Abstract
Many studies focused on gastric motility require the use of synthetic tracers to map the motion of content. Our study instead takes advantage of an unusual MRI acquisition protocol, combined with multi-objective optimised clustering to map the motion of food (peas, a natural ‘tracer’) in a human stomach. We chose NSGA-II to optimise the starting positions for a modified k-means to create optimum clusters. We compared our optimisation approach with a purely random approach that took an equal amount of processing time. Since we have no ground truth available, we have created alternative measures to evaluate our solutions: if the resulting pea velocities are within an expected range, and if each pea’s motion is correlated with neighbouring peas. We found that the optimised version has a significant improvement over the purely random search. Furthermore, we found many interesting food motion behaviours, such as correlated pea motion and more complex motion dynamics such as collision. Overall we found that the combined optimisation and clustering approach produced interesting findings relating to food dynamics in a human stomach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Al-Maliki, S.F., Vidal, F.P.: Visualisation, optimisation and Machine Learning: application in PET Reconstruction and Pea segmentation in MRI Images. Ph.D. thesis, Bangor University (2020)
Blank, J., Deb, K.: pymoo: multi-Objective Optimization in Python. IEEE Access 8, 89497–89509 (2020). https://doi.org/10.1109/ACCESS.2020.2990567
Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002). https://doi.org/10.1109/4235.996017
Deb, K., Sindhya, K., Okabe, T.: Self-adaptive simulated binary crossover for real-parameter optimization. In: Proceedings of the 9th Annual Conference on Genetic and Evolutionary Computation, GECCO 2007, pp. 1187–1194. Association for Computing Machinery, New York (2007). https://doi.org/10.1145/1276958.1277190
Freitas, D.: Novel insights into starch digestion and the glycaemic response: from in vitro digestions to a human study using magnetic resonance imaging (MRI). Ph.D. thesis, Université Paris-Saclay (2018)
Gardner, J., Al-Maliki, S., Lutton, E., Boué, F., Vidal, F.: Recognising specific foods in MRI scans using CNN and visualisation. In: Ritsos, P.D., Xu, K. (eds.) Computer Graphics and Visual Computing (CGVC). The Eurographics Association (2020). https://doi.org/10.2312/cgvc.20201145
Goetze, O., et al.: The effect of macronutrients on gastric volume responses and gastric emptying in humans: a magnetic resonance imaging study. Am. J. Physiol. Gastrointest. Liver Physiol. 292(1), G11–G17 (2007). https://doi.org/10.1152/ajpgi.00498.2005
Goyal, R.K., Guo, Y., Mashimo, H.: Advances in the physiology of gastric emptying. Neurogastroenterol. Motil. 31(4), e13546 (2019). https://doi.org/10.1111/nmo.13546
Hamerly, G., Elkan, C.: Alternatives to the k-means algorithm that find better clusterings. In: Proceedings of the Eleventh International Conference on Information and Knowledge Management, CIKM 2002, pp. 600–607. Association for Computing Machinery, New York (2002). https://doi.org/10.1145/584792.584890
Heissam, K., et al.: Measurement of fasted state gastric antral motility before and after a standard bioavailability and bioequivalence 240 mL drink of water: validation of MRI method against concomitant perfused manometry in healthy participants. PLOS ONE 15(11), e0241441 (2020). https://doi.org/10.1371/journal.pone.0241441. https://dx.plos.org/10.1371/journal.pone.0241441
Kong, F., Singh, R.: A model stomach system to investigate disintegration kinetics of solid foods during gastric digestion. J. Food Sci. 73(5), E202–E210 (2008). https://doi.org/10.1111/j.1750-3841.2008.00745.x
Krishna, K., Narasimha Murty, M.: Genetic k-means algorithm. IEEE Trans. Syst. Man Cybern. Part B (Cybern.) 29(3), 433–439 (1999). https://doi.org/10.1109/3477.764879
Kunz, P., Feinle, C., Schwizer, W., Fried, M., Boesiger, P.: Assessment of gastric motor function during the emptying of solid and liquid meals in humans by MRI. J. Magn. Reson. Imaging 9(1), 75–80 (1999). https://doi.org/10.1002/(SICI)1522-2586(199901)9:1<75::AID-JMRI10>3.0.CO;2-I. https://onlinelibrary.wiley.com/doi/10.1002/(SICI)1522-2586(199901)9:1<75::AID-JMRI10>3.0.CO;2-I
Li, Y., Kong, F.: Simulating human gastrointestinal motility in dynamic in vitro models. Compr. Rev. Food Sci. Food Saf. 21(5), 3804–3833 (2022). https://doi.org/10.1111/1541-4337.13007
Likas, A., Vlassis, N., J. Verbeek, J.: The global k-means clustering algorithm. Pattern Recogn. 36(2), 451–461 (2003). https://doi.org/10.1016/S0031-3203(02)00060-2
Lorensen, W., Cline, H.: Marching cubes: a high resolution 3D surface construction algorithm. Comput. Graph. 21(4), 163–169 (1987)
Maccioni, F., Busato, L., Valenti, A., Cardaccio, S., Longhi, A., Catalano, C.: Magnetic resonance imaging of the gastrointestinal tract: current role, recent advancements and future prospectives. Diagnostics 13(14), 2410 (2023). https://doi.org/10.3390/diagnostics13142410. https://www.mdpi.com/2075-4418/13/14/2410
MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability (1967). https://api.semanticscholar.org/CorpusID:6278891
Marciani, L., et al.: Antral motility measurements by magnetic resonance imaging. Neurogastroenterol. Motil. 13(5), 511–518 (2001). https://doi.org/10.1046/j.1365-2982.2001.00285.x
Menys, A., et al.: Spatio-temporal motility MRI analysis of the stomach and colon. Neurogastroenterol. Motil. 31(5), e13557 (2019). https://doi.org/10.1111/nmo.13557. https://onlinelibrary.wiley.com/doi/10.1111/nmo.13557
Nonaka, H., Onishi, H., Watanabe, M., Nam, V.H.: Assessment of abdominal organ motion using cine magnetic resonance imaging in different gastric motilities: a comparison between fasting and postprandial states. J. Radiat. Res. 60(6), 837–843 (2019)
Parker, H.L., et al.: Clinical assessment of gastric emptying and sensory function utilizing gamma scintigraphy: establishment of reference intervals for the liquid and solid components of the nottingham test meal in healthy subjects. Neurogastroenterol. Motil. 29(11), e13122 (2017). https://doi.org/10.1111/nmo.13122
Peña, J., Lozano, J., Larrañaga, P.: An empirical comparison of four initialization methods for the k-means algorithm. Pattern Recogn. Lett. 20(10), 1027–1040 (1999). https://doi.org/10.1016/S0167-8655(99)00069-0
Schroeder, W., Martin, K., Lorensen, B.: The Visualization Toolkit, 4th edn. Kitware (2006)
Spann, C., Al-Maliki, S., Boué, F., Lutton, E., Vidal, F.P.: Interactive visualisation of the food content of a human stomach in MRI. In: Computer Graphics and Visual Computing (CGVC), pp. 47–54. The Eurographics Association (2022). https://doi.org/10.2312/cgvc.20221171
Steingoetter, A., et al.: Magnetic resonance imaging for the in vivo evaluation of gastric-retentive tablets. Pharm. Res. 20(12), 2001–2007 (2003). https://doi.org/10.1023/B:PHAM.0000008049.40370.5a. http://link.springer.com/10.1023/B:PHAM.0000008049.40370.5a
Tao, F., Lin-sheng, L., Qi-chuan, T.: A novel adaptive motion detection based on k-means clustering. In: 2010 3rd International Conference on Computer Science and Information Technology, vol. 3, pp. 136–140 (2010). https://doi.org/10.1109/ICCSIT.2010.5564529
Vidal, F.P., Villard, P.F., Lutton, É.: Tuning of patient-specific deformable models using an adaptive evolutionary optimization strategy. IEEE Trans. Biomed. Eng. 59, 2942–2949 (2012). https://doi.org/10.1109/TBME.2012.2213251
Acknowledgements
This work was partially supported by a STSM Grant from COST Action CA15118 (FoodMC) and the MRI data used in this study were collected at CEA-SHFJ with the support of IR4M CNRS/Orsay University (Xavier Maître and Luc Darrasse) in the framework of the IDI/Paris Saclay PhD of Daniela Freitas.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Ethical Approval
The study protocol has been approved by the Ethics Committee Lyon Sud-Est IV, and it has been registered in the Clinical Trial Registry (clinicaltrials.gov; NCT03265392) (see https://clinicaltrials.gov/ct2/show/NCT03265392). All volunteers gave their written informed consent after being provided with oral and written information about the aims and protocol of the study.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Spann, C., Lutton, E., Boué, F., Vidal, F. (2024). 3D Motion Analysis in MRI Using a Multi-objective Evolutionary k-means Clustering. In: Smith, S., Correia, J., Cintrano, C. (eds) Applications of Evolutionary Computation. EvoApplications 2024. Lecture Notes in Computer Science, vol 14634. Springer, Cham. https://doi.org/10.1007/978-3-031-56852-7_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-56852-7_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-56851-0
Online ISBN: 978-3-031-56852-7
eBook Packages: Computer ScienceComputer Science (R0)