Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Rethinking model prototyping through the MedMNIST+ dataset collection

Publication

Rethinking model prototyping through the MedMNIST+ dataset collection

Doerrich, Sebastian; Di Salvo, Francesco; Brockmann, Julius; u. a. (2025): Rethinking model prototyping through the MedMNIST+ dataset collection, in: Scientific reports, London: Springer Nature, Jg. 15, Nr. 1, 7669, S. 1–15, doi: 10.1038/s41598-025-92156-9.

Details

Faculty/Chair
Faculty/Professorship
Author
Brockmann, Julius
By
Doerrich, Sebastian; ...
Title of the Journal
Scientific reports
ISSN
2045-2322
Publisher Information
Springer Nature : London
Year of publication
2025
Volume
15
Issue
1, 7669
Language
English
DOI
Abstract

The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets. In addition, the field has increasingly prioritized marginal performance gains on a few, narrowly scoped benchmarks over clinical applicability, slowing down meaningful algorithmic progress. This trend often results in excessive fine-tuning of existing methods on selected datasets rather than fostering clinically relevant innovations. In response, this work introduces a comprehensive benchmark for the MedMNIST+ dataset collection, designed to diversify the evaluation landscape across several imaging modalities, anatomical regions, classification tasks and sample sizes. We systematically reassess commonly used Convolutional Neural Networks (CNNs) and Vision Transformer (ViT) architectures across distinct medical datasets, training methodologies, and input resolutions to validate and refine existing assumptions about model effectiveness and development. Our findings suggest that computationally efficient training schemes and modern foundation models offer viable alternatives to costly end-to-end training. Additionally, we observe that higher image resolutions do not consistently improve performance beyond a certain threshold. This highlights the potential benefits of using lower resolutions, particularly in prototyping stages, to reduce computational demands without sacrificing accuracy. Notably, our analysis reaffirms the competitiveness of CNNs compared to ViTs, emphasizing the importance of comprehending the intrinsic capabilities of different architectures. Finally, by establishing a standardized evaluation framework, we aim to enhance transparency, reproducibility, and comparability within the MedMNIST+ dataset collection as well as future research. Code is available at github.com/sdoerrich97/rethinking-model-prototyping-MedMNISTPlus.

GND Keywords
Deep Learning
Medizin
Bild
Datensatz
Benchmarking
Prototyping
Empfehlung
Klassifikation
Keywords
Benchmarking
Prototyping recommendations
Medical image classification
Standardized evaluation framework
Foundation models
DDC Classification
004 Computer science
RVK Classification
ST 330
Peer Reviewed
yes
International Distribution
yes
Open Access Journal
yes
Type
Article
URI
Activation date
2025-03-17
Project(s)

Permalink: https://fis.uni-bamberg.de/handle/uniba/107047 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-15

Restricted read-only access: login, editing and submission are temporarily disabled.