Evolutionary design of explainable algorithms for biomedical image segmentation
Open Access
- 6 November 2023
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-18
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.Keywords
All Related Versions
This publication has 49 references indexed in Scilit:
- Cartesian Genetic Programming for Image Processing2013
- An initial and rapid step of lytic granule secretion precedes microtubule organizing center polarization at the cytotoxic T lymphocyte/target cell synapseProceedings of the National Academy of Sciences, 2013
- OpenSlide: A vendor-neutral software foundation for digital pathologyJournal of Pathology Informatics, 2013
- Fiji: an open-source platform for biological-image analysisNature Methods, 2012
- Image Processing and CGP2011
- Analytical Capabilities of the ImageStream CytometerMethods in Cell Biology, 2011
- A fast and elitist multiobjective genetic algorithm: NSGA-IIIEEE Transactions on Evolutionary Computation, 2002
- The Immunological Synapse of CTL Contains a Secretory Domain and Membrane BridgesImmunity, 2001
- Comparative study of Hough Transform methods for circle findingImage and Vision Computing, 1990
- Principal component analysisChemometrics and Intelligent Laboratory Systems, 1987