Evolutionary design of explainable algorithms for biomedical image segmentation
Created by W.Langdon from
gp-bibliography.bib Revision:1.7831
- @Article{Cortacero:2023:NatCommun,
-
author = "Kevin Cortacero and Brienne McKenzie and
Sabina Mueller and Roxana Khazen and Fanny Lafouresse and
Gaelle Corsaut and Nathalie {Van Acker} and
Francois-Xavier Frenois and Laurence Lamant and
Nicolas Meyer and Beatrice Vergier and Dennis G. Wilson and
Herve Luga and Oskar Staufer and Michael L. Dustin and
Salvatore Valitutti and Sylvain Cussat-Blanc",
-
title = "Evolutionary design of explainable algorithms for
biomedical image segmentation",
-
journal = "Nature Communications",
-
year = "2023",
-
volume = "14",
-
pages = "article 7112",
-
month = "06 " # nov,
-
note = "Gold Humie award",
-
keywords = "genetic algorithms, genetic programming, Cartesian
Genetic Programming, Kartezio, Cytotoxic T cells, Image
processing, Machine learning",
-
ISSN = "2041-1723",
-
URL = "
https://human-competitive.org/sites/default/files/entryform_5.txt",
-
URL = "
https://human-competitive.org/sites/default/files/paper_4.pdf",
-
URL = "
https://rdcu.be/dqvF0",
-
DOI = "
doi:10.1038/s41467-023-42664-x",
-
code_url = "
https://github.com/KevinCortacero/Kartezio",
-
size = "18 pages",
-
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. 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 parameterising 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.",
-
notes = "filed patent; EP 22307041.8
See also arXiv https://arxiv.org/abs/2302.14762
Leibniz Institute for New Materials, 66123,
Saarbruecken, Germany",
- }
Genetic Programming entries for
Kevin Cortacero
Brienne McKenzie
Sabina Mueller
Roxana Khazen
Fanny Lafouresse
Gaelle Corsaut
Nathalie Van Acker
Francois-Xavier Frenois
Laurence Lamant
Nicolas Meyer
Beatrice Vergier
Dennis G Wilson
Herve Luga
Oskar Staufer
Michael L Dustin
Salvatore Valitutti
Sylvain Cussat-Blanc
Citations