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

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

Prognostic value of ROS1 rearrangement in lung adenocarcinoma stratified by clinicopathologic and radiological features: a retrospective cohort study.

Translational lung cancer research·2026

Same author

Occupational physical workload and risk of lung cancer and chronic respiratory diseases: a prospective cohort study of the UK Biobank.

Translational lung cancer research·2026

Same author

Real-World Outcomes of Induction Immunochemotherapy Followed by Surgery for Advanced Non-Small Cell Lung Cancer.

International journal of cancer·2026

Same author

Understanding Public Perceptions of Lung Cancer in China: Infodemiology Study of Baidu Index and Weibo Posts.

Journal of medical Internet research·2026

Same author

Totally Video-Assisted Thoracoscopic Surgery for Lung Transplantation: A Case Series.

Transplant international : official journal of the European Society for Organ Transplantation·2026

Same author

Author Correction: A proteogenomic atlas of 1032 brain metastases identifies molecular subtypes, immune landscapes, and therapeutic vulnerabilities.

Nature communications·2026

Same journal

Development and experimental characterization of a cadaveric stance simulator for residual limb biomechanics.

Medical engineering & physics·2026

Same journal

Rapid personalized computational modeling of the wrist.

Medical engineering & physics·2026

Same journal

SHAP-enabled explainable AI framework for clinical interpretation of valvular heart diseases via digital acoustic features.

Medical engineering & physics·2026

Same journal

Three-dimensional motion analysis of a total wrist prosthesis during the dart-throwing motion: a cadaveric study.

Medical engineering & physics·2026

Same journal

Patient-specific left ventricular hypertrophy under severe hypertension: mechanistic insights from Hill-type computational simulations.

Medical engineering & physics·2026

Same journal

Enabling laboratory-based personalization of musculoskeletal spine models: a standardized rail-guided ultrasound method.

Medical engineering & physics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 10, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Automatically predicting lung tumor invasiveness using deep neural networks.

Xiuyuan Xu¹, Nan Chen², Zongxuan Jin¹

¹Department of Computer Science, Sichuan University, No. 24 South Section 1, Yihuan Road, Chengdu, 610065, Sichuan, China.

Medical Engineering & Physics

|August 20, 2025

Summary

This summary is machine-generated.

Accurate lung tumor invasiveness prediction is crucial for early lung cancer treatment. A new AI system, LTI-Net, effectively classifies lung tumors using CT scans, overcoming data challenges and improving diagnostic accuracy.

Keywords:

Intelligent system Lung tumor invasiveness Pulmonary adenocarcinomas

More Related Videos

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

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

Published on: October 13, 2023

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

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

Published on: May 19, 2023

Related Experiment Videos

Last Updated: Sep 10, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

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

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

Published on: October 13, 2023

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

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

Published on: May 19, 2023

Area of Science:

Medical Imaging
Artificial Intelligence
Oncology

Background:

Early detection of lung cancer invasiveness is critical for patient outcomes.
Current clinical methods for lung tumor invasiveness (LTI) detection are challenging and invasive.
Limited public datasets and class imbalance hinder the development of automated LTI prediction algorithms.

Purpose of the Study:

To develop a novel artificial intelligence system for non-invasive lung tumor invasiveness prediction using computed tomography (CT) data.
To address the challenges of limited data availability and class imbalance in automated LTI detection.
To improve the diagnostic performance of lung tumor invasiveness classification.

Main Methods:

Collected and curated a large, high-quality computed tomography dataset from 804 patients, with binary labels based on post-surgical pathological reports.
Developed the lung tumor invasiveness prediction neural network (LTI-Net), utilizing a 3D residual neural network backbone to analyze intra-tumor heterogeneity from CT values.
Introduced a novel surrogate function to approximate the Area Under the Curve (AUC) metric, enhancing feature discrimination and stable optimization through paired sample training.

Main Results:

The LTI-Net system demonstrated significant potential in classifying lung tumor invasiveness on the collected dataset.
LTI-Net achieved a notable improvement in the harmonic mean of true positives and true negatives rate (HMoPN) compared to existing state-of-the-art methods.
The proposed method showed a 2.92% increase in HMoPN score across various imbalanced data settings, highlighting its robustness.

Conclusions:

The developed LTI-Net provides an effective non-invasive approach for lung tumor invasiveness prediction using CT imaging.
The system successfully addresses data limitations and class imbalance issues prevalent in this field.
LTI-Net offers a promising advancement for improving early lung cancer diagnosis and treatment planning.