A fuzzy feature fusion method for auto-segmentation of gliomas with multi-modality diffusion and perfusion magnetic resonance images in radiotherapy

ECU Author/Contributor (non-ECU co-authors, if there are any, appear on document)

Lu,Wang,Ping,Sun,Ranran,Yang,Chengwen,Zhang,Ning,G Guo (Creator)

Institution

East Carolina University (ECU )

Web Site: http://www.ecu.edu/lib/

Abstract: The difusion and perfusion magnetic resonance (MR) images can provide functional information abouttumour and enable more sensitive detection of the tumour extent. We aimed to develop a fuzzy featurefusion method for auto-segmentation of gliomas in radiotherapy planning using multi-parametricfunctional MR images including apparent difusion coefcient (ADC), fractional anisotropy (FA) andrelative cerebral blood volume (rCBV). For each functional modality, one histogram-based fuzzy modelwas created to transform image volume into a fuzzy feature space. Based on the fuzzy fusion resultof the three fuzzy feature spaces, regions with high possibility belonging to tumour were generatedautomatically. The auto-segmentations of tumour in structural MR images were added in fnal autosegmented gross tumour volume (GTV). For evaluation, one radiation oncologist delineated GTVs fornine patients with all modalities. Comparisons between manually delineated and auto-segmented GTVsshowed that, the mean volume diference was 8.69% (±5.62%); the mean Dice"s similarity coefcient(DSC) was 0.88 (±0.02); the mean sensitivity and specifcity of auto-segmentation was 0.87 (±0.04)and 0.98 (±0.01) respectively. High accuracy and efciency can be achieved with the new method,which shows potential of utilizing functional multi-parametric MR images for target defnition inprecision radiation treatment planning for patients with gliomas.

Additional Information

Publication

Other

Language: English

Date: 2018

Email this document to