卷积LSTM模型用于预测腹部运动的电影图像预测
J Weng1, S H V Bhupathiraju2, T Samant3
1Department of Radiation Oncology, University of Florida, Gainesville, FL, United States of America.
Physics in medicine and biology
|March 22, 2024
概括
我们开发了一种卷积式长期短期记忆 (convLSTM) 模型,用电影核磁共振成像来预测腹部器官运动. 这通过解决MR-Linac系统中的延迟来提高实时放射治疗的准确性.
科学领域:
- 医学物理 医学物理
- 放射治疗技术 放射治疗技术
- 人工智能在医学中的应用
背景情况:
- 磁共振线性加速器 (MR-Linac) 系统中的延迟阻碍了实时放射治疗中准确的目标覆盖.
- 精确预测腹部器官的运动对于减轻这一挑战至关重要.
研究的目的:
- 开发和评估一个卷积长期短期记忆 (convLSTM) 模型,用于增强腹部器官的运动预测.
- 通过解决MR-Linac系统延迟,提高封闭实时放射治疗的准确性.
主要方法:
- 使用了一个具有序列对一架构的convLSTM模型,处理六个输入来预测一个输出.
- 使用了来自17名患者的二维电影磁共振 (cine-MR) 成像数据,重点是胃,肝脏,胰腺和脏.
- 结构相似性指数测量 (SSIM) 被用作损失函数,使用SSIM,NMSE,NCC和PSNR来评估性能.
主要成果:
- 在convLSTM模型中,平均SSIM值为0.54 (胃),0.64 (肝脏),0.77 (脏) 和0.66 (胰腺),用于预测前四的运动.
- 通过微调转移学习进一步改善了SSIM值,为0.69肝脏和0.78脏.
- 该模型通过使用Elekta Unity MR-Linac等效序列,对多个腹部器官进行了准确的运动预测.
结论:
- 开发的convLSTM模型有效地预测了使用cine-MR成像的腹部器官运动.
- 这种预测能力对于减少MR-Linac系统的延迟至关重要.
- 这项进展有可能提高腹部癌症实时放射治疗的精度和疗效.
相关概念视频
01:24Convolution: Math, Graphics, and Discrete Signals
250
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
250
01:20Convolution Properties I
147
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
147
01:17Convolution Properties II
198
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
198