Early and late fusion machine learning on multi-frequency electrical impedance data to improve radiofrequency ablation monitoring

Emre Besler; Yearnchee Curtis Wang; Alan V. Sahakian

doi:10.1109/JBHI.2019.2952922

Early and late fusion machine learning on multi-frequency electrical impedance data to improve radiofrequency ablation monitoring

Emre Besler, Yearnchee Curtis Wang, Alan V. Sahakian^*

^*Corresponding author for this work

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Radiofrequency ablation (RFA) is a popular modality for tumor treatment. However, inexpensive real-time monitoring of RFA within multiple tissue types is still an ongoing research topic. The objective of this study is to utilize multi-frequency electrical impedance data within real-time RFA depth estimation through data fusion schemes that include non-linear machine learning (ML) models. Multi-frequency tissue complex electrical impedance measurements are used to provide input data to the data fusion schemes. Our results show that the fusion schemes significantly decrease both the spread of residuals and the mean of the residuals for depth estimation. Thus, data fusion can be a significant tool for use in improving the performance of ML-based monitoring for RFA.

Original language	English (US)
Article number	8895991
Pages (from-to)	2359-2367
Number of pages	9
Journal	IEEE Journal of Biomedical and Health Informatics
Volume	24
Issue number	8
DOIs	https://doi.org/10.1109/JBHI.2019.2952922
State	Published - Aug 2020

Keywords

Data fusion
adaptive boosting
cancer
control
depth
ensemble
lesion
machine learning
monitoring
radiofrequency ablation
random forest
svm
tumor

ASJC Scopus subject areas

Biotechnology
Computer Science Applications
Electrical and Electronic Engineering
Health Information Management

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/JBHI.2019.2952922

Cite this

@article{de9befe33a2247cc9a393025f28a86e5,

title = "Early and late fusion machine learning on multi-frequency electrical impedance data to improve radiofrequency ablation monitoring",

abstract = "Radiofrequency ablation (RFA) is a popular modality for tumor treatment. However, inexpensive real-time monitoring of RFA within multiple tissue types is still an ongoing research topic. The objective of this study is to utilize multi-frequency electrical impedance data within real-time RFA depth estimation through data fusion schemes that include non-linear machine learning (ML) models. Multi-frequency tissue complex electrical impedance measurements are used to provide input data to the data fusion schemes. Our results show that the fusion schemes significantly decrease both the spread of residuals and the mean of the residuals for depth estimation. Thus, data fusion can be a significant tool for use in improving the performance of ML-based monitoring for RFA. ",

keywords = "Data fusion, adaptive boosting, cancer, control, depth, ensemble, lesion, machine learning, monitoring, radiofrequency ablation, random forest, svm, tumor",

author = "Emre Besler and Wang, {Yearnchee Curtis} and Sahakian, {Alan V.}",

note = "Funding Information: Manuscript received July 24, 2019; revised November 1, 2019; accepted November 4, 2019. Date of publication November 11, 2019; date of current version August 5, 2020. This work was supported by National Science Foundation under Grants 1622842 and 1738541. (Corresponding author: Alan V. Sahakian.) E. Besler is with the Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL 60208 USA (e-mail: emrebesler2020@u.northwestern.edu). Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2020",

month = aug,

doi = "10.1109/JBHI.2019.2952922",

language = "English (US)",

volume = "24",

pages = "2359--2367",

journal = "IEEE Journal of Biomedical and Health Informatics",

issn = "2168-2194",

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

number = "8",

}

TY - JOUR

T1 - Early and late fusion machine learning on multi-frequency electrical impedance data to improve radiofrequency ablation monitoring

AU - Besler, Emre

AU - Wang, Yearnchee Curtis

AU - Sahakian, Alan V.

N1 - Funding Information: Manuscript received July 24, 2019; revised November 1, 2019; accepted November 4, 2019. Date of publication November 11, 2019; date of current version August 5, 2020. This work was supported by National Science Foundation under Grants 1622842 and 1738541. (Corresponding author: Alan V. Sahakian.) E. Besler is with the Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL 60208 USA (e-mail: emrebesler2020@u.northwestern.edu). Publisher Copyright: © 2013 IEEE.

PY - 2020/8

Y1 - 2020/8

N2 - Radiofrequency ablation (RFA) is a popular modality for tumor treatment. However, inexpensive real-time monitoring of RFA within multiple tissue types is still an ongoing research topic. The objective of this study is to utilize multi-frequency electrical impedance data within real-time RFA depth estimation through data fusion schemes that include non-linear machine learning (ML) models. Multi-frequency tissue complex electrical impedance measurements are used to provide input data to the data fusion schemes. Our results show that the fusion schemes significantly decrease both the spread of residuals and the mean of the residuals for depth estimation. Thus, data fusion can be a significant tool for use in improving the performance of ML-based monitoring for RFA.

AB - Radiofrequency ablation (RFA) is a popular modality for tumor treatment. However, inexpensive real-time monitoring of RFA within multiple tissue types is still an ongoing research topic. The objective of this study is to utilize multi-frequency electrical impedance data within real-time RFA depth estimation through data fusion schemes that include non-linear machine learning (ML) models. Multi-frequency tissue complex electrical impedance measurements are used to provide input data to the data fusion schemes. Our results show that the fusion schemes significantly decrease both the spread of residuals and the mean of the residuals for depth estimation. Thus, data fusion can be a significant tool for use in improving the performance of ML-based monitoring for RFA.

KW - Data fusion

KW - adaptive boosting

KW - cancer

KW - control

KW - depth

KW - ensemble

KW - lesion

KW - machine learning

KW - monitoring

KW - radiofrequency ablation

KW - random forest

KW - svm

KW - tumor

UR - http://www.scopus.com/inward/record.url?scp=85089204339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85089204339&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2019.2952922

DO - 10.1109/JBHI.2019.2952922

M3 - Article

C2 - 31715579

AN - SCOPUS:85089204339

VL - 24

SP - 2359

EP - 2367

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 8

M1 - 8895991

ER -

Early and late fusion machine learning on multi-frequency electrical impedance data to improve radiofrequency ablation monitoring

Abstract

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this