相关实验视频

Updated: Jul 23, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

从共聚焦激光内微镜用改进的U-Net进行杯状细胞细分

Dejian Su^1,2, Xiangwei Zheng^1,2, Shaotong Wang³

¹School of Information Science and Engineering, Shandong Normal University, Jinan, People's Republic of China.

Biomedical physics & engineering express

|July 19, 2023

概括

使用改进的U-Net进行自动化杯状细胞细分,可以从共聚焦激光内分显微镜 (CLE) 图像中准确评估胃肠道代谢 (GIM). 与手动分析相比,这种方法提高了准确性和效率,有助于检测胃癌前体.

科学领域:

胃肠病学和医学成像学
计算病理学计算病理学
人工智能在医学中的应用

背景情况:

胃肠转化症 (GIM) 是肠类胃癌的关键前体.
对GIM的准确评估依赖于从共聚焦激光内分显微镜 (CLE) 图像中的杯状细胞 (GC) 分段.
手动GC细分是劳动密集型,容易出现错误,并与CLE图像质量作斗争.

研究的目的:

开发一种自动化和准确的方法,用于CLE图像中的GC细分.
改善GIM对早期胃癌检测的评估.
克服手动细分和现有的自动化方法的局限性.

主要方法:

从62名患者中收集并手动注释了343张CLE图像.
开发了一种改进的U-Net模型,其中包含了像素梯度注意力机制.
该模型侧重于颜色渐变信息,以增强功能地图指导.

主要成果:

拟议的GCSCLE方法实现了高细分性能.
实现了87.95%的IOU交叉点和86.64%的子系数.
在临床环境中,其表现与手动细分相提并论.

结论:

GCSCLE方法为手动GC细分提供了可靠和高效的替代方案.
这种自动化方法可以显著提高细分精度,节省时间和成本.
有助于更好地评估GIM,并有助于早期诊断胃癌.

关键词:

同焦点的激光内微镜.深度学习是一种深度学习.胃肠胃肠道转化症.玻璃杯细胞玻璃杯细胞

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

Correlative Confocal and 3D Electron Microscopy of a Specific Sensory Cell

Correlative Confocal and 3D Electron Microscopy of a Specific Sensory Cell

Published on: July 19, 2015

相关概念视频

Confocal Fluorescence Microscopy

Confocal Fluorescence Microscopy

Confocal microscopy is an advanced microscopic technique. The prime advantage of the confocal microscope over other microscopy techniques is its ability to block the out-of-focus light from the illuminated samples using pinholes. It is widely used with fluorescence optics to obtain high-resolution, sharp contrast images. Unlike optical microscopes, confocal microscopes use a focused beam of light laser to scan the entire sample surface at different z-planes. These microscopes are, therefore,...