Automatic 3D detection and segmentation of head and neck cancer from MRI data

Zhao, Baixiang and Soraghan, John and Grose, Derek and Doshi, Trushali and Di-Caterina, Gaetano; Tabus, I. and Larabi, C. and Battisti, F. and Egiazarian, K. and Oudre, L. and Beghdadi, A., eds. (2019) Automatic 3D detection and segmentation of head and neck cancer from MRI data. In: Proceedings of the 2018 7th European Workshop on Visual Information Processing, EUVIP 2018. IEEE, FIN. ISBN 9781538668979

[thumbnail of Zhao-etal-EUVIP2018-Automatic-3D-detection-and-segmentation-of-head-and-neck]
Text (Zhao-etal-EUVIP2018-Automatic-3D-detection-and-segmentation-of-head-and-neck)
Accepted Author Manuscript

Download (1MB)| Preview


    A novel algorithm for automatic head and neck 3D tumour segmentation from magnetic resonance imaging (MRI) is presented. The proposed algorithm pre-processes the MRI data slices to enhance quality and reduce artefacts. An intensity standardisation process is performed between slices, followed by cancer region segmentation of central slice, to get the correct intensity range and rough location of tumour regions. Fourier interpolation is applied to create isotropic 3D MR I volume. A new location-constrained 3D level set method segments the tumour from the interpolated MRI volume. The proposed algorithm is tested on real MRI data. The results show that the novel 3D tumour volume extraction algorithm has an improved dice score and F-measure when compared to the previous 2D and 3D segmentation method.

    ORCID iDs

    Zhao, Baixiang ORCID logoORCID:, Soraghan, John ORCID logoORCID:, Grose, Derek, Doshi, Trushali and Di-Caterina, Gaetano ORCID logoORCID:; Tabus, I., Larabi, C., Battisti, F., Egiazarian, K., Oudre, L. and Beghdadi, A.