无监督域自适应剂量预测通过交叉注意力变压器和特定目标知识保存
Jiaqi Cui1, Jianghong Xiao2, Yun Hou3
1School of Computer Science, Sichuan University, Chengdu, P. R. China.
International journal of neural systems
|September 29, 2023
概括
本研究引入了使用交叉注意力转换器的无监督域适应方法,通过利用高发病率直肠癌的数据来改善基于深度学习的宫癌的放射治疗剂量预测.
科学领域:
- 医学物理 医学物理
- 人工智能在医学中的应用
- 在瘤学瘤学.
背景情况:
- 用于放射治疗剂量预测的深度学习模型需要广泛的标记数据,这对于宫癌等低发病率癌症来说很少.
- 无监督域调整 (UDA) 通过将知识从数据丰富的域转移到数据稀缺的域提供了一个解决方案.
- 准确的剂量预测对于优化放射治疗治疗计划和交付至关重要.
研究的目的:
- 开发一种有效的无监督域适应策略,以使用直肠癌数据准确预测宫癌的放射治疗剂量.
- 为了应对有限的标记数据在低发病率癌症放射治疗规划中的挑战.
- 利用跨领域的知识转移来提高剂量预测的准确性.
主要方法:
- 开发了一种基于交叉注意力变压器的编码器,以学习域不变特征,用于对准直肠和宫癌数据.
- 采用多个域分类器来保留特定目标的知识,并提取宫癌的歧视性特征.
- 使用两个独立的卷积神经网络 (CNN) 解码器,为两个域生成准确的剂量图,以弥补变压器缺乏空间感应偏差.
- 知识蒸损失 (KDL) 和域分类损失 (DCL) 被纳入,以增强特征传输和保存域特定信息.
主要成果:
- 提出的方法在宫癌剂量预测方面取得了卓越的定量结果,具体指标[公式:见文本],[公式:见文本]和HI分别为1.446,1.231和0.082.
- 定性评估表明,该方法在预测准确剂量分布方面优于现有方法.
- 统一发展战略有效地将知识从来源 (直肠癌) 转移到目标 (宫癌) 领域.
结论:
- 开发的基于交叉注意力变压器的UDA方法显著提高了对宫癌的放射治疗剂量预测准确度,即使具有有限的标记数据.
- 这种方法为医疗人工智能应用中的数据稀缺性挑战提供了可行的解决方案,特别是在放射治疗规划中.
- 交叉注意力,CNN解码器和专业损失的整合提供了一个强大的框架,用于医疗成像中的域调整.
相关概念视频
01:25Dose-Response Relationship: Selectivity and Specificity
6.9K
Drugs exert their therapeutic effects by interacting with receptors, enzymes, or ion channels that are present throughout the human body. The strength and duration of the interaction between a drug and its target receptor are characterized by the selectivity and specificity of the drug. Selectivity refers to a drug's strong preference for its intended target over other targets. For instance, isoprenaline, a non-selective β-adrenergic agonist, interacts with both β1- and...
6.9K
02:07Improving Translational Accuracy
11.5K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.5K
01:03Dose-Response Relationship: Overview
3.2K
Agonists can bind with and activate receptors, resulting in the formation of drug-receptor complexes. Once formed, these complexes catalyze many biochemical processes at the cellular level and subsequently induce a pharmacologic response. The degree of response is directly proportional to the fraction of activated receptors, which in turn, depends on the concentration of the drug at the receptor site as well as the sensitivity of the receptor. An increase in the administered dose contributes to...
3.2K
01:26Transformers
1.1K
A device that transforms voltages from one value to another using induction is called a transformer. A transformer consists of two separate coils, or windings, wrapped around the same soft iron core. However, they are electrically insulated from each other.
The iron core has a substantial relative permeability. Therefore, the magnetic field lines generated due to the current in one winding are almost entirely confined within the core, such that the same magnetic flux permeates each turn of both...
The iron core has a substantial relative permeability. Therefore, the magnetic field lines generated due to the current in one winding are almost entirely confined within the core, such that the same magnetic flux permeates each turn of both...
1.1K