实时喉病变视频对象检测网络
Yan Wang1,2, Yiran Pan3,4, Wulin Wen5
1School of Computer Science & Technology, Xi`an University of Posts & Telecommunications, Xi'an, 710121, China. wangyanlxz@126.com.
Journal of imaging informatics in medicine
|February 6, 2026
概括
一个新的深度学习模型,DynSTPN,通过使用参考框架来克服图像质量问题,提高了视频中的鼻喉瘤检测. 这种方法提高了诊断准确度和临床应用的速度.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 计算机视觉 计算机视觉
背景情况:
- 鼻喉瘤的早期诊断对于患者的治疗结果至关重要.
- 深度学习在静态图像损伤检测方面表现出色,但在像动作模糊和文物等视频质量问题上扎.
- 现有的方法在具有挑战性的内镜视频条件下检测病变是不理想的.
研究的目的:
- 开发一个新的深度学习网络,DynSTPN,用于在鼻喉内镜视频中准确检测病变.
- 为应对动作模糊,不均曝光和内镜视频分析中文物所带来的挑战.
- 为了提高临床鼻喉检查的实时检测能力.
主要方法:
- 提出了一个两阶段的视频损伤检测网络,DynSTPN.
- 实施了一个动态提示生成器,使用参考框架的时空特征来缓解质量退化.
- 引入了自适应式可差异化门机制,以整合参考框架信息,以进行增强的推理框架分析.
主要成果:
- 在NLLVOD数据集上,DynSTPN实现了79.6%的卓越检测准确度和29.4 FPS的速度,满足实时临床要求.
- 在NLLVOD数据集上表现优于SOTA静态图像探测器YOLOv12-M.
- 与SOTA方法相比,在ImageNet VID数据集上显示了检测准确性和效率之间的强烈平衡.
结论:
- DynSTPN有效地利用视频参考框架,在具有挑战性的内镜场景中提高病变检测性能.
- 拟议的方法显著提高了比现有的静态和基于视频的方法的准确性和效率.
- DynSTPN显示了对实时鼻喉瘤诊断的增强临床适用性.
相关概念视频
Real Time RT-PCR
65.3K
Real-time reverse transcription-polymerase chain reaction, or Real-time RT-PCR, is an analytical tool used to determine the expression level of target genes. The method involves converting mRNA to complementary DNA with the help of an enzyme known as reverse transcriptase, followed by the PCR amplification of the cDNA. These two processes can be performed simultaneously in a single tube or separately as a two-step reaction.
The real-time quantification of the number of amplified products is...
The real-time quantification of the number of amplified products is...
65.3K
Protein Networks
4.6K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.6K
Protein Networks
2.9K
2.9K
Network Covalent Solids
16.2K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.2K
Velocity of an Object
207
Understanding how an object moves along a path requires distinguishing between motion over a time span and motion at a precise moment. A useful example is a vehicle traveling along a straight and level path, where its position at any given time is known. The initial step in analyzing this motion is to measure how far the vehicle travels over a fixed time period. This measurement, called average velocity, is computed by dividing the total change in position by the duration over which the change...
207
Potential Due to a Polarized Object
803
A neutral atom consists of a positively charged nucleus surrounded by a negatively charged electron cloud. When placed in an external electric field, the external electric force pulls the electrons and nucleus apart, opposite to the intrinsic attraction between the nucleus and the electrons. The opposing forces balance each other with a slight shift between the center of masses of the nucleus and the electron cloud, resulting in a polarized atom. On the other hand, a few molecules, like water,...
803


