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

Search research articles

Related Experiment Video

Updated: May 5, 2026

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

Physics-Guided Deep Learning for Interpretable Biomedical Image Reconstruction and Pattern Recognition in Diagnostic

Akeel Qadir^1,2, Saad Arif³, Prajoona Valsalan⁴

¹School of Information Engineering, Xi'an Eurasia University, Xi'an 710065, China.

Bioengineering (Basel, Switzerland)

|May 4, 2026

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

Performance analysis of a biomass gasification combined cycle power plant using rice husk and sugarcane bagasse with circular utilization of ash in green concrete.

Scientific reports·2026

Same author

Enhancing mechanical performance, durability, and environmental impact assessment of green concrete incorporating industrial and agricultural wastes.

Scientific reports·2026

Same author

Flexible Surface Acoustic Wave (SAW) Magnetic Sensor Based on Terfenol-D Grating-Arrayed Thin Polymer Film.

Micromachines·2026

Same author

AI-Driven Hybrid Detection and Classification Framework for Secure Sleep Health IoT Networks.

Clocks & sleep·2026

Same author

Machine learning-driven evaluation of mechanical and microstructural properties of agro-waste-derived geopolymer concrete.

Scientific reports·2026

Same author

Exploring multi-feedstock biodiesel-hydrogen synergies for enhanced diesel engine performance using hybrid AI techniques.

Scientific reports·2026

Same journal

Correction: Komatsu et al. Three-Dimensional Visualization and Detection of the Pulmonary Venous-Left Atrium Connection Using Artificial Intelligence in Fetal Cardiac Ultrasound Screening. <i>Bioengineering</i> 2026, <i>13</i>, 100.

Bioengineering (Basel, Switzerland)·2026

Same journal

Comparison of CO<sub>2</sub> Laser and Microdebrider in the Surgical Treatment of Pediatric Recurrent Respiratory Papillomatosis: A Retrospective Analysis.

Bioengineering (Basel, Switzerland)·2026

Same journal

Toward More Translational Tumor Models: Breast dECM-Based 3D Systems Capture Native Microenvironmental Cues.

Bioengineering (Basel, Switzerland)·2026

Same journal

Postural Stability Changes During the 4 Phases of the Half Squat: Kinematics Profile of the Center of Pressure and Center of Mass in High-Performance Weightlifters-A Pilot Study.

Bioengineering (Basel, Switzerland)·2026

Same journal

Definite Implant Position as Novel Readout for Effectiveness of Ridge Preservation Indicates to Beneficial Effect of Combined Treatment with Platelet-Rich Fibrin (PRF) and Xenogenic Biomaterial in Bone Regeneration.

Bioengineering (Basel, Switzerland)·2026

Same journal

Trueness and Precision of Intraoral Scanners for 3D-Printed Orthodontic Models with Attachments: An In Vitro Comparative Study.

Bioengineering (Basel, Switzerland)·2026

See all related articles

This summary is machine-generated.

This study presents a physics-guided deep learning model for biomedical imaging, improving diagnostic accuracy and offering explainable AI. The framework enhances image reconstruction and pattern recognition for clinical decision support.

Area of Science:

Biomedical Imaging
Artificial Intelligence
Deep Learning

Background:

Traditional artificial intelligence (AI) in biomedical imaging often acts as a 'black box', limiting clinical interpretation and diagnostic accuracy.
Integrating physical principles into AI models can enhance transparency and robustness in medical image analysis.

Purpose of the Study:

To introduce a physics-guided deep learning architecture for biomedical image simulation, reconstruction, and pattern recognition.
To address the limitations of traditional AI by providing an explainable AI pathway for enhanced diagnostic accuracy and clinical interpretation.

Main Methods:

Developed a novel deep learning architecture that explicitly integrates physical priors into the learning model.
Evaluated the framework using systematic simulation studies with complex geometric configurations, multimodal physical fields, and noise-corrupted synthetic 3D brain volumes.

Keywords:

AI-assisted diagnostic workflows automated disease classification biomedical image reconstruction clinical decision support systems deep learning-based image segmentation explainable artificial intelligence physics-informed deep learning predictive imaging biomarkers radiomics-based feature extraction translational medical imaging

Related Experiment Videos

Last Updated: May 5, 2026

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

Conducted volumetric brain experiments to assess performance in functional imaging and disease prognosis.

Main Results:

Achieved significant improvements in reconstruction fidelity, with peak signal-to-noise ratio (PSNR) up to 47 dB and structural similarity index exceeding 0.90.
Demonstrated robust performance under moderate noise levels (0.05), maintaining a PSNR greater than 32 dB, crucial for computer-aided diagnosis.
Reported a 38-44% reduction in activation localization errors in volumetric brain experiments, indicating utility in functional imaging.

Conclusions:

The physics-guided deep learning framework offers a transparent and robust solution for automated disease classification and advanced biomedical imaging tasks.
Grounding deep learning in physical constraints enhances the reliability and interpretability of AI in clinical decision support systems.
The proposed architecture shows significant potential for improving the accuracy and efficiency of diagnostic processes in clinical settings.