Deep learning-based electrical impedance spectroscopy analysis for malignant and potentially malignant oral disorder detection

Abstract Electrical impedance spectroscopy (EIS) is a powerful tool used to investigate the properties of materials and biological tissues. This study presents one of the first applications of EIS for the detection and classification of oral potentially malignant disorders (OPMDs) and oral cancer. W...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhicheng Lin, Zi-Qiang Lang, Lingzhong Guo, Dawn C Walker, Malwina Matella, Mengxiao Wang, Craig Murdoch
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-05116-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849724889769967616
author Zhicheng Lin
Zi-Qiang Lang
Lingzhong Guo
Dawn C Walker
Malwina Matella
Mengxiao Wang
Craig Murdoch
author_facet Zhicheng Lin
Zi-Qiang Lang
Lingzhong Guo
Dawn C Walker
Malwina Matella
Mengxiao Wang
Craig Murdoch
author_sort Zhicheng Lin
collection DOAJ
description Abstract Electrical impedance spectroscopy (EIS) is a powerful tool used to investigate the properties of materials and biological tissues. This study presents one of the first applications of EIS for the detection and classification of oral potentially malignant disorders (OPMDs) and oral cancer. We aimed to apply EIS in conjunction with deep learning to assist the clinical diagnosis of OPMD and oral cancer as a non-invasive diagnostic technology. Currently, the diagnosis of OPMD and oral cancer relies on clinical examination and histopathological analysis of invasive scalpel tissue biopsies, which is stressful for patients, time-consuming for clinicians and subject to histopathological interobserver variation in diagnosis, although recent advances in artificial intelligence may circumvent discrepancy. Here we developed a novel deep learning convolutional neural network (CNN)-based method to automatically differentiate normal, OPMD and malignant oral tissues using EIS measurements. EIS readings were initially taken from untreated or glacial acetic acid-treated porcine oral mucosa and analyzed via CNN to determine if this method could discriminate between normal and damaged oral epithelium. CNN models achieved area under the curve (AUC) values of 0.92 ± 0.03, with specificity 0.95 and sensitivity 0.84, showing good discrimination. EIS data from ventral tongue and floor-of-the-mouth were collected from 51 healthy humans and 11 patients with OPMD and oral cancer. When a binary classification (low or high risk of malignancy) was applied, the best CNN model achieved an AUC 0.91 ± 0.1, with accuracy 0.91 ± 0.05, specificity 0.97 and sensitivity 0.74. These results demonstrate the considerable potential of EIS in combination with CNN models as an adjunctive non-invasive diagnostic tool for OPMD and oral cancer.
format Article
id doaj-art-14cfeeef59c146d08c8feb68b2eb94fa
institution DOAJ
issn 2045-2322
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-14cfeeef59c146d08c8feb68b2eb94fa2025-08-20T03:10:36ZengNature PortfolioScientific Reports2045-23222025-06-0115111710.1038/s41598-025-05116-8Deep learning-based electrical impedance spectroscopy analysis for malignant and potentially malignant oral disorder detectionZhicheng Lin0Zi-Qiang Lang1Lingzhong Guo2Dawn C Walker3Malwina Matella4Mengxiao Wang5Craig Murdoch6School of Electrical and Electronic Engineering, University of SheffieldSchool of Electrical and Electronic Engineering, University of SheffieldSchool of Electrical and Electronic Engineering, University of SheffieldInsigneo, University of SheffieldInsigneo, University of SheffieldSchool of Electrical and Electronic Engineering, University of SheffieldInsigneo, University of SheffieldAbstract Electrical impedance spectroscopy (EIS) is a powerful tool used to investigate the properties of materials and biological tissues. This study presents one of the first applications of EIS for the detection and classification of oral potentially malignant disorders (OPMDs) and oral cancer. We aimed to apply EIS in conjunction with deep learning to assist the clinical diagnosis of OPMD and oral cancer as a non-invasive diagnostic technology. Currently, the diagnosis of OPMD and oral cancer relies on clinical examination and histopathological analysis of invasive scalpel tissue biopsies, which is stressful for patients, time-consuming for clinicians and subject to histopathological interobserver variation in diagnosis, although recent advances in artificial intelligence may circumvent discrepancy. Here we developed a novel deep learning convolutional neural network (CNN)-based method to automatically differentiate normal, OPMD and malignant oral tissues using EIS measurements. EIS readings were initially taken from untreated or glacial acetic acid-treated porcine oral mucosa and analyzed via CNN to determine if this method could discriminate between normal and damaged oral epithelium. CNN models achieved area under the curve (AUC) values of 0.92 ± 0.03, with specificity 0.95 and sensitivity 0.84, showing good discrimination. EIS data from ventral tongue and floor-of-the-mouth were collected from 51 healthy humans and 11 patients with OPMD and oral cancer. When a binary classification (low or high risk of malignancy) was applied, the best CNN model achieved an AUC 0.91 ± 0.1, with accuracy 0.91 ± 0.05, specificity 0.97 and sensitivity 0.74. These results demonstrate the considerable potential of EIS in combination with CNN models as an adjunctive non-invasive diagnostic tool for OPMD and oral cancer.https://doi.org/10.1038/s41598-025-05116-8Deep learningElectrical impedance spectroscopyOral cancerPotentially malignant lesionsDysplasia
spellingShingle Zhicheng Lin
Zi-Qiang Lang
Lingzhong Guo
Dawn C Walker
Malwina Matella
Mengxiao Wang
Craig Murdoch
Deep learning-based electrical impedance spectroscopy analysis for malignant and potentially malignant oral disorder detection
Scientific Reports
Deep learning
Electrical impedance spectroscopy
Oral cancer
Potentially malignant lesions
Dysplasia
title Deep learning-based electrical impedance spectroscopy analysis for malignant and potentially malignant oral disorder detection
title_full Deep learning-based electrical impedance spectroscopy analysis for malignant and potentially malignant oral disorder detection
title_fullStr Deep learning-based electrical impedance spectroscopy analysis for malignant and potentially malignant oral disorder detection
title_full_unstemmed Deep learning-based electrical impedance spectroscopy analysis for malignant and potentially malignant oral disorder detection
title_short Deep learning-based electrical impedance spectroscopy analysis for malignant and potentially malignant oral disorder detection
title_sort deep learning based electrical impedance spectroscopy analysis for malignant and potentially malignant oral disorder detection
topic Deep learning
Electrical impedance spectroscopy
Oral cancer
Potentially malignant lesions
Dysplasia
url https://doi.org/10.1038/s41598-025-05116-8
work_keys_str_mv AT zhichenglin deeplearningbasedelectricalimpedancespectroscopyanalysisformalignantandpotentiallymalignantoraldisorderdetection
AT ziqianglang deeplearningbasedelectricalimpedancespectroscopyanalysisformalignantandpotentiallymalignantoraldisorderdetection
AT lingzhongguo deeplearningbasedelectricalimpedancespectroscopyanalysisformalignantandpotentiallymalignantoraldisorderdetection
AT dawncwalker deeplearningbasedelectricalimpedancespectroscopyanalysisformalignantandpotentiallymalignantoraldisorderdetection
AT malwinamatella deeplearningbasedelectricalimpedancespectroscopyanalysisformalignantandpotentiallymalignantoraldisorderdetection
AT mengxiaowang deeplearningbasedelectricalimpedancespectroscopyanalysisformalignantandpotentiallymalignantoraldisorderdetection
AT craigmurdoch deeplearningbasedelectricalimpedancespectroscopyanalysisformalignantandpotentiallymalignantoraldisorderdetection