Accurate Segmentation and Tracking of Chorda Tympani in Endoscopic Middle Ear Surgery with Artificial Intelligence
Objective: We introduce a novel endoscopic middle ear surgery dataset specifically designed for evaluating deep learning (DL)-based semantic segmentation of chorda tympani. Methods: We curated a dataset comprising 8240 images from 25 patients, divided into a training set (20%, 1648 images), validation set (5%, 412 images), and test set (75%, 6180 images). We employed data enhancement techniques to expand the picture size of the training and validation sets by 5 times (training set: 8240 images, verification set: 2060 images). Subsequently, we employed a multistage transfer learning training method to establish, train, and validate various convolutional neural networks. Results: On the validation set of 2060 labeled images, our proposed network achieved good results, with the U-net exhibiting the highest effectiveness (mIOU = 0.8737, mPA = 0.9263). Furthermore, when applied to the test dataset of 6180 raw images and contrasted with the prediction of otologists, the overall performance of the U-net was excellent (accuracy = 0.911, precision = 0.9823, sensitivity = 0.8777, specificity = 0.9714). Conclusions: Our findings demonstrate that DL can be successfully employed for automatic segmentation of chorda tympani in endoscopic middle ear surgery, yielding high-performance results. This study validates the potential feasibility of future intelligent navigation technologies to assist in endoscopic middle ear surgery.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - year:2023 |
|---|---|
| Enthalten in: |
Ear, nose, & throat journal - (2023) vom: 11. Dez., Seite 1455613231212051 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Ding, Xin [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Artificial intelligence |
|---|
| Anmerkungen: |
Date Revised 12.12.2023 published: Print-Electronic Citation Status Publisher |
|---|
| doi: |
10.1177/01455613231212051 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM365746029 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM365746029 | ||
| 003 | DE-627 | ||
| 005 | 20231229123544.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1177/01455613231212051 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1227.xml |
| 035 | |a (DE-627)NLM365746029 | ||
| 035 | |a (NLM)38083840 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Ding, Xin |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Accurate Segmentation and Tracking of Chorda Tympani in Endoscopic Middle Ear Surgery with Artificial Intelligence |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 12.12.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status Publisher | ||
| 520 | |a Objective: We introduce a novel endoscopic middle ear surgery dataset specifically designed for evaluating deep learning (DL)-based semantic segmentation of chorda tympani. Methods: We curated a dataset comprising 8240 images from 25 patients, divided into a training set (20%, 1648 images), validation set (5%, 412 images), and test set (75%, 6180 images). We employed data enhancement techniques to expand the picture size of the training and validation sets by 5 times (training set: 8240 images, verification set: 2060 images). Subsequently, we employed a multistage transfer learning training method to establish, train, and validate various convolutional neural networks. Results: On the validation set of 2060 labeled images, our proposed network achieved good results, with the U-net exhibiting the highest effectiveness (mIOU = 0.8737, mPA = 0.9263). Furthermore, when applied to the test dataset of 6180 raw images and contrasted with the prediction of otologists, the overall performance of the U-net was excellent (accuracy = 0.911, precision = 0.9823, sensitivity = 0.8777, specificity = 0.9714). Conclusions: Our findings demonstrate that DL can be successfully employed for automatic segmentation of chorda tympani in endoscopic middle ear surgery, yielding high-performance results. This study validates the potential feasibility of future intelligent navigation technologies to assist in endoscopic middle ear surgery | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a artificial intelligence | |
| 650 | 4 | |a chorda tympani | |
| 650 | 4 | |a deep learning | |
| 650 | 4 | |a endoscopic middle ear surgery | |
| 700 | 1 | |a Huang, Yu |e verfasserin |4 aut | |
| 700 | 1 | |a Zhao, Yang |e verfasserin |4 aut | |
| 700 | 1 | |a Tian, Xu |e verfasserin |4 aut | |
| 700 | 1 | |a Feng, Guodong |e verfasserin |4 aut | |
| 700 | 1 | |a Gao, Zhiqiang |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Ear, nose, & throat journal |d 1984 |g (2023) vom: 11. Dez., Seite 1455613231212051 |w (DE-627)NLM000261459 |x 1942-7522 |7 nnns |
| 773 | 1 | 8 | |g year:2023 |g day:11 |g month:12 |g pages:1455613231212051 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1177/01455613231212051 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |j 2023 |b 11 |c 12 |h 1455613231212051 | ||