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 Videos

Optimizing Radiographic Diagnosis Through Signal-Balanced Convolutional Models.

Sakina Juzar Neemuchwala¹, Raja Hashim Ali^1,2, Qamar Abbas²

¹Innovation Hub-Machine Intelligence & Data Science (iHub-MInDS) Laboratory, University of Europe for Applied Sciences, 14469 Potsdam, Germany.

Journal of Imaging

|March 27, 2026

Summary

Related Concept Videos

Computed Tomography

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...

You might also read

Related Articles

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

Sort by

Same author

ML-driven quantum dots: novel HOXB13 imaging for porokeratosis with underlying squamous dysplasia associations.

Annals of medicine and surgery (2012)·2026

Same author

EXPRESS: Improvement in the Sensitivity and Reproducibility of Laser-Induced Soil Plasma Produced in a Microwave Environment.

Applied spectroscopy·2026

Same author

Transformational Catalytic Innovation Supports CO<sub>2</sub> Resource Utilization: Bridging Sustainability and Industrial Applications.

ChemistryOpen·2026

Same author

Design, synthesis, and anticancer activity of novel isocryptolepine 'aza' type acyl thiourea derivatives via combined experimental and computational approach.

Bioscience reports·2025

Same author

Epicardial adipose tissue: a potential biomarker and therapeutic target in patients with paradoxical low-gradient aortic stenosis and preserved ejection fraction.

Annals of medicine and surgery (2012)·2025

Same author

Classifying complex multimorbidity using latent class analysis and machine learning to generate insights into clustering of mental and cardiometabolic conditions.

PloS one·2025

Same journal

Human-AI Interaction in Interventional Radiology: A Narrative Review of Current Applications, Challenges, and Future Directions.

Journal of imaging·2026

Same journal

Coronary Artery Anomalies and Anatomical Variants: Cross-Sectional Diagnostic Imaging and Clinical Background.

Journal of imaging·2026

Same journal

YoLeTooth: A Unified Framework for Joint Tooth Segmentation and Periapical Lesion Detection in Panoramic Radiographs.

Journal of imaging·2026

Same journal

Radiomics-Guided Multi-Sequence Learning for Pathological Complete Response Prediction from Breast MRI with Missing Auxiliary Sequences.

Journal of imaging·2026

Same journal

Cutaneous Thermography in Arthropathies: Quantitative Imaging, Machine Learning, and Clinical Translation.

Journal of imaging·2026

Same journal

Two-Stage Dynamic Synergistic Segmentation Method for Myocardial Pathology.

Journal of imaging·2026

See all related articles

This summary is machine-generated.

This study introduces an explainable deep learning framework for chest X-ray analysis, improving diagnostic accuracy for pulmonary disorders. The signal-aware transfer learning approach enhances reliability and transparency in medical imaging.

Area of Science:

Medical Imaging
Artificial Intelligence
Radiology

Background:

Accurate chest radiograph interpretation is crucial for diagnosing pulmonary disorders.
Deep learning offers potential for enhancing diagnostic accuracy but often lacks transparency.
Integrating signal fidelity analysis with deep learning can improve reliability.

Purpose of the Study:

To develop an explainable deep learning framework for chest radiograph interpretation.
To enhance diagnostic reliability and transparency using signal fidelity analysis and transfer learning.
To evaluate the performance of different deep learning architectures on a large chest X-ray dataset.

Main Methods:

Utilized the COVID-19 Radiography Dataset (21,165 images) with four classes: COVID-19, Viral Pneumonia, Lung Opacity, and Normal.

Keywords:

EfficientNet Grad-CAM ResNet-50 biomedical signal processing deep learning explainable AI image classification multimedia analysis signal fidelity (SSIM)

Related Experiment Videos

Trained and evaluated baseline Convolutional Neural Network (CNN), ResNet-50, and EfficientNetB3 architectures.

Incorporated signal preservation verification using Structural Similarity Index Measure (SSIM) and explainability via Gradient-weighted Class Activation Mapping (Grad-CAM).

Main Results:

ResNet-50 achieved the highest classification accuracy (93.7%) and macro-AUC (0.97) on a class-balanced dataset.
EfficientNetB3 showed superior generalization with reduced parameter overhead.
Grad-CAM visualizations confirmed anatomically relevant activations, supporting clinical interpretability.

Conclusions:

The proposed explainable deep learning framework integrates signal fidelity metrics and transfer learning for reproducible medical image analysis.
This signal-aware approach supports reliable, transparent, and resource-efficient diagnostic decision-making in radiology.
The framework demonstrates potential for advancing AI applications in medical imaging beyond chest radiography.