Zhang Fan, Zhong Lian-Zhen, Zhao Xun, Dong Di, Yao Ji-Jin, Wang Si-Yang, Liu Ye, Zhu Ding, Wang Yin, Wang Guo-Jie, Wang Yi-Ming, Li Dan, Wei Jiang, Tian Jie, Shan Hong
Department of Head and Neck Oncology, The Cancer Center of the Fifth Affiliated Hospital, Sun Yat-sen University, Zhuhai, Guangdong Province, P. R. China.
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P. R. China.
Ther Adv Med Oncol. 2020 Dec 14;12:1758835920971416. doi: 10.1177/1758835920971416. eCollection 2020.
To explore the prognostic value of radiomics-based and digital pathology-based imaging biomarkers from macroscopic magnetic resonance imaging (MRI) and microscopic whole-slide images for patients with nasopharyngeal carcinoma (NPC).
We recruited 220 NPC patients and divided them into training ( = 132), internal test ( = 44), and external test ( = 44) cohorts. The primary endpoint was failure-free survival (FFS). Radiomic features were extracted from pretreatment MRI and selected and integrated into a radiomic signature. The histopathological signature was extracted from whole-slide images of biopsy specimens using an end-to-end deep-learning method. Incorporating two signatures and independent clinical factors, a multi-scale nomogram was constructed. We also tested the correlation between the key imaging features and genetic alternations in an independent cohort of 16 patients (biological test cohort).
Both radiomic and histopathologic signatures presented significant associations with treatment failure in the three cohorts (C-index: 0.689-0.779, all < 0.050). The multi-scale nomogram showed a consistent significant improvement for predicting treatment failure compared with the clinical model in the training (C-index: 0.817 0.730, < 0.050), internal test (C-index: 0.828 0.602, < 0.050) and external test (C-index: 0.834 0.679, < 0.050) cohorts. Furthermore, patients were stratified successfully into two groups with distinguishable prognosis (log-rank < 0.0010) using our nomogram. We also found that two texture features were related to the genetic alternations of chromatin remodeling pathways in another independent cohort.
The multi-scale imaging features showed a complementary value in prognostic prediction and may improve individualized treatment in NPC.
探讨基于放射组学和数字病理学的成像生物标志物，分别从宏观磁共振成像（MRI）和微观全切片图像中提取，对鼻咽癌（NPC）患者的预后价值。
我们招募了220例NPC患者，并将他们分为训练组（n = 132）、内部测试组（n = 44）和外部测试组（n = 44）。主要终点是无失败生存期（FFS）。从治疗前的MRI中提取放射组学特征，进行选择并整合为一个放射组学特征图谱。使用端到端深度学习方法从活检标本的全切片图像中提取组织病理学特征图谱。结合两个特征图谱和独立的临床因素，构建了一个多尺度列线图。我们还在一个由16名患者组成的独立队列（生物学测试队列）中测试了关键成像特征与基因改变之间的相关性。
在三个队列中，放射组学和组织病理学特征图谱均与治疗失败呈现出显著相关性（C指数：0.689 - 0.779，均P < 0.050）。与临床模型相比，多尺度列线图在训练组（C指数：0.817对0.730，P < 0.050）、内部测试组（C指数：0.828对0.602，P < 0.050）和外部测试组（C指数：0.834对0.679，P < 0.050）中预测治疗失败方面显示出一致的显著改善。此外，使用我们的列线图，患者被成功分层为两组，预后具有明显差异（对数秩检验P < 0.0010）。我们还发现，在另一个独立队列中，两个纹理特征与染色质重塑途径的基因改变有关。
多尺度成像特征在预后预测中显示出互补价值，可能改善NPC的个体化治疗。
