Homological radiomics analysis for prognostic prediction in lung cancer patients
Homological radiomics analysis for prognostic prediction in lung cancer patients
复制标题
DOI：
10.1016/j.ejmp.2019.11.026
复制
发表时间：
2020-01-01
影响因子：
3.4
通讯作者：
Arimura, Hidetaka
中科院分区：
文献类型：
--
作者：
Ninomiya, Kenta;Arimura, Hidetaka
目的：探讨一种新的用于肺癌患者预后预测的同源分析方法。材料和方法：使用训练（n = 135）和验证（n = 70）数据集，以及Kaplan-Meier分析，通过将基于同源的放射组学特征（HFs）与传统的基于小波的放射组学特征（WFs）以及由HFs和WFs组成的组合放射组学特征（HWFs）进行比较，研究了基于同源的放射组学特征（HFs）的潜力。利用代表肺癌拓扑不变形态学特征的Betti数进行同源性纹理分析，共得到13824个HFs。采用统计学显著性差异（p值，log-rank检验）评价HFs的预后潜力，比较高危和低危患者的生存曲线。使用弹性网络正则化Cox比例风险模型构建的特征放射组评分中位数，将这些患者分为高危组和低危组。此外，基于AlexNet的深度学习（DL）通过使用来自ImageNet数据库的100多万张自然图像预训练的网络将患者分为两组来比较HFs。结果：对于训练数据集，两条生存曲线之间的p值分别为6.7 × 10(-6) （HF）、5.9 × 10(-3) （WF）、7.4 × 10(-6) （HWF）和1.1 × 10(-3) （DL）。验证数据集的p值分别为3.4 × 10(-5) （HF）、6.7 × 10(-1) （WF）、1.7 × 10(-7) （HWF）和1.2 × 10(-1) （DL）。结论：本研究表明HFs在预测肺癌患者预后方面具有良好的潜力。
Purpose: This study explored a novel homological analysis method for prognostic prediction in lung cancer patients.Materials and methods: The potential of homology-based radiomic features (HFs) was investigated by comparing HFs to conventional wavelet-based radiomic features (WFs) and combined radiomic features consisting of HFs and WFs (HWFs), using training (n = 135) and validation (n = 70) datasets, and Kaplan-Meier analysis. A total of 13,824 HFs were derived through homology-based texture analysis using Betti numbers, which represent the topologically invariant morphological characteristics of lung cancer. The prognostic potential of HFs was evaluated using statistically significant differences (p-values, log-rank test) to compare the survival curves of high- and low-risk patients. Those patients were stratified into high- and low-risk groups using the medians of the radiomic scores of signatures constructed with an elastic-net-regularized Cox proportional hazard model. Furthermore, deep learning (DL) based on AlexNet was utilized to compare HFs by stratifying patients into the two groups using a network that was pre-trained with over one million natural images from an ImageNet database.Results: For the training dataset, the p-values between the two survival curves were 6.7 x 10(-6) (HF), 5.9 x 10(-3) (WF), 7.4 x 10(-6) (HWF), and 1.1 x 10(-3) (DL). The p-values for the validation dataset were 3.4 x 10(-5) (HF), 6.7 x 10(-1) (WF), 1.7 x 10(-7) (HWF), and 1.2 x 10(-1) (DL).Conclusion: This study demonstrates the excellent potential of HFs for prognostic prediction in lung cancer patients.