Related Experiment Video
Updated: Jan 29, 2026
13:18
Network Pharmacology Prediction and Experimental Validation of Trichosanthes-Fritillaria thunbergii Action Mechanism Against Lung Adenocarcinoma
Published on: March 3, 2023
1.7K
Prognosis from Pixels: A Vendor-Protocol-Specific CT-Radiomics Model for Predicting Recurrence in Resected Lung
Abdalla Ibrahim1, Eduardo J Ortiz1, Stella T Tsui2
1Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA.
Cancers
|January 28, 2026
Summary
This study developed a CT radiomics model to predict 5-year recurrence in stage I lung adenocarcinoma patients after surgery. The model demonstrated high accuracy, showing potential for personalized treatment strategies in lung cancer patients.
Area of Science:
- Medical Imaging
- Oncology
- Radiomics
Background:
- Quantitative descriptors of tumor phenotype using radiomics are valuable but often limited by feature instability across different scanners and protocols.
- This study addresses the need for a reliable radiomics model by focusing on protocol-specific CT imaging.
- The goal is to predict 5-year recurrence in patients with stage I lung adenocarcinoma post-surgical resection.
Purpose of the Study:
- To develop and internally validate a protocol-specific CT-radiomics model.
- To predict 5-year recurrence in patients with stage I lung adenocarcinoma after complete surgical resection using preoperative imaging.
Main Methods:
- A retrospective study of 270 patients with completely resected stage I lung adenocarcinoma.
- Radiomic features were extracted from preoperative CT scans, followed by preprocessing to remove unstable features.
- XGBoost classifier trained using Recursive Feature Elimination and optimized hyperparameters, with Synthetic Minority Over-sampling Technique for class imbalance.
Main Results:
- Five radiomic features (Shape Sphericity, first-order 90Percentile, GLCM Autocorrelation, GLCM Cluster Shade, GLDM Large Dependence Low Gray Level Emphasis) significantly differed between recurrence groups.
- The CT-radiomics model achieved excellent discriminatory ability with AUC values of 0.99, 0.97, and 0.96 on training, validation, and test sets, respectively.
- The model demonstrated high performance on the test set: 100% sensitivity, 94% specificity, and 95% overall accuracy.
Conclusions:
- CT radiomics can accurately predict recurrence in patients with stage I lung adenocarcinoma under homogeneous imaging conditions.
- The developed protocol-specific model shows promise for clinical application in lung cancer management.
- Further external multi-vendor validation is recommended before widespread clinical deployment.
More Related Videos
Related Concept Videos
01:13Sensitivity, Specificity, and Predicted Value
1.3K
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
Sensitivity is the...
1.3K
02:27Predicting Molecular Geometry
45.7K
VSEPR Theory for Determination of Electron Pair Geometries
45.7K
01:47Lung Capacity
56.2K
The air in the lungs is measured in volumes and capacities. Lung volume measures reflect the amount of air taken in, released, or left over after a lung function, like a single inhalation. Lung capacity measures are sums of two or more lung volume measures.
56.2K
01:03Prediction Intervals
3.4K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
3.4K
01:07End Point Prediction: Gran Plot
1.2K
A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...
For potentiometric titration, the Gran plot is created by plotting...
1.2K
01:30Radiological Investigation I: X-ray and CT
1.1K
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
1.1K