A Genetic Programming Approach to Radiomic-Based Feature Construction for Survival Prediction in Non-Small Cell Lung Cancer

被引:1
作者
Scalco, Elisa [1 ]
Gomez-Flores, Wilfrido [2 ]
Rizzo, Giovanna [3 ]
机构
[1] Italian Natl Res Council, Inst Biomed Technol, Via Fratelli Cervi 93, I-20054 Segrate, Italy
[2] Ctr Invest & Estudios Avanzados IPN, Unidad Tamaulipas, Km 5-5 Carretera Cd Victoria Soto Marina,Parque Ci, Ciudad Victoria 87138, Mexico
[3] Italian Natl Res Council, Inst Intelligent Ind Technol & Syst, Via Alfonso Corti 12, I-20133 Milan, Italy
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 16期
关键词
computer tomography; feature construction; genetic programming; radiomics; non-small cell lung cancer; CLASSIFICATION; INFORMATION; 2D;
D O I
10.3390/app14166923
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Machine learning (ML) is commonly used to develop survival-predictive radiomic models in non-small cell lung cancer (NSCLC) patients, which helps assist treatment decision making. Radiomic features derived from computer tomography (CT) lung images aim to capture quantitative tumor characteristics. However, these features are determined by humans, which poses a risk of including irrelevant or redundant variables, thus reducing the model's generalization. To address this issue, we propose using genetic programming (GP) to automatically construct new features with higher discriminant power than the original radiomic features. To achieve this goal, we introduce a fitness function that measures the classification performance ratio of output to input. The constructed features are then input for various classifiers to predict the two-year survival of NSCLC patients from two public CT datasets. Our approach is compared against two popular feature selection methods in radiomics to choose relevant radiomic features, and two GP-based feature construction methods whose fitness functions are based on measuring the constructed features' quality. The experimental results show that survival prediction models trained on GP-based constructed features outperform feature selection methods. Also, maximizing the classification performance gain output-to-input ratio produces features with higher discriminative power than only maximizing the classification accuracy from constructed features. Furthermore, a survival analysis demonstrated statistically significant differences between survival and non-survival groups in the Kaplan-Meier curves. Therefore, the proposed approach can be used as a complementary method for oncologists in determining the clinical management of NSCLC patients.
引用
收藏
页数:19
相关论文
共 55 条
[41]   Survival Prediction of Lung Cancer Using Small-Size Clinical Data with a Multiple Task Variational Autoencoder [J].
Thanh-Hung Vo ;
Lee, Guee-Sang ;
Yang, Hyung-Jeong ;
Oh, In-Jae ;
Kim, Soo-Hyung ;
Kang, Sae-Ryung .
ELECTRONICS, 2021, 10 (12)
[42]   Genetic programming for automatic skin cancer image classification [J].
Ul Ain, Qurrat ;
Al-Sahaf, Harith ;
Xue, Bing ;
Zhang, Mengjie .
EXPERT SYSTEMS WITH APPLICATIONS, 2022, 197
[43]   A Genetic Programming Approach to Feature Construction for Ensemble Learning in Skin Cancer Detection [J].
Ul Ain, Qurrat ;
Al-Sahaf, Harith ;
Xue, Bing ;
Zhang, Mengjie .
GECCO'20: PROCEEDINGS OF THE 2020 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, 2020, :1186-1194
[44]   A Multi-tree Genetic Programming Representation for Melanoma Detection Using Local and Global Features [J].
Ul Ain, Qurrat ;
Al-Sahaf, Harith ;
Xue, Bing ;
Zhang, Mengjie .
AI 2018: ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, 11320 :111-123
[45]   Computational Radiomics System to Decode the Radiographic Phenotype [J].
van Griethuysen, Joost J. M. ;
Fedorov, Andriy ;
Parmar, Chintan ;
Hosny, Ahmed ;
Aucoin, Nicole ;
Narayan, Vivek ;
Beets-Tan, Regina G. H. ;
Fillion-Robin, Jean-Christophe ;
Pieper, Steve ;
Aerts, Hugo J. W. L. .
CANCER RESEARCH, 2017, 77 (21) :E104-E107
[46]  
Vanneschi L., 2021, Machine Learning for Survival Prediction in Breast Cancer
[47]   Risk Score Generated from CT-Based Radiomics Signatures for Overall Survival Prediction in Non-Small Cell Lung Cancer [J].
Viet-Huan Le ;
Quang-Hien Kha ;
Truong Nguyen Khanh Hung ;
Nguyen Quoc Khanh Le .
CANCERS, 2021, 13 (14)
[48]   Feature Selection for Maximizing the Area Under the ROC Curve [J].
Wang, Rui ;
Tang, Ke .
2009 IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW 2009), 2009, :400-405
[49]   A prognostic analysis method for non-small cell lung cancer based on the computed tomography radiomics [J].
Wang, Xu ;
Duan, Huihong ;
Li, Xiaobing ;
Ye, Xiaodan ;
Huang, Gang ;
Nie, Shengdong .
PHYSICS IN MEDICINE AND BIOLOGY, 2020, 65 (04)
[50]   Vulnerabilities of radiomic signature development: The need for safeguards [J].
Welch, Mattea L. ;
McIntosh, Chris ;
Haibe-Kains, Benjamin ;
Milosevic, Michael F. ;
Wee, Leonard ;
Dekker, Andre ;
Huang, Shao Hui ;
Purdie, Thomas G. ;
O'Sullivan, Brian ;
Aerts, Hugo J. W. L. ;
Jaffray, David A. .
RADIOTHERAPY AND ONCOLOGY, 2019, 130 :2-9