Automatic multi-segmentation method for tumor detection in MRI Images using constrained kmeans method and region Growing-Quasi Monte Carlo Method

• Autorzy: Bagdaoui Amina , Chama Zouaoui , Hachemi Belkacem , El-Bay Bourennane

Identyfikatory

DOI

10.15199/48.2024.06.08

Warianty tytułu

PL

Automatyczna metoda wielosegmentacyjna do wykrywania nowotworu w obrazach MRI przy użyciu metody ograniczonych kmean i metody Quasi Monte Carlo wzrostu regionu

• Języki publikacji: EN

Abstrakty

EN

Magnetic Resonance Imaging (MRI) has become an indispensable tool in the medical field, enabling the detection of critical abnormalities affecting various organs within the human body. Despite its inherent complexity, the development of automated or semi-automated detection and recognition techniques has made significant strides. In this paper, we present an innovative approach for the automatic multi and full segmentation of tumor regions within MRI scans. An enhanced region-growing method founded on the Quasi-Monte Carlo sampling and constrained k-means algorithm is presented in this paper, we define distinct classes to facilitate precise segmentation. The efficacy of our technique is evaluated through a range of metrics, demonstrating its robust performance. The proposed fully automated multi-segmentation method showcases superior results and holds potential to supplant conventional techniques for tumor detection in MRI images.

PL

Rezonans magnetyczny (MRI) stał się niezastąpionym narzędziem w medycynie, umożliwiającym wykrycie krytycznych nieprawidłowości wpływających na różne narządy w organizmie człowieka. Pomimo swojej nieodłącznej złożoności, rozwój zautomatyzowanych lub półautomatycznych technik wykrywania i rozpoznawania poczynił znaczne postępy. W artykule przedstawiamy innowacyjne podejście do automatycznej wieloi pełnej segmentacji obszarów nowotworowych w obrazach MRI. W artykule przedstawiono ulepszoną metodę powiększania, regionów opartą na próbkowaniu Quasi-Monte Carlo i ograniczonym algorytmie k- ̨średnich. Definiujemy odrębne klasy, aby u ̨ łatwi c precyzyjną segmentacje. Skuteczność naszej techniki ocenia się za pomocą szeregu wskaźników, co pokazuje jej solidne działanie. Proponowana w pełni zautomatyzowana metoda wielosegmentacyjna zapewnia doskonałe wyniki i może zastąpić konwencjonalne techniki wykrywania nowotworów na obrazach MRI.

Słowa kluczowe

EN

brain tumor; multi segmentation; region growing constrained k-mean; Quasi Monte Carlo; naive Bayes

PL

guz mózgu; wielosegmentacja; rosnące w regionie średnie bayesowskie k; Quasi Monte Carlo

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2024
• Tom: R. 100, nr 6
• Strony: 42--47
• Opis fizyczny: Bibliogr. 28 poz., rys., tab.

Twórcy

autor

Bagdaoui Amina

• Department of Electronics, University of Djillali Liabes in Sidi Bel Abbes, Algeria

autor

Chama Zouaoui

• Department of Electronics, University of Djillali Liabes in Sidi Bel Abbes, Algeria

autor

Hachemi Belkacem

• Department of Electronics, University of Djillali Liabes in Sidi Bel Abbes, Algeria
• Centre de Développement des Téchnologies Avancées, Algiers, Algeria

autor

El-Bay Bourennane

• ImVia Laboratory, Université de Bourgogne, France

Bibliografia

• [1] Alim-Ferhat, F and Boudjelal, A and Seddiki, S and Hachemi, B and Oudjemia, S.: Wavelet Energy Embedded into a Level Set Method for Medical Images Segmentation in the Presence of Highly Similar Regions, Mathematics and Computers in Sciences and in Industry (MCSI), 2014 International Conference on, IEEE, pp. 149–153, 2014.
• [2] Anitha, R and Raja, D : Segmentation of glioma tumors using convolutional neural networks, International Journal of Imaging Systems and Technology, Wiley Online Library, 27(4), pp. 354– 360, 2017.
• [3] Cheng, Jun and Huang, Wei and Cao, Shuangliang and Yang, Ru and Yang, Wei and Yun, Zhaoqiang and Wang, Zhijianand Feng, Qianjin : Enhanced performance of brain tumor classification via tumor region augmentation and partition, PloS one, Public Library of Science, 10(10), pp. e0140381, 2015.
• [4] Donoso, Ramiro and Veloz, Alejandro and Allende, Hector : Modified expectation maximization algorithm for MRI segmentation, Ibero american Congress on Pattern Recognition, Springer, pp. 63–70, 2010.
• [5] El-Dahshan, El-Sayed A and Mohsen, Heba M and Revett, Kenneth and Salem, Abdel-Badeeh M : Computer-aided diagnosis of human brain tumor through MRI: A survey and a new algorithm, Expert systems with Applications, Elsevier, 41(11), pp. 5526–5545, 2014.
• [6] Gordillo, Nelly and Montseny, Eduard and Sobrevilla, Pilar :State of the art survey on MRI brain tumor segmentation,
• [7] Magnetic resonance imaging, Elsevier, 31(8), pp. 1426–1438, 2013.
• [8] Kuwazuru, Jumpei and Arimura, Hidetaka and Kakeda, Shingo and Yamamoto, Daisuke and Magome, Taiki and Yamashita, Yasuo and Ohki, Masafumi and Toyofuku, Fukai and Korogi, Yukunori : Automated detection of multiple sclerosis candidate regions in MR images: false-positive removal with use of an ANN-controlled level-set method, Radiological physics and technology, Springer, 5(1), pp. 105–113, 2012.
• [9] Lu, Xiaoqi and Wu, Jianshuai and Ren, Xiaoying and Zhang, Baohua and Li, Yinhui : The study and application of the improved region growing algorithm for liver segmentation,
• [10] Optik-International Journal for Light and Electron Optics, Elsevier, 125(9), pp. 2142–2147, 2014.
• [11] Maiti, Ishita and Chakraborty, Monisha : A new method for brain tumor segmentation based on watershed and edge detection algorithms in HSV colour model, Computing and Communication Systems (NCCCS), 2012 National Conference on, IEEE, pp. 1–5, 2012.
• [12] Maitra, Madhubanti and Chatterjee, Amitava: Hybrid multiresolution Slantlet transform and fuzzy c-means clustering approach for normal-pathological brain MR image segregation, Medical Engineering and Physics, Elsevier, 30(5), pp. 615–623, 2008.
• [13] Oliva, Diego and Cuevas, Erik and Pajares, Gonzalo and Zaldivar, Daniel and Perez-Cisneros, Marco : Multilevel thresholding segmentation based on harmony search optimization, Journal of Applied Mathematics, Hindawi, 2013, 2013.
• [14] Rifai, Hilmi and Bloch, Isabelle and Hutchinson, Seth and Wiart, Joe and Garnero, Line : Segmentation of the skull in MRI volumes using deformable model and taking the partial volume effect into account, Medical image analysis, Elsevier, 4(3), pp. 219–233, 2000.
• [15] Saritha, Saladi and Amutha Prabha, N : A comprehensive review: Segmentation of MRI images—brain tumor, International Journal of Imaging Systems and Technology, International Journal of Imaging Systems and Technology, 26(4), pp. 295–304, 2016.
• [16] Somkantha, Krit and Theera-Umpon, Nipon and Auephanwiriyakul, Sansanee : Boundary detection in medical images using edge following algorithm based on intensity gradient and texture gradient features, IEEE transactions on biomedical engineering, IEEE, title=Boundary detection in medical images using edge following algorithm based on intensity gradient and texture gradient features, 58(3), pp. 567– 573, 2011.
• [17] Taha, Abdel Aziz and Hanbury, Allan : Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool, BMC medical imaging, BioMed Central, 15(1), pp. 29–38, 2015.
• [18] Weili, Shi and Yu, Miao and Zhanfang, Chen and Hongbiao, Zhang : Research of automatic medical image segmentation algorithm based on Tsallis entropy and improved PCNN,Mechatronics and Automation, 2009. ICMA 2009. International Conference on, IEEE, pp. 1004–1008, 2009.
• [19] Zhang, Yudong and Wu, Lenan : An MR brain images classifier via principal component analysis and kernel support vector machine, Progress In Electromagnetics Research, EMW Publishing, pp. 369–388, 2012.
• [20] MICCAI BraTS Database 2015, [web page] http://braintumorsegmentation.org/, Nov. 20015.
• [21] Menze, Bjoern H and Jakab, Andras and Bauer, Stefan and Kalpathy-Cramer, Jayashree and Farahani, Keyvan and Kirby, Justin and Burren, Yuliya and Porz, Nicole and Slotboom, Johannes and Wiest, Roland and others: The multimodal brain tumor image segmentation benchmark (BRATS), IEEE transactions on medical imaging, IEEE, 34(10), pp. 1993–2024, 2015.
• [22] Z. Muda and Warusia, Mohamed and md, nasir, Sulaiman and Nur, Izura, Udzir : K-Means Clustering and Naive Bayes Classification for Intrusion Detection, Journal of IT in Asia, UNIMAS, 4(1), pp. 13–25, 2016.
• [23] B. Hachemi and Z. Chama : Fully automatic multi segmentation approach for magnetic resonance imaging brain tumor detection using improved region-growing and quasi Monte Carlo expectation maximization algorithm, Int. J. Imaging Syst. Technol, Wiley, 30(1), pp. 104–111, 2020.
• [24] K. Vaidhya and S. Thirunavukkarasu and V. Alex and G. Krishnamurthi : Multi-modal brain tumor segmentation using stacked Denoising autoencoders, Lecture Notes in Computer Science, Springer International Publishing, 30(1), pp. 181–194, 2016.
• [25] S. Pereira and A. Pinto and V. Alves and CA. Silva : Brain tumor segmentation using convolutional neural networks in MRI images, IEEE Trans Med Imaging, IEEE, 35(5), pp. 1240– 1251, 2016.
• [26] A. Demirhan and M. Toru and I. Guler : Segmentation of tumor and edema along with healthy tissues of brain using wavelets and neural networks, IEEE J Biomed Health Inform, IEEE, 19(4), pp. 1451–1458, 2015.
• [27] Brain Tumor Segmantation Using Random Forest Trained on Iteratively Selected Patients, [web page] https://www.springerprofessional.de/en/braintumorsegmantatio n using-random-forest-trained-on-iterativ/+, 2016. [Accessed on 23 March. 2019.].
• [28] J. Besag : On the Statistical Analysis of Dirty Pictures, Journal of the Royal Statistical Society, serie B, 48(3), pp. 259–302, 1980

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki i promocja sportu (2025).