Evolutionary design of explainable algorithms for biomedical image segmentation

Kévin Cortacero, Brienne McKenzie, Sabina Müller, Roxana Khazen, Fanny Lafouresse, Gaëlle Corsaut, Nathalie Acker, François-Xavier Frenois, Laurence Lamant, Nicolas Meyer, Béatrice Vergier, Dennis G. Wilson, Hervé Luga, Oskar Staufer, Michael L. Dustin, Salvatore Valitutti () and Sylvain Cussat-Blanc ()
Additional contact information
Kévin Cortacero: Centre de Recherche en Cancérologie de Toulouse (CRCT)
Brienne McKenzie: Centre de Recherche en Cancérologie de Toulouse (CRCT)
Sabina Müller: Centre de Recherche en Cancérologie de Toulouse (CRCT)
Roxana Khazen: Centre de Recherche en Cancérologie de Toulouse (CRCT)
Fanny Lafouresse: Centre de Recherche en Cancérologie de Toulouse (CRCT)
Gaëlle Corsaut: Centre de Recherche en Cancérologie de Toulouse (CRCT)
Nathalie Acker: Institut Universitaire du Cancer-Oncopole de Toulouse (IUCT)
François-Xavier Frenois: Institut Universitaire du Cancer-Oncopole de Toulouse (IUCT)
Laurence Lamant: Institut Universitaire du Cancer-Oncopole de Toulouse (IUCT)
Nicolas Meyer: IUCT
Béatrice Vergier: Centre Hospitalier Universitaire de Bordeaux
Dennis G. Wilson: Artificial and Natural Intelligence Toulouse Institute
Hervé Luga: Artificial and Natural Intelligence Toulouse Institute
Oskar Staufer: University of Oxford
Michael L. Dustin: University of Oxford
Salvatore Valitutti: Centre de Recherche en Cancérologie de Toulouse (CRCT)
Sylvain Cussat-Blanc: Artificial and Natural Intelligence Toulouse Institute

Nature Communications, 2023, vol. 14, issue 1, 1-18

Abstract: Abstract An unresolved issue in contemporary biomedicine is the overwhelming number and diversity of complex images that require annotation, analysis and interpretation. Recent advances in Deep Learning have revolutionized the field of computer vision, creating algorithms that compete with human experts in image segmentation tasks. However, these frameworks require large human-annotated datasets for training and the resulting “black box” models are difficult to interpret. In this study, we introduce Kartezio, a modular Cartesian Genetic Programming-based computational strategy that generates fully transparent and easily interpretable image processing pipelines by iteratively assembling and parameterizing computer vision functions. The pipelines thus generated exhibit comparable precision to state-of-the-art Deep Learning approaches on instance segmentation tasks, while requiring drastically smaller training datasets. This Few-Shot Learning method confers tremendous flexibility, speed, and functionality to this approach. We then deploy Kartezio to solve a series of semantic and instance segmentation problems, and demonstrate its utility across diverse images ranging from multiplexed tissue histopathology images to high resolution microscopy images. While the flexibility, robustness and practical utility of Kartezio make this fully explicable evolutionary designer a potential game-changer in the field of biomedical image processing, Kartezio remains complementary and potentially auxiliary to mainstream Deep Learning approaches.

Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-023-42664-x Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:14:y:2023:i:1:d:10.1038_s41467-023-42664-x

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-023-42664-x

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().