期刊
PROGRESS IN ARTIFICIAL INTELLIGENCE AND PATTERN RECOGNITION
卷 13055, 期 -, 页码 124-133出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-030-89691-1_13
关键词
Nerve segmentation; U-Net; Deep learning; Ultrasound; Peripheral nerve blocking
类别
资金
- Doctorate Scholarship Convocatoria del Fondo de Ciencia, Tecnologia e Innovacion del Sistema General de Regalias para la conformacion de una lista de proyectos elegibles para ser viabilizados, priorizados y aprobados por el OCAD en el marco del Programa d
- [111084467950]
Peripheral Nerve Blocking (PNB) is a regional anesthesia procedure commonly guided by ultrasound images. An automatic nerve segmentation system can assist specialists in performing successful nerve blocks. The proposed deep neural network, C-UNet, outperforms conventional methods in ultrasound-guided regional anesthesia.
Peripheral Nerve Blocking (PNB) is a regional anesthesia procedure that delivers an anesthetic in the proximity of a nerve to avoid nociceptive transmission. Anesthesiologists have widely used ultrasound images to guide the PNB due to their low cost, non-invasivity, and lack of radiation. Due to the difficulties in visually locating the target nerve, automatic nerve segmentation systems attempt to support the specialist to perform a successful nerve block. This work introduces a deep neural network for automatic nerve segmentation in ultrasound images. The proposed approach consists of a conditioned U-Net model that includes the kind of target nerve as a second input allowing the network to learn new features to improve the segmentation. The model is trained and tested on a dataset holding four different peripheral nerves, achieving an average Dice coefficient of 0.70. Results show that the proposed C-UNet outperforms the conventional U-Net, benefiting the ultrasound-guided regional anesthesia.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据