Deep learning for tumor margin identification in electromagnetic imaging
Abstract In this work, a novel method for tumor margin identification in electromagnetic imaging is proposed to optimize the tumor removal surgery. This capability will enable the visualization of the border of the cancerous tissue for the surgeon prior or during the excision surgery. To this end, t...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-09-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-42625-w |
_version_ | 1797453267456753664 |
---|---|
author | Amir Mirbeik Negar Ebadi |
author_facet | Amir Mirbeik Negar Ebadi |
author_sort | Amir Mirbeik |
collection | DOAJ |
description | Abstract In this work, a novel method for tumor margin identification in electromagnetic imaging is proposed to optimize the tumor removal surgery. This capability will enable the visualization of the border of the cancerous tissue for the surgeon prior or during the excision surgery. To this end, the border between the normal and tumor parts needs to be identified. Therefore, the images need to be segmented into tumor and normal areas. We propose a deep learning technique which divides the electromagnetic images into two regions: tumor and normal, with high accuracy. We formulate deep learning from a perspective relevant to electromagnetic image reconstruction. A recurrent auto-encoder network architecture (termed here DeepTMI) 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) average of normalized reconstructed results by the DeepTMI method are about 0.94 and 0.04 respectively, while that average obtained from the conventional backpropagation (BP) method can hardly overcome 0.35 and 0.41 respectively. |
first_indexed | 2024-03-09T15:19:22Z |
format | Article |
id | doaj.art-41bfa68e0b154e3d8e298d522caa96e3 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-03-09T15:19:22Z |
publishDate | 2023-09-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-41bfa68e0b154e3d8e298d522caa96e32023-11-26T12:52:09ZengNature PortfolioScientific Reports2045-23222023-09-0113111010.1038/s41598-023-42625-wDeep learning for tumor margin identification in electromagnetic imagingAmir Mirbeik0Negar Ebadi1RadioSight LLCDepartment of Electrical and Computer Engineering, Stevens Institute of TechnologyAbstract In this work, a novel method for tumor margin identification in electromagnetic imaging is proposed to optimize the tumor removal surgery. This capability will enable the visualization of the border of the cancerous tissue for the surgeon prior or during the excision surgery. To this end, the border between the normal and tumor parts needs to be identified. Therefore, the images need to be segmented into tumor and normal areas. We propose a deep learning technique which divides the electromagnetic images into two regions: tumor and normal, with high accuracy. We formulate deep learning from a perspective relevant to electromagnetic image reconstruction. A recurrent auto-encoder network architecture (termed here DeepTMI) 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) average of normalized reconstructed results by the DeepTMI method are about 0.94 and 0.04 respectively, while that average obtained from the conventional backpropagation (BP) method can hardly overcome 0.35 and 0.41 respectively.https://doi.org/10.1038/s41598-023-42625-w |
spellingShingle | Amir Mirbeik Negar Ebadi Deep learning for tumor margin identification in electromagnetic imaging Scientific Reports |
title | Deep learning for tumor margin identification in electromagnetic imaging |
title_full | Deep learning for tumor margin identification in electromagnetic imaging |
title_fullStr | Deep learning for tumor margin identification in electromagnetic imaging |
title_full_unstemmed | Deep learning for tumor margin identification in electromagnetic imaging |
title_short | Deep learning for tumor margin identification in electromagnetic imaging |
title_sort | deep learning for tumor margin identification in electromagnetic imaging |
url | https://doi.org/10.1038/s41598-023-42625-w |
work_keys_str_mv | AT amirmirbeik deeplearningfortumormarginidentificationinelectromagneticimaging AT negarebadi deeplearningfortumormarginidentificationinelectromagneticimaging |