A Multi-Task Convolutional Neural Network for Semantic Segmentation and Event Detection in Laparoscopic Surgery
Journal of Personalized Medicine · 25.02.2023 · 13 (3) · 413
DOI: 10.3390/jpm13030413 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Personalized Medicine, online erschienen am 25.02.2023. Verfasst von Giorgia Marullo und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Management, Production, and Design Engineering, Polytechnic University of Turin, 10129 Turin, Italy. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The current study presents a multi-task end-to-end deep learning model for real-time blood accumulation detection and tools semantic segmentation from a laparoscopic surgery video. Intraoperative bleeding is one of the most problematic aspects of laparoscopic surgery. It is challenging to control and limits the visibility of the surgical site. Consequently, prompt treatment is required to avoid undesirable outcomes. This system exploits a shared backbone based on the encoder of the U-Net architecture and two separate branches to classify the blood accumulation event and output the segmentation map, respectively. Our main contribution is an efficient multi-task approach that achieved satisfactory results during the test on surgical videos, although trained with only RGB images and no other additional information. The proposed multi-tasking convolutional neural network did not employ any pre- or postprocessing step. It achieved a Dice Score equal to 81.89% for the semantic segmentation task and an accuracy of 90.63% for the event detection task. The results demonstrated that the concurrent tasks were properly combined since the common backbone extracted features proved beneficial for tool segmentation and event detection. Indeed, active bleeding usually happens when one of the instruments closes or interacts with anatomical tissues, and it decreases when the aspirator begins to remove the accumulated blood. Even if different aspects of the presented methodology could be improved, this work represents a preliminary attempt toward an end-to-end multi-task deep learning model for real-time video understanding.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Management, Production, and Design Engineering, Polytechnic University of Turin, 10129 Turin, Italy.
- Division of Urology, Department of Oncology, School of Medicine, University of Turin, 10124 Turin, Italy.
ORCID-Profile: Giorgia Marullo, Leonardo Tanzi, Luca Ulrich, Francesco Porpiglia
Zitieren
APA
Marullo, G., Tanzi, L., Ulrich, L., Porpiglia, F., & Vezzetti, E. (2023). A Multi-Task Convolutional Neural Network for Semantic Segmentation and Event Detection in Laparoscopic Surgery. Journal of Personalized Medicine, 13(3), 413. https://doi.org/10.3390/jpm13030413
Vancouver
Marullo G, Tanzi L, Ulrich L, Porpiglia F, Vezzetti E. A Multi-Task Convolutional Neural Network for Semantic Segmentation and Event Detection in Laparoscopic Surgery. Journal of Personalized Medicine. 2023;13(3):413. doi:10.3390/jpm13030413
BibTeX
@article{Marullo2023,
author = {Marullo, Giorgia and Tanzi, Leonardo and Ulrich, Luca and Porpiglia, Francesco and Vezzetti, Enrico},
title = {A Multi-Task Convolutional Neural Network for Semantic Segmentation and Event Detection in Laparoscopic Surgery},
journal = {Journal of Personalized Medicine},
year = {2023},
volume = {13},
number = {3},
pages = {413},
doi = {10.3390/jpm13030413}
}
EUVIMED