Accurate and automatic multi-needle detection in three-dimensional (3D) ultrasound (US) is a key step of treatmentplanning for US-guided brachytherapy. However, most current studies are concentrated on single-needle detection byonly using a small number of images with a needle, regardless of the massive database of US images without needles. Inthis paper, we propose a workflow of multi-needle detection via considering the images without needles as auxiliary.Specifically, we train position-specific dictionaries on 3D overlapping patches of auxiliary images, where we developedan enhanced sparse dictionary learning method by integrating spatial continuity of 3D US, dubbed order-graphregularized dictionary learning (ORDL). Using the learned dictionaries, target images are reconstructed to obtainresidual pixels which are then clustered in every slice to determine the centers. With the obtained centers, regions ofinterest (ROIs) are constructed via seeking cylinders. Finally, we detect needles by using the random sample consensusalgorithm (RANSAC) per ROI and then locate the tips by finding the sharp intensity drops along the detected axis forevery needle. Extensive experiments are conducted on a prostate data set of 70/21 patients without/with needles.Visualization and quantitative results show the effectiveness of our proposed workflow. Specifically, our approach cancorrectly detect 95% needles with a tip location error of 1.01 mm on the prostate dataset. This technique could provideaccurate needle detection for US-guided high-dose-rate prostate brachytherapy and facilitate the clinical workflow.
展开▼
