Multi-Organ Omics-Based Prediction for Adaptive Radiation Therapy Eligibility in Nasopharyngeal Carcinoma Patients Undergoing Concurrent Chemoradiotherapy.

Saikit Lam ,Jing Cai,Xinzhi Teng,Yuanpeng Zhang,Pak-Hei Chou,Tao Peng,Francis Kar-Ho Lee,Tian Li,Ge Ren,Bing Li,Ta Zhou,Jiang Zhang,Carol Yee-Tung Liu,Celia Wai-Yi Yip,Ruiyan Ni ,Victor Lee ,Haonan Xiao ,Kwok‐Hung Au ,Ankie Tan Cheung ,Zongrui Ma ,Amy Chang ,Jiachen Sun ,Lawrence Chan

doi:10.3389/fonc.2021.792024

Abstract

PurposeTo investigate the role of different multi-organ omics-based prediction models for pre-treatment prediction of Adaptive Radiotherapy (ART) eligibility in patients with nasopharyngeal carcinoma (NPC).Methods and MaterialsPre-treatment contrast-enhanced computed tomographic and magnetic resonance images, radiotherapy dose and contour data of 135 NPC patients treated at Hong Kong Queen Elizabeth Hospital were retrospectively analyzed for extraction of multi-omics features, namely Radiomics (R), Morphology (M), Dosiomics (D), and Contouromics (C), from a total of eight organ structures. During model development, patient cohort was divided into a training set and a hold-out test set in a ratio of 7 to 3 via 20 iterations. Four single-omics models (R, M, D, C) and four multi-omics models (RD, RC, RM, RMDC) were developed on the training data using Ridge and Multi-Kernel Learning (MKL) algorithm, respectively, under 10-fold cross validation, and evaluated on hold-out test data using average area under the receiver-operator-characteristics curve (AUC). The best-performing single-omics model was first determined by comparing the AUC distribution across the 20 iterations among the four single-omics models using two-sided student t-test, which was then retrained using MKL algorithm for a fair comparison with the four multi-omics models.ResultsThe R model significantly outperformed all other three single-omics models (all p-value<0.0001), achieving an average AUC of 0.942 (95%CI: 0.938-0.946) and 0.918 (95%CI: 0.903-0.933) in training and hold-out test set, respectively. When trained with MKL, the R model (R_MKL) yielded an increased AUC of 0.984 (95%CI: 0.981-0.988) and 0.927 (95%CI: 0.905-0.948) in training and hold-out test set respectively, while demonstrating no significant difference as compared to all studied multi-omics models in the hold-out test sets. Intriguingly, Radiomic features accounted for the majority of the final selected features, ranging from 64% to 94%, in all the studied multi-omics models.ConclusionsAmong all the studied models, the Radiomic model was found to play a dominant role for ART eligibility in NPC patients, and Radiomic features accounted for the largest proportion of features in all the multi-omics models.

Highlights

Nasopharyngeal carcinoma (NPC) presents immediate proximity to a variety of surrounding critical healthy organs such as spinal cord and brainstem within an intricated nosepharynx ministry, dysfunction of which can incur catastrophic complications
We were the first to demonstrate the capability of tumoral Radiomics from pretreatment magnetic resonance images (MRI) for prediction of Adaptive Radiotherapy (ART) eligibility in NPC patients [15]
We investigated a variety of singleomics and multi-omics models from multi-modal images, with an eye towards identifying their roles in predicting ART eligibility in NPC and providing insights into development of ART eligibility screening strategy in NPC in the long run

Summary

Introduction

Nasopharyngeal carcinoma (NPC) presents immediate proximity to a variety of surrounding critical healthy organs such as spinal cord and brainstem within an intricated nosepharynx ministry, dysfunction of which can incur catastrophic complications. In response to treatment perturbations, tumors and surrounding healthy organs may exhibit significant morphometric volume and/or geometric alterations, which may jointly alter patient anatomy and jeopardize the efficacy of the original treatment plan [1,2,3]. The issue of these variabilities can be more detrimental in the IMRT era, where slight anatomic deviations may deleteriously lead to significant dosimetric consequences due to the sharp dose falloff beyond the target lesions. The dosimetric and clinical benefits of ART for NPC patients have been well-documented in the literature [1,2,3,4,5,6,7]

Objectives

Methods

Results

Conclusion