在适应性放射治疗中,基于CBCT的合成CT的不确定性估计的变压器CycleGAN
Branimir Rusanov1,2,3, Ghulam Mubashar Hassan1, Mark Reynolds1
1School of Physics, Mathematics and Computing, University of Western Australia, Perth, Western Australia, Australia.
Physics in medicine and biology
|January 10, 2024
概括
这项研究引入了一种新的CycleGAN-Best模型,用于从CBCT生成合成CT (sCT),显著提高适应性放射治疗的解剖完整性和Hounsfield单元精度. 该模型利用先进的图像质量指标和不确定性估计,以获得强大的临床应用.
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:
- 从束CTCT (CBCT) 进行合成CT (sCT) 的临床实施需要高解剖完整性,Hounsfield单位 (HU) 精度和图像质量.
- 现有方法在实现适应性放射治疗所需的精度方面面临挑战.
研究的目的:
- 开发和评估一个先进的CycleGAN模型 (CycleGAN-Best) 来从CBCT生成高保真性sCT.
- 实施可靠的图像质量量量化,使用Fréchet初始距离 (FID) 和不确定性估计进行风险评估.
主要方法:
- 在CycleGAN框架内使用视觉转换器和解剖学敏感损失功能.
- 通过废除研究和使用FID,马指数和细分分析的评估进行实证优化.
- 纳入蒙特卡洛脱落 (MCD) 和测试时间增长 (TTA) 进行不确定性估计.
主要成果:
- 循环GAN-Best实现了优越的图像质量,FID为42.11 ± 5.99和MAE为25.00 ± 1.97 HU,表现优于基线模型和CBCT.
- 玛1%/1毫米的通过率达到CycleGAN-Best的98.66±0.54%,明显高于CBCT的86.72±2.55%.
- FID与感知图像质量有很强的相关性 (r = -0.83),而不确定性图与合成错误有相关性.
结论:
- 循环GAN-Best模型有效地抑制了文物,确保了解剖学准确性和改善了sCT生成的HU准确性.
- 对于图像质量评估,FID是一个比MAE等基于对齐的指标更可靠的指标.
- 不确定性估计为适应性放射治疗中的模型风险评估和质量保证提供了临床相关的见解.
相关概念视频
01:10Computed Tomography
4.5K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
4.5K
01:25Transformers with Off-Nominal Turns Ratios
157
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
157