Abstract
In this paper, we advocate that combining several frameworks in artificial intelligence, adopting a hybrid point of view for both knowledge data representation and reasoning, offers opportunities towards explainability. This idea is illustrated on the example of image understanding, in particular in medical imaging, formulated as a spatial reasoning problem.
This work was partly supported by the author’s chair in Artificial Intelligence (Sorbonne Université and SCAI). A part of the work mentioned in this paper was performed while the author was with LTCI, Télécom Paris, Institut Polytechnique de Paris.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
These are only examples and similar approaches have been developed in other application domains, such as satellite imaging, video, music representations, etc.
References
Aiello, M., Pratt-Hartmann, I., van Benthem, J. (ed.).: Handbook of Spatial Logic. Springer, Cham (2007). https://doi.org/10.1007/978-1-4020-5587-4
Aiguier, M., Atif, J., Bloch, I., Pino Pérez, R.: Explanatory relations in arbitrary logics based on satisfaction systems, cutting and retraction. Int. J. Approximate Reasoning 102, 1–20 (2018)
Aldea, E., Bloch, I.: Toward a better integration of spatial relations in learning with graphical models. In: H. Briand, F. Guillet, G.R., Zighed, D. (eds.) Advances in Knowledge Discovery and Management. Studies in Computational Intelligence, vol. 292. pp. 77–94. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-00580-0_5
Atif, J., Hudelot, C., Fouquier, G., Bloch, I., Angelini, E.: From Generic Knowledge to Specific Reasoning for Medical Image Interpretation using Graph-based Representations. In: International Joint Conference on Artificial Intelligence IJCAI 2007, pp. 224–229. Hyderabad, India (2007)
Bloch, I.: On fuzzy spatial distances. In: Hawkes, P. (ed.) Advances in Imaging and Electron Physics, vol. 128, pp. 51–122. Elsevier, Amsterdam (2003)
Bloch, I.: Fuzzy spatial relationships for image processing and interpretation: a review. Image Vision Comput. 23(2), 89–110 (2005)
Bloch, I.: Spatial reasoning under imprecision using fuzzy set theory, formal logics and mathematical morphology. Int. J. Approximate Reasoning 41(2), 77–95 (2006)
Bloch, I.: Mathematical morphology and spatial reasoning: fuzzy and bipolar setting. TWMS J. Pure Appl. Math. 12(1), 104–125 (2021). Special Issue on Fuzzy Sets in Dealing with Imprecision and Uncertainty: Past and Future Dedicated to the memory of Lotfi A. Zadeh
Bloch, I.: Modeling imprecise and bipolar algebraic and topological relations using morphological dilations. Math. Morphol. Theory Appl. 5(1), 1–20 (2021)
Bloch, I., Géraud, T., Maître, H.: Representation and fusion of heterogeneous fuzzy information in the 3D space for model-based structural recognition - application to 3D brain imaging. Artif. Intell. 148, 141–175 (2003)
Bloch, I., Lang, J., Pino Pérez, R., Uzcátegui, C.: Morphologic for knowledge dynamics: revision, fusion, abduction. Technical report arXiv:1802.05142, arXiv cs.AI (2018)
Cesar, R., Bengoetxea, E., Bloch, I., Larranaga, P.: Inexact graph matching for model-based recognition: evaluation and comparison of optimization algorithms. Pattern Recognit. 38, 2099–2113 (2005)
Chopin, J., Fasquel, J.B., Mouchère, H., Dahyot, R., Bloch, I.: Improving semantic segmentation with graph-based structural knowledge. In: El Yacoubi, M., Granger, E., Yuen, P.C., Pal, U., Vincent, N. (eds.) International Conference on Pattern Recognition and Artificial Intelligence. ICPRAI 2022. Lecture Notes in Computer Science, vol. 13363, pp. 173–184. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-09037-0_15
Colliot, O., Camara, O., Bloch, I.: Integration of fuzzy spatial relations in deformable models - application to brain MRI segmentation. Pattern Recognit. 39, 1401–1414 (2006)
Coradeschi, S., Saffiotti, A.: Anchoring symbols to vision data by fuzzy logic. In: Hunter, A., Parsons, S. (eds.) ECSQARU’99. LNCS, vol. 1638, pp. 104–115. Springer, London (1999)
Coste-Marquis, S., Marquis, P.: From explanations to intelligible explanations. In: 1st International Workshop on Explainable Logic-Based Knowledge Representation (XLoKR 2020) (2020)
Couteaux, V., et al.: Automatic knee meniscus tear detection and orientation classification with Mask-RCNN. Diagn. Interv. Imaging 100, 235–242 (2019)
De Raedt, L., Dumancic, S., Manhaeve, R., Marra, G.: From statistical relational to neuro-symbolic artificial intelligence. In: Bessiere, C. (ed.) Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20, pp. 4943–4950 (2020)
Delmonte, A., Mercier, C., Pallud, J., Bloch, I., Gori, P.: White matter multi-resolution segmentation using fuzzy set theory. In: IEEE International Symposium on Biomedical Imaging (ISBI), pp. 459–462. Venice, Italy (2019)
Denis, C., Varenne, F.: Interprétabilité et explicabilité de phénomènes prédits par de l’apprentissage machine. Rev. Ouverte Intell. Artif. 3, 287–310 (2022)
Deruyver, A., Hodé, Y.: Constraint satisfaction problem with bilevel constraint: application to interpretation of over-segmented images. Artif. Intell. 93(1–2), 321–335 (1997)
Fasquel, J., Delanoue, N.: A graph based image interpretation method using a priori qualitative inclusion and photometric relationships. IEEE Trans. Pattern Anal. Mach. Intell. 41(5), 1043–1055 (2019)
Fouquier, G., Atif, J., Bloch, I.: Sequential model-based segmentation and recognition of image structures driven by visual features and spatial relations. Comput. Vis. Image Underst. 116(1), 146–165 (2012)
Freeman, J.: The modelling of spatial relations. Comput. Graph. Image Process. 4(2), 156–171 (1975)
d’Avila Garcez, A., Lamb, L.C.: Neurosymbolic AI: the 3rd wave. CoRR abs/2012.05876 (2020)
Garnelo, M., Shanahan, M.: Reconciling deep learning with symbolic artificial intelligence: representing objects and relations. Curr. Opin. Behav. Sci. 29, 17–23 (2019)
Halpern, J.Y., Pearl, J.: Causes and explanations: a structural-model approach. Part I: causes. Br. J. Philos. Sci. 56(4), 843–887 (2005)
Halpern, J.Y., Pearl, J.: Causes and explanations: a structural-model approach. Part II: explanations. Br. J. Philos. Sci. 56(4), 889–911 (2005)
Harnad, S.: The symbol grounding problem. Physica 42, 335–346 (1990)
Hudelot, C., Atif, J., Bloch, I.: Fuzzy spatial relation ontology for image interpretation. Fuzzy Sets Syst. 159, 1929–1951 (2008)
Kahneman, D.: Thinking. Fast and Slow, Penguin, New York (2012)
Kautz, H.: The third AI summer: AAAI Robert S. Engelmore Memorial Lect. AI Mag. 43(1), 93–104 (2022)
Landini, G., Galton, A., Randell, D., Fouad., S.: Novel applications of discrete mereotopology to mathematical morphology: signal processing: image communications 76, 109–117 (2019)
Marcus, G.: The next decade in AI: four steps towards robust artificial intelligence. CoRR abs/2002.06177 (2020)
Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019)
Miller, T.: Contrastive explanation: a structural-model approach. Knowl. Eng. Rev. 36, E14 (2021)
Nempont, O., Atif, J., Bloch, I.: A constraint propagation approach to structural model based image segmentation and recognition. Inf. Sci. 246, 1–27 (2013)
Perchant, A., Bloch, I.: Fuzzy morphisms between graphs. Fuzzy Sets Syst. 128(2), 149–168 (2002)
Randell, D., Cui, Z., Cohn, A.: A Spatial Logic based on Regions and Connection. In: Nebel, B., Rich, C., Swartout, W. (eds.) Principles of Knowledge Representation and Reasoning KR’92, pp. 165–176. Kaufmann, San Mateo, CA (1992)
Schockaert, S., De Cock, M., Cornelis, C., Kerre, E.E.: Fuzzy region connection calculus: representing vague topological information. Int. J. Approximate Reasoning 48(1), 314–331 (2008)
Schockaert, S., De Cock, M., Kerre, E.E.: Spatial reasoning in a fuzzy region connection calculus. Artif. Intell. 173(2), 258–298 (2009)
Smeulders, A., Worring, M., Santini, S., Gupta, A., Jain, R.: Content-based image retrieval at the end of the early years. IEEE Trans. Pattern Anal. Mach. Intell. 22(12), 1349–1380 (2000)
Virzi, A., et al.: Segmentation of pelvic vessels in pediatric MRI using a patch-based deep learning approach. In: Melbourne, A., et al. (eds.) PIPPI/DATRA -2018. LNCS, vol. 11076, pp. 97–106. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00807-9_10
Xie, X., Niu, J., Liu, X., Chen, Z., Tang, S., Yu, S.: A survey on incorporating domain knowledge into deep learning for medical image analysis. Med. Image Anal. 69, 101985 (2021)
Yang, Y., Atif, J., Bloch, I.: Abductive reasoning using tableau methods for high-level image interpretation. In: Hölldobler, S., Krötzsch, M., Peñaloza, R., Rudolph, S. (eds.) KI 2015. LNCS (LNAI), vol. 9324, pp. 356–365. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24489-1_34
Zadeh, L.A.: Fuzzy Sets. Inf. Control 8, 338–353 (1965)
Zadeh, L.A.: The concept of a linguistic variable and its application to approximate reasoning. Inf. Sci. 8, 199–249 (1975)
Acknowledgements
The author would like to emphasize that the ideas summarized in this paper benefited from many joint works with post-doctoral researchers and PhD candidates, with colleagues in universities and research centers in several countries, with university hospitals, and with industrial partners. Thanks to all of them!
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Bloch, I. (2022). Hybrid Artificial Intelligence for Knowledge Representation and Model-Based Medical Image Understanding - Towards Explainability. In: Baudrier, É., Naegel, B., Krähenbühl, A., Tajine, M. (eds) Discrete Geometry and Mathematical Morphology. DGMM 2022. Lecture Notes in Computer Science, vol 13493. Springer, Cham. https://doi.org/10.1007/978-3-031-19897-7_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-19897-7_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19896-0
Online ISBN: 978-3-031-19897-7
eBook Packages: Computer ScienceComputer Science (R0)