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

Deep learning of CT imaging predicts PD-L1 expression and immunotherapy response in metastatic NSCLC: A multi-center study.

Cancer letters·2026
Same author

Subclinical immunometabolic perturbations in the neonatal lung following maternal microplastic exposure in mice.

Toxicology·2026
Same author

A multi-task masked autoencoder with GAN-based augmentation for PD-L1 prediction from chest CT images.

Scientific reports·2026
Same author

Hippo signaling pathway regulates branching morphogenesis of the fetal lung under hypoxia.

Pediatric research·2026
Same author

ASO Visual Abstract: CT-Based Prediction of Visceral Pleural Invasion in Lung Adenocarcinoma ≤ 3 cm: Enhancing Deep Learning Specificity by Waiving Chest Wall Information.

Annals of surgical oncology·2026
Same author

CT-based Prediction of Visceral Pleural Invasion in Lung Adenocarcinoma ≤ 3 cm: Enhancing Deep Learning Specificity by Waiving Chest Wall Information.

Annals of surgical oncology·2026

Related Experiment Video

Updated: Sep 5, 2025

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

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

Published on: May 19, 2023

2.0K

Solid Attenuation Components Attention Deep Learning Model to Predict Micropapillary and Solid Patterns in Lung

Li-Wei Chen1,2, Shun-Mao Yang1,3, Ching-Chia Chuang1

  • 1Department of Biomedical Engineering, College of Medicine and College of Engineering, National Taiwan University, Taipei, Taiwan.

Annals of Surgical Oncology
|July 5, 2022
PubMed
Summary
This summary is machine-generated.

Deep learning with solid attenuation component masks accurately predicts high-grade lung adenocarcinoma subtypes. This approach optimizes surgical strategy by improving preoperative diagnosis for better patient outcomes.

More Related Videos

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.6K
Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
03:38

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

306

Related Experiment Videos

Last Updated: Sep 5, 2025

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

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

Published on: May 19, 2023

2.0K
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.6K
Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
03:38

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

306

Area of Science:

  • Medical imaging and artificial intelligence in oncology.
  • Radiomics and deep learning for cancer subtyping.

Background:

  • High-grade lung adenocarcinoma subtypes (micropapillary, solid) treated with sublobar resection show poorer prognosis than lobectomy.
  • Accurate preoperative identification of these subtypes is crucial for optimizing surgical strategy.

Purpose of the Study:

  • To investigate the utility of incorporating solid attenuation component (SAC) masks with deep learning (DL) for predicting high-grade lung adenocarcinoma subtypes.
  • To enhance preoperative diagnostic accuracy for optimizing surgical planning.

Main Methods:

  • A deep learning model with SACs attention (SACA-DL) was developed using 502 patients with high-grade adenocarcinomas (2016-2020).
  • The model applied subregion masks based on solid attenuation components (tumor area ≥ -190 HU) to guide DL prediction.
  • Performance was evaluated using 5-fold cross-validation and external validation, comparing SACA-DL against DL without SACs attention, a radiomics model, and the consolidation/tumor ratio.

Main Results:

  • SACA-DL achieved an AUC of 0.91 in cross-validation and 0.93 in external validation.
  • These results were significantly superior to DL without SACs attention (AUCs 0.88/0.89), the radiomics model (AUCs 0.85/0.85), and the C/T ratio (AUCs 0.84/0.85).
  • The SACA-DL model demonstrated superior predictive performance for high-grade adenocarcinoma subtypes.

Conclusions:

  • Combining solid-attenuation-component-like subregion masks with deep learning models shows significant promise.
  • This approach enables accurate preoperative prediction of high-grade lung adenocarcinoma subtypes, aiding in surgical strategy optimization.