使用卷积神经网络的腰椎脊髓缩X射线图像的分类
Wutong Chen1,2, Du Junsheng3,4, Yanzhen Chen5
1Hubei Key Laboratory of Tumor Microenvironment and Immunotherapy, Three Gorges University, Yichang, 443002, Hubei, China.
Journal of imaging informatics in medicine
|April 18, 2024
概括
一个深层卷积神经网络 (DCNN) 已开发,以识别X射线中的脊髓解剖或脊髓解剖. 人工智能模型表现出高准确度,在识别这些腰椎状况时优于人类专家诊断.
科学领域:
- 放射学 放射学是一门学科.
- 人工智能的人工智能
- 医学成像分析 医学成像分析
背景情况:
- 脊髓溶解和脊髓溶解是导致腰部疼痛的常见原因,特别是在年轻人群中.
- 准确的诊断依赖于解释复杂的放射图像,往往需要专门的专业知识.
- 当前的诊断方法可能会耗时,并且受观察者之间的变化影响.
研究的目的:
- 开发和验证深度卷积神经网络 (DCNN) 用于自动识别脊髓解剖或脊髓解剖.
- 评估DCNN模型对人类专家诊断的诊断性能.
- 评估模型在不同成像数据集中概括的能力.
主要方法:
- 收集和分类了2449张腰部侧面和动态X射线图像的数据集.
- 使用EfficientNetV2-M架构进行DCNN模型的培训和验证.
- 该模型的性能在一个独立的测试集上严格评估,使用准确度,灵敏度,特异性和F1得分,并与骨科医生和放射科医生的诊断进行了比较.
主要成果:
- 该DCNN模型实现了高性能指标:92.0%的准确性,91.9%的精度,92.2%的灵敏性,95.7%的特异性和92.0%的F1得分.
- 该模型的性能超过了人类专家组的平均性能 (平均准确率为89.0%).
- 梯度加权类激活映射 (Grad-CAM) 可视化了该模型的重点是脊椎间前区域.
结论:
- 一个DCNN模型已成功开发和验证,用于在腰部X射线图上准确检测脊髓解剖或脊髓解剖.
- 人工智能模型展示了作为一个有价值的工具来帮助临床医生诊断这些脊柱疾病的潜力.
- DCNN提供了一种可靠和有效的方法来识别腰椎脊髓解剖或脊髓解剖,从而有可能改善诊断工作流程.
相关概念视频
01:54The Spinal Cord
The spinal cord is the body’s major nerve tract of the central nervous system, communicating afferent sensory information from the periphery to the brain and efferent motor information from the brain to the body. The human spinal cord extends from the hole at the base of the skull, or foramen magnum, to the level of the first or second lumbar vertebra.
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...