IDRM: Brain tumor image segmentation with boosted RIME optimization
Timely diagnosis of medical conditions can significantly mitigate the risks they pose to human life. Consequently, there is an urgent demand for an effective auxiliary model that assists physicians in accurately diagnosing medical conditions based on imaging data. While multi-threshold image segment...
- Autores:
-
Zhu, Wei
Fang, Liming
Ye, Xia
Medani, Mohamed
Escorcia-Gutierrez, José
- Tipo de recurso:
- Article of journal
- Fecha de publicación:
- 2023
- Institución:
- Corporación Universidad de la Costa
- Repositorio:
- REDICUC - Repositorio CUC
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.cuc.edu.co:11323/13926
- Acceso en línea:
- https://hdl.handle.net/11323/13926
https://repositorio.cuc.edu.co/
- Palabra clave:
- RIME
Image segmentation
Multi-threshold
Meta-heuristic algorithms
Rényi's entropy
Brain tumor detection
- Rights
- openAccess
- License
- Atribución 4.0 Internacional (CC BY 4.0)
| id |
RCUC2_9c0296450459eaa507b85cb69d4b2a32 |
|---|---|
| oai_identifier_str |
oai:repositorio.cuc.edu.co:11323/13926 |
| network_acronym_str |
RCUC2 |
| network_name_str |
REDICUC - Repositorio CUC |
| repository_id_str |
|
| dc.title.eng.fl_str_mv |
IDRM: Brain tumor image segmentation with boosted RIME optimization |
| title |
IDRM: Brain tumor image segmentation with boosted RIME optimization |
| spellingShingle |
IDRM: Brain tumor image segmentation with boosted RIME optimization RIME Image segmentation Multi-threshold Meta-heuristic algorithms Rényi's entropy Brain tumor detection |
| title_short |
IDRM: Brain tumor image segmentation with boosted RIME optimization |
| title_full |
IDRM: Brain tumor image segmentation with boosted RIME optimization |
| title_fullStr |
IDRM: Brain tumor image segmentation with boosted RIME optimization |
| title_full_unstemmed |
IDRM: Brain tumor image segmentation with boosted RIME optimization |
| title_sort |
IDRM: Brain tumor image segmentation with boosted RIME optimization |
| dc.creator.fl_str_mv |
Zhu, Wei Fang, Liming Ye, Xia Medani, Mohamed Escorcia-Gutierrez, José |
| dc.contributor.author.none.fl_str_mv |
Zhu, Wei Fang, Liming Ye, Xia Medani, Mohamed Escorcia-Gutierrez, José |
| dc.subject.proposal.eng.fl_str_mv |
RIME Image segmentation Multi-threshold Meta-heuristic algorithms Rényi's entropy Brain tumor detection |
| topic |
RIME Image segmentation Multi-threshold Meta-heuristic algorithms Rényi's entropy Brain tumor detection |
| description |
Timely diagnosis of medical conditions can significantly mitigate the risks they pose to human life. Consequently, there is an urgent demand for an effective auxiliary model that assists physicians in accurately diagnosing medical conditions based on imaging data. While multi-threshold image segmentation models have garnered considerable attention due to their simplicity and ease of implementation, the selection of threshold combinations greatly influences the segmentation performance. Traditional optimization algorithms often require substantial time to address multi-threshold image segmentation problems, and their segmentation accuracy is frequently unsatisfactory. As a result, metaheuristic algorithms have been employed in this domain. However, several algorithms suffer from drawbacks such as premature convergence and inadequate exploration of the solution space when it comes to threshold selection. For instance, the recently proposed optimization algorithm RIME, inspired by the physical phenomenon of rime-ice, falls short in terms of avoiding local optima and fully exploring the solution space. Therefore, this study introduces an enhanced version of RIME, called IDRM, which incorporates an interactive mechanism and Gaussian diffusion strategy. The interactive mechanism facilitates information exchange among agents, enabling them to evolve towards more promising directions and increasing the likelihood of discovering the optimal solution. Additionally, the Gaussian diffusion strategy enhances the agents' local exploration capabilities and expands their search within the solution space, effectively preventing them from becoming trapped in local optima. Experimental results on 30 benchmark test functions demonstrate that IDRM exhibits favorable optimization performance across various optimization functions, showcasing its robustness and convergence properties. Furthermore, the algorithm is applied to select threshold combinations for brain tumor image segmentation, and the results are evaluated using metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM). The overall findings consistently highlight the exceptional performance of this approach, further validating the effectiveness of IDRM in addressing image segmentation problems. |
| publishDate |
2023 |
| dc.date.issued.none.fl_str_mv |
2023-11 |
| dc.date.accessioned.none.fl_str_mv |
2025-01-20T22:10:46Z |
| dc.date.available.none.fl_str_mv |
2025-01-20T22:10:46Z |
| dc.type.none.fl_str_mv |
Artículo de revista |
| dc.type.coar.fl_str_mv |
http://purl.org/coar/resource_type/c_2df8fbb1 |
| dc.type.coar.none.fl_str_mv |
http://purl.org/coar/resource_type/c_6501 |
| dc.type.content.none.fl_str_mv |
Text |
| dc.type.driver.none.fl_str_mv |
info:eu-repo/semantics/article |
| dc.type.redcol.none.fl_str_mv |
http://purl.org/redcol/resource_type/ART |
| dc.type.version.none.fl_str_mv |
info:eu-repo/semantics/acceptedVersion |
| format |
http://purl.org/coar/resource_type/c_6501 |
| status_str |
acceptedVersion |
| dc.identifier.citation.none.fl_str_mv |
Wei Zhu, Liming Fang, Xia Ye, Mohamed Medani, José Escorcia-Gutierrez, IDRM: Brain tumor image segmentation with boosted RIME optimization, Computers in Biology and Medicine, Volume 166, 2023, 107551, ISSN 0010-4825, https://doi.org/10.1016/j.compbiomed.2023.107551 |
| dc.identifier.issn.none.fl_str_mv |
0010-4825 |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/11323/13926 |
| dc.identifier.doi.none.fl_str_mv |
10.1016/j.compbiomed.2023.107551 |
| dc.identifier.eissn.none.fl_str_mv |
1879-0534 |
| dc.identifier.instname.none.fl_str_mv |
Corporación Universidad de la Costa |
| dc.identifier.reponame.none.fl_str_mv |
REDICUC - Repositorio CUC |
| dc.identifier.repourl.none.fl_str_mv |
https://repositorio.cuc.edu.co/ |
| identifier_str_mv |
Wei Zhu, Liming Fang, Xia Ye, Mohamed Medani, José Escorcia-Gutierrez, IDRM: Brain tumor image segmentation with boosted RIME optimization, Computers in Biology and Medicine, Volume 166, 2023, 107551, ISSN 0010-4825, https://doi.org/10.1016/j.compbiomed.2023.107551 0010-4825 10.1016/j.compbiomed.2023.107551 1879-0534 Corporación Universidad de la Costa REDICUC - Repositorio CUC |
| url |
https://hdl.handle.net/11323/13926 https://repositorio.cuc.edu.co/ |
| dc.language.iso.none.fl_str_mv |
eng |
| language |
eng |
| dc.relation.ispartofjournal.none.fl_str_mv |
Computers in Biology and Medicine |
| dc.relation.references.none.fl_str_mv |
[1] E.-S.A. El-Dahshan, et al., Computer-aided diagnosis of human brain tumor through MRI: a survey and a new algorithm, Expert Syst. Appl. 41 (11) (2014) 5526–5545. [2] G. Chen, et al., MTANS: multi-scale mean teacher combined adversarial network with shape-aware embedding for semi-supervised brain lesion segmentation, Neuroimage 244 (2021), 118568. [3] G. Chen, et al., RFDCR: automated brain lesion segmentation using cascaded random forests with dense conditional random fields, Neuroimage 211 (2020), 116620. [4] H. Saleem, A.R. Shahid, B. Raza, Visual interpretability in 3D brain tumor segmentation network, Comput. Biol. Med. 133 (2021), 104410. [5] J. Nodirov, A.B. Abdusalomov, T.K. Whangbo, Attention 3D U-net with multiple skip connections for segmentation of brain tumor images, Sensors 22 (2022), https://doi.org/10.3390/s22176501. [6] R. Sindhiya Devi, B. Perumal, M. Pallikonda Rajasekaran, A hybrid deep learning based brain tumor classification and segmentation by stationary wavelet packet transform and adaptive kernel fuzzy c means clustering, Adv. Eng. Software 170 (2022), 103146. [7] Y. Zhuang, et al., An effective WSSENet-based similarity retrieval method of large lung CT image databases, KSII Transactions on Internet & Information Systems 16 (7) (2022). [8] Y. Zhuang, N. Jiang, Y. Xu, Progressive distributed and parallel similarity retrieval of large CT image sequences in mobile telemedicine networks, Wireless Commun. Mobile Comput. 2022 (2022), 6458350. [9] Z. Zhang, et al., Endoscope image mosaic based on pyramid ORB, Biomed. Signal Process Control 71 (2022), 103261. [10] S. Lu, et al., Soft tissue feature tracking based on DeepMatching network, CMESComputer Modeling in Engineering & Sciences 136 (1) (2023). [11] Y. Zhu, et al., Deep learning-based predictive identification of neural stem cell differentiation, Nat. Commun. 12 (1) (2021) 2614. [12] S. Lu, et al., Iterative reconstruction of low-dose CT based on differential sparse, Biomed. Signal Process Control 79 (2023), 104204. [13] N. Narappanawar, B.M. Rao, M. Joshi, Graph theory based segmentation of traced boundary into open and closed sub-sections, Comput. Vis. Image Understand. 115 (11) (2011) 1552–1558. [14] A. Ahilan, et al., Segmentation by fractional order darwinian particle swarm optimization based multilevel thresholding and improved lossless prediction based compression algorithm for medical images, IEEE Access 7 (2019) 89570–89580. [15] J. Michetti, et al., Influence of CBCT parameters on the output of an automatic edge-detection-based endodontic segmentation, Dentomaxillofacial Radiol. 44 (8) (2015). [16] D. Zhang, et al., A region-based segmentation method for ultrasound images in HIFU therapy, Med. Phys. 43 (6) (2016) 2975–2989. [17] X. Xia, Q. Liu, M.L. Huang, The use of artificial intelligence based magnifying image segmentation algorithm combined with endoscopy in early diagnosis and nursing of esophageal cancer patients, J. Med. Imaging Health Inform. 11 (4) (2021) 1306–1311. [18] S. Zhao, et al., Boosted crow search algorithm for handling multi-threshold image problems with application to X-ray images of COVID-19, Expert Syst. Appl. 213 (2023), 119095. [19] D. Zhao, et al., Ant colony optimization with horizontal and vertical crossover search: fundamental visions for multi-threshold image segmentation, Expert Syst. Appl. (2021) 167. [20] Y. Zheng, et al., Sine-SSA-BP ship trajectory prediction based on chaotic mapping improved sparrow search algorithm, Sensors 23 (2) (2023) 704. [21] B. Cao, et al., Multiobjective 3-D topology optimization of next-generation wireless data center network, IEEE Trans. Ind. Inf. 16 (5) (2019) 3597–3605. [22] C. Min, et al., Trajectory optimization of an electric vehicle with minimum energy consumption using inverse dynamics model and servo constraints, Mech. Mach. Theor. 181 (2023), 105185. [23] B. Cao, et al., Applying graph-based differential grouping for multiobjective largescale optimization, Swarm Evol. Comput. 53 (2020), 100626. [24] B. Cao, et al., Diversified personalized recommendation optimization based on mobile data, IEEE Trans. Intell. Transport. Syst. 22 (4) (2020) 2133–2139. [25] B. Li, et al., A distributionally robust optimization based method for stochastic model predictive control, IEEE Trans. Automat. Control 67 (11) (2021) 5762–5776. [26] X. Xu, et al., Multi-objective robust optimisation model for MDVRPLS in refined oil distribution, Int. J. Prod. Res. 60 (22) (2022) 6772–6792. [27] B. Cao, et al., Large-scale many-objective deployment optimization of edge servers, IEEE Trans. Intell. Transport. Syst. 22 (6) (2021) 3841–3849. [28] X. Liu, et al., Federated neural architecture search for medical data security, IEEE Trans. 18 (2022) 5628–5636. [29] Y. Zheng, et al., An optimal bp neural network track prediction method based on a ga–aco hybrid algorithm, J. Mar. Sci. Eng. 10 (10) (2022) 1399. [30] L. Qian, et al., A new method of inland water ship trajectory prediction based on long short-term memory network optimized by genetic algorithm, Appl. Sci. 12 (8) (2022) 4073. [31] X. Zhang, Z. Wang, Z. Lu, Multi-objective load dispatch for microgrid with electric vehicles using modified gravitational search and particle swarm optimization algorithm, Appl. Energy 306 (2022), 118018. [32] A.A. Heidari, et al., Harris hawks optimization: algorithm and applications, Future Generat. Comput. Syst. 97 (2019) 849–872. [33] H. Chen, et al., Slime mould algorithm: a comprehensive review of recent variants and applications, Int. J. Syst. Sci. (2022) 1–32. [34] S. Li, et al., Slime mould algorithm: a new method for stochastic optimization, Future Generat. Comput. Syst. 111 (2020) 300–323. [35] S. Mirjalili, J.S. Dong, A. Lewis, Nature-inspired Optimizers: Theories, Literature Reviews and Applications, Springer, 2019, 811. [36] R. Storn, K. Price, Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces, J. Global Optim. 11 (4) (1997) 341–359. [37] J. Tu, et al., The colony predation algorithm, JBE 18 (3) (2021) 674–710. [38] I. Ahmadianfar, et al., INFO: an efficient optimization algorithm based on weighted mean of vectors, Expert Syst. Appl. (2022), 116516. [39] I. Ahmadianfar, et al., RUN beyond the Metaphor: an Efficient Optimization Algorithm Based on Runge Kutta Method, Expert Systems with Applications, 2021, 115079. [40] H. Su, et al., RIME: A Physics-Based Optimization, Neurocomputing, 2023. [41] Y. Yang, et al., Hunger games search: visions, conception, implementation, deep analysis, perspectives, and towards performance shifts, Expert Syst. Appl. 177 (2021), 114864. [42] S. Zhao, et al., Performance optimization of salp swarm algorithm for multithreshold image segmentation: comprehensive study of breast cancer microscopy, Comput. Biol. Med. 139 (2021), 105015. [43] S. Hao, et al., Performance optimization of water cycle algorithm for multilevel lupus nephritis image segmentation, Biomed. Signal Process Control 80 (2023), 104139. [44] H. Su, et al., RIME: a physics-based optimization, Neurocomputing 532 (2023) 183–214. [45] S. García, et al., Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining: experimental analysis of power, Inf. Sci. 180 (10) (2010) 2044–2064. [46] J. Derrac, et al., A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms, Swarm Evol. Comput. 1 (1) (2011) 3–18. [47] Q. Huynh-Thu, M. Ghanbari, Scope of validity of PSNR in image/video quality assessment, Electron. Lett. 44 (13) (2008), 800-U35. [48] Z. Wang, et al., Image quality assessment: from error visibility to structural similarity, IEEE Trans. Image Process. 13 (4) (2004) 600–612. [49] J. Liang, et al., TransConver: transformer and convolution parallel network for developing automatic brain tumor segmentation in MRI images, Quant. Imag. Med. Surg. 12 (2021). [50] M.U. Rehman, et al., BrainSeg-net: brain tumor MR image segmentation via enhanced encoder–decoder network, Diagnostics 11 (2021), https://doi.org/ 10.3390/diagnostics11020169. [51] J. Zhang, et al., Attention Gate ResU-Net for Automatic MRI Brain Tumor Segmentation, IEEE Access, 2020, 1-1. [52] T. Dhamija, et al., Semantic segmentation in medical images through transfused convolution and transformer networks, Appl. Intell. 53 (1) (2023) 1132–1148. [53] J. Zhang, et al., Inter-slice context residual learning for 3D medical image segmentation, IEEE Trans. Med. Imag. 40 (2) (2021) 661–672. [54] C.-W. Lin, Y. Hong, J. Liu, Aggregation-and-Attention Network for brain tumor segmentation, BMC Med. Imag. 21 (1) (2021) 109. [55] T. Zhang, et al., A brain tumor image segmentation method based on quantum entanglement and wormhole behaved particle swarm optimization, Front. Med. 9 (2022), 794126. [56] H. Su, et al., Horizontal and vertical search artificial bee colony for image segmentation of COVID-19 X-ray images, Comput. Biol. Med. 142 (2022), 105181. [57] A. Qi, et al., Directional mutation and crossover boosted ant colony optimization with application to COVID-19 X-ray image segmentation, Comput. Biol. Med. 148 (2022), 105810. [58] H. Nematzadeh, et al., Ensemble-based genetic algorithm explainer with automized image segmentation: a case study on melanoma detection dataset, Comput. Biol. Med. 155 (2023), 106613. [59] M. Abdel-Basset, et al., HWOA: a hybrid whale optimization algorithm with a novel local minima avoidance method for multi-level thresholding color image segmentation, Expert Syst. Appl. 190 (2022), 116145. [60] L. Ren, et al., Gaussian kernel probability-driven slime mould algorithm with new movement mechanism for multi-level image segmentation, Measurement 192 (2022), 110884. [61] A.S. Abutaleb, Automatic thresholding of gray-level pictures using twodimensional entropy, Comput. Vis. Graph Image Process 47 (1) (1989) 22–32. [62] S. Borjigin, P.K. Sahoo, Color image segmentation based on multi-level Tsallis–Havrda–Charvat ´ entropy and 2D histogram using PSO algorithms, Pattern Recogn. 92 (2019) 107–118. [63] J. Luo, Y. Yang, B. Shi, Multi-threshold image segmentation of 2D otsu based on improved adaptive differential evolution algorithm, Dianzi Yu Xinxi Xuebao/ Journal of Electronics and Information Technology 41 (8) (2019) 2017–2024. [64] S. Zhao, et al., Multilevel threshold image segmentation with diffusion association slime mould algorithm and Renyi’s entropy for chronic obstructive pulmonary disease, Comput. Biol. Med. 134 (2021), 104427. [65] B. Coll, J.-M. Morel, A Non-local Algorithm for Image Denoising, 2005, pp. 60–65, vol. 2 [66] B. Coll, J.-M. Morel, A review of image denoising algorithms, with a new one, SIAM Journal on Multiscale Modeling and Simulation 4 (2005). [67] A. R’eny, On Measures of Entropy and Information. Symposium on Mathematics Statistics and Probabilities, 1961, pp. 547–561. [68] A.F. Kamaruzaman, et al., Levy flight algorithm for optimization problems-a literature review, Appl. Mech. Mater. 421 (2013) 496–501. [69] S. Mirjalili, et al., Whale optimization algorithm: theory, literature review, and application in designing photonic crystal filters, in: Studies in Computational Intelligence, 2020, pp. 219–238. [70] D. Simon, Biogeography-based optimization, IEEE Trans. Evol. Comput. 12 (6) (2008) 702–713. [71] A.A. Heidari, et al., An Enhanced Associative Learning-Based Exploratory Whale Optimizer for Global Optimization, Neural Computing and Applications, 2019. [72] S. Mirjalili, Moth-flame optimization algorithm: a novel nature-inspired heuristic paradigm, Knowl. Base Syst. 89 (2015) 228–249. [73] X.-S. Yang, Firefly algorithms for multimodal optimization, in: Stochastic Algorithms: Foundations and Applications: 5th International Symposium, SAGA 2009, Sapporo, Japan, October 26-28, 2009. Proceedings 5, Springer, 2009. [74] X.-S. Yang, A new metaheuristic bat-inspired algorithm, in: Nature Inspired Cooperative Strategies for Optimization (NICSO 2010), 2010, pp. 65–74. [75] S. Gupta, K. Deep, A hybrid self-adaptive sine cosine algorithm with opposition based learning, Expert Syst. Appl. 119 (2019) 210–230. [76] H. Nenavath, R.K. Jatoth, Hybridizing sine cosine algorithm with differential evolution for global optimization and object tracking, Applied Soft Computing Journal 62 (2018) 1019–1043. [77] S. Li, et al., Slime mould algorithm: a new method for stochastic optimization, FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 111 (2020) 300–323. [78] M. Tubishat, et al., Improved whale optimization algorithm for feature selection in Arabic sentiment analysis, Appl. Intell. 49 (5) (2019) 1688–1707. [79] J.J. Liang, et al., Comprehensive learning particle swarm optimizer for global optimization of multimodal functions, IEEE Trans. Evol. Comput. 10 (3) (2006) 281–295. [80] S. Mirjalili, et al., Salp Swarm Algorithm: a bio-inspired optimizer for engineering design problems, Adv. Eng. Software 114 (2017) 163–191. [81] J. Xing, et al., Boosting whale optimizer with quasi-oppositional learning and Gaussian barebone for feature selection and COVID-19 image segmentation, Journal of bionic engineering 20 (2) (2023) 797–818. [82] X. Wang, et al., Crisscross Harris hawks optimizer for global tasks and feature selection, JBE 20 (3) (2023) 1153–1174. [83] J. Xia, et al., Adaptive barebones salp swarm algorithm with quasi-oppositional learning for medical diagnosis systems: a comprehensive analysis, JBE 19 (1) (2022) 240–256. [84] J. Xia, et al., Generalized oppositional moth flame optimization with crossover strategy: an approach for medical diagnosis, JBE 18 (4) (2021) 991–1010. [85] C. Lin, et al., Double mutational salp swarm algorithm: from optimal performance design to analysis, JBE 20 (1) (2023) 184–211. [86] L. Hu, et al., An intelligent prognostic system for analyzing patients with paraquat poisoning using arterial blood gas indexes, J. Pharmacol. Toxicol. Methods 84 (2017) 78–85. [87] H. Zhang, et al., Differential evolution-assisted salp swarm algorithm with chaotic structure for real-world problems, Eng. Comput. 39 (3) (2023) 1735–1769. [88] X. Yu, et al., Synergizing the enhanced RIME with fuzzy K-nearest neighbor for diagnose of pulmonary hypertension, Comput. Biol. Med. 165 (2023), 107408. |
| dc.relation.citationendpage.none.fl_str_mv |
18 |
| dc.relation.citationstartpage.none.fl_str_mv |
1 |
| dc.relation.citationvolume.none.fl_str_mv |
166 |
| dc.rights.eng.fl_str_mv |
© 2023 Elsevier Ltd. All rights reserved. |
| dc.rights.license.none.fl_str_mv |
Atribución 4.0 Internacional (CC BY 4.0) |
| dc.rights.uri.none.fl_str_mv |
https://creativecommons.org/licenses/by/4.0/ |
| dc.rights.accessrights.none.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.coar.none.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| rights_invalid_str_mv |
Atribución 4.0 Internacional (CC BY 4.0) © 2023 Elsevier Ltd. All rights reserved. https://creativecommons.org/licenses/by/4.0/ http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.none.fl_str_mv |
18 páginas |
| dc.format.mimetype.none.fl_str_mv |
application/pdf |
| dc.publisher.none.fl_str_mv |
Elsevier Ltd |
| dc.publisher.place.none.fl_str_mv |
United Kingdom |
| publisher.none.fl_str_mv |
Elsevier Ltd |
| dc.source.none.fl_str_mv |
https://www.sciencedirect.com/science/article/pii/S0010482523010168?via%3Dihub |
| institution |
Corporación Universidad de la Costa |
| bitstream.url.fl_str_mv |
https://repositorio.cuc.edu.co/bitstreams/a451c05e-be10-409f-8109-b9c5f1d81ee6/download https://repositorio.cuc.edu.co/bitstreams/a0a4d70d-fe34-4558-88dc-cc7277a8dac2/download https://repositorio.cuc.edu.co/bitstreams/af72517e-2d86-4020-a740-c11594dfcac7/download https://repositorio.cuc.edu.co/bitstreams/36898136-0ec0-49a4-99ab-48eef075a833/download |
| bitstream.checksum.fl_str_mv |
e96d9d6d483c696c81c5228b9de6fd70 73a5432e0b76442b22b026844140d683 b6949af6299462e2bdb15dc9086261c9 25c5069af53f123088c87ed27c9ca997 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio de la Universidad de la Costa CUC |
| repository.mail.fl_str_mv |
repdigital@cuc.edu.co |
| _version_ |
1828166774684647424 |
| spelling |
Atribución 4.0 Internacional (CC BY 4.0)© 2023 Elsevier Ltd. All rights reserved.https://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Zhu, WeiFang, LimingYe, XiaMedani, MohamedEscorcia-Gutierrez, José2025-01-20T22:10:46Z2025-01-20T22:10:46Z2023-11Wei Zhu, Liming Fang, Xia Ye, Mohamed Medani, José Escorcia-Gutierrez, IDRM: Brain tumor image segmentation with boosted RIME optimization, Computers in Biology and Medicine, Volume 166, 2023, 107551, ISSN 0010-4825, https://doi.org/10.1016/j.compbiomed.2023.1075510010-4825https://hdl.handle.net/11323/1392610.1016/j.compbiomed.2023.1075511879-0534Corporación Universidad de la CostaREDICUC - Repositorio CUChttps://repositorio.cuc.edu.co/Timely diagnosis of medical conditions can significantly mitigate the risks they pose to human life. Consequently, there is an urgent demand for an effective auxiliary model that assists physicians in accurately diagnosing medical conditions based on imaging data. While multi-threshold image segmentation models have garnered considerable attention due to their simplicity and ease of implementation, the selection of threshold combinations greatly influences the segmentation performance. Traditional optimization algorithms often require substantial time to address multi-threshold image segmentation problems, and their segmentation accuracy is frequently unsatisfactory. As a result, metaheuristic algorithms have been employed in this domain. However, several algorithms suffer from drawbacks such as premature convergence and inadequate exploration of the solution space when it comes to threshold selection. For instance, the recently proposed optimization algorithm RIME, inspired by the physical phenomenon of rime-ice, falls short in terms of avoiding local optima and fully exploring the solution space. Therefore, this study introduces an enhanced version of RIME, called IDRM, which incorporates an interactive mechanism and Gaussian diffusion strategy. The interactive mechanism facilitates information exchange among agents, enabling them to evolve towards more promising directions and increasing the likelihood of discovering the optimal solution. Additionally, the Gaussian diffusion strategy enhances the agents' local exploration capabilities and expands their search within the solution space, effectively preventing them from becoming trapped in local optima. Experimental results on 30 benchmark test functions demonstrate that IDRM exhibits favorable optimization performance across various optimization functions, showcasing its robustness and convergence properties. Furthermore, the algorithm is applied to select threshold combinations for brain tumor image segmentation, and the results are evaluated using metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM). The overall findings consistently highlight the exceptional performance of this approach, further validating the effectiveness of IDRM in addressing image segmentation problems.18 páginasapplication/pdfengElsevier LtdUnited Kingdomhttps://www.sciencedirect.com/science/article/pii/S0010482523010168?via%3DihubIDRM: Brain tumor image segmentation with boosted RIME optimizationArtículo de revistahttp://purl.org/coar/resource_type/c_6501http://purl.org/coar/resource_type/c_2df8fbb1Textinfo:eu-repo/semantics/articlehttp://purl.org/redcol/resource_type/ARTinfo:eu-repo/semantics/acceptedVersionComputers in Biology and Medicine[1] E.-S.A. El-Dahshan, et al., Computer-aided diagnosis of human brain tumor through MRI: a survey and a new algorithm, Expert Syst. Appl. 41 (11) (2014) 5526–5545.[2] G. Chen, et al., MTANS: multi-scale mean teacher combined adversarial network with shape-aware embedding for semi-supervised brain lesion segmentation, Neuroimage 244 (2021), 118568.[3] G. Chen, et al., RFDCR: automated brain lesion segmentation using cascaded random forests with dense conditional random fields, Neuroimage 211 (2020), 116620.[4] H. Saleem, A.R. Shahid, B. Raza, Visual interpretability in 3D brain tumor segmentation network, Comput. Biol. Med. 133 (2021), 104410.[5] J. Nodirov, A.B. Abdusalomov, T.K. Whangbo, Attention 3D U-net with multiple skip connections for segmentation of brain tumor images, Sensors 22 (2022), https://doi.org/10.3390/s22176501.[6] R. Sindhiya Devi, B. Perumal, M. Pallikonda Rajasekaran, A hybrid deep learning based brain tumor classification and segmentation by stationary wavelet packet transform and adaptive kernel fuzzy c means clustering, Adv. Eng. Software 170 (2022), 103146.[7] Y. Zhuang, et al., An effective WSSENet-based similarity retrieval method of large lung CT image databases, KSII Transactions on Internet & Information Systems 16 (7) (2022).[8] Y. Zhuang, N. Jiang, Y. Xu, Progressive distributed and parallel similarity retrieval of large CT image sequences in mobile telemedicine networks, Wireless Commun. Mobile Comput. 2022 (2022), 6458350.[9] Z. Zhang, et al., Endoscope image mosaic based on pyramid ORB, Biomed. Signal Process Control 71 (2022), 103261.[10] S. Lu, et al., Soft tissue feature tracking based on DeepMatching network, CMESComputer Modeling in Engineering & Sciences 136 (1) (2023).[11] Y. Zhu, et al., Deep learning-based predictive identification of neural stem cell differentiation, Nat. Commun. 12 (1) (2021) 2614.[12] S. Lu, et al., Iterative reconstruction of low-dose CT based on differential sparse, Biomed. Signal Process Control 79 (2023), 104204.[13] N. Narappanawar, B.M. Rao, M. Joshi, Graph theory based segmentation of traced boundary into open and closed sub-sections, Comput. Vis. Image Understand. 115 (11) (2011) 1552–1558.[14] A. Ahilan, et al., Segmentation by fractional order darwinian particle swarm optimization based multilevel thresholding and improved lossless prediction based compression algorithm for medical images, IEEE Access 7 (2019) 89570–89580.[15] J. Michetti, et al., Influence of CBCT parameters on the output of an automatic edge-detection-based endodontic segmentation, Dentomaxillofacial Radiol. 44 (8) (2015).[16] D. Zhang, et al., A region-based segmentation method for ultrasound images in HIFU therapy, Med. Phys. 43 (6) (2016) 2975–2989.[17] X. Xia, Q. Liu, M.L. Huang, The use of artificial intelligence based magnifying image segmentation algorithm combined with endoscopy in early diagnosis and nursing of esophageal cancer patients, J. Med. Imaging Health Inform. 11 (4) (2021) 1306–1311.[18] S. Zhao, et al., Boosted crow search algorithm for handling multi-threshold image problems with application to X-ray images of COVID-19, Expert Syst. Appl. 213 (2023), 119095.[19] D. Zhao, et al., Ant colony optimization with horizontal and vertical crossover search: fundamental visions for multi-threshold image segmentation, Expert Syst. Appl. (2021) 167.[20] Y. Zheng, et al., Sine-SSA-BP ship trajectory prediction based on chaotic mapping improved sparrow search algorithm, Sensors 23 (2) (2023) 704.[21] B. Cao, et al., Multiobjective 3-D topology optimization of next-generation wireless data center network, IEEE Trans. Ind. Inf. 16 (5) (2019) 3597–3605.[22] C. Min, et al., Trajectory optimization of an electric vehicle with minimum energy consumption using inverse dynamics model and servo constraints, Mech. Mach. Theor. 181 (2023), 105185.[23] B. Cao, et al., Applying graph-based differential grouping for multiobjective largescale optimization, Swarm Evol. Comput. 53 (2020), 100626.[24] B. Cao, et al., Diversified personalized recommendation optimization based on mobile data, IEEE Trans. Intell. Transport. Syst. 22 (4) (2020) 2133–2139.[25] B. Li, et al., A distributionally robust optimization based method for stochastic model predictive control, IEEE Trans. Automat. Control 67 (11) (2021) 5762–5776.[26] X. Xu, et al., Multi-objective robust optimisation model for MDVRPLS in refined oil distribution, Int. J. Prod. Res. 60 (22) (2022) 6772–6792.[27] B. Cao, et al., Large-scale many-objective deployment optimization of edge servers, IEEE Trans. Intell. Transport. Syst. 22 (6) (2021) 3841–3849.[28] X. Liu, et al., Federated neural architecture search for medical data security, IEEE Trans. 18 (2022) 5628–5636.[29] Y. Zheng, et al., An optimal bp neural network track prediction method based on a ga–aco hybrid algorithm, J. Mar. Sci. Eng. 10 (10) (2022) 1399.[30] L. Qian, et al., A new method of inland water ship trajectory prediction based on long short-term memory network optimized by genetic algorithm, Appl. Sci. 12 (8) (2022) 4073.[31] X. Zhang, Z. Wang, Z. Lu, Multi-objective load dispatch for microgrid with electric vehicles using modified gravitational search and particle swarm optimization algorithm, Appl. Energy 306 (2022), 118018.[32] A.A. Heidari, et al., Harris hawks optimization: algorithm and applications, Future Generat. Comput. Syst. 97 (2019) 849–872.[33] H. Chen, et al., Slime mould algorithm: a comprehensive review of recent variants and applications, Int. J. Syst. Sci. (2022) 1–32.[34] S. Li, et al., Slime mould algorithm: a new method for stochastic optimization, Future Generat. Comput. Syst. 111 (2020) 300–323.[35] S. Mirjalili, J.S. Dong, A. Lewis, Nature-inspired Optimizers: Theories, Literature Reviews and Applications, Springer, 2019, 811.[36] R. Storn, K. Price, Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces, J. Global Optim. 11 (4) (1997) 341–359.[37] J. Tu, et al., The colony predation algorithm, JBE 18 (3) (2021) 674–710.[38] I. Ahmadianfar, et al., INFO: an efficient optimization algorithm based on weighted mean of vectors, Expert Syst. Appl. (2022), 116516.[39] I. Ahmadianfar, et al., RUN beyond the Metaphor: an Efficient Optimization Algorithm Based on Runge Kutta Method, Expert Systems with Applications, 2021, 115079.[40] H. Su, et al., RIME: A Physics-Based Optimization, Neurocomputing, 2023.[41] Y. Yang, et al., Hunger games search: visions, conception, implementation, deep analysis, perspectives, and towards performance shifts, Expert Syst. Appl. 177 (2021), 114864.[42] S. Zhao, et al., Performance optimization of salp swarm algorithm for multithreshold image segmentation: comprehensive study of breast cancer microscopy, Comput. Biol. Med. 139 (2021), 105015.[43] S. Hao, et al., Performance optimization of water cycle algorithm for multilevel lupus nephritis image segmentation, Biomed. Signal Process Control 80 (2023), 104139.[44] H. Su, et al., RIME: a physics-based optimization, Neurocomputing 532 (2023) 183–214.[45] S. García, et al., Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining: experimental analysis of power, Inf. Sci. 180 (10) (2010) 2044–2064.[46] J. Derrac, et al., A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms, Swarm Evol. Comput. 1 (1) (2011) 3–18.[47] Q. Huynh-Thu, M. Ghanbari, Scope of validity of PSNR in image/video quality assessment, Electron. Lett. 44 (13) (2008), 800-U35.[48] Z. Wang, et al., Image quality assessment: from error visibility to structural similarity, IEEE Trans. Image Process. 13 (4) (2004) 600–612.[49] J. Liang, et al., TransConver: transformer and convolution parallel network for developing automatic brain tumor segmentation in MRI images, Quant. Imag. Med. Surg. 12 (2021).[50] M.U. Rehman, et al., BrainSeg-net: brain tumor MR image segmentation via enhanced encoder–decoder network, Diagnostics 11 (2021), https://doi.org/ 10.3390/diagnostics11020169.[51] J. Zhang, et al., Attention Gate ResU-Net for Automatic MRI Brain Tumor Segmentation, IEEE Access, 2020, 1-1.[52] T. Dhamija, et al., Semantic segmentation in medical images through transfused convolution and transformer networks, Appl. Intell. 53 (1) (2023) 1132–1148.[53] J. Zhang, et al., Inter-slice context residual learning for 3D medical image segmentation, IEEE Trans. Med. Imag. 40 (2) (2021) 661–672.[54] C.-W. Lin, Y. Hong, J. Liu, Aggregation-and-Attention Network for brain tumor segmentation, BMC Med. Imag. 21 (1) (2021) 109.[55] T. Zhang, et al., A brain tumor image segmentation method based on quantum entanglement and wormhole behaved particle swarm optimization, Front. Med. 9 (2022), 794126.[56] H. Su, et al., Horizontal and vertical search artificial bee colony for image segmentation of COVID-19 X-ray images, Comput. Biol. Med. 142 (2022), 105181.[57] A. Qi, et al., Directional mutation and crossover boosted ant colony optimization with application to COVID-19 X-ray image segmentation, Comput. Biol. Med. 148 (2022), 105810.[58] H. Nematzadeh, et al., Ensemble-based genetic algorithm explainer with automized image segmentation: a case study on melanoma detection dataset, Comput. Biol. Med. 155 (2023), 106613.[59] M. Abdel-Basset, et al., HWOA: a hybrid whale optimization algorithm with a novel local minima avoidance method for multi-level thresholding color image segmentation, Expert Syst. Appl. 190 (2022), 116145.[60] L. Ren, et al., Gaussian kernel probability-driven slime mould algorithm with new movement mechanism for multi-level image segmentation, Measurement 192 (2022), 110884.[61] A.S. Abutaleb, Automatic thresholding of gray-level pictures using twodimensional entropy, Comput. Vis. Graph Image Process 47 (1) (1989) 22–32.[62] S. Borjigin, P.K. Sahoo, Color image segmentation based on multi-level Tsallis–Havrda–Charvat ´ entropy and 2D histogram using PSO algorithms, Pattern Recogn. 92 (2019) 107–118.[63] J. Luo, Y. Yang, B. Shi, Multi-threshold image segmentation of 2D otsu based on improved adaptive differential evolution algorithm, Dianzi Yu Xinxi Xuebao/ Journal of Electronics and Information Technology 41 (8) (2019) 2017–2024.[64] S. Zhao, et al., Multilevel threshold image segmentation with diffusion association slime mould algorithm and Renyi’s entropy for chronic obstructive pulmonary disease, Comput. Biol. Med. 134 (2021), 104427.[65] B. Coll, J.-M. Morel, A Non-local Algorithm for Image Denoising, 2005, pp. 60–65, vol. 2[66] B. Coll, J.-M. Morel, A review of image denoising algorithms, with a new one, SIAM Journal on Multiscale Modeling and Simulation 4 (2005).[67] A. R’eny, On Measures of Entropy and Information. Symposium on Mathematics Statistics and Probabilities, 1961, pp. 547–561.[68] A.F. Kamaruzaman, et al., Levy flight algorithm for optimization problems-a literature review, Appl. Mech. Mater. 421 (2013) 496–501.[69] S. Mirjalili, et al., Whale optimization algorithm: theory, literature review, and application in designing photonic crystal filters, in: Studies in Computational Intelligence, 2020, pp. 219–238.[70] D. Simon, Biogeography-based optimization, IEEE Trans. Evol. Comput. 12 (6) (2008) 702–713.[71] A.A. Heidari, et al., An Enhanced Associative Learning-Based Exploratory Whale Optimizer for Global Optimization, Neural Computing and Applications, 2019.[72] S. Mirjalili, Moth-flame optimization algorithm: a novel nature-inspired heuristic paradigm, Knowl. Base Syst. 89 (2015) 228–249.[73] X.-S. Yang, Firefly algorithms for multimodal optimization, in: Stochastic Algorithms: Foundations and Applications: 5th International Symposium, SAGA 2009, Sapporo, Japan, October 26-28, 2009. Proceedings 5, Springer, 2009.[74] X.-S. Yang, A new metaheuristic bat-inspired algorithm, in: Nature Inspired Cooperative Strategies for Optimization (NICSO 2010), 2010, pp. 65–74.[75] S. Gupta, K. Deep, A hybrid self-adaptive sine cosine algorithm with opposition based learning, Expert Syst. Appl. 119 (2019) 210–230.[76] H. Nenavath, R.K. Jatoth, Hybridizing sine cosine algorithm with differential evolution for global optimization and object tracking, Applied Soft Computing Journal 62 (2018) 1019–1043.[77] S. Li, et al., Slime mould algorithm: a new method for stochastic optimization, FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 111 (2020) 300–323.[78] M. Tubishat, et al., Improved whale optimization algorithm for feature selection in Arabic sentiment analysis, Appl. Intell. 49 (5) (2019) 1688–1707.[79] J.J. Liang, et al., Comprehensive learning particle swarm optimizer for global optimization of multimodal functions, IEEE Trans. Evol. Comput. 10 (3) (2006) 281–295.[80] S. Mirjalili, et al., Salp Swarm Algorithm: a bio-inspired optimizer for engineering design problems, Adv. Eng. Software 114 (2017) 163–191.[81] J. Xing, et al., Boosting whale optimizer with quasi-oppositional learning and Gaussian barebone for feature selection and COVID-19 image segmentation, Journal of bionic engineering 20 (2) (2023) 797–818.[82] X. Wang, et al., Crisscross Harris hawks optimizer for global tasks and feature selection, JBE 20 (3) (2023) 1153–1174.[83] J. Xia, et al., Adaptive barebones salp swarm algorithm with quasi-oppositional learning for medical diagnosis systems: a comprehensive analysis, JBE 19 (1) (2022) 240–256.[84] J. Xia, et al., Generalized oppositional moth flame optimization with crossover strategy: an approach for medical diagnosis, JBE 18 (4) (2021) 991–1010.[85] C. Lin, et al., Double mutational salp swarm algorithm: from optimal performance design to analysis, JBE 20 (1) (2023) 184–211.[86] L. Hu, et al., An intelligent prognostic system for analyzing patients with paraquat poisoning using arterial blood gas indexes, J. Pharmacol. Toxicol. Methods 84 (2017) 78–85.[87] H. Zhang, et al., Differential evolution-assisted salp swarm algorithm with chaotic structure for real-world problems, Eng. Comput. 39 (3) (2023) 1735–1769.[88] X. Yu, et al., Synergizing the enhanced RIME with fuzzy K-nearest neighbor for diagnose of pulmonary hypertension, Comput. Biol. Med. 165 (2023), 107408.181166RIMEImage segmentationMulti-thresholdMeta-heuristic algorithmsRényi's entropyBrain tumor detectionPublicationORIGINALIDRM. Brain tumor image segmentation with boosted RIME optimization.pdfIDRM. Brain tumor image segmentation with boosted RIME optimization.pdfapplication/pdf8247762https://repositorio.cuc.edu.co/bitstreams/a451c05e-be10-409f-8109-b9c5f1d81ee6/downloade96d9d6d483c696c81c5228b9de6fd70MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-815543https://repositorio.cuc.edu.co/bitstreams/a0a4d70d-fe34-4558-88dc-cc7277a8dac2/download73a5432e0b76442b22b026844140d683MD52TEXTIDRM. Brain tumor image segmentation with boosted RIME optimization.pdf.txtIDRM. Brain tumor image segmentation with boosted RIME optimization.pdf.txtExtracted texttext/plain100905https://repositorio.cuc.edu.co/bitstreams/af72517e-2d86-4020-a740-c11594dfcac7/downloadb6949af6299462e2bdb15dc9086261c9MD53THUMBNAILIDRM. Brain tumor image segmentation with boosted RIME optimization.pdf.jpgIDRM. Brain tumor image segmentation with boosted RIME optimization.pdf.jpgGenerated Thumbnailimage/jpeg14581https://repositorio.cuc.edu.co/bitstreams/36898136-0ec0-49a4-99ab-48eef075a833/download25c5069af53f123088c87ed27c9ca997MD5411323/13926oai:repositorio.cuc.edu.co:11323/139262025-01-21 04:02:25.42https://creativecommons.org/licenses/by/4.0/© 2023 Elsevier Ltd. All rights reserved.open.accesshttps://repositorio.cuc.edu.coRepositorio de la Universidad de la Costa CUCrepdigital@cuc.edu.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 |