基于表观扩散系数图的一阶和高阶放射组学特征在鉴别具有重叠常规成像特征的骶骨脊索瘤和软骨肉瘤中的作用。

Role of Apparent Diffusion Coefficient Map-Based First- and High-Order Radiomic Features for the Discrimination of Sacral Chordomas and Chondrosarcomas With Overlapping Conventional Imaging Features.

机构信息

University of Texas MD Anderson Cancer Center, Houston, TX.

Houston Methodist Hospital, Houston, TX.

出版信息

JCO Precis Oncol. 2023 Sep;7:e2300243. doi: 10.1200/PO.23.00243.

DOI:10.1200/PO.23.00243

PMID:38127828

Abstract

PURPOSE

Chondrosarcomas arise from the lateral pelvis; however, midline chondrosarcomas (10%) display similar imaging features to chordoma, causing a diagnostic challenge. This study aims to determine the diagnostic accuracy of apparent diffusion coefficient (ADC)-based radiomic features and two novel diffusion indices for differentiating sacral chordomas and chondrosarcomas.

METHODS

A retrospective, multireader review was performed of 82 pelvic MRIs (42 chordomas and 40 chondrosarcomas) between December 2014 and September 2021, split into training (n = 69) and validation (n = 13) data sets. Lesions were segmented on a single slice from ADC maps. Eight first-order features (minimum, mean, median, and maximum ADC, standard deviation, skewness, kurtosis, and entropy) and two novel indices: restriction index (RI, proportion of lesions with restricted diffusion) and facilitation index (FI, proportion of lesions with facilitated diffusion) were estimated. One hundred seven radiomic features comparing patients with chondrosarcoma versus chordoma were sorted based on mean group differences.

RESULTS

There was good to excellent interobserver reliability for eight of the 10 ADC metrics on the training data set. Significant differences were observed ( < .005) for RI, FI, median, mean, and skewness using the training data set. Optimal cutpoints for diagnosis of chordoma were RI > 0.015; FI < 0.25; mean ADC < 1.7 × 10 mm/s; and skewness >0.177. The optimal decision tree relied on FI. In a secondary analysis, significant differences ( < .00047) in chondrosarcoma versus chordoma were found in 18 of 107 radiomic features, including six first-order and 12 high-order features.

CONCLUSION

The novel ADC index, FI, in addition to ADC mean, skewness, and 12 high-order radiomic features, could help differentiate sacral chordomas from chondrosarcomas.

摘要

目的

软骨肉瘤起源于骨盆外侧；然而，中线软骨肉瘤（10%）具有与 chordoma 相似的影像学特征，这给诊断带来了挑战。本研究旨在确定基于表观扩散系数（ADC）的放射组学特征和两个新的扩散指数在区分骶骨 chordoma 和软骨肉瘤方面的诊断准确性。

方法

回顾性地对 2014 年 12 月至 2021 年 9 月间的 82 例骨盆 MRI（42 例 chordoma 和 40 例软骨肉瘤）进行了多读者回顾性研究，将其分为训练集（n=69）和验证集（n=13）。在 ADC 图上对病变进行单层面分割。计算了 8 个一阶特征（最小、平均、中位数和最大 ADC、标准差、偏度、峰度和熵）和两个新指数：限制指数（RI，病变受限扩散的比例）和促进指数（FI，病变促进扩散的比例）。根据平均组间差异，对 107 个比较软骨肉瘤与 chordoma 患者的放射组学特征进行了排序。

结果

在训练数据集上，8 个 ADC 指标中有 7 个具有良好到极好的观察者间可靠性。使用训练数据集观察到 RI、FI、中位数、平均值和偏度存在显著差异（<0.005）。诊断 chordoma 的最佳切点为 RI>0.015；FI<0.25；平均 ADC<1.7×10mm/s；偏度>0.177。最优决策树依赖于 FI。在二次分析中，在 107 个放射组学特征中，有 18 个（<0.00047）在软骨肉瘤与 chordoma 之间存在显著差异，包括 6 个一阶特征和 12 个高阶特征。