Institute of Biomedical Engineering and Instrumentation, Hangzhou Dianzi University, Hangzhou, China.
Department of Radiology, First Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China.
Med Phys. 2021 Dec;48(12):7685-7697. doi: 10.1002/mp.15316. Epub 2021 Nov 13.
Clinical indicators of histological information are important for breast cancer treatment and operational decision making, but these histological data suffer from frequent missing values due to various experimental/clinical reasons. The limited amount of histological information from breast cancer samples impedes the accuracy of data imputation. The purpose of this study was to impute missing histological data, including Ki-67 expression level, luminal A subtype, and histological grade, by integrating tumor radiomics.
To this end, a deep matrix completion (DMC) method was proposed for imputing missing histological data using nonmissing features composed of histological and tumor radiomics (termed radiohistological features). DMC finds a latent nonlinear association between radiohistological features across all samples and samples for all the features. Radiomic features of morphologic, statistical, and texture were extracted from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) inside the tumor. Experiments on missing histological data imputation were performed with a variable number of features and missing data rates. The performance of the DMC method was compared with those of the nonnegative matrix factorization (NMF) and collaborative filtering (MCF)-based data imputation methods. The area under the curve (AUC) was used to assess the performance of missing histological data imputation.
By integrating radiomics from DCE-MRI, the DMC method showed significantly better performance in terms of AUC than that using only histological data. Additionally, DMC using 120 radiomic features showed an optimal prediction performance (AUC = 0.793), which was better than the NMF (AUC = 0.756) and MCF methods (AUC = 0.706; corrected p = 0.001). The DMC method consistently performed better than the NMF and MCF methods with a variable number of radiomic features and missing data rates.
DMC improves imputation performance by integrating tumor histological and radiomics data. This study transforms latent imaging-scale patterns for interactions with molecular-scale histological information and is promising in the tumor characterization and management of patients.
组织学信息的临床指标对乳腺癌的治疗和手术决策至关重要，但由于各种实验/临床原因，这些组织学数据经常出现缺失值。由于乳腺癌样本中组织学信息有限，数据插补的准确性受到影响。本研究旨在通过整合肿瘤放射组学来插补缺失的组织学数据，包括 Ki-67 表达水平、腔 A 亚型和组织学分级。
为此，提出了一种深度矩阵补全（DMC）方法，用于使用由组织学和肿瘤放射组学（称为放射组织学特征）组成的非缺失特征来插补缺失的组织学数据。DMC 发现了所有样本之间的放射组织学特征和所有特征的样本之间的潜在非线性关联。从肿瘤内动态对比增强磁共振成像（DCE-MRI）中提取形态、统计和纹理的放射组学特征。在缺失组织学数据插补中，针对不同数量的特征和缺失数据率进行了实验。比较了 DMC 方法与非负矩阵分解（NMF）和基于协同过滤（MCF）的数据插补方法的性能。使用曲线下面积（AUC）评估缺失组织学数据插补的性能。
通过整合来自 DCE-MRI 的放射组学信息，DMC 方法在 AUC 方面的表现明显优于仅使用组织学数据的方法。此外，使用 120 个放射组学特征的 DMC 显示出最佳的预测性能（AUC=0.793），优于 NMF（AUC=0.756）和 MCF 方法（AUC=0.706；校正 p=0.001）。DMC 方法在不同数量的放射组学特征和缺失数据率下均优于 NMF 和 MCF 方法。
DMC 通过整合肿瘤组织学和放射组学数据来提高插补性能。本研究将潜在的成像尺度模式转化为与分子尺度组织学信息的相互作用，有望用于肿瘤特征描述和患者管理。
