Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Autologous transplant versus matched sibling donor transplant in intermediate-risk AML in CR1 with no detectable MRD: a biological assignment comparative study.

Experimental hematology & oncology·2026
Same author

Bushen Huoxue Decoction alleviates osteoporosis by promoting the osteogenic differentiation of BMSCs by targeting the OTUD5/PDCD5/p53 signaling pathway.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Runx1-Snx9 axis drives the pathological secretion of mitochondrial-derived vesicles to activate cGAS-STING signaling in acute pancreatitis.

Journal of nanobiotechnology·2026
Same author

Global optimization and structural evolution of platinum clusters (Pt<sub><i>N</i></sub>, <i>N</i> = 6-50) <i>via</i> deep potential and hybrid evolutionary algorithm.

Physical chemistry chemical physics : PCCP·2026
Same author

MZB1 Modulates Inflammatory Severity in Severe Acute Pancreatitis through an IgA-Associated Intestinal Barrier Axis.

Inflammation·2026
Same author

Artificial Intelligence for Bioinspired Nanofluidic Iontronics.

Nano letters·2026

Related Experiment Video

Updated: Jan 15, 2026

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
07:15

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

2.4K

Weak redundancy U-shaped network and heatmap-based object prompt method for real-time medical image processing.

Chenzhuo Lu1,2, Zhuang Fu1,2, Ziwen Guo1,2

  • 1School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China.

Quantitative Imaging in Medicine and Surgery
|October 13, 2025
PubMed
Summary

This study introduces a lightweight AI model for rapid medical image segmentation, significantly reducing computational load and enhancing real-time performance for efficient diagnostics.

Keywords:
Lightweightdeep learningmedical imagesegmentation

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.3K
An Experimental Protocol for Assessing the Performance of New Ultrasound Probes Based on CMUT Technology in Application to Brain Imaging
16:01

An Experimental Protocol for Assessing the Performance of New Ultrasound Probes Based on CMUT Technology in Application to Brain Imaging

Published on: September 24, 2017

10.9K

Related Experiment Videos

Last Updated: Jan 15, 2026

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
07:15

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

2.4K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

3.3K
An Experimental Protocol for Assessing the Performance of New Ultrasound Probes Based on CMUT Technology in Application to Brain Imaging
16:01

An Experimental Protocol for Assessing the Performance of New Ultrasound Probes Based on CMUT Technology in Application to Brain Imaging

Published on: September 24, 2017

10.9K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Artificial intelligence (AI) aids radiologists in medical image interpretation and diagnostics.
  • Object detection and segmentation are key in medical image processing for efficiency.
  • Existing networks are complex and computationally intensive, hindering real-time segmentation.

Purpose of the Study:

  • Design a lightweight segmentation algorithm to reduce resource consumption.
  • Enhance real-time performance for medical image analysis.
  • Develop an efficient AI solution for medical image segmentation.

Main Methods:

  • Proposed a compact U-shaped network, weak redundancy U-Net (WRU-Net), for real-time segmentation.
  • Reduced channel count and feature redundancy for efficient resource utilization.
  • Introduced "object prompt" using heatmaps for semantic detection.

Main Results:

  • Achieved average Dice similarity coefficient (DSC) of 88.53% and Intersection over Union (IoU) of 82.58%.
  • WRU-Net demonstrated a model size of 130.67 KB and 488 FPS, outperforming larger models.
  • Heatmap prediction network achieved 107.93 FPS on CPU and 9,862.13 FPS on GPU.

Conclusions:

  • Lightweight networks are crucial for high-speed data processing in resource-constrained environments.
  • The proposed method significantly reduces parameters, computational cost, and enhances speed.
  • This approach optimizes computational efficiency for practical applications like embedded devices and real-time ultrasound.