Rapid multi-task diagnosis of oral cancer leveraging fiber-optic Raman spectroscopy and deep learning algorithms
IntroductionOral cancer, a predominant malignancy in developing nations, represents a global health challenge with a five-year survival rate below 50%. Nonetheless, substantial reductions in both its incidence and mortality rates can be achieved through early detection and appropriate treatment. Cru...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-10-01
|
Series: | Frontiers in Oncology |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2023.1272305/full |
_version_ | 1797662907772698624 |
---|---|
author | Xing Li Lianyu Li Qing Sun Bo Chen Chenjie Zhao Yuting Dong Zhihui Zhu Ruiqi Zhao Xinsong Ma Mingxin Yu Tao Zhang |
author_facet | Xing Li Lianyu Li Qing Sun Bo Chen Chenjie Zhao Yuting Dong Zhihui Zhu Ruiqi Zhao Xinsong Ma Mingxin Yu Tao Zhang |
author_sort | Xing Li |
collection | DOAJ |
description | IntroductionOral cancer, a predominant malignancy in developing nations, represents a global health challenge with a five-year survival rate below 50%. Nonetheless, substantial reductions in both its incidence and mortality rates can be achieved through early detection and appropriate treatment. Crucial to these treatment plans and prognosis predictions is the identification of the pathological type of oral cancer.MethodsToward this end, fiber-optic Raman spectroscopy emerges as an effective tool. This study combines Raman spectroscopy technology with deep learning algorithms to develop a portable intelligent prototype for oral case analysis. We propose, for the first time, a multi-task network (MTN) Raman spectroscopy classification model that utilizes a shared backbone network to simultaneously achieve different clinical staging and histological grading diagnoses.ResultsThe developed model demonstrated accuracy rates of 94.88%, 94.57%, and 94.34% for tumor staging, lymph node staging, and histological grading, respectively. Its sensitivity, specificity, and accuracy compare closely with the gold standard: routine histopathological examination.DiscussionThus, this prototype proposed in this study has great potential for rapid, non-invasive, and label-free pathological diagnosis of oral cancer. |
first_indexed | 2024-03-11T19:05:55Z |
format | Article |
id | doaj.art-08c068f4180a497aaae06328eb19d7ea |
institution | Directory Open Access Journal |
issn | 2234-943X |
language | English |
last_indexed | 2024-03-11T19:05:55Z |
publishDate | 2023-10-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Oncology |
spelling | doaj.art-08c068f4180a497aaae06328eb19d7ea2023-10-10T07:05:46ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2023-10-011310.3389/fonc.2023.12723051272305Rapid multi-task diagnosis of oral cancer leveraging fiber-optic Raman spectroscopy and deep learning algorithmsXing Li0Lianyu Li1Qing Sun2Bo Chen3Chenjie Zhao4Yuting Dong5Zhihui Zhu6Ruiqi Zhao7Xinsong Ma8Mingxin Yu9Tao Zhang10Department of Stomatology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, ChinaKey Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument, Beijing Information Science and Technology University, Beijing, ChinaDepartment of Plastic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, ChinaDepartment of Pathology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, ChinaPlastic Surgery Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, ChinaPlastic Surgery Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, ChinaDepartment of Stomatology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, ChinaDepartment of Stomatology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, ChinaKey Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument, Beijing Information Science and Technology University, Beijing, ChinaKey Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument, Beijing Information Science and Technology University, Beijing, ChinaDepartment of Stomatology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, ChinaIntroductionOral cancer, a predominant malignancy in developing nations, represents a global health challenge with a five-year survival rate below 50%. Nonetheless, substantial reductions in both its incidence and mortality rates can be achieved through early detection and appropriate treatment. Crucial to these treatment plans and prognosis predictions is the identification of the pathological type of oral cancer.MethodsToward this end, fiber-optic Raman spectroscopy emerges as an effective tool. This study combines Raman spectroscopy technology with deep learning algorithms to develop a portable intelligent prototype for oral case analysis. We propose, for the first time, a multi-task network (MTN) Raman spectroscopy classification model that utilizes a shared backbone network to simultaneously achieve different clinical staging and histological grading diagnoses.ResultsThe developed model demonstrated accuracy rates of 94.88%, 94.57%, and 94.34% for tumor staging, lymph node staging, and histological grading, respectively. Its sensitivity, specificity, and accuracy compare closely with the gold standard: routine histopathological examination.DiscussionThus, this prototype proposed in this study has great potential for rapid, non-invasive, and label-free pathological diagnosis of oral cancer.https://www.frontiersin.org/articles/10.3389/fonc.2023.1272305/fullRaman spectroscopyoral cancerTNM classificationhistological diagnosismachine learning algorithm |
spellingShingle | Xing Li Lianyu Li Qing Sun Bo Chen Chenjie Zhao Yuting Dong Zhihui Zhu Ruiqi Zhao Xinsong Ma Mingxin Yu Tao Zhang Rapid multi-task diagnosis of oral cancer leveraging fiber-optic Raman spectroscopy and deep learning algorithms Frontiers in Oncology Raman spectroscopy oral cancer TNM classification histological diagnosis machine learning algorithm |
title | Rapid multi-task diagnosis of oral cancer leveraging fiber-optic Raman spectroscopy and deep learning algorithms |
title_full | Rapid multi-task diagnosis of oral cancer leveraging fiber-optic Raman spectroscopy and deep learning algorithms |
title_fullStr | Rapid multi-task diagnosis of oral cancer leveraging fiber-optic Raman spectroscopy and deep learning algorithms |
title_full_unstemmed | Rapid multi-task diagnosis of oral cancer leveraging fiber-optic Raman spectroscopy and deep learning algorithms |
title_short | Rapid multi-task diagnosis of oral cancer leveraging fiber-optic Raman spectroscopy and deep learning algorithms |
title_sort | rapid multi task diagnosis of oral cancer leveraging fiber optic raman spectroscopy and deep learning algorithms |
topic | Raman spectroscopy oral cancer TNM classification histological diagnosis machine learning algorithm |
url | https://www.frontiersin.org/articles/10.3389/fonc.2023.1272305/full |
work_keys_str_mv | AT xingli rapidmultitaskdiagnosisoforalcancerleveragingfiberopticramanspectroscopyanddeeplearningalgorithms AT lianyuli rapidmultitaskdiagnosisoforalcancerleveragingfiberopticramanspectroscopyanddeeplearningalgorithms AT qingsun rapidmultitaskdiagnosisoforalcancerleveragingfiberopticramanspectroscopyanddeeplearningalgorithms AT bochen rapidmultitaskdiagnosisoforalcancerleveragingfiberopticramanspectroscopyanddeeplearningalgorithms AT chenjiezhao rapidmultitaskdiagnosisoforalcancerleveragingfiberopticramanspectroscopyanddeeplearningalgorithms AT yutingdong rapidmultitaskdiagnosisoforalcancerleveragingfiberopticramanspectroscopyanddeeplearningalgorithms AT zhihuizhu rapidmultitaskdiagnosisoforalcancerleveragingfiberopticramanspectroscopyanddeeplearningalgorithms AT ruiqizhao rapidmultitaskdiagnosisoforalcancerleveragingfiberopticramanspectroscopyanddeeplearningalgorithms AT xinsongma rapidmultitaskdiagnosisoforalcancerleveragingfiberopticramanspectroscopyanddeeplearningalgorithms AT mingxinyu rapidmultitaskdiagnosisoforalcancerleveragingfiberopticramanspectroscopyanddeeplearningalgorithms AT taozhang rapidmultitaskdiagnosisoforalcancerleveragingfiberopticramanspectroscopyanddeeplearningalgorithms |