Deep Learning for Tumor Margin Identification in Electromagnetic Imaging

Amir Mirbeik; Negar Ebadi Tavassolian

doi:10.1109/USNC-URSI52151.2023.10237765

Deep Learning for Tumor Margin Identification in Electromagnetic Imaging

Amir Mirbeik
, Negar Ebadi Tavassolian

Department of Electrical and Computer Engineering

Stevens Institute of Technology

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

Abstract

This paper proposes a deep learning technique which accurately divides the electromagnetic images of cancer-affected tissues into two regions of tumorous and normal sections. This capability will enable the visualization of the border of the cancerous tissue for the surgeon prior to or during the excision surgery. We formulate deep learning from a perspective relevant to electromagnetic image reconstruction. A recurrent auto-encoder network architecture is presented. The effectiveness of the algorithm is demonstrated by segmenting the reconstructed images of an experimental tissue-mimicking phantom. The structure similarity measure (SSIM) and mean-square-error (MSE) of the reconstructed result are approximately 0.94 and 0.04 respectively, while the values obtained from conventional frequency-domain reconstruction methods can hardly overcome 0.35 and 0.41 respectively.

Original language	English
Title of host publication	2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023 - Proceedings
Pages	1873-1874
Number of pages	2
ISBN (Electronic)	9781665442282
DOIs	https://doi.org/10.1109/USNC-URSI52151.2023.10237765
State	Published - 2023
Event	2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023 - Portland, United States Duration: 23 Jul 2023 → 28 Jul 2023

Publication series

Name	IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)
Volume	2023-July
ISSN (Print)	1522-3965

Conference

Conference	2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023
Country/Territory	United States
City	Portland
Period	23/07/23 → 28/07/23

UN SDGs

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

SDG 3 Good Health and Well-being

Access to Document

10.1109/USNC-URSI52151.2023.10237765

Cite this

Mirbeik, A., & Tavassolian, N. E. (2023). Deep Learning for Tumor Margin Identification in Electromagnetic Imaging. In 2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023 - Proceedings (pp. 1873-1874). (IEEE Antennas and Propagation Society, AP-S International Symposium (Digest); Vol. 2023-July). https://doi.org/10.1109/USNC-URSI52151.2023.10237765

@inproceedings{eed793d1cfa5450ca7da48313cba7356,

title = "Deep Learning for Tumor Margin Identification in Electromagnetic Imaging",

abstract = "This paper proposes a deep learning technique which accurately divides the electromagnetic images of cancer-affected tissues into two regions of tumorous and normal sections. This capability will enable the visualization of the border of the cancerous tissue for the surgeon prior to or during the excision surgery. We formulate deep learning from a perspective relevant to electromagnetic image reconstruction. A recurrent auto-encoder network architecture is presented. The effectiveness of the algorithm is demonstrated by segmenting the reconstructed images of an experimental tissue-mimicking phantom. The structure similarity measure (SSIM) and mean-square-error (MSE) of the reconstructed result are approximately 0.94 and 0.04 respectively, while the values obtained from conventional frequency-domain reconstruction methods can hardly overcome 0.35 and 0.41 respectively.",

author = "Amir Mirbeik and Tavassolian, \{Negar Ebadi\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023 ; Conference date: 23-07-2023 Through 28-07-2023",

year = "2023",

doi = "10.1109/USNC-URSI52151.2023.10237765",

language = "English",

series = "IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)",

pages = "1873--1874",

booktitle = "2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023 - Proceedings",

}

Mirbeik, A & Tavassolian, NE 2023, Deep Learning for Tumor Margin Identification in Electromagnetic Imaging. in 2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023 - Proceedings. IEEE Antennas and Propagation Society, AP-S International Symposium (Digest), vol. 2023-July, pp. 1873-1874, 2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023, Portland, United States, 23/07/23. https://doi.org/10.1109/USNC-URSI52151.2023.10237765

Deep Learning for Tumor Margin Identification in Electromagnetic Imaging. / Mirbeik, Amir; Tavassolian, Negar Ebadi.
2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023 - Proceedings. 2023. p. 1873-1874 (IEEE Antennas and Propagation Society, AP-S International Symposium (Digest); Vol. 2023-July).

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

TY - GEN

T1 - Deep Learning for Tumor Margin Identification in Electromagnetic Imaging

AU - Mirbeik, Amir

AU - Tavassolian, Negar Ebadi

PY - 2023

Y1 - 2023

N2 - This paper proposes a deep learning technique which accurately divides the electromagnetic images of cancer-affected tissues into two regions of tumorous and normal sections. This capability will enable the visualization of the border of the cancerous tissue for the surgeon prior to or during the excision surgery. We formulate deep learning from a perspective relevant to electromagnetic image reconstruction. A recurrent auto-encoder network architecture is presented. The effectiveness of the algorithm is demonstrated by segmenting the reconstructed images of an experimental tissue-mimicking phantom. The structure similarity measure (SSIM) and mean-square-error (MSE) of the reconstructed result are approximately 0.94 and 0.04 respectively, while the values obtained from conventional frequency-domain reconstruction methods can hardly overcome 0.35 and 0.41 respectively.

AB - This paper proposes a deep learning technique which accurately divides the electromagnetic images of cancer-affected tissues into two regions of tumorous and normal sections. This capability will enable the visualization of the border of the cancerous tissue for the surgeon prior to or during the excision surgery. We formulate deep learning from a perspective relevant to electromagnetic image reconstruction. A recurrent auto-encoder network architecture is presented. The effectiveness of the algorithm is demonstrated by segmenting the reconstructed images of an experimental tissue-mimicking phantom. The structure similarity measure (SSIM) and mean-square-error (MSE) of the reconstructed result are approximately 0.94 and 0.04 respectively, while the values obtained from conventional frequency-domain reconstruction methods can hardly overcome 0.35 and 0.41 respectively.

UR - https://www.scopus.com/pages/publications/85172412365

UR - https://www.scopus.com/pages/publications/85172412365#tab=citedBy

U2 - 10.1109/USNC-URSI52151.2023.10237765

DO - 10.1109/USNC-URSI52151.2023.10237765

M3 - Conference contribution

AN - SCOPUS:85172412365

T3 - IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)

SP - 1873

EP - 1874

BT - 2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023 - Proceedings

T2 - 2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023

Y2 - 23 July 2023 through 28 July 2023

ER -

Mirbeik A, Tavassolian NE. Deep Learning for Tumor Margin Identification in Electromagnetic Imaging. In 2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023 - Proceedings. 2023. p. 1873-1874. (IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)). doi: 10.1109/USNC-URSI52151.2023.10237765

Deep Learning for Tumor Margin Identification in Electromagnetic Imaging

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this