论著摘要 |【AI-CT】使用放射组学与深度学习方法进行膀胱癌治疗反应评估(双语版)

2018-03-14 16:01:43 admin
标签:   深度学习 膀胱癌 治疗评估 CNN

Bladder Cancer Treatment Response Assessment in CT using Radiomics with Deep-Learning

【发表日期】2017.08.18   【来源】Sci Rep. 2017 Aug 18;7(1):8738

作者: Cha KH1, Hadjiiski L2, Chan HP2, Weizer AZ3, Alva A4, Cohan RH2, Caoili EM2, Paramagul C2, Samala RK2.

作者信息:
1. Department of Radiology, The University of Michigan, Ann Arbor, Michigan, 48109, United States. heekon@med.umich.edu.
2. Department of Radiology, The University of Michigan, Ann Arbor, Michigan, 48109, United States.
3. Department of Urology, Comprehensive Cancer Center, The University of Michigan, Ann Arbor, Michigan, 48109, United States.
4. Department of Internal Medicine, Hematology-Oncology, The University of Michigan, Ann Arbor, Michigan, 48109, United States.

摘要

横截面X射线影像已成为大多数恶性实体肿瘤分级的标准。然而,对于一些恶性肿瘤如膀胱癌,准确评估局部病灶情况和了解人体对系统性化疗反应情况的能力受限于当前成像方法。在这项研究中,我们探讨了基于治疗前和治疗后计算机断层扫描(CT)图像的放射组学预测模型能否区分是否进行化疗的膀胱癌的可行性。我们评估了三种独特的放射组学预测模型,每种模型都利用从图像中提取出放射组学特征,采用了不同的基本设计原则:从基于深度学习卷积神经网络(DL-CNN)的模式识别方法到更明确的基于放射组学特征的方法,以及介于两者之间的桥梁法。我们的研究表明,使用基于治疗前和治疗后的膀胱癌患者CT放射组学信息的计算机化评估有助于评估治疗反应。

Abstact

Cross-sectional X-ray imaging has become the standard for staging most solid organ malignancies. However, for some malignancies such as urinary bladder cancer, the ability to accurately assess local extent of the disease and understand response to systemic chemotherapy is limited with current imaging approaches. In this study, we explored the feasibility that radiomics-based predictive models using pre- and post-treatment computed tomography (CT) images might be able to distinguish between bladder cancers with and without complete chemotherapy responses. We assessed three unique radiomics-based predictive models, each of which employed different fundamental design principles ranging from a pattern recognition method via deep-learning convolution neural network (DL-CNN), to a more deterministic radiomics feature-based approach and then a bridging method between the two, utilizing a system which extracts radiomics features from the image patterns. Our study indicates that the computerized assessment using radiomics information from the pre- and post-treatment CT of bladder cancer patients has the potential to assist in assessment of treatment response.

【阅读原文】 PMID: 28821822    PMCID: PMC5562694    DOI: 10.1038/s41598-017-09315-w

标题图片来自于本文


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