Intelligent DRL-Based Adaptive Region of Interest for Delay-Sensitive Telemedicine Applications

Abdulrahman Soliman; Amr Mohamed; Elias Yaacoub; Nikhil V. Navkar; Aiman Erbad

doi:10.1109/ICC45041.2023.10279455

Intelligent DRL-Based Adaptive Region of Interest for Delay-Sensitive Telemedicine Applications

Abdulrahman Soliman^*, Amr Mohamed^*, Elias Yaacoub^*, Nikhil V. Navkar, Aiman Erbad

^*Corresponding author for this work

CSE Information & Computing Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Telemedicine applications have recently received substantial potential and interest, especially after the COVID-19 pandemic. Remote experience will help people get their complex surgery done or transfer knowledge to local surgeons, without the need to travel abroad. Even with breakthrough improvements in internet speeds, the delay in video streaming is still a hurdle in telemedicine applications. This imposes using image compression and region of interest (ROI) techniques to reduce the data size and transmission needs. This paper proposes a Deep Reinforcement Learning (DRL) model that intelligently adapts the ROI size and non-ROI quality depending on the estimated throughput. The delay and structural similarity index measure (SSIM) comparison are used to assess the DRL model. The comparison findings and the practical application reveal that DRL is capable of reducing the delay by 13% and keeping the overall quality in an acceptable range. Since the latency has been significantly reduced, these findings are a valuable enhancement to telemedicine applications.

Original language	English
Title of host publication	ICC 2023 - IEEE International Conference on Communications
Subtitle of host publication	Sustainable Communications for Renaissance
Editors	Michele Zorzi, Meixia Tao, Walid Saad
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2419-2424
Number of pages	6
ISBN (Electronic)	9781538674628
DOIs	https://doi.org/10.1109/ICC45041.2023.10279455
Publication status	Published - 2023
Event	2023 IEEE International Conference on Communications, ICC 2023 - Rome, Italy Duration: 28 May 2023 → 1 Jun 2023

Publication series

Name	IEEE International Conference on Communications
Volume	2023-May
ISSN (Print)	1550-3607

Conference

Conference	2023 IEEE International Conference on Communications, ICC 2023
Country/Territory	Italy
City	Rome
Period	28/05/23 → 1/06/23

Keywords

Deep Reinforcement Learning (DRL)
Telemedicine
optimization
region of interest (ROI)
structural similarity index measure (SSIM)

Access to Document

10.1109/ICC45041.2023.10279455

Cite this

Soliman, A., Mohamed, A., Yaacoub, E., Navkar, N. V., & Erbad, A. (2023). Intelligent DRL-Based Adaptive Region of Interest for Delay-Sensitive Telemedicine Applications. In M. Zorzi, M. Tao, & W. Saad (Eds.), ICC 2023 - IEEE International Conference on Communications: Sustainable Communications for Renaissance (pp. 2419-2424). (IEEE International Conference on Communications; Vol. 2023-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICC45041.2023.10279455

Soliman, Abdulrahman ; Mohamed, Amr ; Yaacoub, Elias et al. / Intelligent DRL-Based Adaptive Region of Interest for Delay-Sensitive Telemedicine Applications. ICC 2023 - IEEE International Conference on Communications: Sustainable Communications for Renaissance. editor / Michele Zorzi ; Meixia Tao ; Walid Saad. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 2419-2424 (IEEE International Conference on Communications).

@inproceedings{3259debd2ea84d6baf1621d2cf5b5abf,

title = "Intelligent DRL-Based Adaptive Region of Interest for Delay-Sensitive Telemedicine Applications",

abstract = "Telemedicine applications have recently received substantial potential and interest, especially after the COVID-19 pandemic. Remote experience will help people get their complex surgery done or transfer knowledge to local surgeons, without the need to travel abroad. Even with breakthrough improvements in internet speeds, the delay in video streaming is still a hurdle in telemedicine applications. This imposes using image compression and region of interest (ROI) techniques to reduce the data size and transmission needs. This paper proposes a Deep Reinforcement Learning (DRL) model that intelligently adapts the ROI size and non-ROI quality depending on the estimated throughput. The delay and structural similarity index measure (SSIM) comparison are used to assess the DRL model. The comparison findings and the practical application reveal that DRL is capable of reducing the delay by 13% and keeping the overall quality in an acceptable range. Since the latency has been significantly reduced, these findings are a valuable enhancement to telemedicine applications.",

keywords = "Deep Reinforcement Learning (DRL), Telemedicine, optimization, region of interest (ROI), structural similarity index measure (SSIM)",

author = "Abdulrahman Soliman and Amr Mohamed and Elias Yaacoub and Navkar, {Nikhil V.} and Aiman Erbad",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Conference on Communications, ICC 2023 ; Conference date: 28-05-2023 Through 01-06-2023",

year = "2023",

doi = "10.1109/ICC45041.2023.10279455",

language = "English",

series = "IEEE International Conference on Communications",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2419--2424",

editor = "Michele Zorzi and Meixia Tao and Walid Saad",

booktitle = "ICC 2023 - IEEE International Conference on Communications",

address = "United States",

}

Soliman, A, Mohamed, A, Yaacoub, E, Navkar, NV & Erbad, A 2023, Intelligent DRL-Based Adaptive Region of Interest for Delay-Sensitive Telemedicine Applications. in M Zorzi, M Tao & W Saad (eds), ICC 2023 - IEEE International Conference on Communications: Sustainable Communications for Renaissance. IEEE International Conference on Communications, vol. 2023-May, Institute of Electrical and Electronics Engineers Inc., pp. 2419-2424, 2023 IEEE International Conference on Communications, ICC 2023, Rome, Italy, 28/05/23. https://doi.org/10.1109/ICC45041.2023.10279455

Intelligent DRL-Based Adaptive Region of Interest for Delay-Sensitive Telemedicine Applications. / Soliman, Abdulrahman; Mohamed, Amr; Yaacoub, Elias et al.
ICC 2023 - IEEE International Conference on Communications: Sustainable Communications for Renaissance. ed. / Michele Zorzi; Meixia Tao; Walid Saad. Institute of Electrical and Electronics Engineers Inc., 2023. p. 2419-2424 (IEEE International Conference on Communications; Vol. 2023-May).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Intelligent DRL-Based Adaptive Region of Interest for Delay-Sensitive Telemedicine Applications

AU - Soliman, Abdulrahman

AU - Mohamed, Amr

AU - Yaacoub, Elias

AU - Navkar, Nikhil V.

AU - Erbad, Aiman

PY - 2023

Y1 - 2023

N2 - Telemedicine applications have recently received substantial potential and interest, especially after the COVID-19 pandemic. Remote experience will help people get their complex surgery done or transfer knowledge to local surgeons, without the need to travel abroad. Even with breakthrough improvements in internet speeds, the delay in video streaming is still a hurdle in telemedicine applications. This imposes using image compression and region of interest (ROI) techniques to reduce the data size and transmission needs. This paper proposes a Deep Reinforcement Learning (DRL) model that intelligently adapts the ROI size and non-ROI quality depending on the estimated throughput. The delay and structural similarity index measure (SSIM) comparison are used to assess the DRL model. The comparison findings and the practical application reveal that DRL is capable of reducing the delay by 13% and keeping the overall quality in an acceptable range. Since the latency has been significantly reduced, these findings are a valuable enhancement to telemedicine applications.

AB - Telemedicine applications have recently received substantial potential and interest, especially after the COVID-19 pandemic. Remote experience will help people get their complex surgery done or transfer knowledge to local surgeons, without the need to travel abroad. Even with breakthrough improvements in internet speeds, the delay in video streaming is still a hurdle in telemedicine applications. This imposes using image compression and region of interest (ROI) techniques to reduce the data size and transmission needs. This paper proposes a Deep Reinforcement Learning (DRL) model that intelligently adapts the ROI size and non-ROI quality depending on the estimated throughput. The delay and structural similarity index measure (SSIM) comparison are used to assess the DRL model. The comparison findings and the practical application reveal that DRL is capable of reducing the delay by 13% and keeping the overall quality in an acceptable range. Since the latency has been significantly reduced, these findings are a valuable enhancement to telemedicine applications.

KW - Deep Reinforcement Learning (DRL)

KW - Telemedicine

KW - optimization

KW - region of interest (ROI)

KW - structural similarity index measure (SSIM)

UR - http://www.scopus.com/inward/record.url?scp=85178296032&partnerID=8YFLogxK

U2 - 10.1109/ICC45041.2023.10279455

DO - 10.1109/ICC45041.2023.10279455

M3 - Conference contribution

AN - SCOPUS:85178296032

T3 - IEEE International Conference on Communications

SP - 2419

EP - 2424

BT - ICC 2023 - IEEE International Conference on Communications

A2 - Zorzi, Michele

A2 - Tao, Meixia

A2 - Saad, Walid

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE International Conference on Communications, ICC 2023

Y2 - 28 May 2023 through 1 June 2023

ER -

Soliman A, Mohamed A, Yaacoub E, Navkar NV, Erbad A. Intelligent DRL-Based Adaptive Region of Interest for Delay-Sensitive Telemedicine Applications. In Zorzi M, Tao M, Saad W, editors, ICC 2023 - IEEE International Conference on Communications: Sustainable Communications for Renaissance. Institute of Electrical and Electronics Engineers Inc. 2023. p. 2419-2424. (IEEE International Conference on Communications). doi: 10.1109/ICC45041.2023.10279455

Intelligent DRL-Based Adaptive Region of Interest for Delay-Sensitive Telemedicine Applications

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

EX-QNRF-NPRPS-58: A Telemedicine System for Minimally Invasive Surgeries - Application Towards Surgical Treatment of Cancer and Renal Diseases

Cite this

Intelligent DRL-Based Adaptive Region of Interest for Delay-Sensitive Telemedicine Applications

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

EX-QNRF-NPRPS-58: A Telemedicine System for Minimally Invasive Surgeries - Application Towards Surgical Treatment of Cancer and Renal Diseases

Cite this