Allows to perform registration and segmentation for image analysis. Segmentation is the process of identifying and classifying data found in a digitally sampled representation. ITK uses a model of software development known as Extreme Programming. The sampled representation is an image acquired from such medical instrumentation as Computed Tomography (CT), Magnetic Resonance Imaging (MRI) or ultrasound scanners. Registration is the task of aligning or developing correspondences between data. For example, in the medical environment, a CT scan may be aligned with a MRI scan in order to combine the information contained in both.
Allows users to segment structures in 3D medical images. ITK-SNAP provides semi-automatic segmentation using active contour methods, as well as manual delineation and image navigation. It is an application providing a method to extract structures in 3D image data of different modalities and from different anatomical regions. Moreover, it permits users to link cursor for 3D navigation or to post-process the segmentation results.
Offers a framework dedicated to image segmentation. SegAN proposes an approach derived from Generative Adversarial Networks (GANs) framework, trained on whole images with the aim of optimizing segmentation tasks in medical images. The application is based on multi-scale loss function for both the segmentor and critic networks. The application was tested on the segmentation of brain tumor images.
Rebuilds 3D models of lesioned arteries and enabled quantitative assessment of stenoses. 3D reconstruction algorithm builds a 3D computational patient-specific model of lesioned vessel, directly from 2D projections acquired while computing invasive coronary X-ray angiography, and is relevant for immediate geometric and quantitative analysis. The 3D model result is appropriate for isogeometric analysis (IGA) of blood flow in the coronary arteries.
Provides a superpixel segmentation algorithm focused on the lung CT images. HMSLIC uses a hexagonal method to obtain more regular segmented superpixels and improve edge information preservation. Besides, it uses morphology to combine bright superpixels to eliminate the influence of bright blob-like blood vessels with the aim of reducing the complexity of the subsequent calculation of distance.
You can access more results by creating a free plan account or unlimited content via a premium account.