Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Easy-to-use and easy-to-interpret quality control of 3D gradient echo T1-weighted MR acquisition sequences for improved test-retest stability of MRI-based hippocampus volumetry.

Journal of Alzheimer's disease : JAD·2025

Same author

Incorporating label uncertainty during the training of convolutional neural networks improves performance for the discrimination between certain and inconclusive cases in dopamine transporter SPECT.

European journal of nuclear medicine and molecular imaging·2024

Same author

Fast 3D YOLOv3 based standard plane regression of vertebral bodies in intra-operative CBCT volumes.

Journal of medical imaging (Bellingham, Wash.)·2023

Same author

Assessment of a deep-learning system for fracture detection in musculoskeletal radiographs.

NPJ digital medicine·2020

Same author

Volume Change in Frontal Cholinergic Structures After Traumatic Brain Injury and Cognitive Outcome.

Frontiers in neurology·2020

Same author

Integrative Analysis of Circulating Metabolite Profiles and Magnetic Resonance Imaging Metrics in Patients with Traumatic Brain Injury.

International journal of molecular sciences·2020

Search research articles

Related Experiment Video

Updated: May 3, 2026

Rapid Formation and Testing of Self-expanding NiTi Frames with a Small Form Factor Suitable for Minimally Invasive Implants

Rapid Formation and Testing of Self-expanding NiTi Frames with a Small Form Factor Suitable for Minimally Invasive Implants

Published on: March 7, 2025

Rethinking model prototyping through the MedMNIST+ dataset collection.

Sebastian Doerrich¹, Francesco Di Salvo², Julius Brockmann^2,3

¹University of Bamberg, xAILab Bamberg, Bamberg, 96047, Germany. sebastian.doerrich@uni-bamberg.de.

Scientific Reports

|March 5, 2025

Summary

This study introduces a new benchmark for medical deep learning, evaluating Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) on diverse datasets. Findings show efficient training and lower resolutions are effective, with CNNs remaining competitive.

Keywords:

Benchmarking Foundation models Medical image classification Prototyping recommendations Standardized evaluation framework

More Related Videos

Surrogate Model Development for Digital Experiments in Welding

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Related Experiment Videos

Last Updated: May 3, 2026

Rapid Formation and Testing of Self-expanding NiTi Frames with a Small Form Factor Suitable for Minimally Invasive Implants

Rapid Formation and Testing of Self-expanding NiTi Frames with a Small Form Factor Suitable for Minimally Invasive Implants

Published on: March 7, 2025

Surrogate Model Development for Digital Experiments in Welding

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Area of Science:

Medical Imaging
Deep Learning
Computer Vision

Background:

Deep learning integration in clinical practice faces hurdles from limited, heterogeneous medical data.
Focus on narrow benchmarks over clinical applicability hinders meaningful progress.

Purpose of the Study:

Introduce a comprehensive benchmark for the MedMNIST+ dataset collection.
Diversify evaluation across imaging modalities, anatomical regions, tasks, and sample sizes.
Systematically reassess CNN and Vision Transformer (ViT) architectures.

Main Methods:

Evaluated CNNs and ViTs across diverse medical datasets, training methods, and input resolutions.
Utilized the MedMNIST+ dataset collection for a broad evaluation landscape.
Assessed model effectiveness and development assumptions.

Main Results:

Computationally efficient training and foundation models are viable alternatives to costly end-to-end training.
Higher image resolutions do not consistently improve performance beyond a threshold.
CNNs remain competitive against ViTs, highlighting the need to understand architecture-specific capabilities.

Conclusions:

Standardized evaluation framework enhances transparency, reproducibility, and comparability in medical AI research.
Lower image resolutions can reduce computational demands without sacrificing accuracy.
Understanding intrinsic architectural capabilities is crucial for effective deep learning model development in medicine.