Multi-Stage Temporal Convolutional Network with Moment Loss and Positional Encoding for Surgical Phase Recognition
In recent times, many studies concerning surgical video analysis are being conducted due to its growing importance in many medical applications. In particular, it is very important to be able to recognize the current surgical phase because the phase information can be utilized in various ways both d...
| المؤلفون الرئيسيون: | , , , |
|---|---|
| التنسيق: | مقال |
| اللغة: | English |
| منشور في: |
MDPI AG
2022-12-01
|
| سلاسل: | Diagnostics |
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://www.mdpi.com/2075-4418/13/1/107 |
| _version_ | 1827760838789824512 |
|---|---|
| author | Minyoung Park Seungtaek Oh Taikyeong Jeong Sungwook Yu |
| author_facet | Minyoung Park Seungtaek Oh Taikyeong Jeong Sungwook Yu |
| author_sort | Minyoung Park |
| collection | DOAJ |
| description | In recent times, many studies concerning surgical video analysis are being conducted due to its growing importance in many medical applications. In particular, it is very important to be able to recognize the current surgical phase because the phase information can be utilized in various ways both during and after surgery. This paper proposes an efficient phase recognition network, called MomentNet, for cholecystectomy endoscopic videos. Unlike LSTM-based network, MomentNet is based on a multi-stage temporal convolutional network. Besides, to improve the phase prediction accuracy, the proposed method adopts a new loss function to supplement the general cross entropy loss function. The new loss function significantly improves the performance of the phase recognition network by constraining un-desirable phase transition and preventing over-segmentation. In addition, MomnetNet effectively applies positional encoding techniques, which are commonly applied in transformer architectures, to the multi-stage temporal convolution network. By using the positional encoding techniques, MomentNet can provide important temporal context, resulting in higher phase prediction accuracy. Furthermore, the MomentNet applies label smoothing technique to suppress overfitting and replaces the backbone network for feature extraction to further improve the network performance. As a result, the MomentNet achieves 92.31% accuracy in the phase recognition task with the Cholec80 dataset, which is 4.55% higher than that of the baseline architecture. |
| first_indexed | 2024-03-11T10:04:48Z |
| format | Article |
| id | doaj.art-46e10a71b40842a4997648e4752725c3 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T10:04:48Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-46e10a71b40842a4997648e4752725c32023-11-16T15:08:56ZengMDPI AGDiagnostics2075-44182022-12-0113110710.3390/diagnostics13010107Multi-Stage Temporal Convolutional Network with Moment Loss and Positional Encoding for Surgical Phase RecognitionMinyoung Park0Seungtaek Oh1Taikyeong Jeong2Sungwook Yu3School of Electrical and Electronics Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 06974, Republic of KoreaSchool of Electrical and Electronics Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 06974, Republic of KoreaSchool of Artificial Intelligence Convergence, Hallym University, Chuncheon 24252, Republic of KoreaSchool of Electrical and Electronics Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 06974, Republic of KoreaIn recent times, many studies concerning surgical video analysis are being conducted due to its growing importance in many medical applications. In particular, it is very important to be able to recognize the current surgical phase because the phase information can be utilized in various ways both during and after surgery. This paper proposes an efficient phase recognition network, called MomentNet, for cholecystectomy endoscopic videos. Unlike LSTM-based network, MomentNet is based on a multi-stage temporal convolutional network. Besides, to improve the phase prediction accuracy, the proposed method adopts a new loss function to supplement the general cross entropy loss function. The new loss function significantly improves the performance of the phase recognition network by constraining un-desirable phase transition and preventing over-segmentation. In addition, MomnetNet effectively applies positional encoding techniques, which are commonly applied in transformer architectures, to the multi-stage temporal convolution network. By using the positional encoding techniques, MomentNet can provide important temporal context, resulting in higher phase prediction accuracy. Furthermore, the MomentNet applies label smoothing technique to suppress overfitting and replaces the backbone network for feature extraction to further improve the network performance. As a result, the MomentNet achieves 92.31% accuracy in the phase recognition task with the Cholec80 dataset, which is 4.55% higher than that of the baseline architecture.https://www.mdpi.com/2075-4418/13/1/107surgical phase recognitionCholec80moment losspositional encodinglabel smoothingEfficientNet |
| spellingShingle | Minyoung Park Seungtaek Oh Taikyeong Jeong Sungwook Yu Multi-Stage Temporal Convolutional Network with Moment Loss and Positional Encoding for Surgical Phase Recognition Diagnostics surgical phase recognition Cholec80 moment loss positional encoding label smoothing EfficientNet |
| title | Multi-Stage Temporal Convolutional Network with Moment Loss and Positional Encoding for Surgical Phase Recognition |
| title_full | Multi-Stage Temporal Convolutional Network with Moment Loss and Positional Encoding for Surgical Phase Recognition |
| title_fullStr | Multi-Stage Temporal Convolutional Network with Moment Loss and Positional Encoding for Surgical Phase Recognition |
| title_full_unstemmed | Multi-Stage Temporal Convolutional Network with Moment Loss and Positional Encoding for Surgical Phase Recognition |
| title_short | Multi-Stage Temporal Convolutional Network with Moment Loss and Positional Encoding for Surgical Phase Recognition |
| title_sort | multi stage temporal convolutional network with moment loss and positional encoding for surgical phase recognition |
| topic | surgical phase recognition Cholec80 moment loss positional encoding label smoothing EfficientNet |
| url | https://www.mdpi.com/2075-4418/13/1/107 |
| work_keys_str_mv | AT minyoungpark multistagetemporalconvolutionalnetworkwithmomentlossandpositionalencodingforsurgicalphaserecognition AT seungtaekoh multistagetemporalconvolutionalnetworkwithmomentlossandpositionalencodingforsurgicalphaserecognition AT taikyeongjeong multistagetemporalconvolutionalnetworkwithmomentlossandpositionalencodingforsurgicalphaserecognition AT sungwookyu multistagetemporalconvolutionalnetworkwithmomentlossandpositionalencodingforsurgicalphaserecognition |