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

Deconvolution01:20

Deconvolution

527
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...
527

You might also read

Related Articles

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

Sort by
Same author

Adaptive federated learning for resource-constrained IoT devices through edge intelligence and multi-edge clustering.

Scientific reports·2024
Same author

Unsupervised Dual Transformer Learning for 3-D Textured Surface Segmentation.

IEEE transactions on neural networks and learning systems·2024
Same author

Multimodal-Boost: Multimodal Medical Image Super-Resolution Using Multi-Attention Network With Wavelet Transform.

IEEE/ACM transactions on computational biology and bioinformatics·2022
Same author

Foodborne Disease Risk Prediction Using Multigraph Structural Long Short-term Memory Networks: Algorithm Design and Validation Study.

JMIR medical informatics·2021
Same author

Comparison of Machine Learning Techniques Based Brain Source Localization Using EEG Signals.

Current medical imaging·2020
Same author

Antioxidant and angiotensin I-converting enzyme inhibitory activities of Xuanwei ham before and after cooking and <i>in vitro</i> simulated gastrointestinal digestion.

Royal Society open science·2018
Same journal

Multimodal Contrastive Spatiotemporal Self-Organizing Neural Networks for In-Home Activity Learning of Mild Cognitive Impairment.

IEEE journal of biomedical and health informatics·2026
Same journal

Integrating Multi-View Residue Graph and Protein Language Model for Cell-Penetrating Peptide Prediction via Global-Local Graph Aggregation and Cross-Attentive Fusion.

IEEE journal of biomedical and health informatics·2026
Same journal

An Ultra-Lightweight Cross-scale Attention Mamba Network for Accurate Skin Lesion Segmentation.

IEEE journal of biomedical and health informatics·2026
Same journal

Explanation-Guided Reconstruction of Missing Clinical Features for Survival Prediction in Pancreatic Cancer.

IEEE journal of biomedical and health informatics·2026
Same journal

stDGCN: A dual-augmentation graph convolutional network for identifying spatial domains with attention mechanism.

IEEE journal of biomedical and health informatics·2026
Same journal

Patient-specific Biomechanical Investigation of Percutaneous Pulmonary Valves: Towards the Integration of Routinely Acquired Clinical Data and Fluid-structure Interaction Simulations.

IEEE journal of biomedical and health informatics·2026
See all related articles

Related Experiment Video

Updated: Jan 9, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K

Spec-ViT: A Vision Transformer With Wavelet for Anti-Aliasing and Denoising in Medical Image Classification.

Xiong Zhang, Le Wang, Yanying Rao

    IEEE Journal of Biomedical and Health Informatics
    |December 4, 2025
    PubMed
    Summary
    This summary is machine-generated.

    Spec-ViT, a novel wavelet-based anti-aliasing Transformer, enhances medical image analysis by reducing artifacts. This new architecture improves lesion characterization and diagnostic accuracy in medical imaging.

    More Related Videos

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    725
    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

    Related Experiment Videos

    Last Updated: Jan 9, 2026

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    2.3K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    725
    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

    Area of Science:

    • Medical Image Analysis
    • Artificial Intelligence in Healthcare
    • Deep Learning for Medical Imaging

    Background:

    • Medical image analysis faces challenges from imaging modality limitations, causing aliasing and noise artifacts that reduce diagnostic accuracy.
    • Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) show promise but can worsen high-frequency distortions due to sampling and spectral biases, impacting lesion characterization.

    Purpose of the Study:

    • To introduce Spec-ViT, a novel wavelet-based anti-aliasing Transformer architecture.
    • To address limitations in current deep learning models for medical image analysis by integrating spectral purification and hierarchical attention.

    Main Methods:

    • Developed the Wavelet Anti-aliasing Module (WAM) for learnable wavelet domain smoothing to suppress high-frequency artifacts while preserving low-frequency details.
    • Integrated Lightweight Enhanced Attention (LEA) with dual-path channel-spatial and global multi-head self-attention for improved lesion context modeling.
    • Employed Smoothed Convolutional Gate (SCG) with depth-wise convolution and adaptive Swish gating to enhance local discriminability.

    Main Results:

    • Spec-ViT consistently outperformed baseline and state-of-the-art methods across five benchmark medical image classification datasets.
    • Achieved a maximum accuracy of 84.04% on the Pediatric Pneumonia Chest X-rays dataset.
    • Demonstrated effective frequency-aware purification and global-local attentive analysis.

    Conclusions:

    • Spec-ViT offers a robust solution for enhancing medical image analysis by mitigating artifacts and improving feature representation.
    • The proposed architecture shows significant potential for advancing diagnostic accuracy in various medical imaging applications.
    • Wavelet-based anti-aliasing integrated with attention mechanisms provides a powerful approach for medical image classification.