相关实验视频

Updated: Jun 12, 2025

Author Spotlight: Enhancing Success of Ultrasound-Guided Neuraxial Anesthesia in Cases with Difficult Anatomy

Author Spotlight: Enhancing Success of Ultrasound-Guided Neuraxial Anesthesia in Cases with Difficult Anatomy

Published on: January 31, 2025

基于人工智能对超声波引导的Quadratus Lumborum块进行自动细分

Qiang Wang¹, Bingxi He^2,3, Jie Yu¹

¹Department of Anesthesiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, No. 17, Panjiayuan Nanli, Chaoyang District, Beijing, 100021, China.

Journal of imaging informatics in medicine

|September 25, 2024

概括

人工智能通过精确识别解剖结构来帮助超声波引导的四角腰部块 (QLB). Q-VUM深度学习模型提高了麻醉师的精度,提高了神经阻断的有效性并减少了并发症.

科学领域:

医学成像医学成像
医学中的人工智能.
麻醉学麻醉学

背景情况:

在腹部和盆腔手术中,超声指导的四角腰部阻断 (QLB) 对于外科手术期间止痛至关重要.
超声波图像的解剖学复杂性和变异性挑战了精确的QLB执行,需要经验丰富的麻醉师.
人工智能 (AI) 为医疗成像中的自动组织识别提供了解决方案.

研究的目的:

开发和评估一个深度学习模型,用于精确细分与QLB相关的解剖结构.
为了提高超声波引导的四角腰部块手术的准确性和可靠性.
帮助麻醉科医生实时识别四角腰肌和周围组织.

主要方法:

基于VGG16架构的U形深度学习网络 (Q-VUM) 的开发.
追溯分析了来自112名患者的3162张超声波图像.
使用mIoU,像素精度和Dice系数等指标评估细分性能.

主要成果:

Q-VUM模型实现了高性能,mIoU为0.734,精度为0.944.
对四角腰部肌肉的特定细分产生了0.711的IOU和0.831.83的Dice系数.
与其他常见的深度学习网络相比,Q-VUM表现出优越的细分性能.

结论:

拟议的Q-VUM模型在实时超声波图像中准确地识别了四角腰部和相关的解剖结构.
这种人工智能工具可以增强麻醉师精确定位神经阻塞部位的能力.
Q-VUM模型有可能减少并发症并提高QLB程序的有效性.

关键词:

卷积神经网络是一种卷积神经网络.深度学习是一种深度学习.图像细分图像细分图像细分四角腰部块块块块块块块超声波学超声波学超声波学

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Published on: March 21, 2021

相关概念视频

Abdominal Regions and Quadrants

Abdominal Regions and Quadrants

To promote clear communication, for instance, about the location of a patient's abdominal pain or a suspicious mass, anatomists and clinicians typically use imaginary lines to categorize the abdominopelvic cavity into either four quadrants or nine regions to identify organs in the cavity.
The simpler quadrants approach, which is more commonly used in medicine, subdivides the cavity with one horizontal and one vertical line that intersects at the patient's umbilicus (navel). The four...