Meeting Banner
Abstract #1435

Computer-Aided Arteriovenous Malformation Nidus Segmentation from 3D Time-Of-Flight MRA Datasets

Nils Daniel Forkert1, Till Illies1, Einar Goebell1, Jens Fiehler1, Heinz Handels2

1Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany; 2Institute of Medical Informatics, University of Luebeck, Luebeck, Schleswig-Holstein, Germany

This work presents a computer-assisted method for the segmentation of the arteriovenous malformation nidus from time-of-flight (TOF) MRA datasets. Therefore, the cerebrovascular system is automatically extracted from the TOF dataset and used for a voxel-wise support vector machine classification into nidus and non-nidus vascular structures based on four features. The resulting classification dataset is used for extracting the nidus using 3D region growing. An evaluation based on fifteen datasets with available manual nidus segmentations from two observers demonstrated that the computer-aided method leads to segmentation results within the range of the inter-observer agreement but with a considerably reduced interaction time.

Abstract PDF

Keywords

actual advances aided allows application applying assigned assisted assumptions automatic automatically available background basis beneficial blob blood brain capillaries cause challenging characterized classification close coefficient coefficients combination complete complexity computer conglomerate connections consensus contrast cross dataset datasets depending detailed developed diagnostic diameter dice dilatation direct distance enables evaluate evaluated except exhibits experts extracted fact fast filter fistulas flight flow furthermore generalized generating good growing hamburg include indicate informatics intensities intensity inter interaction interactive interposing knowledge larger lead leave locally machine malformation malformations malformed manual manually material measure medical metric minute minutes missing moreover morphological observer offer optimal overall part patients planning positive post precise precisely previously proposed prove quantitative ranging real referred replaced represented representing required resection resolution restricted rupture segmentation segmentations segmented separating serves shape shapes similarity slab slice step strategies structure structures subsequent support therapy tortuous trained training treatment tubular variations vector veins vessel vessels volume walls weakening wise