OSCR

NeuroPlast: a learnable activation function evaluated under knowledge distillation for medical image classification.

Overview

Authors: Fabrice Vaussenat1, Abhiroop Bhattacharya1, Julie Payette1, Thibaut Desmettre2, Alireza Saidi3, Ghyslain Gagnon1, Sylvain G Cloutier1
  1. Department of Electrical Engineering, École de technologie supérieure, Montréal, QC, Canada
  2. Department of Acute Medicine, Hôpital Universitaire de Genève, Genève, Switzerland
  3. Institut de recherche Robert-Sauvé en santé et en sécurité du travail (IRSST), Montréal, QC, Canada
Journal: Frontiers in artificial intelligence, volume 9, article 1849571
Dates: received 7 April 2026; accepted 31 July 2026; published online 31 August 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3389/frai.2026.1849571 · PMID 42741410 · PMCID PMC13572696 · OpenAlex W7204747779
Open access: gold, a free copy (OpenAlex)
Categories: other condition (population), methods / tools (subfield)
Methods: Machine learning, Spectral & time-frequency, Evoked potentials, Complexity, Statistics, Smoothing, state filtering, decompositions
Keywords: bio-inspired activation function, convolutional neural network, deep learning, from-scratch training, knowledge distillation, learnable activation, medical image classification, metaplasticity
Topic: COVID-19 diagnosis using AI (Radiology, Nuclear Medicine and Imaging, Medicine), according to OpenAlex
Citations: not cited yet (Europe PMC); 61 references in the paper

Abstract

Deep neural networks for medical image classification rely almost exclusively on fixed activation functions such as ReLU. We introduce NeuroPlast, a parametric activation function whose four differentiable components (a shifted sigmoid modeling NMDA-type voltage gating, a Gaussian plateau inspired by AMPA receptor scaling, an excitatory rectifier, and an inhibitory leak) are combined through six learnable parameters. Two mixing strategies are evaluated: a static variant with fixed learned weights, and a metaplastic variant whose mixing coefficients adapt per sample via a lightweight squeeze-excite gate conditioned on channel statistics. NeuroPlast is embedded within NADN Ultra, a 13.5 M-parameter residual convolutional neural network (CNN) with convolutional block attention modules (CBAM), trained entirely from scratch through a two-phase knowledge distillation (KD) pipeline. The teacher is a fine-tuned EfficientNet-B0; the student combines logit-level KD with optional feature-level alignment losses. Across four medical imaging benchmarks (Brain Tumor MRI, 7,200 images, 4 classes; Chest X-ray Pneumonia, 5,856 images, 2 classes; Skin Cancer HAM10000, 10,015 images, 7 classes; COVID-19 Radiography, 10,848 images, 2 classes), evaluated under five-fold stratified cross-validation with 95% confidence intervals, the static-KD variant reaches 99.4–99.5% accuracy on COVID-19 X-ray across three seeds, on par with pretrained EfficientNet-B0 (99.18%, within replication noise) and above ResNet-18 (98.69%). It closes 65% of the accuracy gap on Brain Tumor MRI (98.29% vs. 99.13%), reaches 92.5% on Chest X-ray under a uniform class-balancing rule, and 79.5% on Skin Cancer under lesion-grouped cross-validation. The metaplastic variant achieves 99.28% on COVID-19 X-ray, still above pretrained baselines, but does not consistently outperform the static version, a negative result analyzed through ablation experiments. On three tabular medical datasets spanning three orders of magnitude in sample size (569 to 253,680), NeuroPlast matches five established activations within ±1.7 percentage points; at 253 K samples all activations converge within 0.09 pp. Our findings indicate that knowledge distillation is the primary enabler for from-scratch architectures to approach pretrained-level performance on medical images; under an identical distillation pipeline, NeuroPlast adds a small but consistent gain over ReLU, GELU, Swish, Mish, and PReLU, leading on all four imaging benchmarks by margins below one point.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data and to no code of its authors: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

Data availability statement

Publicly available datasets were analysed in this study: Brain Tumor MRI (https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset); Chest X-ray Pneumonia (Kermany et al., 2018; https://data.mendeley.com/datasets/rscbjbr9sj/2); Skin Cancer HAM10000 (Tschandl et al., 2018; https://doi.org/10.7910/DVN/DBW86T); COVID-19 Radiography (Chowdhury et al., 2020; https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database); Wisconsin Breast Cancer, Pima Indians Diabetes, and Heart Disease BRFSS 2022 from the UCI Machine Learning Repository/CDC BRFSS.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 2, 28 September 2026

  • Funding: added Nvidia; École de technologie supérieure; Natural Sciences and Engineering Research Council of Canada

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, pages, dates, 7 authors, 8 keywords, 37 references.

Cite

This paper

Vaussenat, F., Bhattacharya, A., Payette, J., Desmettre, T., Saidi, A., Gagnon, G., & Cloutier, S. G. (2026). NeuroPlast: a learnable activation function evaluated under knowledge distillation for medical image classification. Frontiers in artificial intelligence, 9, 1849571. https://doi.org/10.3389/frai.2026.1849571

BibTeX

@article{vaussenat2026neuroplast,
author = {Vaussenat, Fabrice and Bhattacharya, Abhiroop and Payette, Julie and Desmettre, Thibaut and Saidi, Alireza and Gagnon, Ghyslain and Cloutier, Sylvain G},
title = {{NeuroPlast: a learnable activation function evaluated under knowledge distillation for medical image classification}},
journal = {Frontiers in artificial intelligence},
year = {2026},
month = aug,
volume = {9},
pages = {1849571},
publisher = {Frontiers Media SA},
issn = {2624-8212},
doi = {10.3389/frai.2026.1849571},
url = {https://doi.org/10.3389/frai.2026.1849571},
pmid = {42741410},
pmcid = {PMC13572696}
}

RIS

TY - JOUR
AU - Vaussenat, Fabrice
AU - Bhattacharya, Abhiroop
AU - Payette, Julie
AU - Desmettre, Thibaut
AU - Saidi, Alireza
AU - Gagnon, Ghyslain
AU - Cloutier, Sylvain G
TI - NeuroPlast: a learnable activation function evaluated under knowledge distillation for medical image classification
T2 - Frontiers in artificial intelligence
J2 - Front Artif Intell
PY - 2026
DA - 2026/08/31
VL - 9
SP - 1849571
SN - 2624-8212
PB - Frontiers Media SA
DO - 10.3389/frai.2026.1849571
UR - https://doi.org/10.3389/frai.2026.1849571
LA - en
ER -

CSL-JSON

{
"id": "10.3389/frai.2026.1849571",
"type": "article-journal",
"title": "NeuroPlast: a learnable activation function evaluated under knowledge distillation for medical image classification",
"container-title": "Frontiers in artificial intelligence",
"author": [
{
"family": "Vaussenat",
"given": "Fabrice"
},
{
"family": "Bhattacharya",
"given": "Abhiroop"
},
{
"family": "Payette",
"given": "Julie"
},
{
"family": "Desmettre",
"given": "Thibaut"
},
{
"family": "Saidi",
"given": "Alireza"
},
{
"family": "Gagnon",
"given": "Ghyslain"
},
{
"family": "Cloutier",
"given": "Sylvain G"
}
],
"container-title-short": "Front Artif Intell",
"volume": "9",
"page": "1849571",
"DOI": "10.3389/frai.2026.1849571",
"PMID": "42741410",
"PMCID": "PMC13572696",
"ISSN": "2624-8212",
"publisher": "Frontiers Media SA",
"URL": "https://doi.org/10.3389/frai.2026.1849571",
"language": "en",
"issued": {
"date-parts": [
[
2026,
8,
31
]
]
}
}

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.3389/fonc.2026.1834400
BrainFusionNet: an attention-augmented deep convolutional framework with hybrid loss optimisation and test-time augmentation for multi-class brain tumour detection in magnetic resonance images.
Journal: Frontiers in oncology
In common: kaggle.com/datasets/masoudnickparvar, methods / tools, other condition, 4 references
[2] doi:10.3390/s22166312 [code]
Database and AI Diagnostic Tools Improve Understanding of Lung Damage, Correlation of Pulmonary Disease and Brain Damage in COVID-19.
Journal: Sensors (Basel, Switzerland)
In common: kaggle.com/datasets/tawsifurrahman, other condition, 2 references
[3] doi:10.1038/s41598-026-55179-4 [code]
Vision-Language Models for automated quality control: a benchmarking framework and comprehensive study.
Journal: Scientific reports
In common: DOI 10.7910/dvn/dbw86t, methods / tools, other condition, 1 reference
[4] doi:10.3389/fmed.2025.1589587
Advancing patient care with AI: a unified framework for medical image segmentation using transfer learning and hybrid feature extraction.
Journal: Frontiers in medicine
In common: DOI 10.7910/dvn/dbw86t, other condition, 1 reference
[5] doi:10.3390/bioengineering10070823
Multi-Stage Classification of Retinal OCT Using Multi-Scale Ensemble Deep Architecture.
Journal: Bioengineering (Basel, Switzerland)
In common: data.mendeley.com/datasets/rscbjbr9sj, methods / tools, 2 references
[6] doi:10.1007/s11042-023-14831-1
MediNet: transfer learning approach with MediNet medical visual database.
Journal: Multimedia tools and applications
In common: data.mendeley.com/datasets/rscbjbr9sj, methods / tools, other condition, 1 reference
[7] doi:10.1038/s41598-026-51120-x [code]
A compact and interpretable multi-source framework for heterogeneous medical image classification.
Journal: Scientific reports
In common: data.mendeley.com/datasets/rscbjbr9sj, methods / tools, other condition, 1 reference
[8] doi:10.3390/e23121651
Multilevel Deep Feature Generation Framework for Automated Detection of Retinal Abnormalities Using OCT Images.
Journal: Entropy (Basel, Switzerland)
In common: data.mendeley.com/datasets/rscbjbr9sj, methods / tools, 1 reference
[9] doi:10.1038/s41598-025-32886-y [code]
Language assisted learnable hyperdimensional computing framework for retinal disease classification.
Journal: Scientific reports
In common: data.mendeley.com/datasets/rscbjbr9sj, other condition, 1 reference
[10] doi:10.1371/journal.pone.0304943
Stitched vision transformer for age-related macular degeneration detection using retinal optical coherence tomography images.
Journal: PloS one
In common: data.mendeley.com/datasets/rscbjbr9sj, other condition, 1 reference

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.