6533b851fe1ef96bd12a9087
RESEARCH PRODUCT
A fully automatic method for biological target volume segmentation of brain metastases
Davide D’ursoCorrado D’arrigoGiorgio Ivan RussoOrazio GambinoMassimo IppolitoRoberto PirroneAlessandro StefanoAlessandro StefanoEdoardo ArdizzoneSalvatore VitabileFranco MarlettaMaria Carla Gilardisubject
gamma knifePET imagingcerebral tumors segmentation030218 nuclear medicine & medical imagingrandom walk03 medical and health sciences0302 clinical medicinemedicineSegmentationElectrical and Electronic EngineeringRadiation treatment planningCluster analysisImage resolution1707Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazionimedicine.diagnostic_testbusiness.industryElectronic Optical and Magnetic Materialbiological target volumePattern recognitionThresholdingElectronic Optical and Magnetic MaterialsRegion growingPositron emission tomography030220 oncology & carcinogenesisbiological target volume cerebral tumors segmentation gamma knife PET imaging random walkComputer Vision and Pattern RecognitionArtificial intelligenceNuclear medicinebusinessSoftwareVolume (compression)description
Leksell Gamma Knife is a mini-invasive technique to obtain a complete destruction of cerebral lesions delivering a single high dose radiation beam. Positron Emission Tomography (PET) imaging is increasingly utilized for radiation treatment planning. Nevertheless, lesion volume delineation in PET datasets is challenging because of the low spatial resolution and high noise level of PET images. Nowadays, the biological target volume (BTV) is manually contoured on PET studies. This procedure is time expensive and operator-dependent. In this article, a fully automatic algorithm for the BTV delineation based on random walks (RW) on graphs is proposed. The results are compared with the outcomes of the original RW method, 40% thresholding method, region growing method, and fuzzy c-means clustering method. To validate the effectiveness of the proposed approach in a clinical environment, BTV segmentation on 18 patients with cerebral metastases is performed. Experimental results show that the segmentation algorithm is accurate and has real-time performance satisfying the physician requirements in a radiotherapy environment.
year | journal | country | edition | language |
---|---|---|---|---|
2016-03-01 | International Journal of Imaging Systems and Technology |