SOKAC, Mario ;VUKELIC, Djordje ;JAKOVLJEVIC, Zivana ;SANTOSI, Zeljko ;HADZISTEVIC, Miodrag ;BUDAK, Igor . Fuzzy Hybrid Method for the Reconstruction of 3D Models Based on CT/MRI Data. Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 65, n.9, p. 482-494, september 2019. ISSN 0039-2480. Available at: <https://www.sv-jme.eu/article/fuzzy-hybrid-method-for-reconstruction-of-3d-models-based-on-ctmri-data/>. Date accessed: 20 dec. 2024. doi:http://dx.doi.org/10.5545/sv-jme.2019.6136.
Sokac, M., Vukelic, D., Jakovljevic, Z., Santosi, Z., Hadzistevic, M., & Budak, I. (2019). Fuzzy Hybrid Method for the Reconstruction of 3D Models Based on CT/MRI Data. Strojniški vestnik - Journal of Mechanical Engineering, 65(9), 482-494. doi:http://dx.doi.org/10.5545/sv-jme.2019.6136
@article{sv-jmesv-jme.2019.6136,
author = {Mario Sokac and Djordje Vukelic and Zivana Jakovljevic and Zeljko Santosi and Miodrag Hadzistevic and Igor Budak},
title = {Fuzzy Hybrid Method for the Reconstruction of 3D Models Based on CT/MRI Data},
journal = {Strojniški vestnik - Journal of Mechanical Engineering},
volume = {65},
number = {9},
year = {2019},
keywords = {fuzzy C-means clustering, region growing, image segmentation, surface 3D model},
abstract = {This research proposes a hybrid method for improving the segmentation accuracy of reconstructed 3D models from computed tomography/magnetic resonance imaging (CT/MRI) data. A semi-automatic hybrid method based on combination of Fuzzy C-Means clustering (FCM) and region growing (RG) is proposed. In this approach, FCM is used in the first stage as a preprocessing step in order to classify and improve images by assigning pixels to the clusters for which they have the maximum membership, and manual selection of the membership intensity map with the best contrast separation. Afterwards, automatic seed selection is performed for RG, for which a new parameter standard deviation (STD) of pixel intensities, is included. It is based on the selection of an initial seed inside a region with maximum value of STD. To evaluate the performance of the proposed method, it was compared to several other segmentation methods. Experimental results show that the proposed method overall provides better results compared to other methods in terms of accuracy. The average sensitivity and accuracy rates for cone-beam computed tomography CBCT 1 and CBCT 2 datasets are 99 %, 98.4 %, 47.2 % and 89.9 %, respectively. For MRI 1 and MRI 2 datasets, the average sensitivity and accuracy values are 99.1 %, 100 %, 75.6 % and 99.6 %, respectively. The average values for the Dice coefficient and Jaccard index for the CBCT 1 and CBCT 2 datasets are 95.88, 0.88, 0.6, and 0.51, respectively, while for MRI 1 and MRI 2 datasets, average values are 0.96, 0.93, 0.81 and 0.7, respectively, which confirms the high accuracy of the proposed method.},
issn = {0039-2480}, pages = {482-494}, doi = {10.5545/sv-jme.2019.6136},
url = {https://www.sv-jme.eu/article/fuzzy-hybrid-method-for-reconstruction-of-3d-models-based-on-ctmri-data/}
}
Sokac, M.,Vukelic, D.,Jakovljevic, Z.,Santosi, Z.,Hadzistevic, M.,Budak, I. 2019 September 65. Fuzzy Hybrid Method for the Reconstruction of 3D Models Based on CT/MRI Data. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 65:9
%A Sokac, Mario %A Vukelic, Djordje %A Jakovljevic, Zivana %A Santosi, Zeljko %A Hadzistevic, Miodrag %A Budak, Igor %D 2019 %T Fuzzy Hybrid Method for the Reconstruction of 3D Models Based on CT/MRI Data %B 2019 %9 fuzzy C-means clustering, region growing, image segmentation, surface 3D model %! Fuzzy Hybrid Method for the Reconstruction of 3D Models Based on CT/MRI Data %K fuzzy C-means clustering, region growing, image segmentation, surface 3D model %X This research proposes a hybrid method for improving the segmentation accuracy of reconstructed 3D models from computed tomography/magnetic resonance imaging (CT/MRI) data. A semi-automatic hybrid method based on combination of Fuzzy C-Means clustering (FCM) and region growing (RG) is proposed. In this approach, FCM is used in the first stage as a preprocessing step in order to classify and improve images by assigning pixels to the clusters for which they have the maximum membership, and manual selection of the membership intensity map with the best contrast separation. Afterwards, automatic seed selection is performed for RG, for which a new parameter standard deviation (STD) of pixel intensities, is included. It is based on the selection of an initial seed inside a region with maximum value of STD. To evaluate the performance of the proposed method, it was compared to several other segmentation methods. Experimental results show that the proposed method overall provides better results compared to other methods in terms of accuracy. The average sensitivity and accuracy rates for cone-beam computed tomography CBCT 1 and CBCT 2 datasets are 99 %, 98.4 %, 47.2 % and 89.9 %, respectively. For MRI 1 and MRI 2 datasets, the average sensitivity and accuracy values are 99.1 %, 100 %, 75.6 % and 99.6 %, respectively. The average values for the Dice coefficient and Jaccard index for the CBCT 1 and CBCT 2 datasets are 95.88, 0.88, 0.6, and 0.51, respectively, while for MRI 1 and MRI 2 datasets, average values are 0.96, 0.93, 0.81 and 0.7, respectively, which confirms the high accuracy of the proposed method. %U https://www.sv-jme.eu/article/fuzzy-hybrid-method-for-reconstruction-of-3d-models-based-on-ctmri-data/ %0 Journal Article %R 10.5545/sv-jme.2019.6136 %& 482 %P 13 %J Strojniški vestnik - Journal of Mechanical Engineering %V 65 %N 9 %@ 0039-2480 %8 2019-09-10 %7 2019-09-10
Sokac, Mario, Djordje Vukelic, Zivana Jakovljevic, Zeljko Santosi, Miodrag Hadzistevic, & Igor Budak. "Fuzzy Hybrid Method for the Reconstruction of 3D Models Based on CT/MRI Data." Strojniški vestnik - Journal of Mechanical Engineering [Online], 65.9 (2019): 482-494. Web. 20 Dec. 2024
TY - JOUR AU - Sokac, Mario AU - Vukelic, Djordje AU - Jakovljevic, Zivana AU - Santosi, Zeljko AU - Hadzistevic, Miodrag AU - Budak, Igor PY - 2019 TI - Fuzzy Hybrid Method for the Reconstruction of 3D Models Based on CT/MRI Data JF - Strojniški vestnik - Journal of Mechanical Engineering DO - 10.5545/sv-jme.2019.6136 KW - fuzzy C-means clustering, region growing, image segmentation, surface 3D model N2 - This research proposes a hybrid method for improving the segmentation accuracy of reconstructed 3D models from computed tomography/magnetic resonance imaging (CT/MRI) data. A semi-automatic hybrid method based on combination of Fuzzy C-Means clustering (FCM) and region growing (RG) is proposed. In this approach, FCM is used in the first stage as a preprocessing step in order to classify and improve images by assigning pixels to the clusters for which they have the maximum membership, and manual selection of the membership intensity map with the best contrast separation. Afterwards, automatic seed selection is performed for RG, for which a new parameter standard deviation (STD) of pixel intensities, is included. It is based on the selection of an initial seed inside a region with maximum value of STD. To evaluate the performance of the proposed method, it was compared to several other segmentation methods. Experimental results show that the proposed method overall provides better results compared to other methods in terms of accuracy. The average sensitivity and accuracy rates for cone-beam computed tomography CBCT 1 and CBCT 2 datasets are 99 %, 98.4 %, 47.2 % and 89.9 %, respectively. For MRI 1 and MRI 2 datasets, the average sensitivity and accuracy values are 99.1 %, 100 %, 75.6 % and 99.6 %, respectively. The average values for the Dice coefficient and Jaccard index for the CBCT 1 and CBCT 2 datasets are 95.88, 0.88, 0.6, and 0.51, respectively, while for MRI 1 and MRI 2 datasets, average values are 0.96, 0.93, 0.81 and 0.7, respectively, which confirms the high accuracy of the proposed method. UR - https://www.sv-jme.eu/article/fuzzy-hybrid-method-for-reconstruction-of-3d-models-based-on-ctmri-data/
@article{{sv-jme}{sv-jme.2019.6136},
author = {Sokac, M., Vukelic, D., Jakovljevic, Z., Santosi, Z., Hadzistevic, M., Budak, I.},
title = {Fuzzy Hybrid Method for the Reconstruction of 3D Models Based on CT/MRI Data},
journal = {Strojniški vestnik - Journal of Mechanical Engineering},
volume = {65},
number = {9},
year = {2019},
doi = {10.5545/sv-jme.2019.6136},
url = {https://www.sv-jme.eu/article/fuzzy-hybrid-method-for-reconstruction-of-3d-models-based-on-ctmri-data/}
}
TY - JOUR AU - Sokac, Mario AU - Vukelic, Djordje AU - Jakovljevic, Zivana AU - Santosi, Zeljko AU - Hadzistevic, Miodrag AU - Budak, Igor PY - 2019/09/10 TI - Fuzzy Hybrid Method for the Reconstruction of 3D Models Based on CT/MRI Data JF - Strojniški vestnik - Journal of Mechanical Engineering; Vol 65, No 9 (2019): Strojniški vestnik - Journal of Mechanical Engineering DO - 10.5545/sv-jme.2019.6136 KW - fuzzy C-means clustering, region growing, image segmentation, surface 3D model N2 - This research proposes a hybrid method for improving the segmentation accuracy of reconstructed 3D models from computed tomography/magnetic resonance imaging (CT/MRI) data. A semi-automatic hybrid method based on combination of Fuzzy C-Means clustering (FCM) and region growing (RG) is proposed. In this approach, FCM is used in the first stage as a preprocessing step in order to classify and improve images by assigning pixels to the clusters for which they have the maximum membership, and manual selection of the membership intensity map with the best contrast separation. Afterwards, automatic seed selection is performed for RG, for which a new parameter standard deviation (STD) of pixel intensities, is included. It is based on the selection of an initial seed inside a region with maximum value of STD. To evaluate the performance of the proposed method, it was compared to several other segmentation methods. Experimental results show that the proposed method overall provides better results compared to other methods in terms of accuracy. The average sensitivity and accuracy rates for cone-beam computed tomography CBCT 1 and CBCT 2 datasets are 99 %, 98.4 %, 47.2 % and 89.9 %, respectively. For MRI 1 and MRI 2 datasets, the average sensitivity and accuracy values are 99.1 %, 100 %, 75.6 % and 99.6 %, respectively. The average values for the Dice coefficient and Jaccard index for the CBCT 1 and CBCT 2 datasets are 95.88, 0.88, 0.6, and 0.51, respectively, while for MRI 1 and MRI 2 datasets, average values are 0.96, 0.93, 0.81 and 0.7, respectively, which confirms the high accuracy of the proposed method. UR - https://www.sv-jme.eu/article/fuzzy-hybrid-method-for-reconstruction-of-3d-models-based-on-ctmri-data/
Sokac, Mario, Vukelic, Djordje, Jakovljevic, Zivana, Santosi, Zeljko, Hadzistevic, Miodrag, AND Budak, Igor. "Fuzzy Hybrid Method for the Reconstruction of 3D Models Based on CT/MRI Data" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 65 Number 9 (10 September 2019)
Strojniški vestnik - Journal of Mechanical Engineering 65(2019)9, 482-494
© The Authors, CC-BY 4.0 Int. Change in copyright policy from 2022, Jan 1st.
This research proposes a hybrid method for improving the segmentation accuracy of reconstructed 3D models from computed tomography/magnetic resonance imaging (CT/MRI) data. A semi-automatic hybrid method based on combination of Fuzzy C-Means clustering (FCM) and region growing (RG) is proposed. In this approach, FCM is used in the first stage as a preprocessing step in order to classify and improve images by assigning pixels to the clusters for which they have the maximum membership, and manual selection of the membership intensity map with the best contrast separation. Afterwards, automatic seed selection is performed for RG, for which a new parameter standard deviation (STD) of pixel intensities, is included. It is based on the selection of an initial seed inside a region with maximum value of STD. To evaluate the performance of the proposed method, it was compared to several other segmentation methods. Experimental results show that the proposed method overall provides better results compared to other methods in terms of accuracy. The average sensitivity and accuracy rates for cone-beam computed tomography CBCT 1 and CBCT 2 datasets are 99 %, 98.4 %, 47.2 % and 89.9 %, respectively. For MRI 1 and MRI 2 datasets, the average sensitivity and accuracy values are 99.1 %, 100 %, 75.6 % and 99.6 %, respectively. The average values for the Dice coefficient and Jaccard index for the CBCT 1 and CBCT 2 datasets are 95.88, 0.88, 0.6, and 0.51, respectively, while for MRI 1 and MRI 2 datasets, average values are 0.96, 0.93, 0.81 and 0.7, respectively, which confirms the high accuracy of the proposed method.