- author = "Camilo {De La Torre} and Giorgia Nadizar and Yuri Lavinas and Robin Schwob and Camille Franchet and Herve Luga and Dennis Wilson and Sylvain Cussat-Blanc",
- title = "Evolved and Transparent Pipelines for Biomedical Image Classification",
- booktitle = "European Conference on Genetic Programming, EuroGP 2025",
- year = "2025",
- editor = "Bing Xue and Luca Manzoni and Illya Bakurov",
- volume = "15609",
- series = "LNCS",
- pages = "173--189",
- address = "Trieste",
- month = "23-25 " # apr,
- publisher = "Springer Nature",
- keywords = "genetic algorithms, genetic programming, Image Classification, Interpretable Machine Learning",
- isbn13 = "978-3-031-89990-4",
-
URL = "
https://rdcu.be/ejgFt",
-
DOI = "
10.1007/978-3-031-89991-1_11",
- abstract = "This article presents an interpretable approach to binary image classification using Genetic Programming (GP), applied to the PatchCamelyon (PCAM) dataset, which contains small tissue biopsy patches labeled as malignant or benign. While Deep Neural Networks (DNNs) achieve high performance in image classification, their opaque decision making processes, prone to overfitting behaviour and dependency on large amounts of annotated data limit their utility in critical fields like digital pathology, where interpretability is essential. To address this, we employ GP, specifically using the Multi-Modal Adaptive Graph Evolution (MAGE) framework, to evolve end-to-end image classification pipelines. We trained MAGE a hundred times with the best optimised key hyper-parameters for this task. Among all MAGE models trained, the best one achieved 78percent accuracy on the validation set and 76 percent accuracy on the test set. Among Convolutional Neural Networks (CNNs), our baseline, the best model obtained 84.5 percent accuracy on the validation set and 77.1 percent accuracy on the test set. Unlike CNNs, our GP approach enables program-level transparency, facilitating interpretability through example-based reasoning. By analysing evolved programs with medical experts, we highlight the transparency of decision-making in MAGE pipelines, offering an interpretable alternative for medical image classification tasks where model interpretability is paramount.",
-
notes = "also known as
\cite{paper_116_biomedical_image_classification}
Part of \cite{Xue:2025:GP} EuroGP'2025 held in conjunction with EvoCOP2025, EvoMusArt2025 and EvoApplications2025",
