressive enlargement of the head. Sometimes it may also cause mental disability or death. For these reasons early detection of ventriculomegaly has become an important task. In order to identify ventriculomegaly from neonatal brain ultrasound images, we propose an automated image processing based approach that measures the anterior horn width as the distance between medial wall and floor of the lateral ventricle at the widest point. Measurement is done in the plane of the scan at the level of the intraventricular foramina. Our study is based on neonatal brain ultrasound images in the midline coronal view. In addition to ventriculomegaly detection, this work also includes both cross sectional and longitudinal study of anterior horn width of lateral ventricles. Experiments were carried out on brain ultrasound images of 96 neonates with gestational age ranging from 26 to 39 weeks and results have been verified with the ground truth provided by doctors. Accuracy of the proposed scheme is quite promising.
