Multi-objective radiomics model for predicting distant failure in lung SBRT

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Stereotactic body radiation therapy (SBRT) has demonstrated high local control rates in early stage non-small cell lung cancer patients who are not ideal surgical candidates. However, distant failure after SBRT is still common. For patients at high risk of early distant failure after SBRT treatment, additional systemic therapy may reduce the risk of distant relapse and improve overall survival. Therefore, a strategy that can correctly stratify patients at high risk of failure is needed. The field of radiomics holds great potential in predicting treatment outcomes by using high-throughput extraction of quantitative imaging features. The construction of predictive models in radiomics is typically based on a single objective such as overall accuracy or the area under the curve (AUC). However, because of imbalanced positive and negative events in the training datasets, a single objective may not be ideal to guide model construction. To overcome these limitations, we propose a multi-objective radiomics model that simultaneously considers sensitivity and specificity as objective functions. To design a more accurate and reliable model, an iterative multi-objective immune algorithm (IMIA) was proposed to optimize these objective functions. The multi-objective radiomics model is more sensitive than the single-objective model, while maintaining the same levels of specificity and AUC. The IMIA performs better than the traditional immune-inspired multi-objective algorithm.

Original languageEnglish (US)
Pages (from-to)4460-4478
Number of pages19
JournalPhysics in Medicine and Biology
Volume62
Issue number11
DOIs
StatePublished - May 8 2017

Fingerprint

Radiotherapy
Lung
Area Under Curve
Non-Small Cell Lung Carcinoma
Recurrence
Sensitivity and Specificity
Survival
Therapeutics
Datasets

Keywords

  • lung SBRT
  • multi-objective learning
  • pareto-optimal solution
  • radiomics

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging

Cite this

@article{223caaf84c594214860aa2eb1407a265,
title = "Multi-objective radiomics model for predicting distant failure in lung SBRT",
abstract = "Stereotactic body radiation therapy (SBRT) has demonstrated high local control rates in early stage non-small cell lung cancer patients who are not ideal surgical candidates. However, distant failure after SBRT is still common. For patients at high risk of early distant failure after SBRT treatment, additional systemic therapy may reduce the risk of distant relapse and improve overall survival. Therefore, a strategy that can correctly stratify patients at high risk of failure is needed. The field of radiomics holds great potential in predicting treatment outcomes by using high-throughput extraction of quantitative imaging features. The construction of predictive models in radiomics is typically based on a single objective such as overall accuracy or the area under the curve (AUC). However, because of imbalanced positive and negative events in the training datasets, a single objective may not be ideal to guide model construction. To overcome these limitations, we propose a multi-objective radiomics model that simultaneously considers sensitivity and specificity as objective functions. To design a more accurate and reliable model, an iterative multi-objective immune algorithm (IMIA) was proposed to optimize these objective functions. The multi-objective radiomics model is more sensitive than the single-objective model, while maintaining the same levels of specificity and AUC. The IMIA performs better than the traditional immune-inspired multi-objective algorithm.",
keywords = "lung SBRT, multi-objective learning, pareto-optimal solution, radiomics",
author = "Zhiguo Zhou and Michael Folkert and Puneeth Iyengar and Kenneth Westover and Yuanyuan Zhang and Hak Choy and Robert Timmerman and Steve Jiang and Jing Wang",
year = "2017",
month = "5",
day = "8",
doi = "10.1088/1361-6560/aa6ae5",
language = "English (US)",
volume = "62",
pages = "4460--4478",
journal = "Physics in Medicine and Biology",
issn = "0031-9155",
publisher = "IOP Publishing Ltd.",
number = "11",

}

TY - JOUR

T1 - Multi-objective radiomics model for predicting distant failure in lung SBRT

AU - Zhou, Zhiguo

AU - Folkert, Michael

AU - Iyengar, Puneeth

AU - Westover, Kenneth

AU - Zhang, Yuanyuan

AU - Choy, Hak

AU - Timmerman, Robert

AU - Jiang, Steve

AU - Wang, Jing

PY - 2017/5/8

Y1 - 2017/5/8

N2 - Stereotactic body radiation therapy (SBRT) has demonstrated high local control rates in early stage non-small cell lung cancer patients who are not ideal surgical candidates. However, distant failure after SBRT is still common. For patients at high risk of early distant failure after SBRT treatment, additional systemic therapy may reduce the risk of distant relapse and improve overall survival. Therefore, a strategy that can correctly stratify patients at high risk of failure is needed. The field of radiomics holds great potential in predicting treatment outcomes by using high-throughput extraction of quantitative imaging features. The construction of predictive models in radiomics is typically based on a single objective such as overall accuracy or the area under the curve (AUC). However, because of imbalanced positive and negative events in the training datasets, a single objective may not be ideal to guide model construction. To overcome these limitations, we propose a multi-objective radiomics model that simultaneously considers sensitivity and specificity as objective functions. To design a more accurate and reliable model, an iterative multi-objective immune algorithm (IMIA) was proposed to optimize these objective functions. The multi-objective radiomics model is more sensitive than the single-objective model, while maintaining the same levels of specificity and AUC. The IMIA performs better than the traditional immune-inspired multi-objective algorithm.

AB - Stereotactic body radiation therapy (SBRT) has demonstrated high local control rates in early stage non-small cell lung cancer patients who are not ideal surgical candidates. However, distant failure after SBRT is still common. For patients at high risk of early distant failure after SBRT treatment, additional systemic therapy may reduce the risk of distant relapse and improve overall survival. Therefore, a strategy that can correctly stratify patients at high risk of failure is needed. The field of radiomics holds great potential in predicting treatment outcomes by using high-throughput extraction of quantitative imaging features. The construction of predictive models in radiomics is typically based on a single objective such as overall accuracy or the area under the curve (AUC). However, because of imbalanced positive and negative events in the training datasets, a single objective may not be ideal to guide model construction. To overcome these limitations, we propose a multi-objective radiomics model that simultaneously considers sensitivity and specificity as objective functions. To design a more accurate and reliable model, an iterative multi-objective immune algorithm (IMIA) was proposed to optimize these objective functions. The multi-objective radiomics model is more sensitive than the single-objective model, while maintaining the same levels of specificity and AUC. The IMIA performs better than the traditional immune-inspired multi-objective algorithm.

KW - lung SBRT

KW - multi-objective learning

KW - pareto-optimal solution

KW - radiomics

UR - http://www.scopus.com/inward/record.url?scp=85019979324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019979324&partnerID=8YFLogxK

U2 - 10.1088/1361-6560/aa6ae5

DO - 10.1088/1361-6560/aa6ae5

M3 - Article

C2 - 28480871

AN - SCOPUS:85019979324

VL - 62

SP - 4460

EP - 4478

JO - Physics in Medicine and Biology

JF - Physics in Medicine and Biology

SN - 0031-9155

IS - 11

ER -