论著摘要 |【MR】基于放射学的靶向放射治疗计划:用于前列腺癌治疗计划与MRI的计算框架(双语版)

2017-08-19 09:21:34 admin 16

Radiomics based targeted radiotherapy planning (Rad-TRaP): a computational framework for prostate cancer treatment planning with MRI.

发表日期:2016 Nov 10     来源:Radiat Oncol. 

作者:Shiradkar R1Podder TK2Algohary A3Viswanath S3Ellis RJ2Madabhushi A3.

作者介绍

    1.Department of Biomedical Engineering, Case Western Reserve University, Cleveland, 44106, USA. 

    2.Department of Radiation Oncology, Case School of Medicine, Cleveland, 44106, USA.

    3.Department of Biomedical Engineering, Case Western Reserve University, Cleveland, 44106, USA.

背景

放射组学或者计算机提取特征已经表明在靶向前列腺癌(PCa)病变中比多参数MRI(mpMRI)性能优越。放射组学与变形配准工具相结合可以用于靶向放射治疗计划提供框架。

Radiomics or computer - extracted texture features have been shown to achieve superior performance than multiparametric MRI (mpMRI) signal intensities alone in targeting prostate cancer (PCa) lesions. Radiomics along with deformable co-registration tools can be used to develop a framework to generate targeted focal radiotherapy treatment plans.

方法

Rad-TRaP框架包括三个不同的模块。首先,一个模块在mpMRI通过容许机器学习分类器的特征来基于放射组学检测PCa。第二个模块包括多模态变形配准方案从MRI到CT来检测组织、器官和划定的目标体积。第三个模块是在MRI的近距疗法和CT的EBRT中用从MRI到CT的目标描述转移中生产出一个放射组学的剂量计划。

The Rad-TRaP framework comprises three distinct modules. Firstly, a module for radiomics based detection of PCa lesions on mpMRI via a feature enabled machine learning classifier. The second module comprises a multi-modal deformable co-registration scheme to map tissue, organ, and delineated target volumes from MRI onto CT. Finally, the third module involves generation of a radiomics based dose plan on MRI for brachytherapy and on CT for EBRT using the target delineations transferred from the MRI to the CT.

结果

用来自两个不同单位的23个病人的回顾性队列对Rad-TRaP框架进行评估。第一个单位的11个病人用来训练放射组学的分类器,然后用来对第二个单位的12位病人进行肿瘤检测。对于训练机器学习分类器真正的癌症规划是通过有经验的放射肿瘤学家通过多功能参数MRI(mpMRI)、活检部位的知识以及放射科的报告中得来的。检测到的肿瘤区域用来对用mpMRI的近距治疗提供方案,从MRI到CT产生的肿瘤区域对EBRT产生相应的处理。对于每一个BRET和近距疗法都会有3个剂量的方法,整个腺体均匀是目前临床的标准,基于表面的放射组学和基于表面提升放射组学的整个腺体。对比传统的疗法发现有目标的局部治疗在剂量对于OARs中会有一个显著的下降,并且可以确保处方药剂量送到了病灶。[Formula: see text]跟[Formula: see text]相比,对OARs只增加了边缘性的剂量。类似的趋势在EBRT案例中被观察到。

Rad-TRaP framework was evaluated using a retrospective cohort of 23 patient studies from two different institutions. 11 patients from the first institution were used to train a radiomics classifier, which was used to detect tumor regions in 12 patients from the second institution. The ground truth cancer delineations for training the machine learning classifier were made by an experienced radiation oncologist using mpMRI, knowledge of biopsy location and radiology reports. The detected tumor regions were used to generate treatment plans for brachytherapy using mpMRI, and tumor regions mapped from MRI to CT to generate corresponding treatment plans for EBRT. For each of EBRT and brachytherapy, 3 dose plans were generated - whole gland homogeneous ([Formula: see text]) which is the current clinical standard, radiomics based focal ([Formula: see text]), and whole gland with a radiomics based focal boost ([Formula: see text]). Comparison of [Formula: see text] against conventional [Formula: see text] revealed that targeted focal brachytherapy would result in a marked reduction in dosage to the OARs while ensuring that the prescribed dose is delivered to the lesions. [Formula: see text] resulted in only a marginal increase in dosage to the OARs compared to [Formula: see text]. A similar trend was observed in case of EBRT with [Formula: see text] and [Formula: see text] compared to [Formula: see text].

结论

本文呈现了基于放射学的靶向治疗计划,这一方案可以降低器官的用药剂量,同时可以增强药物抵达病灶。

A radiotherapy planning framework to generate targeted focal treatment plans has been presented. The focal treatmentplans generated using the framework showed reduction in dosage to the organs at risk and a boosted dose delivered to the cancerous lesions.

关键词

计算机辅助诊断(CAD),放射组学,治疗计划,前列腺癌

Computer aided diagnosis (CAD); Radiomics; Treatment planning; prostate cancer


阅读原文:10.1186/s13014-016-0718-3


慧影医疗科技(北京)有限公司

地点:北京市海淀区中关村东升科技园B2-C103

电话:400-890-9020

邮箱:radcloud@huiyihuiying.com

关闭
图片
图片
  • 人工智能诊断云平台