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

The diffusion and perfusion magnetic resonance (MR) images can provide functional information about tumour and enable more sensitive detection of the tumour extent. We aimed to develop a fuzzy feature fusion method for auto-segmentation of gliomas in radiotherapy planning using multi-parametric functional MR images including apparent diffusion coefficient (ADC), fractional anisotropy (FA) and relative cerebral blood volume (rCBV). For each functional modality, one histogram-based fuzzy model was created to transform image volume into a fuzzy feature space. Based on the fuzzy fusion result of the three fuzzy feature spaces, regions with high possibility belonging to tumour were generated automatically. The auto-segmentations of tumour in structural MR images were added in final auto-segmented gross tumour volume (GTV). For evaluation, one radiation oncologist delineated GTVs for nine patients with all modalities. Comparisons between manually delineated and auto-segmented GTVs showed that, the mean volume difference was 8.69% (±5.62%); the mean Dice’s similarity coefficient (DSC) was 0.88 (±0.02); the mean sensitivity and specificity of auto-segmentation was 0.87 (±0.04) and 0.98 (±0.01) respectively. High accuracy and efficiency can be achieved with the new method, which shows potential of utilizing functional multi-parametric MR images for target definition in precision radiation treatment planning for patients with gliomas.

[1]  J D Pickard,et al.  Diffusion tensor imaging: possible implications for radiotherapy treatment planning of patients with high-grade glioma. , 2005, Clinical oncology (Royal College of Radiologists (Great Britain)).

[2]  Zhen Ma,et al.  A review of algorithms for medical image segmentation and their applications to the female pelvic cavity , 2010, Computer methods in biomechanics and biomedical engineering.

[3]  C. Zimmer,et al.  Multimodal Imaging to Delineate Tumor Heterogeneity in Cerebral Gliomas , 2014 .

[4]  Peter McGraw,et al.  Peritumoral brain regions in gliomas and meningiomas: investigation with isotropic diffusion-weighted MR imaging and diffusion-tensor MR imaging. , 2004, Radiology.

[5]  Kyu H. Shin,et al.  A data fusion approach to tumor delineation , 1995, Proceedings., International Conference on Image Processing.

[6]  K. Fountas,et al.  Investigating brain tumor differentiation with diffusion and perfusion metrics at 3T MRI using pattern recognition techniques. , 2013, Magnetic resonance imaging.

[7]  Bram Stieltjes,et al.  MRI for identification of progression in brain tumors: from morphology to function , 2008, Expert review of neurotherapeutics.

[8]  Mohammad Hossein Fazel Zarandi,et al.  Systematic image processing for diagnosing brain tumors: A Type-II fuzzy expert system approach , 2011, Appl. Soft Comput..

[9]  J. Gillard,et al.  Imaging biomarkers of brain tumour margin and tumour invasion. , 2011, The British journal of radiology.

[10]  J. Ferda,et al.  Diffusion tensor magnetic resonance imaging of glial brain tumors. , 2010, European journal of radiology.

[11]  B A Kall,et al.  Imaging-based stereotaxic serial biopsies in untreated intracranial glial neoplasms. , 1987, Journal of neurosurgery.

[12]  N. Datta,et al.  Implications of contrast-enhanced CT-based and MRI-based target volume delineations in radiotherapy treatment planning for brain tumors. , 2008, Journal of cancer research and therapeutics.

[13]  G A Whitfield,et al.  Imaging and target volume delineation in glioma. , 2014, Clinical oncology (Royal College of Radiologists (Great Britain)).

[14]  N. Sobol,et al.  Preliminary results , 2020, Asymptotic Analysis of Random Walks: Light-Tailed Distributions.

[15]  Glyn Johnson,et al.  Glioma grading: sensitivity, specificity, and predictive values of perfusion MR imaging and proton MR spectroscopic imaging compared with conventional MR imaging. , 2003, AJNR. American journal of neuroradiology.

[16]  Yue Cao,et al.  Functional and metabolic magnetic resonance imaging and positron emission tomography for tumor volume definition in high-grade gliomas. , 2009, Seminars in radiation oncology.

[17]  P. Yen,et al.  White Matter tract involvement in brain tumors: a diffusion tensor imaging analysis. , 2009, Surgical neurology.

[18]  Jean-Marc Constans,et al.  A framework of fuzzy information fusion for the segmentation of brain tumor tissues on MR images , 2007, Image Vis. Comput..

[19]  吳柏林.  Fuzzy statistics and computation on the lexical semantics , 1996 .

[20]  G. Tedeschi,et al.  Spectroscopic, diffusion and perfusion magnetic resonance imaging at 3.0 Tesla in the delineation of glioblastomas: preliminary results. , 2006, Journal of experimental & clinical cancer research : CR.

[21]  Sasa Mutic,et al.  Concurrent multimodality image segmentation by active contours for radiotherapy treatment planning. , 2007, Medical physics.

[22]  I. Turksen,et al.  A model for the measurement of membership and the consequences of its empirical implementation , 1984 .

[23]  J. Guyotat,et al.  Clinical relevance of diffusion and perfusion magnetic resonance imaging in assessing intra-axial brain tumors , 2006, Neuroradiology.

[24]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[25]  A R Hounsell,et al.  Geometrical analysis of radiotherapy target volume delineation: a systematic review of reported comparison methods. , 2010, Clinical oncology (Royal College of Radiologists (Great Britain)).

[26]  L. Remonda,et al.  Diffusion tensor imaging for target volume definition in glioblastoma multiforme , 2014, Strahlentherapie und Onkologie.

[27]  Grégoire Malandain,et al.  Evaluation of an atlas-based automatic segmentation software for the delineation of brain organs at risk in a radiation therapy clinical context. , 2008, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[28]  Yang Du.  Diffusion tensor imaging analysis , 2005 .

[29]  L. Zadeh.  Fuzzy sets as a basis for a theory of possibility , 1999 .

[30]  Tommaso Scarabino,et al.  Multiparametric 3T MR approach to the assessment of cerebral gliomas: tumor extent and malignancy , 2006, Neuroradiology.

[31]  Swarup Medasani,et al.  An overview of membership function generation techniques for pattern recognition , 1998, Int. J. Approx. Reason..

[32]  A. Stecco,et al.  DTI and PWI analysis of peri-enhancing tumoral brain tissue in patients treated for glioblastoma , 2011, Journal of Neuro-Oncology.

[33]  S. Bauer,et al.  A survey of MRI-based medical image analysis for brain tumor studies , 2013, Physics in medicine and biology.

[34]  Z. Song,et al.  Differentiation between low-grade and high-grade glioma using combined diffusion tensor imaging metrics , 2013, Clinical Neurology and Neurosurgery.

[35]  Isabelle Bloch,et al.  Fuzzy relative position between objects in images: a morphological approach , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[36]  Hamidreza Saligheh Rad,et al.  Multi-parametric (ADC/PWI/T2-w) image fusion approach for accurate semi-automatic segmentation of tumorous regions in glioblastoma multiforme , 2015, Magnetic Resonance Materials in Physics, Biology and Medicine.

[37]  G. Johnson,et al.  Conventional MR imaging with simultaneous measurements of cerebral blood volume and vascular permeability in ganglioglioma. , 2004, Magnetic resonance imaging.

[38]  Sarah J Nelson,et al.  Assessment of therapeutic response and treatment planning for brain tumors using metabolic and physiological MRI , 2011, NMR in biomedicine.