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

Deconvolution

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

You might also read

Related Articles

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

Sort by

Same author

Shame in sport: tracing the past and looking to the future.

Frontiers in public health·2026

Same author

Hallucinated domain generalization network with domain-aware dynamic representation for medical image segmentation.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2025

Same author

Effects of physical activity on patients with posttraumatic stress disorder: A systematic review and meta-analysis of randomized controlled trials.

Medicine·2025

Same author

Automatic breast ultrasound (ABUS) tumor segmentation based on global and local feature fusion.

Physics in medicine and biology·2024

Same author

Attention decoupled contrastive learning for semi-supervised segmentation method based on data augmentation.

Physics in medicine and biology·2024

Same author

Coco-Attention for Tumor Segmentation in Weakly Paired Multimodal MRI Images.

IEEE journal of biomedical and health informatics·2023

Search research articles

Related Experiment Video

Updated: Jul 9, 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

ABUS tumor segmentation via decouple contrastive knowledge distillation.

Pan Pan¹, Yanfeng Li¹, Houjin Chen¹

¹Beijing Jiaotong University, Shangyuancun No.3, Haidian, Beijing, 100044, People's Republic of China.

Physics in Medicine and Biology

|December 5, 2023

Summary

This study introduces a new knowledge distillation method for automated breast ultrasound (ABUS) tumor segmentation. The approach significantly reduces computational needs while achieving state-of-the-art accuracy in medical image analysis.

Keywords:

ABUS contrastive learning knowledge distillation ranking loss segmentation

More Related Videos

Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

Published on: July 14, 2020

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Related Experiment Videos

Last Updated: Jul 9, 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

Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

Published on: July 14, 2020

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Area of Science:

Medical Imaging
Artificial Intelligence
Computer-Aided Diagnosis

Background:

Deep learning methods dominate medical image segmentation.
Accurate automated breast ultrasound (ABUS) tumor segmentation is crucial for computer-aided diagnosis.
Current deep learning models are computationally intensive and parameter-heavy.

Purpose of the Study:

To develop a novel knowledge distillation method for ABUS tumor segmentation.
To address the high computational demands of existing deep learning models.
To improve the accuracy and efficiency of ABUS tumor segmentation.

Main Methods:

Proposed a knowledge distillation method for ABUS tumor segmentation.
Introduced a decoupled contrastive learning approach to differentiate tumor and non-tumor features.
Designed a ranking loss function for effective hard-negative mining in medical images.

Main Results:

The method achieved state-of-the-art performance on ABUS tumor segmentation.
Student networks showed significant improvements in Dice Similarity Coefficient (DSC), with one enhanced by 7%.
A student network (3D HR-Net) achieved a DSC of 0.780 with substantially fewer parameters than the teacher network.

Conclusions:

The novel knowledge distillation method significantly reduces computational requirements for ABUS tumor segmentation.
The approach achieves state-of-the-art performance, enhancing accuracy and feasibility for computer-aided diagnosis.
This research offers a promising solution for efficient and accurate medical image analysis.