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

You might also read

Related Articles

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

Sort by

Same author

IMMUND: A Diagnostic and Therapeutic Pipeline to Uncover the Convergence in Functional Perturbation at Early Stages of Neurodegenerative Diseases and Multiple Sclerosis Based on Protein Markers.

International journal of molecular sciences·2026

Same author

Optimizing genomics-aware clinical agents in precision oncology.

NPJ systems biology and applications·2026

Same author

Ex vivo testing of inflatable penile prosthesis in human cadaveric penis with paired in silico model offering surgical and biomechanical insights.

The journal of sexual medicine·2026

Same author

Altered chromatin accessibility and nucleosome positioning landscape upon HDAC and LSD1 inhibition in cancer cell.

bioRxiv : the preprint server for biology·2026

Same author

Urological benchtop and in silico models validated by human penile tissue inflation tests.

Annals of biomedical engineering·2025

Same author

Advancing breast cancer prediction using blockchain-secured hybrid genetic algorithm.

Computers in biology and medicine·2025

Search research articles

Related Experiment Video

Updated: Oct 4, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Dense Dilated Deep Multiscale Supervised U-Network for biomedical image segmentation.

Shirsha Bose¹, Ritesh Sur Chowdhury¹, Rangan Das²

¹Department of Electronics and Telecommunication Engineering, Jadavpur University, 188, Raja S.C. Mallick Rd, Kolkata, 700032, West Bengal, India.

Computers in Biology and Medicine

|February 5, 2022

Summary

This summary is machine-generated.

The novel D3MSU-Net improves biomedical image segmentation by varying receptive fields and using multi-level supervision. This deep learning approach enhances analysis across diverse medical imaging datasets.

Keywords:

Biomedical image segmentation Deep learning Deep multiscale supervision Dense dilated convolution

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Related Experiment Videos

Last Updated: Oct 4, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Area of Science:

Medical Image Analysis
Computer Vision
Deep Learning

Background:

Biomedical image segmentation is crucial for medical image analysis.
Deep learning, particularly U-Net variants, shows promise but has limitations.
Existing models share receptive fields and lack deep supervision.

Purpose of the Study:

To introduce D3MSU-Net, a novel deep learning architecture for biomedical image segmentation.
To address limitations of existing U-Net models regarding receptive fields and supervision levels.

Main Methods:

Proposed D3MSU-Net with varied receptive fields across resolution layers.
Implemented multi-level supervision at each resolution level.
Evaluated on eight diverse benchmark datasets including EM, lung, chest X-ray, and MRI.

Main Results:

D3MSU-Net demonstrated superior performance compared to existing methods.
Ablation studies confirmed the effectiveness of the proposed architectural modifications.
The model achieved state-of-the-art results on multiple segmentation tasks.

Conclusions:

The proposed D3MSU-Net effectively enhances biomedical image segmentation.
Varied receptive fields and multi-level supervision are key improvements.
The architecture offers a promising advancement for computerized medical image analysis.