Neoplasms in the Nasal Cavity Identified and Tracked with an Artificial Intelligence-Assisted Nasal Endoscopic Diagnostic System
Objective: We aim to construct an artificial intelligence (AI)-assisted nasal endoscopy diagnostic system capable of preliminary differentiation and identification of nasal neoplasia properties, as well as intraoperative tracking, providing an important basis for nasal endoscopic surgery. Methods: W...
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/12/1/10 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589045980463104 |
|---|---|
| author | Xiayue Xu Boxiang Yun Yumin Zhao Ling Jin Yanning Zong Guanzhen Yu Chuanliang Zhao Kai Fan Xiaolin Zhang Shiwang Tan Zimu Zhang Yan Wang Qingli Li Shaoqing Yu |
| author_facet | Xiayue Xu Boxiang Yun Yumin Zhao Ling Jin Yanning Zong Guanzhen Yu Chuanliang Zhao Kai Fan Xiaolin Zhang Shiwang Tan Zimu Zhang Yan Wang Qingli Li Shaoqing Yu |
| author_sort | Xiayue Xu |
| collection | DOAJ |
| description | Objective: We aim to construct an artificial intelligence (AI)-assisted nasal endoscopy diagnostic system capable of preliminary differentiation and identification of nasal neoplasia properties, as well as intraoperative tracking, providing an important basis for nasal endoscopic surgery. Methods: We retrospectively analyzed 1050 video data of nasal endoscopic surgeries involving four types of nasal neoplasms. Using Deep Snake, U-Net, and Att-Res2-UNet, we developed a nasal neoplastic detection network based on endoscopic images. After deep learning, the optimal network was selected as the initialization model and trained to optimize the SiamMask online tracking algorithm. Results: The Att-Res2-UNet network demonstrated the highest accuracy and precision, with the most accurate recognition results. The overall accuracy of the model established by us achieved an overall accuracy similar to that of residents (0.9707 ± 0.00984), while slightly lower than that of rhinologists (0.9790 ± 0.00348). SiamMask’s segmentation range was consistent with rhinologists, with a 99% compliance rate and a neoplasm probability value ≥ 0.5. Conclusions: This study successfully established an AI-assisted nasal endoscopic diagnostic system that can preliminarily identify nasal neoplasms from endoscopic images and automatically track them in real time during surgery, enhancing the efficiency of endoscopic diagnosis and surgery. |
| format | Article |
| id | doaj-art-5e20b9d0936546ae85a8b098b597872a |
| institution | Kabale University |
| issn | 2306-5354 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj-art-5e20b9d0936546ae85a8b098b597872a2025-01-24T13:22:56ZengMDPI AGBioengineering2306-53542024-12-011211010.3390/bioengineering12010010Neoplasms in the Nasal Cavity Identified and Tracked with an Artificial Intelligence-Assisted Nasal Endoscopic Diagnostic SystemXiayue Xu0Boxiang Yun1Yumin Zhao2Ling Jin3Yanning Zong4Guanzhen Yu5Chuanliang Zhao6Kai Fan7Xiaolin Zhang8Shiwang Tan9Zimu Zhang10Yan Wang11Qingli Li12Shaoqing Yu13Department of Otolaryngology and Neck Surgery, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, ChinaShanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200241, ChinaDepartment of Otolaryngology and Neck Surgery, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, ChinaDepartment of Otolaryngology and Neck Surgery, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, ChinaShanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200241, ChinaDepartment of Otolaryngology and Neck Surgery, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, ChinaDepartment of Otolaryngology and Neck Surgery, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, ChinaDepartment of Otolaryngology and Neck Surgery, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, ChinaDepartment of Otolaryngology and Neck Surgery, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, ChinaDepartment of Otolaryngology and Neck Surgery, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, ChinaDepartment of Otolaryngology and Neck Surgery, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, ChinaShanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200241, ChinaShanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200241, ChinaDepartment of Otolaryngology and Neck Surgery, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, ChinaObjective: We aim to construct an artificial intelligence (AI)-assisted nasal endoscopy diagnostic system capable of preliminary differentiation and identification of nasal neoplasia properties, as well as intraoperative tracking, providing an important basis for nasal endoscopic surgery. Methods: We retrospectively analyzed 1050 video data of nasal endoscopic surgeries involving four types of nasal neoplasms. Using Deep Snake, U-Net, and Att-Res2-UNet, we developed a nasal neoplastic detection network based on endoscopic images. After deep learning, the optimal network was selected as the initialization model and trained to optimize the SiamMask online tracking algorithm. Results: The Att-Res2-UNet network demonstrated the highest accuracy and precision, with the most accurate recognition results. The overall accuracy of the model established by us achieved an overall accuracy similar to that of residents (0.9707 ± 0.00984), while slightly lower than that of rhinologists (0.9790 ± 0.00348). SiamMask’s segmentation range was consistent with rhinologists, with a 99% compliance rate and a neoplasm probability value ≥ 0.5. Conclusions: This study successfully established an AI-assisted nasal endoscopic diagnostic system that can preliminarily identify nasal neoplasms from endoscopic images and automatically track them in real time during surgery, enhancing the efficiency of endoscopic diagnosis and surgery.https://www.mdpi.com/2306-5354/12/1/10computer-assisted surgerynasal cavityartificial intelligencediagnosis |
| spellingShingle | Xiayue Xu Boxiang Yun Yumin Zhao Ling Jin Yanning Zong Guanzhen Yu Chuanliang Zhao Kai Fan Xiaolin Zhang Shiwang Tan Zimu Zhang Yan Wang Qingli Li Shaoqing Yu Neoplasms in the Nasal Cavity Identified and Tracked with an Artificial Intelligence-Assisted Nasal Endoscopic Diagnostic System Bioengineering computer-assisted surgery nasal cavity artificial intelligence diagnosis |
| title | Neoplasms in the Nasal Cavity Identified and Tracked with an Artificial Intelligence-Assisted Nasal Endoscopic Diagnostic System |
| title_full | Neoplasms in the Nasal Cavity Identified and Tracked with an Artificial Intelligence-Assisted Nasal Endoscopic Diagnostic System |
| title_fullStr | Neoplasms in the Nasal Cavity Identified and Tracked with an Artificial Intelligence-Assisted Nasal Endoscopic Diagnostic System |
| title_full_unstemmed | Neoplasms in the Nasal Cavity Identified and Tracked with an Artificial Intelligence-Assisted Nasal Endoscopic Diagnostic System |
| title_short | Neoplasms in the Nasal Cavity Identified and Tracked with an Artificial Intelligence-Assisted Nasal Endoscopic Diagnostic System |
| title_sort | neoplasms in the nasal cavity identified and tracked with an artificial intelligence assisted nasal endoscopic diagnostic system |
| topic | computer-assisted surgery nasal cavity artificial intelligence diagnosis |
| url | https://www.mdpi.com/2306-5354/12/1/10 |
| work_keys_str_mv | AT xiayuexu neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem AT boxiangyun neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem AT yuminzhao neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem AT lingjin neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem AT yanningzong neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem AT guanzhenyu neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem AT chuanliangzhao neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem AT kaifan neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem AT xiaolinzhang neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem AT shiwangtan neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem AT zimuzhang neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem AT yanwang neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem AT qinglili neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem AT shaoqingyu neoplasmsinthenasalcavityidentifiedandtrackedwithanartificialintelligenceassistednasalendoscopicdiagnosticsystem |