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

Search research articles

Related Experiment Video

Updated: Mar 19, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Convpaint-Interactive pixel classification using pretrained neural networks.

Lucien Hinderling¹, Roman Schwob², Guillaume Witz²

¹Institute of Cell Biology, University of Bern, Baltzerstrasse 4, 3012 Bern, Switzerland; Graduate School for Cellular and Biomedical Sciences, University of Bern, Bern, Switzerland.

Cell Reports Methods

|March 17, 2026

Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Correction: Walewicz et al. Effect of Radial Extracorporeal Shock Wave Therapy on Pain Intensity, Functional Efficiency, and Postural Control Parameters in Patients with Chronic Low Back Pain: A Randomized Clinical Trial. <i>J. Clin. Med.</i> 2020, <i>9</i>, 568.

Journal of clinical medicine·2026

Same author

Imaging-Guided Surgical Decision-Making and Bone Healing in Mandibular Cystic and Tumor-like Lesions: A Case-Based Radiologic Observation.

Diagnostics (Basel, Switzerland)·2026

Same author

Radiologic Evaluation of Odontogenic Sinusitis and Its Etiologic Factors: Lessons Learned from a Retrospective Study with a Proposed Imaging-Guided Management Pathway.

Journal of clinical medicine·2026

Same author

How Clinical and Radiological Findings in Chronic Mandibular Osteomyelitis Do Not Always Correlate: Diagnostic Dilemmas in Dental-Related Bone Inflammations.

Diagnostics (Basel, Switzerland)·2026

Same author

Biogenic Selenium Nanoparticles Functionalized with Natural Polymers or Phytochemicals for Targeted Disruption of <i>Candida</i> spp. Biofilms on Denture Materials: A Systematic Review.

Journal of functional biomaterials·2026

Same author

Hypericin-Mediated Antimicrobial Photodynamic Therapy in Dentistry: A Systematic Review of Applications Against Oral Biofilms and Infections.

Pharmaceutics·2026

Same journal

Large-scale discovery platform enables identification of peptides targeting drug-resistant candidiasis.

Cell reports methods·2026

Same journal

A computational method to design broad-spectrum T cell-inducing vaccines applied to Betacoronaviruses.

Cell reports methods·2026

Same journal

MalDeepSeq panel: A targeted ultra-deep sequencing approach to trace drug resistance markers in Plasmodium falciparum.

Cell reports methods·2026

Same journal

Induced pluripotent stem cell-derived macrophages enable broad modeling of human inflammasome signaling.

Cell reports methods·2026

Same journal

Rapid discovery of cell-surface glycosylation regulators using a lectin-based magnetic CRISPR screen.

Cell reports methods·2026

Same journal

A real-time FRET ubiquitin transfer assay for quantitative characterization of ternary complexes in targeted protein degradation.

Cell reports methods·2026

See all related articles

This summary is machine-generated.

Convpaint offers a universal framework for interactive pixel classification using advanced AI models like convolutional neural networks (CNNs) and vision transformers (ViTs). This tool enhances image segmentation across various scales and data types for diverse scientific applications.

Area of Science:

Computational Biology
Computer Vision
Image Analysis

Background:

Pixel classification is crucial for image segmentation in various scientific fields.
Existing methods may lack flexibility or struggle with complex semantic understanding.

Purpose of the Study:

To introduce Convpaint, a versatile computational framework for interactive pixel classification.
To enable easy and efficient image segmentation across diverse tasks and data modalities.

Main Methods:

Utilizes pretrained convolutional neural networks (CNNs), vision transformers (ViTs), or classical filter banks for feature extraction.
Combines feature extractors with fast-to-train machine learning (ML) classifiers.
Integrates within the Python-based napari software ecosystem.

Keywords:

CP: biotechnology CP: systems biology image analysis multi-dimensional data pixel classification

Related Experiment Videos

Last Updated: Mar 19, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Main Results:

Convpaint provides a modular design for rapid switching between feature extractors.
Successfully extends pixel classification to domains requiring rich semantic understanding via ViT integration.
Demonstrates seamless integration into image processing pipelines with example workflows.

Conclusions:

Convpaint offers a flexible and powerful solution for interactive pixel classification.
The framework supports a balance of speed, spatial accuracy, and semantic depth for specific datasets.
Applicable to a wide range of image analysis tasks from subcellular to animal scales.