通过使用自定义的深度学习模型对骨转移进行自动诊断,通过对骨分类进行分类
Yubo Wang1,2, Qiang Lin1,2,3, Shaofang Zhao1,3
1Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou, China.
Current medical imaging
|January 23, 2024
概括
这项研究引入了一种深度学习模型,用于使用骨光学检测在癌症患者中自动检测骨转移. 该模型实现了高精度,证明了改善早期诊断和治疗规划的潜力.
科学领域:
- 医疗成像医学成像
- 在瘤学中使用人工智能
- 核医学是一种核医学.
背景情况:
- 骨转移是癌症患者常见的并发症,约70%的病例影响骨.
- 早期发现骨转移对于有效治疗和改善患者存活率至关重要.
- 深度学习模型越来越多地用于医疗图像分析,在诊断应用中显示出希望.
研究的目的:
- 开发和评估基于深度学习的自动化分类模型,用于从骨光学图像中诊断骨转移.
- 调查卷积神经网络在检测肺癌骨转移中的有效性.
主要方法:
- 设计了一个定制的卷积神经网络 (CNN),包括特征提取和分类子网络.
- 该模型处理了SPECT骨光学图,提取分层特征,将其分类为转移性或非转移性类别.
- 用前后扫描的图像融合,不包括膀,以优化性能.
主要成果:
- 拟议的深度学习模型实现了检测骨转移的曲线下的面积 (AUC) 为0.8489.
- 在排除膀活动后,通过合并前后扫描来获得最佳性能.
- 该模型在各种指标上表现出强的表现,包括精度 (0.8038),精度 (0.8051),回忆 (0.8039) 和F-1得分 (0.8036).
结论:
- 开发的两类分类网络有效地预测了肺癌骨转移的存在.
- 膀活动对自动骨转移诊断产生负面影响,这表明排除它是有益的.
- 对于这个诊断任务,深度学习模型与现有的经典深度学习方法相比显示出更高的性能.
相关概念视频
01:40Bone Remodeling
Bone remodeling is a continuous and balanced process of bone resorption by osteoclasts and bone formation by osteoblasts. In adults, it helps maintain bone mass and calcium homeostasis. While mechanical stress can stimulate turnover as part of the normal maintenance and reparative process, several hormones also regulate bone remodeling.
01:18Classification of Bones
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...