| Summary: | <p>Three-dimensional (3D) fetal neurosonography is used clinically to detect cerebral abnormalities and to assess growth in the developing brain. However, manual identification of key brain structures in 3D ul- trasound images requires expertise to perform and even then is tedious. Inspired by how sonographers view and interact with volumes during real-time clinical scanning, we propose an efficient automatic method to simultaneously localize multiple brain structures in 3D fetal neurosonography. The proposed View-based Projection Networks (VP-Nets) , uses three view-based Convolutional Neural Networks (CNNs), to simplify 3D localizations by directly predicting 2D projections of the key structures onto three anatom- ical views.</p> <br/> <p>While designed for efficient use of data and GPU memory, the proposed VP-Nets allows for full- resolution 3D prediction. We investigated parameters that influence the performance of VP-Nets, e.g. depth and number of feature channels. Moreover, we demonstrate that the model can pinpoint the struc- ture in 3D space by visualizing the trained VP-Nets, despite only 2D supervision being provided for a sin- gle stream during training. For comparison, we implemented two other baseline solutions based on Ran- dom Forest and 3D U-Nets. In the reported experiments, VP-Nets consistently outperformed other meth- ods on localization. To test the importance of loss function, two identical models are trained with binary corss-entropy and dice coefficient loss respectively. Our best VP-Net model achieved prediction center deviation: 1.8 ±1.4 mm, size difference: 1.9 ±1.5 mm, and 3D Intersection Over Union (IOU): 63.2 ±14.7% when compared to the ground truth. To make the whole pipeline intervention free, we also implement a skull-stripping tool using 3D CNN, which achieves high segmentation accuracy. As a result, the proposed processing pipeline takes a raw ultrasound brain image as input, and output a skull-stripped image with five detected key brain structures.</p>
|
|---|