从MRI图像中对肌肉发育不良的分类使用Swin变压器深度学习模型得到了改进
Alfonso Mastropietro1, Nicola Casali1,2, Maria Giovanna Taccogna3
1Istituto di Sistemi e Tecnologie Industriali Intelligenti per il Manifatturiero Avanzato, Consiglio Nazionale delle Ricerche, 20133 Milan, Italy.
Bioengineering (Basel, Switzerland)
|June 27, 2024
概括
深度学习使用MRI扫描准确地分类肌肉发育不良. 斯温变压器模型在区分贝克尔肌肉发育不良和肢体腰带肌肉发育不良2型与健康个体方面表现出卓越的表现.
科学领域:
- 神经学 神经学
- 医疗成像医学成像
- 人工智能的人工智能
背景情况:
- 准确的肌肉发育不良症分类对于有效的患者管理至关重要.
- 骨肌肉MRI是一种关键的诊断工具,但解释可能具有挑战性.
研究的目的:
- 评估深度学习模型,特别是Swin转换器 (SwinT) 和卷积神经网络 (CNN),用于分类肌肉发育不良.
- 为了比较SwinT和CNN在区分健康对照组,贝克尔肌肉发育不良 (BMD) 和四肢腰带肌肉发育不良2型 (LGMD2) 之间的表现.
主要方法:
- 使用T1加权和迪克森序列对75个3T骨肌肉MRI扫描 (54个受试者) 的回顾性分析.
- 训练和验证SwinT和CNN模型的多参数MRI数据,包括脂肪分数 (FF) 图像.
- 基于分类任务的准确性和F-score的绩效评估.
主要成果:
- 斯温特实现了0.96的优异分类准确度,超过了传统的CNN.
- 使用脂肪分数 (FF) 图像作为输入,显著提高了SwinT模型的分类性能.
- 这些模型在区分健康个体,骨质疏松症和LGMD2患者方面表现出有效性.
结论:
- 深度学习,特别是使用FF图像的SwinT架构,为从MRI数据中分类肌肉发育不良提供了非常准确的方法.
- 人工智能驱动的分类有望提高诊断神经肌肉疾病的精度和效率.
- 需要对更大的队列进行进一步的研究,以验证这些发现并探索临床实施.
相关概念视频
Classification of Skeletal Muscle Fibers
56.2K
Skeletal muscles continuously produce ATP to provide the energy that enables muscle contractions. Skeletal muscle fibers can be categorized into three types based on differences in their contraction speed and how they produce ATP, as well as physical differences related to these factors. Most human muscles contain all three muscle fiber types, albeit in varying proportions.
Slow-Twitch Muscle Fibers
Slow oxidative, muscle fibers appear red due to large numbers of capillaries and high levels of...
Slow-Twitch Muscle Fibers
Slow oxidative, muscle fibers appear red due to large numbers of capillaries and high levels of...
56.2K
Satellite Stem Cells and Muscular Dystrophy
2.0K
Satellite stem cells or myosatellite cells are quiescent stem cells that Alexander Mauro first identified in 1961. These cells are located between the sarcolemma, the plasma membrane of muscle fibers, and the basal lamina, the connective tissue sheath covering it. These mononucleated cells are activated in response to muscle injury, can transform into myoblasts, and may form or repair muscle fibers. Myosatellite cells can provide additional myonuclei for muscle regeneration or return to a...
2.0K
Magnetic Resonance Imaging
5.1K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
5.1K


