半监督图像细分使用剩余驱动的平均师和指数式的子损失
Chenyang Mei1, Xiaoguo Yang2, Mi Zhou3
1School of Ophthalmology & Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou 325027, China.
Artificial intelligence in medicine
|February 7, 2024
概括
一种新的剩余驱动的半监督细分方法 (RDMT) 通过减少注释需求来改善医疗图像分析. 这种方法可以提高左心室和光杯细分等任务的性能.
科学领域:
- 计算机视觉 计算机视觉
- 医学图像分析 医学图像分析
- 机器学习 机器学习
背景情况:
- 半监督细分对于减少在计算机视觉和医学成像中需要广泛的专家注释至关重要.
- 像平均教师 (MT) 框架这样的现有方法提供了基础,但可以进一步优化绩效.
- 对于临床诊断和研究来说,对左心室 (LA) 和视力杯 (OC) 等结构的准确细分至关重要.
研究的目的:
- 开发一种新的残余驱动的半监督细分方法 (RDMT),以提高图像细分的效率和准确性.
- 通过模型级残余扰动和指数式的 Dice (eDice) 损失来提高平均教师 (MT) 框架的性能.
- 验证RDMT方法对左心室和光杯细分的具有挑战性的医学成像数据集进行验证.
主要方法:
- 引入了一种新的模型级残余扰动,集成到平均教师 (MT) 框架的指数移动平均 (EMA) 方案中.
- 采用指数级的 Dice (eDice) 损失函数来提高网络对对象边界的灵敏度.
- 在公共LASC和REFUGE数据集上使用V-Net和2D光学杯 (OC) 使用U-Net对3D左心室 (LA) 进行细分. 应用RDMT方法.
主要成果:
- 在RDMT方法中,LA细分的平均Dice分数为0.8776,标记数据为10%.
- 在RDMT方法中,OC细分的平均Dice分数为0.7751,OC细分的标记数据为20%.
- RDMT显著超过了基线平均教师 (MT) 的表现,并表现出与其他最先进的半监督方法相比具有竞争力.
结论:
- 开发的剩余驱动的半监督细分方法 (RDMT) 有效地提高了细分的准确性,同时最大限度地减少了对标记数据的要求.
- 剩余扰动和eDice损失的整合比标准的平均教师框架提供了显著的改进.
- 在医学图像分析中,RDMT具有很强的实际应用潜力,特别是在复杂的结构中,如左心室和光学杯.
相关概念视频
Residuals and Least-Squares Property
7.4K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.4K
Weighted Mean
5.2K
While taking the arithmetic, geometric, or harmonic mean of a sample data set, equal importance is assigned to all the data points. However, all the values may not always be equally important in some data sets. An intrinsic bias might make it more important to give more weightage to specific values over others.
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
5.2K


