一种基于级联变压器的模型,用于预测头癌放射治疗中的3D剂量分布
Tara Gheshlaghi1, Shahabedin Nabavi1, Samireh Shirzadikia2
1Faculty of Computer Science and Engineering, Shahid Beheshti University, Tehran, Iran.
Physics in medicine and biology
|January 19, 2024
概括
这项研究引入了用于放射治疗计划的新型深度学习模型,显著提高了风险器官细分和剂量分布预测的准确性. 该模型提高了癌症护理的治疗精度和效率.
科学领域:
- 医学物理 医学物理
- 人工智能在医学中的应用
- 放射治疗规划 放射治疗规划
背景情况:
- 辐射疗法是癌症治疗的基石,其目的是精确地向瘤输送剂量,同时保护有风险的器官 (OAR).
- 传统的治疗计划是劳动密集的,主观的,并且严重依赖于剂量计师的专业知识.
- 深度学习为自动化和提高辐射剂量预测的准确性提供了一个有希望的途径.
研究的目的:
- 开发和评估一种新的级联深度学习模型,用于同时对OAR进行细分和预测辐射剂量分布.
- 提高辐射治疗规划的效率和客观性.
- 在细分精度和剂量预测准确性方面超越现有方法.
主要方法:
- 一个带有变压器块和多尺度卷积块的级联编码器-解码器网络被设计用于OAR细分.
- 为了剂量分布预测,开发了一个具有金字塔架构的单独级联编码器-解码器网络.
- 该模型在内部头癌数据集 (96名患者) 和公共OpenKBP数据集 (340名患者) 上得到验证.
主要成果:
- 细分子网实现了0.79的Dice分数和2.71的HD95,超过了基线方法.
- 剂量预测子网络的表现优于OpenKBP2020获胜者,剂量和剂量体积直方图分数分别为2.77和1.79.
- 综合端到端模型与相关研究相比,表现优越,特别是在低剂量区域.
结论:
- 拟议的级联深度学习模型准确预测辐射剂量分布和细分OARs.
- 将细分与剂量预测相结合,可以提高模型的性能和临床适用性.
- 这种方法代表了自动化放射治疗规划的重大进步,提供了更高的精度和效率.
更多相关视频
08:34Proton Therapy Delivery and Its Clinical Application in Select Solid Tumor Malignancies
Published on: February 6, 2019
20.4K
07:57Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
Published on: March 24, 2022
2.8K
相关概念视频
01:06Three-Compartment Open Model
The three-compartment open model is a pharmacokinetic model used to describe the distribution and elimination of drugs following extravascular administration. It comprises a central compartment representing the plasma and two peripheral compartments. The highly perfused peripheral compartment represents organs and tissues with a rich blood supply, such as the liver, kidneys, and lungs. The scarcely perfused peripheral compartment represents tissues with lower blood supply, such as adipose...
01:06Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...