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 28, 2026

Three-Dimensional Reconstruction for the Whole Lung with Early Multiple Pulmonary Nodules

Three-Dimensional Reconstruction for the Whole Lung with Early Multiple Pulmonary Nodules

Published on: October 13, 2023

RNNet-MST: A ResNet-50 with Multi-Scale Transformer Blocks for Pulmonary Nodule Classification and Attention-Based

Edrill F Bilan¹, Emman T Manduriaga¹, Hernando S Salapare^2,3

¹College of Information Systems and Technology, Pamantasan ng Lungsod ng Maynila, Manila 1002, Philippines.

Diagnostics (Basel, Switzerland)

|May 27, 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

Molecular docking and dynamics simulations of aptamers for sandwich-type detection of <i>Trichomonas vaginalis</i>.

In silico pharmacology·2026

Same author

Ultrasensitive detection of oral cancer biomarkers CD63 and CD44 in exosomes using janus particles: a rotational diffusometry-based assay.

The Saudi dental journal·2026

Same author

Learnable Context in Multiple Instance Learning for Whole Slide Image Classification and Segmentation.

Journal of imaging informatics in medicine·2024

Same author

Response of Osteoblasts on Amine-Based Nanocoatings Correlates with the Amino Group Density.

Molecules (Basel, Switzerland)·2023

Same author

COVID-19 and Virtual Nutrition: A Pilot Study of Integrating Digital Food Models for Interactive Portion Size Education.

Nutrients·2022

Same author

Cupric Oxide Nanostructures from Plasma Surface Modification of Copper.

Biomimetics (Basel, Switzerland)·2019

Same journal

Correction: Luca et al. Global and Regional Diagnostic Results of Progress Toward Cervical Cancer Elimination, According to the WHO Strategy: A Systematic Literature Review with Narrative Synthesis. <i>Diagnostics</i> 2026, <i>16</i>, 1224.

Diagnostics (Basel, Switzerland)·2026

Same journal

Association Between Systemic Inflammatory Response Biomarkers and Disease Activity in Systemic Lupus Erythematosus: A Multi-Center Retrospective Study.

Diagnostics (Basel, Switzerland)·2026

Same journal

Vertebrogenic Low Back Pain and Basivertebral Nerve Ablation: A Review of Mechanisms, Imaging-Driven Selection, and Clinical Outcomes.

Diagnostics (Basel, Switzerland)·2026

Same journal

Multivalvular Carcinoid Heart Disease: The Role of Echocardiography in Diagnosis and Selection for Heterotopic Bicaval Valve Implantation.

Diagnostics (Basel, Switzerland)·2026

Same journal

Data-Efficient and Explainable Multimodal Survival Prediction in NSCLC Using Deep Image Embeddings, Clinical Variables, and Gradient-Boosted Trees.

Diagnostics (Basel, Switzerland)·2026

Same journal

Anomalous Left Coronary Artery from the Pulmonary Artery: Cinematic Volume Rendering Technique for Enhanced Anatomic Visualization.

Diagnostics (Basel, Switzerland)·2026

See all related articles

This summary is machine-generated.

This study introduces RNNet-MST, a deep learning model that enhances lung nodule detection on chest X-rays (CXRs), improving early lung cancer diagnosis and reducing missed cases in resource-limited settings.

Area of Science:

Artificial Intelligence
Medical Imaging Analysis
Deep Learning for Healthcare

Background:

Early lung cancer detection is crucial for survival but challenged by radiologist workload and chest X-ray (CXR) complexity.
Missed pulmonary nodules and false-negative diagnoses are significant issues, particularly in resource-constrained regions like the Philippines.
Developing advanced AI tools is essential to improve diagnostic accuracy in medical imaging.

Purpose of the Study:

To develop an enhanced deep learning model, RNNet-MST, for improved nodule classification and localization sensitivity in chest X-rays.
To leverage Multi-Scale Transformer blocks and spatial attention mechanisms for better global context modeling and disease-relevant region identification.
To reduce false-negative diagnoses and enhance early lung cancer detection capabilities.

Keywords:

RNNet-MST ResNet-50 chest X-ray analysis computer-aided detection deep learning false negative reduction pulmonary nodule classification pulmonary nodule detection spatial attention mechanism transformers

More Related Videos

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

Related Experiment Videos

Last Updated: May 28, 2026

Three-Dimensional Reconstruction for the Whole Lung with Early Multiple Pulmonary Nodules

Three-Dimensional Reconstruction for the Whole Lung with Early Multiple Pulmonary Nodules

Published on: October 13, 2023

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

Main Methods:

Proposed RNNet-MST, an extension of ResNet-50, integrating Multi-Scale Transformer blocks and a custom spatial attention mechanism.
Trained and evaluated the model on the NODE21 chest X-ray dataset.
Compared RNNet-MST performance against a baseline ResNet-50 using classification metrics and attention map analysis for weak localization.

Main Results:

RNNet-MST demonstrated superior performance over the baseline ResNet-50 across key metrics.
Achieved improved Mean Nodule Recall (91.55 ± 1.41%), Mean Test Precision (90.46 ± 0.99%), and Mean Nodule F1-Score (90.99 ± 0.39%).
Showcased a significant 12.3% improvement in sensitivity for detecting small nodules.

Conclusions:

The integration of multi-scale transformer features and attention mechanisms enhances classification sensitivity and localization accuracy.
RNNet-MST shows promise as a diagnostic support tool for early lung cancer detection.
Further validation on diverse datasets is recommended to support its clinical application in reducing perceptual errors.