Fuzzy clustering approach for brain tumor tissue segmentation in magnetic resonance images
- 18 Downloads
The early and accurate detection of brain tumors is key to improve the quality of life and the survival of cancer patients. Magnetic resonance imaging (MRI) is a widely used imaging technique to assess these tumors, but the large amount of data produced by MRI prevents manual segmentation in a reasonable time, limiting the use of precise quantitative measurements in the clinical practice. Consequently, automatic and reliable segmentation methods are required. However, the large spatial and structural variability among brain tumors make automatic segmentation a challenging problem. In this contribution, we present a new model of segmentation of brain magnetic resonance images. In order to obtain the region of interest, we propose a hybrid approach that carries out both fuzzy c-mean algorithm and multiobjective optimization taking into account both compactness and separation in the clusters with the purpose of improving the cluster center detection and speed up the convergence time. This new segmentation approach is a key component of the proposed magnetic resonance image-based classification system for brain tumors. Experimental results are presented to demonstrate the effectiveness and efficiency of the proposed approach using the DICOM MRI database.
KeywordsMagnetic resonance images segmentation Tumor tissue detection Oncologic Fuzzy C-means clustering algorithm Cluster compelling information Region of interest extraction Optimization fuzzy compactness and separation Genetic algorithm
This research is supported by PhD scholarship subprogram SENACYT-IFARHU (Secretaría Nacional de Ciencia, Tecnología e Innovación y el Instituto para la Formación y Aprovechamiento de Recursos Humanos), CN2070-2013-052, Panamá, Republic of Panama, the scholarship program COOPEN-Erasmus Mundus external cooperation windows: Polytechnic University of Valencia, Spain, the Autonomous University of Chiriqui, David, Panama. UNACHI (Universidad Autónoma de Chiriquí, David, Panamá) and FEDER funds (Grant number TIN2016-75850-R) and H2020-MSCA-IF Funds (Project DeciTrustNET ID: 746398). The authors would like to thank Ph.D. Del Fresno Mariana.
Compliance with ethical standards
Conflict of interest
This study was funded by SENACYT-IFARHU (Grant number CN2070-2013-052) and FEDER funds (Grant number TIN2016-75850-R) and H2020-MSCA-IF Funds (Project DeciTrustNET ID: 746398). Author Iván Ariel Rodríguez Méndez declares he has no conflict of interest. Author Raquel Ureña declares she has no conflict of interest. Author Enrique Herrera-Viedma declares he has no conflict of interest. This article does not contain any studies with human participants performed by any of the authors.
- Coello C (2000) Handling preferences in evolutionary multiobjective optimization: a survey. IEEE Evol Comput 1:30–37Google Scholar
- De Oliveira J, Machado A, Chavez G, Lopes A, Deserno T, Arajo A (2010) Mammosys: a content-based image retrieval system using breast density patterns. Comput Med Imaging Graph 99:289–297Google Scholar
- Dou W, Wu Q, Chen Y, Ruan S, Constans J (2005) Fuzzy modelling of different tumorous cerebral tissues on mri images based on fusion of feature information. In: Engineering in Medicine and Biology Society, 2005, pp. 3104–3107Google Scholar
- Drevelegas A, Papanikolaou N (2011) Imaging modalities in brain tumors. Springer, Berlin, pp 13–33Google Scholar
- Georgiadis P, Cavouras D, Kalatzis I, Daskalakis A, Kagadis G, Sifaki K, Malamas M, Nikiforidis G, Solomou E (2008) Improving brain tumor characterization on mri by probabilistic neural networks and non-linear transformation of textural features. Comput Methods Programs Biomed 89(1):24–32CrossRefGoogle Scholar
- Kinani JMV, Rosales-Silva AJ, Gallegos-Funes FJ, Arellano A (2014) Fuzzy c-means applied to mri images for an automatic lesion detection using image enhancement and constrained clustering. In: 2014 4th International conference on image processing theory, tools and applications (IPTA), pp. 1–7 . https://doi.org/10.1109/IPTA.2014.7001987
- Meschino G, Comas D, Vallarin V, Scandurra A, Passoni L (2014) Automatic design of interpretable fuzzy predicate systems for clustering using self-organizing maps. Neurocomputing 147(5):47–59Google Scholar
- Mukhopadhyay A, Maulik U, Bandyopadhyay S (2011) Gene expression data analysis using multiobjective clustering improved with svm based ensemble. Silico Biol 11(1–2):19–27Google Scholar
- Rosas-Romero R, Rodriguez-Asomoza J (2003) 4-d active contour snake model for object representation from medical images. In: Proceedings of the 25th annual international conference of the IEEE engineering in medicine and biology society (IEEE Cat. No.03CH37439), vol. 1, pp. 717–719 Vol 1Google Scholar
- Ureña R, Martínez-Cañada P, Gómez-López JM, Morillas C, Pelayo F (2012) Real-time tone mapping on gpu and fpga. EURASIP Journal on Image and Video Processing (1)Google Scholar
- Vescan A, Grosan C, Pop HF (2008) Evolutionary algorithms for the component selection problem. In: 2008 19th International workshop on database and expert systems applications, pp. 509–513 . https://doi.org/10.1109/DEXA.2008.138