副脊髓肌肉的自动化分析:在腰部CT中使用卷积神经网络进行细分和多参数量化
Junjie Lu1, Yunfei Wang2,3, Haishan Huang4
1Department of Spinal Surgery, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China.
概括
一个新的深度学习工具从CT扫描中准确地细分了八个腰部副脊髓肌肉,从而能够精确量化肌肉参数. 这克服了大型研究的手动细分局限性.
科学领域:
- 放射学 放射学是一门学科.
- 医疗成像医学成像
- 人工智能的人工智能
背景情况:
- 手动细分腰部副脊髓肌肉是艰苦和不一致的.
- 目前的方法限制了全面分析和大规模研究.
研究的目的:
- 开发一种深度学习算法,用于自动细分八个腰椎脊肌.
- 使用CT图像使这些肌肉的多参数量化成为可能.
主要方法:
- 收集CT扫描 (L1到S1脊椎) 并分成训练,验证和测试集.
- 采用六个卷积神经网络来自动细分大心,四角腰部,直立脊柱和多.
- 评估模型使用子相似系数 (DSC),豪斯多夫距离 (HD) 和平均交叉点 (mIoU). 计算了肌肉横截面积,体积,脂肪透,CT密度和副脊髓肌肉指数.
主要成果:
- 在总体上,TransUNet获得了最高的DSC (0.903) 和mIoU (0.841).
- 个体肌肉细分显示了高准确度,与右多元达0.936.93的DSC的0.936.
- 所有量化参数的平均类内相关系数 (ICC) 为0.931,表明与手动细分有很强的一致性.
结论:
- 开发的深度学习工具提供了准确和自动细分的腰椎脊肌.
- 使用这种工具量化肌肉参数显示出与手动测量的高度一致.
- 这有助于对副脊柱肌肉和脊柱相关疾病进行大规模的流行病学研究.
相关概念视频
01:15Spinal Cord: Gross Anatomy
The spinal cord resides within the protective confines of the vertebral column. It is the main pathway for information traveling between the brain and the body. It plays a fundamental role in nearly all bodily functions, from simple reflexes to complex motor movements. The spinal cord begins at the medulla oblongata at the base of the brainstem and extends downward, terminating at the conus medullaris near the first and second lumbar vertebrae. The spinal cord's length in adults is...
01:16Spinal Cord: Cross-sectional Anatomy
The cross-sectional anatomy of the spinal cord offers a detailed view of its complex structure and function within the central nervous system. At the core of the spinal cord lies the gray matter, characterized by its butterfly or "H"-shaped appearance in cross-section. This central region is enveloped by white matter, with the overall structure divided into symmetrical halves by the dorsal median sulcus and the ventral median fissure.
Gray Matter and its Components
Central to the gray matter is...
Gray Matter and its Components
Central to the gray matter is...