Reliable gene mutation prediction in clear cell renal cell carcinoma through multi-classifier multi-objective radiogenomics model.
Reliable gene mutation prediction in clear cell renal cell carcinoma through multi-classifier multi-objective radiogenomics model.
复制标题
DOI：
10.1088/1361-6560/aae5cd
复制
发表时间：
2018-10-24
影响因子：
3.5
通讯作者：
Wang J
中科院分区：
文献类型：
--
作者：
Chen X;Zhou Z;Hannan R;Thomas K;Pedrosa I;Kapur P;Brugarolas J;Mou X;Wang J
遗传学研究已经确定了基因突变与透明细胞肾细胞癌（ccRCC）之间的关联。由于完整的基因突变景观不能通过每个患者的活检和测序测定来表征，因此需要非侵入性工具来确定肿瘤的突变状态。放射基因组学可能是一个有吸引力的替代工具，以确定疾病基因组学分析的数量特征提取的医学图像。目前大多数放射基因组学预测模型是基于单个分类器构建的，并通过单个目标进行训练。然而，由于有许多分类器可用，因此选择最佳模型是具有挑战性的。另一方面，单一目标可能不是指导模型训练的好措施。提出了一种新的多分类器多目标（MCMO）放射基因组学预测模型。为了获得更可靠的预测结果，定义了基于相似性的灵敏度和特异度，并在训练过程中同时考虑这两个目标函数。为了利用不同分类器的优势，证据推理（ER）的方法被用来融合每个分类器的输出。此外，还开发了一种新的基于相似性的多目标优化算法（SMO），用于训练MCMO，以使用定量CT特征预测ccRCC相关基因突变（VHL、PBRM 1和BAP 1）。使用所提出的MCMO模型，我们实现了VHL、PBRM 1和BAP 1基因的受试者工作特征曲线（AUC）下的预测面积超过0.85，具有平衡的灵敏度和特异性。此外，MCMO优于所有的个人分类器，并产生更可靠的结果比其他优化算法和常用的融合策略。
Genetic studies have identified associations between gene mutations and clear cell renal cell carcinoma (ccRCC). Since the complete gene mutational landscape cannot be characterized through biopsy and sequencing assays for each patient, non-invasive tools are needed to determine the mutation status for tumors. Radiogenomics may be an attractive alternative tool to identify disease genomics by analyzing amounts of features extracted from medical images. Most current radiogenomics predictive models are built based on a single classifier and trained through a single objective. However, since many classifiers are available, selecting an optimal model is challenging. On the other hand, a single objective may not be a good measure to guide model training. We proposed a new multi-classifier multi-objective (MCMO) radiogenomics predictive model. To obtain more reliable prediction results, similarity-based sensitivity and specificity were defined and considered as the two objective functions simultaneously during training. To take advantage of different classifiers, the evidential reasoning (ER) approach was used for fusing the output of each classifier. Additionally, a new similarity-based multi-objective optimization algorithm (SMO) was developed for training the MCMO to predict ccRCC related gene mutations (VHL, PBRM1 and BAP1) using quantitative CT features. Using the proposed MCMO model, we achieved a predictive area under the receiver operating characteristic curve (AUC) over 0.85 for VHL, PBRM1 and BAP1 genes with balanced sensitivity and specificity. Furthermore, MCMO outperformed all the individual classifiers, and yielded more reliable results than other optimization algorithms and commonly used fusion strategies.
登录
查看更多内容
影响因子：
2.9
作者：
Keerthi, SS;Lin, CJ
通讯作者：
Lin, CJ
影响因子：
4.4
作者：
Clark, Kenneth;Vendt, Bruce;Prior, Fred
通讯作者：
Prior, Fred
影响因子：
64.8
作者：
通讯作者：
--
影响因子：
14.3
作者：
Deb, K;Pratap, A;Meyarivan, T
通讯作者：
Meyarivan, T
影响因子：
7.5
作者：
Friedman, N;Geiger, D;Goldszmidt, M
通讯作者：
Goldszmidt, M