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: Nov 5, 2025

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

3.1K

Qutrit-Inspired Fully Self-Supervised Shallow Quantum Learning Network for Brain Tumor Segmentation.

Debanjan Konar, Siddhartha Bhattacharyya, Bijaya K Panigrahi

    IEEE Transactions on Neural Networks and Learning Systems
    |May 13, 2021
    PubMed
    Summary
    This summary is machine-generated.

    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

    IndiVNet A region adaptive semantic image segmentation for autonomous driving in unstructured environments.

    Scientific reports·2025
    Same author

    Alz-QNet: A quantum regression network for studying Alzheimer's gene interactions.

    Computers in biology and medicine·2025
    Same author

    3-D Quantum-Inspired Self-Supervised Tensor Network for Volumetric Segmentation of Medical Images.

    IEEE transactions on neural networks and learning systems·2023
    Same author

    Editorial: Assuring trustworthiness of autonomous systems as intelligent and ethical teammates.

    Frontiers in robotics and AI·2022
    Same author

    A deep fuzzy model for diagnosis of COVID-19 from CT images.

    Applied soft computing·2022
    Same author

    Prolificacy Assessment of Spermatozoan via State-of-the-Art Deep Learning Frameworks.

    IEEE access : practical innovations, open solutions·2022

    A new quantum neural network, the quantum fully self-supervised neural network (QFS-Net), offers improved brain MRI segmentation. This self-supervised model uses qutrits for faster, more accurate tumor detection with less computation.

    Area of Science:

    • Quantum Computing
    • Artificial Intelligence
    • Medical Imaging Analysis

    Background:

    • Classical self-supervised networks face convergence issues and reduced accuracy in segmentation tasks.
    • Quantum neural network models often utilize qubits or bilevel quantum bits.
    • Automated segmentation of medical images like brain MRIs is crucial for diagnostics.

    Purpose of the Study:

    • To introduce a novel self-supervised shallow learning network, the quantum fully self-supervised neural network (QFS-Net), for automated brain MR image segmentation.
    • To leverage a three-level qutrit-inspired quantum information system for enhanced network performance.
    • To address the limitations of classical self-supervised methods in segmentation accuracy and convergence.

    Main Methods:

    • Developed the QFS-Net model using a layered structure of qutrits interconnected via parametric Hadamard gates.

    More Related Videos

    Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
    09:53

    Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

    Published on: August 16, 2020

    7.4K

    Related Experiment Videos

    Last Updated: Nov 5, 2025

    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

    3.1K
    Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
    09:53

    Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

    Published on: August 16, 2020

    7.4K
  • Employed an eight-connected second-order neighborhood-based topology for qutrit interactions.
  • Utilized the nonlinear transformation of qutrit states for unsupervised state encoding and counterpropagation.

    • Main Results:

    • QFS-Net demonstrated promising segmented outcomes in detecting tumors on the Cancer Imaging Archive (TCIA) dataset, achieving high dice similarity and accuracy.
    • Experimental results were favorably compared against state-of-the-art supervised models (U-Net, URes-Net) and existing self-supervised quantum models (QIS-Net).
    • The model also showed robust segmentation performance on natural gray-scale images from the Berkeley segmentation dataset.

    Conclusions:

    • The proposed QFS-Net model offers a robust and efficient approach to automated image segmentation, particularly for brain MRIs.
    • QFS-Net achieves high accuracy with minimal human intervention and reduced computational resources compared to existing methods.
    • The qutrit-based quantum information system provides a powerful framework for developing advanced self-supervised learning models.