Direct Least Square Fitting of Ellipses
IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Image Enhancement and Noise Filtering by Use of Local Statistics
IEEE Transactions on Pattern Analysis and Machine Intelligence
Adaptive Noise Smoothing Filter for Images with Signal-Dependent Noise
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image denoising using scale mixtures of Gaussians in the wavelet domain
IEEE Transactions on Image Processing
| Hi-index | 0.00 |
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.