Blood vessel segmentation in the browser
VesselBoost is a browser-based tool for automatic segmentation of blood vessels from MRI angiography using a 3D UNet model.
Image processing runs locally in your browser using ONNX Runtime Web. Patient image data and generated outputs are not uploaded by the analysis code.
VesselBoost image processing runs in your web browser using WebAssembly and ONNX Runtime. Patient-derived files stay local to your machine.
VesselBoost uses ONNX Runtime Web to run deep learning models directly in the browser via WebAssembly. Your NIfTI or DICOM files are read into browser memory, processed locally, and results are displayed without network transfer of patient data.
Static app files and public model assets may be served from external hosting, but patient-derived files are not sent to those services by the analysis code. The Neurodesk hosting layer records page views only, unless your browser sends Do Not Track or Global Privacy Control. It does not send custom events, patient images, voxel values, screenshots, generated outputs, filenames, or analysis results to Google Analytics.
Marshall K, et al. VesselBoost: A Python Toolbox for Small Blood Vessel Segmentation.
https://github.com/KMarshallX/VesselBoost/VesselBoost uses the following methods and tools:
Paszke A, et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. NeurIPS 2019.
https://pytorch.orgMicrosoft. ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator.
https://onnxruntime.aiLi X, Morgan PS, Ashburner J, Smith J, Rorden C. The first step for neuroimaging data analysis: DICOM to NIfTI conversion. J Neurosci Methods. 2016;264:47-56.
https://github.com/rordenlab/dcm2niixStewart A. QSM.rs: Quantitative Susceptibility Mapping in Rust. FSL-BET2 brain extraction algorithm.
https://github.com/astewartau/QSM.rsSmith SM. Fast robust automated brain extraction. Human Brain Mapping. 2002;17(3):143-155.
https://doi.org/10.1002/hbm.10062Hoopes A, Mora JS, Dalca AV, Fischl B, Hoffmann M. SynthStrip: Skull-Stripping for Any Brain Image. NeuroImage. 2022;260:119474.
https://doi.org/10.1016/j.neuroimage.2022.119474NiiVue Contributors. NiiVue: a WebGL2 medical image viewer.
https://github.com/niivue/niivue