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 Experiment Videos

MCM-UNet++: A Hybrid Soft Computing Framework for Multi-Scale Polyp Segmentation via Enhanced Global Context and

Jinmei Li1, Ming Zhao2, Quan Du1

  • 1School of Computer Science, Yangtze University, Jingzhou 434025, China.

Sensors (Basel, Switzerland)
|June 12, 2026
PubMed
Summary

Related Concept Videos

Classification and Mechanical Properties of Synthetic Polymers01:28

Classification and Mechanical Properties of Synthetic Polymers

Synthetic polymers are classified as elastomers, fibers, or plastics based on their crystallinity. Crystallinity, the degree of long-range order in the solid state, influences the mechanical properties (stretching or contracting) of elastomers. Elastomers are flexible polymers that can expand or contract easily upon the application of an external force. They have numerous crosslinks that pull them back into their original shape when stress is removed. Silicones, for instance, are highly elastic...

You might also read

Related Articles

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

Sort by
Same author

Mitigating Spectral Imbalance and Detail Attenuation in RGB-Thermal Object Detection via Frequency-Guided Multimodal Fusion.

Sensors (Basel, Switzerland)·2026
Same author

Comparative analysis of the complete multi-chromosomal mitogenome of an antitussive herb Fritillaria unibracteata.

BMC genomics·2026
Same author

Comparative analysis of the complete multi-chromosomal mitogenome of Anoectochilus emeiensis (Orchidaceae).

BMC plant biology·2026
Same author

Defect-rich carbon-supported Pt nanoparticles <i>via</i> Joule heating for enhanced oxygen reduction.

Chemical communications (Cambridge, England)·2026
Same author

[Inventory and Distribution Characteristics of Pollutants and Carbon Dioxide Emissions in China's Cement Industry].

Huan jing ke xue= Huanjing kexue·2026
Same author

Gut microbiota-intestinal barrier crosstalk: mechanistic advances, disease relevance, and public health implications.

Frontiers in public health·2026

This study introduces MCM-UNet++, an enhanced AI model for segmenting colon polyps in colonoscopies. The model improves accuracy for colorectal cancer screening by addressing challenges like varied polyp appearance and unclear boundaries.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Colonoscopy polyp segmentation is crucial for colorectal cancer screening.
  • Challenges include morphological variations, low contrast, blurred boundaries, and class imbalance.

Purpose of the Study:

  • To present MCM-UNet++, a novel segmentation framework to improve polyp detection.
  • To enhance segmentation accuracy by addressing key challenges in colonoscopy images.

Main Methods:

  • Developed MCM-UNet++, a hybrid U-Net++ framework incorporating a Multi-Axis Transformer Block (MATransformerBlock).
  • Integrated a Cross-Channel Mixing (CCM) module for feature recalibration.
  • Utilized a Multi-Objective Adaptive Loss (MOALoss) combining focal, Dice, and boundary-aware terms.
Keywords:
Multi-Axis TransformerU-Net++adaptive feature fusionmulti-objective losspolyp segmentationsoft computing

Related Experiment Videos

Main Results:

  • Achieved competitive performance on four public datasets (Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, ETIS-Larib).
  • Reported Dice/IoU scores of 0.9563/0.9278 on Kvasir-SEG and 0.8593/0.7896 on CVC-ColonDB.
  • Demonstrated improved segmentation for small regions and ambiguous boundaries.

Conclusions:

  • The proposed MCM-UNet++ framework shows significant potential for enhancing polyp segmentation accuracy.
  • Further validation is necessary for clinical deployment in colorectal cancer screening.