当前位置: X-MOL 学术IEEE/ACM Trans. Comput. Biol. Bioinform. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-Modal Classification for Human Breast Cancer Prognosis Prediction: Proposal of Deep-Learning Based Stacked Ensemble Model
IEEE/ACM Transactions on Computational Biology and Bioinformatics ( IF 4.5 ) Pub Date : 2020-08-21 , DOI: 10.1109/tcbb.2020.3018467
Nikhilanand Arya 1 , Sriparna Saha 1
Affiliation  

Breast Cancer is a highly aggressive type of cancer generally formed in the cells of the breast. Despite significant advances in the treatment of primary breast cancer in the last decade, there is a dire need to attempt of an accurate predictive model for breast cancer prognosis prediction. Researchers from various disciplines are working together to develop methods to save people from this fatal disease. A good predictive model can help in correct prognosis prediction of breast cancer. This accurate prediction can have several benefits like detection of cancer in the early stage, spare patients from getting unnecessary treatment and medical expenses related to it. Previous works rely mostly on uni-modal data (selected gene expression)for predictive model design. In recent years, however, multi-modal cancer data sets have become available (gene expression, copy number alteration and clinical). Motivated by the enhancement of deep-learning based models, in the current study, we propose to use some deep-learning based predictive models in a stacked ensemble framework to improve the prognosis prediction of breast cancer from available multi-modal data sets. One of the unique advantages of the proposed approach lies in the architecture of the model. It is a two-stage model. Stage one uses a convolutional neural network for feature extraction, while stage two uses the extracted features as input to the stack-based ensemble model. The predictive performance evaluated using different performance measures shows that this model produces better result than already existing approaches. This model results in AUC value of 0.93 and accuracy of 90.2 percent at medium stringency level (Specificity = 95 percent and threshold = 0.45). Keras 2.2.1, along with Tensorflow 1.12, is used for implementing the source code of the model. The source code can be downloaded from Github: https://github.com/nikhilaryan92/BreastCancer .

中文翻译:

人类乳腺癌预后预测的多模态分类:基于深度学习的堆叠集成模型的提议

乳腺癌是一种高度侵袭性的癌症,通常在乳房细胞中形成。尽管在过去十年中原发性乳腺癌的治疗取得了重大进展,但迫切需要尝试建立一种准确的预测模型来预测乳腺癌的预后。来自不同学科的研究人员正在共同努力开发使人们免于这种致命疾病的方法。一个好的预测模型可以帮助正确预测乳腺癌的预后。这种准确的预测可以带来很多好处,例如在早期发现癌症,使患者免于获得不必要的治疗以及与之相关的医疗费用。以前的工作主要依靠单模态数据(选定的基因表达)进行预测模型设计。然而近年来,多模式癌症数据集已经可用(基因表达、拷贝数改变和临床)。受基于深度学习的模型增强的启发,在当前的研究中,我们建议在堆叠集成框架中使用一些基于深度学习的预测模型,以从可用的多模态数据集中改进乳腺癌的预后预测。所提出方法的独特优势之一在于模型的架构。这是一个两阶段模型。第一阶段使用卷积神经网络进行特征提取,而第二阶段使用提取的特征作为基于堆栈的集成模型的输入。使用不同性能度量评估的预测性能表明,该模型比现有方法产生更好的结果。该模型导致 AUC 值为 0。93 和 90.2% 的准确度在中等严格水平(特异性 = 95% 和阈值 = 0.45)。Keras 2.2.1 与 Tensorflow 1.12 一起用于实现模型的源代码。源代码可以从 Github 下载:https://github.com/nikhilaryan92/BreastCancer .
更新日期:2020-08-21
down
wechat
bug