An automatic method for prostate segmentation on 3D MRI scans using local phylogenetic indexes and XGBoost

The detection, diagnosis, and treatment of prostate cancer depends on the correct determination of the prostate anatomy. In current practice, the prostate segmentation is performed manually by a radiologist, which is extremely time-consuming that demands experience and concentration. Therefore, this paper proposes an automatic method for prostate segmentation on 3D magnetic resonance imaging scans using a superpixel technique, phylogenetic indexes, and an optimized XGBoost algorithm. The proposed method has been evaluated on the Prostate 3T and PROMISE12 databases presenting a dice similarity coefficient of 84.48% and a volumetric similarity of 95.91%, demonstrating the high-performance potential of the proposed method.

3D MRI of the Spine

Three-dimensional (3D) magnetic resonance imaging of the spine is now clinically feasible due to technological advancements. Its advantages over two-dimensional imaging include higher in-plane spatial resolution and the ability for reformation in any plane that enables time savings in image acquisition and aids more accurate interpretation. Multispectral 3D techniques for imaging around metal are sometimes useful for evaluating anatomy adjacent to spinal fixation hardware. 3D gradient-recalled echo sequences, including ultrashort or zero time to echo sequences, can provide osseous detail similar to conventional computed tomography.