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: May 28, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

N-Unet: An Efficient Multi-Task Model for Precise Classification and Segmentation of Breast Ultrasound Images.

Yafeng Yang¹, Zhengwei Zhu¹

¹Microelectronics and Control Engineering, Changzhou University, Changzhou 213011, China.

Journal of Imaging

|May 26, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Imaging Studies II: Ultrasonography

Imaging Studies II: Ultrasonography

IntroductionUltrasonography, or renal ultrasound, is a noninvasive medical imaging technique that uses high-frequency sound waves to visualize the kidneys, ureters, bladder, and surrounding tissues.Indications for Urinary System UltrasonographyUrinary system ultrasonography is indicated in various clinical scenarios, such as:Kidney Stones (Urolithiasis): To detect and monitor the size and presence of kidney or urinary tract stones.Hydronephrosis: To assess the dilation of the renal pelvis and...

You might also read

Related Articles

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

Sort by

Same author

Ultradense ZrC Nanoislands Decorated with Pt Single Atoms for Superior Activity and Durability in Water Electrolysis.

Journal of the American Chemical Society·2026

Same author

Erratum to "High-throughput screening of ancient forest plant extracts shows cytotoxicity towards triple-negative breast cancer" [Environ. Int. 181 (2023) 108279].

Environment international·2026

Same author

Noise-robust reward machine induction via probabilistic modeling and genetic local search.

Scientific reports·2026

Same author

Synergistic sonodynamic and ion-interference therapy effectively treats osteomyelitis and promotes neural and osteogenic regeneration.

Biomaterials·2026

Same author

Clinical efficacy and safety analysis of 1.5% ruxolitinib cream in the treatment of facial vitiligo in adolescents: A retrospective study of 74 cases.

Journal of the American Academy of Dermatology·2026

Same author

Targeted synergy for vitiligo in refractory areas: A real-world study of ruxolitinib cream combined with 308-nm excimer lamp.

Journal of the American Academy of Dermatology·2026

N-Unet enhances breast ultrasound analysis by effectively integrating classification and segmentation tasks. This deep learning model improves the delineation of fine structures and offers a strong performance-efficiency balance for clinical applications.

Area of Science:

Medical Imaging
Artificial Intelligence
Computer Vision

Background:

Deep learning significantly advances breast ultrasound image analysis.
Existing methods often fail to fully leverage task correlations and balance classification/segmentation objectives, limiting fine structure delineation.

Purpose of the Study:

To introduce N-Unet, a novel multi-task learning framework designed to improve automated classification and segmentation of breast ultrasound images.
To address limitations in feature representation and task objective balancing in current deep learning models.

Main Methods:

N-Unet employs a unified multi-task framework with a shared encoder and specialized branches for segmentation and classification.
Key components include Adaptive Multi-Task Loss (AMTL) for dynamic objective balancing, Adaptive Feature Fusion (AFF) and Cross-Level Attention Enhancement (CLAE) for improved feature representation, and Conditional Segmentation Boosting (CSB) for refinement.

Keywords:

breast ultrasound diagnosis deep learning image segmentation medical image analysis multi-task learning

Related Experiment Videos

Last Updated: May 28, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Main Results:

N-Unet achieved high classification accuracies (96.54% on BUSI, 95.83% on BUS-UCLM) and Dice scores (80.70% on BUSI, 92.16% on BUS-UCLM).
The model demonstrates a favorable performance-efficiency trade-off with only 8.95 M parameters and 14.74 GFLOPs.
Results confirm the model's effectiveness and robustness across different datasets.

Conclusions:

N-Unet effectively integrates classification and segmentation for breast ultrasound analysis, outperforming existing methods.
The proposed framework shows potential for practical breast nodule assessment, though external generalization requires further validation.