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 Video

Updated: May 27, 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

Vision transformer embeddings and quantum pyramidal circuits for biomedical image analysis.

Xavi F Aragones1,2, Miguel A González Ballester3,4,5

  • 1BCN Medtech, Department of Engineering, Universitat Pompeu Fabra, Barcelona, Spain. font@tecnocampus.cat.

International Journal of Computer Assisted Radiology and Surgery
|May 25, 2026
PubMed
Summary

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

Disentangling metabolic impairment in the liver-heart axis: tissue-specific insulin sensitivity in type 2 diabetes.

Frontiers in endocrinology·2026
Same author

A MultiRater MultiOrgan Abdominal CT Dataset for Calibration Analysis and Uncertainty Modeling in Segmentation.

Scientific data·2026
Same author

Implant density reduction to avoid proximal junctional failure in adult spine surgery: Computer models and simulations.

North American Spine Society journal·2025
Same author

Calibration and Uncertainty for multiRater Volume Assessment in multiorgan Segmentation (CURVAS) challenge results.

Computers in biology and medicine·2025
Same author

JustRAIGS: Justified Referral in AI Glaucoma Screening Challenge.

IEEE transactions on medical imaging·2025
Same author

Meta-UNet: enhancing skin-lesion segmentation with multimodal feature integration and uncertainty estimation.

International journal of computer assisted radiology and surgery·2025

This study introduces a quantum-hybrid pipeline for lung nodule classification using vision transformers and quantum circuits. The novel method significantly reduces computational costs while maintaining high accuracy in medical image analysis.

Area of Science:

  • Medical Imaging
  • Quantum Computing
  • Artificial Intelligence

Background:

  • Lung nodules on CT scans require accurate classification for early diagnosis.
  • Traditional deep learning models can be computationally intensive for medical image analysis.
  • Hybrid quantum-classical approaches offer potential for improved efficiency and performance.

Purpose of the Study:

  • To develop and evaluate a novel quantum-hybrid pipeline for lung nodule classification.
  • To combine vision transformer (ViT) embeddings with quantum orthogonal pyramidal circuits (QOPCs).
  • To assess the computational efficiency and diagnostic accuracy of the proposed hybrid model.

Main Methods:

  • A quantum-hybrid pipeline integrating ViT embeddings with QOPCs was developed.
Keywords:
CT scanLung nodule classificationQuantum pyramidal circuitQuantum-hybrid classificationRBS gatesTrained ViT embeddings

Related Experiment Videos

Last Updated: May 27, 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

  • Two ViT configurations were tested, and features were reduced using principal component analysis.
  • The QOPC with reconfigurable beam splitter (RBS) gates was used for classification.
  • The approach was evaluated on 681 lung nodule CT scans across multiple planes.

    • Main Results:

    • The hybrid approach achieved unprecedented parameter compression (up to 1,470x) while preserving over 99% of baseline accuracy.
    • An accuracy of 83.7% was reached with only 46 trainable parameters, demonstrating high computational efficiency (CE up to 92.0).
    • Training acceleration of up to 28x was observed, with robust diagnostic performance (F1: 0.77-0.82, ROC-AUC: 0.87-0.90).
    • Ablation studies showed the quantum layer outperformed MLPs, and multi-view fusion improved accuracy to 85.4%.

    Conclusions:

    • Hybrid ViT-QOPC architectures represent a practical and resource-efficient framework for medical image analysis.
    • The proposed method significantly reduces computational cost without compromising clinical accuracy.
    • Quantum-hybrid models show promise for advancing AI in medical diagnostics, particularly in resource-constrained environments.