Gauze Detection and Segmentation in Minimally Invasive Surgery Video Using Convolutional Neural Networks
Medical instruments detection in laparoscopic video has been carried out to increase the autonomy of surgical robots, evaluate skills or index recordings. However, it has not been extended to surgical gauzes. Gauzes can provide valuable information to numerous tasks in the operating room, but the la...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/14/5180 |
| _version_ | 1797433116138143744 |
|---|---|
| author | Guillermo Sánchez-Brizuela Francisco-Javier Santos-Criado Daniel Sanz-Gobernado Eusebio de la Fuente-López Juan-Carlos Fraile Javier Pérez-Turiel Ana Cisnal |
| author_facet | Guillermo Sánchez-Brizuela Francisco-Javier Santos-Criado Daniel Sanz-Gobernado Eusebio de la Fuente-López Juan-Carlos Fraile Javier Pérez-Turiel Ana Cisnal |
| author_sort | Guillermo Sánchez-Brizuela |
| collection | DOAJ |
| description | Medical instruments detection in laparoscopic video has been carried out to increase the autonomy of surgical robots, evaluate skills or index recordings. However, it has not been extended to surgical gauzes. Gauzes can provide valuable information to numerous tasks in the operating room, but the lack of an annotated dataset has hampered its research. In this article, we present a segmentation dataset with 4003 hand-labelled frames from laparoscopic video. To prove the dataset potential, we analyzed several baselines: detection using YOLOv3, coarse segmentation, and segmentation with a U-Net. Our results show that YOLOv3 can be executed in real time but provides a modest recall. Coarse segmentation presents satisfactory results but lacks inference speed. Finally, the U-Net baseline achieves a good speed-quality compromise running above 30 FPS while obtaining an IoU of 0.85. The accuracy reached by U-Net and its execution speed demonstrate that precise and real-time gauze segmentation can be achieved, training convolutional neural networks on the proposed dataset. |
| first_indexed | 2024-03-09T10:12:33Z |
| format | Article |
| id | doaj.art-72903f1cf4ba4705ab5160a6025ef953 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T10:12:33Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-72903f1cf4ba4705ab5160a6025ef9532023-12-01T22:39:53ZengMDPI AGSensors1424-82202022-07-012214518010.3390/s22145180Gauze Detection and Segmentation in Minimally Invasive Surgery Video Using Convolutional Neural NetworksGuillermo Sánchez-Brizuela0Francisco-Javier Santos-Criado1Daniel Sanz-Gobernado2Eusebio de la Fuente-López3Juan-Carlos Fraile4Javier Pérez-Turiel5Ana Cisnal6Instituto de las Tecnologías Avanzadas de la Producción (ITAP), Universidad de Valladolid, Paseo del Cauce 59, 47011 Valladolid, SpainEscuela Técnica Superior de Ingenieros Industriales, Universidad Politécnica de Madrid, Calle de José Gutiérrez Abascal, 2, 28006 Madrid, SpainInstituto de las Tecnologías Avanzadas de la Producción (ITAP), Universidad de Valladolid, Paseo del Cauce 59, 47011 Valladolid, SpainInstituto de las Tecnologías Avanzadas de la Producción (ITAP), Universidad de Valladolid, Paseo del Cauce 59, 47011 Valladolid, SpainInstituto de las Tecnologías Avanzadas de la Producción (ITAP), Universidad de Valladolid, Paseo del Cauce 59, 47011 Valladolid, SpainInstituto de las Tecnologías Avanzadas de la Producción (ITAP), Universidad de Valladolid, Paseo del Cauce 59, 47011 Valladolid, SpainInstituto de las Tecnologías Avanzadas de la Producción (ITAP), Universidad de Valladolid, Paseo del Cauce 59, 47011 Valladolid, SpainMedical instruments detection in laparoscopic video has been carried out to increase the autonomy of surgical robots, evaluate skills or index recordings. However, it has not been extended to surgical gauzes. Gauzes can provide valuable information to numerous tasks in the operating room, but the lack of an annotated dataset has hampered its research. In this article, we present a segmentation dataset with 4003 hand-labelled frames from laparoscopic video. To prove the dataset potential, we analyzed several baselines: detection using YOLOv3, coarse segmentation, and segmentation with a U-Net. Our results show that YOLOv3 can be executed in real time but provides a modest recall. Coarse segmentation presents satisfactory results but lacks inference speed. Finally, the U-Net baseline achieves a good speed-quality compromise running above 30 FPS while obtaining an IoU of 0.85. The accuracy reached by U-Net and its execution speed demonstrate that precise and real-time gauze segmentation can be achieved, training convolutional neural networks on the proposed dataset.https://www.mdpi.com/1424-8220/22/14/5180convolutional neural networksimage segmentationimage object detectionsurgical tool detectionminimally invasive surgery |
| spellingShingle | Guillermo Sánchez-Brizuela Francisco-Javier Santos-Criado Daniel Sanz-Gobernado Eusebio de la Fuente-López Juan-Carlos Fraile Javier Pérez-Turiel Ana Cisnal Gauze Detection and Segmentation in Minimally Invasive Surgery Video Using Convolutional Neural Networks Sensors convolutional neural networks image segmentation image object detection surgical tool detection minimally invasive surgery |
| title | Gauze Detection and Segmentation in Minimally Invasive Surgery Video Using Convolutional Neural Networks |
| title_full | Gauze Detection and Segmentation in Minimally Invasive Surgery Video Using Convolutional Neural Networks |
| title_fullStr | Gauze Detection and Segmentation in Minimally Invasive Surgery Video Using Convolutional Neural Networks |
| title_full_unstemmed | Gauze Detection and Segmentation in Minimally Invasive Surgery Video Using Convolutional Neural Networks |
| title_short | Gauze Detection and Segmentation in Minimally Invasive Surgery Video Using Convolutional Neural Networks |
| title_sort | gauze detection and segmentation in minimally invasive surgery video using convolutional neural networks |
| topic | convolutional neural networks image segmentation image object detection surgical tool detection minimally invasive surgery |
| url | https://www.mdpi.com/1424-8220/22/14/5180 |
| work_keys_str_mv | AT guillermosanchezbrizuela gauzedetectionandsegmentationinminimallyinvasivesurgeryvideousingconvolutionalneuralnetworks AT franciscojaviersantoscriado gauzedetectionandsegmentationinminimallyinvasivesurgeryvideousingconvolutionalneuralnetworks AT danielsanzgobernado gauzedetectionandsegmentationinminimallyinvasivesurgeryvideousingconvolutionalneuralnetworks AT eusebiodelafuentelopez gauzedetectionandsegmentationinminimallyinvasivesurgeryvideousingconvolutionalneuralnetworks AT juancarlosfraile gauzedetectionandsegmentationinminimallyinvasivesurgeryvideousingconvolutionalneuralnetworks AT javierperezturiel gauzedetectionandsegmentationinminimallyinvasivesurgeryvideousingconvolutionalneuralnetworks AT anacisnal gauzedetectionandsegmentationinminimallyinvasivesurgeryvideousingconvolutionalneuralnetworks |