Reinforcement Learning Based Vocal Fold Localization in Preoperative Neck CT for Injection Laryngoplasty
Transcutaneous injection laryngoplasty is a well-known procedure for treating a paralyzed vocal fold by injecting augmentation material to it. Hence, vocal fold localization plays a vital role in the preoperative planning, as the fold location is required to determine the optimal injection route. In...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/1/262 |
| _version_ | 1797626291118145536 |
|---|---|
| author | Walid Abdullah Al Wonjae Cha Il Dong Yun |
| author_facet | Walid Abdullah Al Wonjae Cha Il Dong Yun |
| author_sort | Walid Abdullah Al |
| collection | DOAJ |
| description | Transcutaneous injection laryngoplasty is a well-known procedure for treating a paralyzed vocal fold by injecting augmentation material to it. Hence, vocal fold localization plays a vital role in the preoperative planning, as the fold location is required to determine the optimal injection route. In this communication, we propose a mirror environment based reinforcement learning (RL) algorithm for localizing the right and left vocal folds in preoperative neck CT. RL-based methods commonly showed noteworthy outcomes in general anatomic landmark localization problems in recent years. However, such methods suggest training individual agents for localizing each fold, although the right and left vocal folds are located in close proximity and have high feature-similarity. Utilizing the lateral symmetry between the right and left vocal folds, the proposed mirror environment allows for a single agent for localizing both folds by treating the left fold as a flipped version of the right fold. Thus, localization of both folds can be trained using a single training session that utilizes the inter-fold correlation and avoids redundant feature learning. Experiments with 120 CT volumes showed improved localization performance and training efficiency of the proposed method compared with the standard RL method. |
| first_indexed | 2024-03-11T10:08:20Z |
| format | Article |
| id | doaj.art-d97604530a874600940749af927b686e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T10:08:20Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-d97604530a874600940749af927b686e2023-11-16T14:52:54ZengMDPI AGApplied Sciences2076-34172022-12-0113126210.3390/app13010262Reinforcement Learning Based Vocal Fold Localization in Preoperative Neck CT for Injection LaryngoplastyWalid Abdullah Al0Wonjae Cha1Il Dong Yun2Division of Computer Engineering, Hankuk University of Foreign Studies, Yongin 17035, Republic of KoreaDepartment of Otorhinolaryngology-Head and Neck Surgery, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam 13620, Republic of KoreaDivision of Computer Engineering, Hankuk University of Foreign Studies, Yongin 17035, Republic of KoreaTranscutaneous injection laryngoplasty is a well-known procedure for treating a paralyzed vocal fold by injecting augmentation material to it. Hence, vocal fold localization plays a vital role in the preoperative planning, as the fold location is required to determine the optimal injection route. In this communication, we propose a mirror environment based reinforcement learning (RL) algorithm for localizing the right and left vocal folds in preoperative neck CT. RL-based methods commonly showed noteworthy outcomes in general anatomic landmark localization problems in recent years. However, such methods suggest training individual agents for localizing each fold, although the right and left vocal folds are located in close proximity and have high feature-similarity. Utilizing the lateral symmetry between the right and left vocal folds, the proposed mirror environment allows for a single agent for localizing both folds by treating the left fold as a flipped version of the right fold. Thus, localization of both folds can be trained using a single training session that utilizes the inter-fold correlation and avoids redundant feature learning. Experiments with 120 CT volumes showed improved localization performance and training efficiency of the proposed method compared with the standard RL method.https://www.mdpi.com/2076-3417/13/1/262injection laryngoplastyneck CTvocal fold localizationdeep learningreinforcement learningmirror environment |
| spellingShingle | Walid Abdullah Al Wonjae Cha Il Dong Yun Reinforcement Learning Based Vocal Fold Localization in Preoperative Neck CT for Injection Laryngoplasty Applied Sciences injection laryngoplasty neck CT vocal fold localization deep learning reinforcement learning mirror environment |
| title | Reinforcement Learning Based Vocal Fold Localization in Preoperative Neck CT for Injection Laryngoplasty |
| title_full | Reinforcement Learning Based Vocal Fold Localization in Preoperative Neck CT for Injection Laryngoplasty |
| title_fullStr | Reinforcement Learning Based Vocal Fold Localization in Preoperative Neck CT for Injection Laryngoplasty |
| title_full_unstemmed | Reinforcement Learning Based Vocal Fold Localization in Preoperative Neck CT for Injection Laryngoplasty |
| title_short | Reinforcement Learning Based Vocal Fold Localization in Preoperative Neck CT for Injection Laryngoplasty |
| title_sort | reinforcement learning based vocal fold localization in preoperative neck ct for injection laryngoplasty |
| topic | injection laryngoplasty neck CT vocal fold localization deep learning reinforcement learning mirror environment |
| url | https://www.mdpi.com/2076-3417/13/1/262 |
| work_keys_str_mv | AT walidabdullahal reinforcementlearningbasedvocalfoldlocalizationinpreoperativeneckctforinjectionlaryngoplasty AT wonjaecha reinforcementlearningbasedvocalfoldlocalizationinpreoperativeneckctforinjectionlaryngoplasty AT ildongyun reinforcementlearningbasedvocalfoldlocalizationinpreoperativeneckctforinjectionlaryngoplasty |