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

You might also read

Related Articles

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

Sort by
Same author

Medical Microwave Imaging Using Physics-Guided Deep Learning-Part 1: The Forward Solver.

IEEE transactions on medical imaging·2025
Same author

Calibrated Frequency-Division Distorted Born Iterative Tomography for Real-Life Head Imaging.

IEEE transactions on medical imaging·2021
Same author

Glucocorticoids impair bone formation of bone marrow stromal stem cells by reciprocally regulating microRNA-34a-5p.

Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA·2015
Same author

Measurements of Elliptic and Triangular Flow in High-Multiplicity 3He+Au Collisions at √(s(NN))=200 GeV.

Physical review letters·2015
Same author

Isolation and expression analysis of four HD-ZIP III family genes targeted by microRNA166 in peach.

Genetics and molecular research : GMR·2015
Same author

An evaluation of motor evoked potential surrogate endpoints during intracranial vascular procedures.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2015

Related Experiment Video

Updated: Jan 17, 2026

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

9.3K

Medical Microwave Imaging Using Physics-Guided Deep Learning-Part 2: The Inverse Solver.

L Guo, A Bialkowski, A Abbosh

    IEEE Transactions on Medical Imaging
    |January 14, 2026
    PubMed
    Summary
    This summary is machine-generated.

    A novel deep learning approach inspired by the distorted Born iterative method (DBIM) improves medical microwave tomography. This method accurately reconstructs abnormal tissues, overcoming limitations of current deep learning techniques for better diagnostic accuracy.

    More Related Videos

    PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
    10:48

    PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

    Published on: December 28, 2017

    9.9K
    Magnetic Resonance-Guided Stereotaxy for Infusions to the Pig Brain
    08:23

    Magnetic Resonance-Guided Stereotaxy for Infusions to the Pig Brain

    Published on: March 31, 2023

    3.0K

    Related Experiment Videos

    Last Updated: Jan 17, 2026

    Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
    14:14

    Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

    Published on: August 12, 2018

    9.3K
    PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
    10:48

    PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator

    Published on: December 28, 2017

    9.9K
    Magnetic Resonance-Guided Stereotaxy for Infusions to the Pig Brain
    08:23

    Magnetic Resonance-Guided Stereotaxy for Infusions to the Pig Brain

    Published on: March 31, 2023

    3.0K

    Area of Science:

    • Medical Imaging
    • Computational Electromagnetics
    • Artificial Intelligence

    Background:

    • Conventional medical microwave tomography suffers from ill-posed problems and high computational costs.
    • Current deep learning methods in this field may miss critical details, leading to potential misdiagnosis.
    • Existing physics-guided deep learning approaches often struggle with detecting abnormal tissues effectively.

    Purpose of the Study:

    • To develop a deep neural network that overcomes the limitations of current methods in medical microwave tomography.
    • To improve the detection and reconstruction of abnormal tissues in medical microwave imaging.
    • To provide a theoretical basis for the failure of existing iterative physics-guided deep learning algorithms.

    Main Methods:

    • A deep neural network inspired by the distorted Born iterative method (DBIM) was developed, avoiding the use of Green's function.
    • The network comprises forward neural network solvers and inverse neural network blocks for dielectric contrast updating.
    • Training utilized a hybrid loss function (two supervised, one self-supervised) within a sequential iterative framework emulating DBIM.

    Main Results:

    • The proposed method demonstrated significant enhancements in accuracy compared to existing deep learning algorithms.
    • Quantitative assessments showed improvements in relative error (19%), structure similarity (18%), Dice coefficient (40%), and Hausdorff distance (72%).
    • The network accurately reconstructs abnormal tissues masked by signals from healthy tissues by calculating electrical property perturbations.

    Conclusions:

    • The proposed DBIM-inspired deep learning method offers a robust solution for medical microwave tomography.
    • This approach enhances the detection of subtle abnormalities, improving diagnostic reliability in clinical settings.
    • The findings suggest this method is more suitable for real-life clinical applications than current deep learning techniques.