What question did this study set out to answer?

This research aims to evaluate the effectiveness of various dimensionality reduction and feature selection methods in classifying lung adenocarcinomas based on IASLC grading.

March 2, 2026Open Access

Robustness and Accuracy of Radiomics Models for Classifying IASLC Grading in Lung Adenocarcinomas: A Comprehensive Analysis of a Large Multicenter CT Database

Key Points

This research aims to evaluate the effectiveness of various dimensionality reduction and feature selection methods in classifying lung adenocarcinomas based on IASLC grading.
Conducted analytical comparison of dimensionality reduction and feature selection techniques.
Utilized T-test, Pearson correlation, and LASSO for dimensionality reduction, comparing with PCA.
Employed various machine learning algorithms for feature selection, including LR, RF, GBC, XGBoost, LGBM, and CatBoost.
Evaluated diagnostic efficacy using receiver operating characteristic curves and calculated area under the curve.
AUC for PCA-based methods ranged from 0.502 to 0.719.
T-test, Pearson, and LASSO methods combined improved AUC from 0.818 to 0.869.
LGBM achieved the highest performance with an AUC of 0.869, while LR had the lowest with an AUC of 0.818.

Abstract

IntroductionAccurate preoperative prediction of the International Association for the Study of Lung Cancer (IASLC) grading is crucial for developing individualized management and surgical strategies in lung adenocarcinomas (LUAD). Computed tomography (CT) radiomics serves as an important imaging biomarker for classification tasks in LUAD. However, the robustness and accuracy of radiomics models remain subjects of ongoing debate.MethodsIn this study, we conducted an analytical comparison of two critical steps in radiomics: dimensionality reduction and feature selection, aiming to differentiate between Grade 1 and Grade 2-3 tumors according to the preoperative IASLC grading system for LUAD. 1) For dimensionality reduction, we sequentially combined the T-test, Pearson correlation, and Least Absolute Shrinkage and Selection Operator (LASSO), while considering principal component analysis (PCA) for comparison. 2) For feature selection, we utilized various machine learning (ML) techniques including Logistic Regression (LR), Random Forest (RF), Gradient Boosting (GBC), XGBoost, Light Gradient Boosting Machine (LGBM), and Categorical Boosting (CatBoost). The diagnostic efficacy was evaluated using receiver operating characteristic curve (ROC) and the corresponding area under the curve (AUC).Result: The AUC for PCA combined with various ML feature selection methods ranged from 0.502 to 0.719 in this classification task. In contrast, the AUC for the combined T-test, Pearson, and LASSO dimensionality reduction methods, along with various ML feature selection methods, significantly increased from 0.818 to 0.869. Among these, the LGBM achieved the highest performance, reaching an AUC of 0.869, while LR displayed the lowest performance with an AUC of 0.818.ConclusionWe demonstrated that the T-test→Pearson→LASSO approach is more appropriate for radiomics feature dimensionality reduction compared to PCA. Additionally, we improved the commonly used LR feature selection method in medical research by employing the more advanced LGBM for distinguishing between Grade 1 and Grade 2-3 tumors in accordance with the preoperative IASLC grading system for LUAD.

Read Full Paperexternally

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper