Reinforcement learning-based control of tumor growth under anti-angiogenic therapy

Parisa Yazdjerdi, Nader Meskin, Mohammad Al-Naemi, Ala Eddin Al Moustafa, L. Kovács

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Background and objectives: In recent decades, cancer has become one of the most fatal and destructive diseases which is threatening humans life. Accordingly, different types of cancer treatment are studied with the main aim to have the best treatment with minimum side effects. Anti-angiogenic is a molecular targeted therapy which can be coupled with chemotherapy and radiotherapy. Although this method does not eliminate the whole tumor, but it can keep the tumor size in a given state by preventing the formation of new blood vessels. In this paper, a novel model-free method based on reinforcement learning (RL) framework is used to design a closed-loop control of anti-angiogenic drug dosing administration. Methods: A Q-learning algorithm is developed for the drug dosing closed-loop control. This controller is designed using two different values of the maximum drug dosage to reduce the tumor volume up to a desired value. The mathematical model of tumor growth under anti-angiogenic inhibitor is used to simulate a real patient. Results: The effectiveness of the proposed method is shown through in silico simulation and its robustness to patient parameters variation is demonstrated. It is demonstrated that the tumor reaches its minimal volume in 84 days with maximum drug inlet of 30 mg/kg/day. Also, it is shown that the designed controller is robust with respect to ± 20% of tumor growth parameters changes. Conclusion: The proposed closed-loop reinforcement learning-based controller for cancer treatment using anti-angiogenic inhibitor provides an effective and novel result such that with a clinically valid and safe dosage of drug, the volume reduces up to 1mm 3 in a reasonable short period compared to the literature.

Original languageEnglish
Pages (from-to)15-26
Number of pages12
JournalComputer Methods and Programs in Biomedicine
Volume173
DOIs
Publication statusPublished - May 1 2019

Fingerprint

Reinforcement learning
Tumors
Learning
Growth
Angiogenesis Inhibitors
Neoplasms
Oncology
Controllers
Drug dosage
Therapeutics
Pharmaceutical Preparations
Chemotherapy
Blood vessels
Radiotherapy
Molecular Targeted Therapy
Learning algorithms
Reinforcement (Psychology)
Tumor Burden
Computer Simulation
Mathematical models

Keywords

  • Angiogenesis
  • Anti-angiogenic therapy
  • Drug administration control
  • Reinforcement learning

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Health Informatics

Cite this

Reinforcement learning-based control of tumor growth under anti-angiogenic therapy. / Yazdjerdi, Parisa; Meskin, Nader; Al-Naemi, Mohammad; Al Moustafa, Ala Eddin; Kovács, L.

In: Computer Methods and Programs in Biomedicine, Vol. 173, 01.05.2019, p. 15-26.

Research output: Contribution to journalArticle

Yazdjerdi, Parisa ; Meskin, Nader ; Al-Naemi, Mohammad ; Al Moustafa, Ala Eddin ; Kovács, L. / Reinforcement learning-based control of tumor growth under anti-angiogenic therapy. In: Computer Methods and Programs in Biomedicine. 2019 ; Vol. 173. pp. 15-26.
@article{5d4651d1af6b41c2897c94185a5ba861,
title = "Reinforcement learning-based control of tumor growth under anti-angiogenic therapy",
abstract = "Background and objectives: In recent decades, cancer has become one of the most fatal and destructive diseases which is threatening humans life. Accordingly, different types of cancer treatment are studied with the main aim to have the best treatment with minimum side effects. Anti-angiogenic is a molecular targeted therapy which can be coupled with chemotherapy and radiotherapy. Although this method does not eliminate the whole tumor, but it can keep the tumor size in a given state by preventing the formation of new blood vessels. In this paper, a novel model-free method based on reinforcement learning (RL) framework is used to design a closed-loop control of anti-angiogenic drug dosing administration. Methods: A Q-learning algorithm is developed for the drug dosing closed-loop control. This controller is designed using two different values of the maximum drug dosage to reduce the tumor volume up to a desired value. The mathematical model of tumor growth under anti-angiogenic inhibitor is used to simulate a real patient. Results: The effectiveness of the proposed method is shown through in silico simulation and its robustness to patient parameters variation is demonstrated. It is demonstrated that the tumor reaches its minimal volume in 84 days with maximum drug inlet of 30 mg/kg/day. Also, it is shown that the designed controller is robust with respect to ± 20{\%} of tumor growth parameters changes. Conclusion: The proposed closed-loop reinforcement learning-based controller for cancer treatment using anti-angiogenic inhibitor provides an effective and novel result such that with a clinically valid and safe dosage of drug, the volume reduces up to 1mm 3 in a reasonable short period compared to the literature.",
keywords = "Angiogenesis, Anti-angiogenic therapy, Drug administration control, Reinforcement learning",
author = "Parisa Yazdjerdi and Nader Meskin and Mohammad Al-Naemi and {Al Moustafa}, {Ala Eddin} and L. Kov{\'a}cs",
year = "2019",
month = "5",
day = "1",
doi = "10.1016/j.cmpb.2019.03.004",
language = "English",
volume = "173",
pages = "15--26",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Reinforcement learning-based control of tumor growth under anti-angiogenic therapy

AU - Yazdjerdi, Parisa

AU - Meskin, Nader

AU - Al-Naemi, Mohammad

AU - Al Moustafa, Ala Eddin

AU - Kovács, L.

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Background and objectives: In recent decades, cancer has become one of the most fatal and destructive diseases which is threatening humans life. Accordingly, different types of cancer treatment are studied with the main aim to have the best treatment with minimum side effects. Anti-angiogenic is a molecular targeted therapy which can be coupled with chemotherapy and radiotherapy. Although this method does not eliminate the whole tumor, but it can keep the tumor size in a given state by preventing the formation of new blood vessels. In this paper, a novel model-free method based on reinforcement learning (RL) framework is used to design a closed-loop control of anti-angiogenic drug dosing administration. Methods: A Q-learning algorithm is developed for the drug dosing closed-loop control. This controller is designed using two different values of the maximum drug dosage to reduce the tumor volume up to a desired value. The mathematical model of tumor growth under anti-angiogenic inhibitor is used to simulate a real patient. Results: The effectiveness of the proposed method is shown through in silico simulation and its robustness to patient parameters variation is demonstrated. It is demonstrated that the tumor reaches its minimal volume in 84 days with maximum drug inlet of 30 mg/kg/day. Also, it is shown that the designed controller is robust with respect to ± 20% of tumor growth parameters changes. Conclusion: The proposed closed-loop reinforcement learning-based controller for cancer treatment using anti-angiogenic inhibitor provides an effective and novel result such that with a clinically valid and safe dosage of drug, the volume reduces up to 1mm 3 in a reasonable short period compared to the literature.

AB - Background and objectives: In recent decades, cancer has become one of the most fatal and destructive diseases which is threatening humans life. Accordingly, different types of cancer treatment are studied with the main aim to have the best treatment with minimum side effects. Anti-angiogenic is a molecular targeted therapy which can be coupled with chemotherapy and radiotherapy. Although this method does not eliminate the whole tumor, but it can keep the tumor size in a given state by preventing the formation of new blood vessels. In this paper, a novel model-free method based on reinforcement learning (RL) framework is used to design a closed-loop control of anti-angiogenic drug dosing administration. Methods: A Q-learning algorithm is developed for the drug dosing closed-loop control. This controller is designed using two different values of the maximum drug dosage to reduce the tumor volume up to a desired value. The mathematical model of tumor growth under anti-angiogenic inhibitor is used to simulate a real patient. Results: The effectiveness of the proposed method is shown through in silico simulation and its robustness to patient parameters variation is demonstrated. It is demonstrated that the tumor reaches its minimal volume in 84 days with maximum drug inlet of 30 mg/kg/day. Also, it is shown that the designed controller is robust with respect to ± 20% of tumor growth parameters changes. Conclusion: The proposed closed-loop reinforcement learning-based controller for cancer treatment using anti-angiogenic inhibitor provides an effective and novel result such that with a clinically valid and safe dosage of drug, the volume reduces up to 1mm 3 in a reasonable short period compared to the literature.

KW - Angiogenesis

KW - Anti-angiogenic therapy

KW - Drug administration control

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=85062685434&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062685434&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2019.03.004

DO - 10.1016/j.cmpb.2019.03.004

M3 - Article

AN - SCOPUS:85062685434

VL - 173

SP - 15

EP - 26

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

ER -