论著摘要 |【AI-PET/CT】一种在PET / CT图像中评估肿瘤患者的治疗反应的人工神经网络方法

2018-03-21 19:02:41 admin
标签:   人工智能 人工神经网络 治疗反应评估 PET/CT

An artificial neural networks approach for assessment treatment response in oncological patients using PET/CT images.

发表日期: 2017.02.13   来源:BMC Med Imaging. 2017 Feb 13;17(1):13.

作者:

Nogueira MA1, Abreu PH2, Martins P1, Machado P1, Duarte H3, Santos J3.

作者介绍:

1. CISUC - Department of Informatics Engineering - University of Coimbra, - Pólo II Pinhal de Marrocos, Coimbra, 3030-290, Portugal.

2. CISUC - Department of Informatics Engineering - University of Coimbra, - Pólo II Pinhal de Marrocos, Coimbra, 3030-290, Portugal. pha@dei.uc.pt.

3. IPO-Porto Research Centre (CI-IPOP), Rua Dr. António Bernardino de Almeida, Porto, 4200-072, Portugal.

摘要

Abstact

背景

正电子发射断层扫描-计算机断层扫描(PET / CT)成像是评估某些肿瘤疾病治疗反应的基础。在实践中,这种评估是由专家手动完成的,这是相当复杂和耗时的。评估方法提出后,无法保证可靠性。用于评估治疗反应的病灶,其治疗前后影像描述符的使用仍然是一个需要探索的领域。

Background

Positron Emission Tomography - Computed Tomography (PET/CT) imaging is the basis for the evaluation of response-to-treatment of several oncological diseases. In practice, such evaluation is manually performed by specialists, which is rather complex and time-consuming. Evaluation measures have been proposed, but with questionable reliability. The usage of before and after-treatment image descriptors of the lesions for treatment response evaluation is still a territory to be explored.

方法

在该项目中,基于从PET / CT提取的图像特征,使用人工神经网络方法自动评估患有神经内分泌肿瘤和霍奇金淋巴瘤的患者的治疗反应。

Methods

In this project, Artificial Neural Network approaches were implemented to automatically assess treatment response of patients suffering from neuroendocrine tumors and Hodgkyn lymphoma, based on image features extracted from PET/CT.

结果

结果表明,所考虑的特征集实现了非常高的分类性能,特别是在数据适当平衡的情况下。

Results

The results show that the considered set of features allows for the achievement of very high classification performances, especially when data is properly balanced.

结论

生成综合数据并基于PCA方法降维到只有两个成分之后,LVQNN确保了关于4个响应治疗类别的100%,100%,96.3%和100%的分类准确性。

Conclusions

After synthetic data generation and PCA-based dimensionality reduction to only two components, LVQNN assured classification accuracies of 100%, 100%, 96.3% and 100% regarding the 4 response-to-treatment classes.

关键词:

人工神经网络;影像描述符;PET/CT影像;治疗反应评估

Keywords:

Artificial neural networks; Images descriptors; PET/CT images; Treatment response assessment

阅读原文:PMID: 28193201  PMCID: PMC5307785  DOI: 10.1186/s12880-017-0181-0


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