4.6 Article

Comparable Performance of Deep Learning-Based to Manual-Based Tumor Segmentation in KRAS/NRAS/BRAF Mutation Prediction With MR-Based Radiomics in Rectal Cancer

期刊

FRONTIERS IN ONCOLOGY
卷 11, 期 -, 页码 -

出版社

FRONTIERS MEDIA SA
DOI: 10.3389/fonc.2021.696706

关键词

rectal cancer; deep learning; radiomics; magnetic resonance imaging; gene mutation

类别

资金

  1. Key Research and Development Projects in Shaanxi [2018ZDXM-SF-059]

向作者/读者索取更多资源

The study examined the feasibility of using deep learning-based segmentation for predicting KRAS/NRAS/BRAF mutations in rectal cancer using MR radiomics. The 3D V-net architecture showed reliable segmentation performance on T2WI and DWI images. Radiomics-based models combined with DL-based segmentation demonstrated comparable gene prediction performance to manual segmentation.
Radiomic features extracted from segmented tumor regions have shown great power in gene mutation prediction, while deep learning-based (DL-based) segmentation helps to address the inherent limitations of manual segmentation. We therefore investigated whether deep learning-based segmentation is feasible in predicting KRAS/NRAS/BRAF mutations of rectal cancer using MR-based radiomics. In this study, we proposed DL-based segmentation models with 3D V-net architecture. One hundred and eight patients' images (T2WI and DWI) were collected for training, and another 94 patients' images were collected for validation. We evaluated the DL-based segmentation manner and compared it with the manual-based segmentation manner through comparing the gene prediction performance of six radiomics-based models on the test set. The performance of the DL-based segmentation was evaluated by Dice coefficients, which are 0.878 +/- 0.214 and 0.955 +/- 0.055 for T2WI and DWI, respectively. The performance of the radiomics-based model in gene prediction based on DL-segmented VOI was evaluated by AUCs (0.714 for T2WI, 0.816 for DWI, and 0.887 for T2WI+DWI), which were comparable to that of corresponding manual-based VOI (0.637 for T2WI, P=0.188; 0.872 for DWI, P=0.181; and 0.906 for T2WI+DWI, P=0.676). The results showed that 3D V-Net architecture could conduct reliable rectal cancer segmentation on T2WI and DWI images. All-relevant radiomics-based models presented similar performances in KRAS/NRAS/BRAF prediction between the two segmentation manners.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据