多任务深度学习模型用于自动检测和严重程度分级的腰椎脊柱狭窄在MRI:多中心外部验证
Phatcharapon Udomluck1, Watcharaporn Cholamjiak2, Jakkaphong Inpun3
1School of Medicine, University of Phayao, Phayao 56000, Thailand.
Diseases (Basel, Switzerland)
|January 27, 2026
概括
像VGG19这样的深度学习模型与机器学习分类器相结合,可以从MRI扫描中准确地分类腰椎缩 (LSS). 这种自动化方法提供客观和可重复的LSS评估,改善临床决策支持.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 放射学 放射学是一门学科.
背景情况:
- 手动分级的腰椎缩 (LSS) 面临挑战,由于成像的变化和主观性.
- 为了客观和可重复的临床决策,需要对LSS严重性的自动评估.
研究的目的:
- 评估深度学习模型 (VGG19,ConvNeXt-Tiny,DINOv2) 用于自动化LSS分级中的特征提取.
- 评估这些特征在与经典机器学习分类器相结合时的概括性.
主要方法:
- 预训练的深度学习模型 (VGG19,ConvNeXt-Tiny,DINOv2) 从轴性MRI图像中提取了特征.
- 功能被用来训练物流回归,SVM和LightGBM分类器.
- 模型经过内部训练,并根据来自菲亚奥大学医院的数据进行外部验证.
主要成果:
- 使用后勤回归的VGG19功能实现了最高的外部精度 (0.9556) 和F1得分 (0.9558).
- 外部验证显示出优异的歧视 (AUC 0.994-1.000).
- VGG19和ConvNeXt-Tiny表现出良好的通用性,而DINOv2表现出降低的性能.
结论:
- 深度卷积特征,特别是VGG19,与经典的ML分类器相结合,提供了强大的和可泛化的LSS分级.
- 基于CNN的特征提取仍然有效用于脊髓成像分析.
- 这种自动化方法为LSS管理中的临床决策支持提供了一个实际的途径.
更多相关视频
相关概念视频
Multi-input and Multi-variable systems
411
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
In the absence of...
411
Multi-Step Reactions
8.7K
Chemical reactions often occur in a stepwise fashion involving two or more distinct reactions taking place in a sequence. A balanced equation indicates the reacting species and the product species, but it reveals no details about how the reaction occurs at the molecular level. The reaction mechanism (or reaction path) provides details regarding the precise, step-by-step process by which a reaction occurs. Each of the steps in a reaction mechanism is called an elementary reaction. These...
8.7K
Multi-species Conserved Sequences
4.7K
Next-generation sequencing technologies have created large genomic databases of a variety of animals and plants. Ever since the human genome project was completed, scientists studied the genome of primates, mammals, and other phylogenetically distant living beings. Such large-scale studies have provided new insights into the evolutionary relationship between organisms.
Although the genome of each species varies greatly from each other, a few sequences are highly conserved. Such conserved...
Although the genome of each species varies greatly from each other, a few sequences are highly conserved. Such conserved...
4.7K
Insertion of Multi-pass Transmembrane Proteins in the RER
18.3K
The rough ER membrane synthesizes, assembles, and embeds transmembrane proteins in diverse topologies. These proteins function as transporters or channels and can remain in the ER membrane or are sent to the Golgi complex, lysosome, and cell membrane.
The multipass transmembrane proteins are the type IV integral membrane proteins with multiple topogenic sequences determining their spatial arrangement in the ER membrane. Nearly all multipass proteins lack a cleavable signal sequence and use...
The multipass transmembrane proteins are the type IV integral membrane proteins with multiple topogenic sequences determining their spatial arrangement in the ER membrane. Nearly all multipass proteins lack a cleavable signal sequence and use...
18.3K
Multi-pass Transmembrane Proteins and β-barrels
6.5K
In multi-pass transmembrane proteins, the polypeptide chain crosses the membrane more than once. The transmembrane polypeptide chain either forms an α-helix or β-strand structure. α-Helix containing multi-pass transmembrane proteins are ubiquitous, whereas β-strand containing ones are mainly found in gram-negative bacteria, mitochondria, and chloroplasts.
α-Helix containing multi-pass transmembrane proteins
Multi-pass transmembrane proteins such as...
α-Helix containing multi-pass transmembrane proteins
Multi-pass transmembrane proteins such as...
6.5K
Reliability and Validity
13.8K
Reliability and validity are two important considerations that must be made with any type of data collection. Reliability refers to the ability to consistently produce a given result. In the context of psychological research, this would mean that any instruments or tools used to collect data do so in consistent, reproducible ways.
13.8K


