Investigation of radiomic signatures for local recurrence using primary tumor texture analysis in oropharyngeal head and neck cancer patients

doi:10.1038/s41598-017-14687-0

Abstract

Radiomics is one such “big data” approach that applies advanced image refining/data characterization algorithms to generate imaging features that can quantitatively classify tumor phenotypes in a non-invasive manner. We hypothesize that certain textural features of oropharyngeal cancer (OPC) primary tumors will have statistically significant correlations to patient outcomes such as local control. Patients from an IRB-approved database dispositioned to (chemo)radiotherapy for locally advanced OPC were included in this retrospective series. Pretreatment contrast CT scans were extracted and radiomics-based analysis of gross tumor volume of the primary disease (GTVp) were performed using imaging biomarker explorer (IBEX) software that runs in Matlab platform. Data set was randomly divided into a training dataset and test and tuning holdback dataset. Machine learning methods were applied to yield a radiomic signature consisting of features with minimal overlap and maximum prognostic significance. The radiomic signature was adapted to discriminate patients, in concordance with other key clinical prognosticators. 465 patients were available for analysis. A signature composed of 2 radiomic features from pre-therapy imaging was derived, based on the Intensity Direct and Neighbor Intensity Difference methods. Analysis of resultant groupings showed robust discrimination of recurrence probability and Kaplan-Meier-estimated local control rate (LCR) differences between “favorable” and “unfavorable” clusters were noted.

Highlights

Recent investigations into radiomics, which is the extraction of quantitative imaging features from existing computed tomography (CT), magnetic resonance imaging (MRI) or positron-emission tomography (PET) images, has resulted in the capacity to discriminate potentially meaningful phenotypic differences in imaging which are not readily apparent to the human eye[1,2]
Tumor size was almost the only quantitative standard that was extracted from different imaging modalities, and changes over the course of treatment were the guide to treatment planning in the population-based cancer management fashion[12]
We hypothesize that certain local textural features of primary tumors will have statistically significant correlations to patient outcomes such as local control

Summary

Results

This difference in 5-year LCR was statistically significant by both Log-Rank and Wilcoxon tests, with p < 0.001 in both tests. Wald and effect likelihood ratio tests were applied to find out if radiomic signature and/or clinical variables have a true added value on the model-based stratification of patients in terms of local control These parametric statistical tests were run on ‘training’ and ‘tuning’ sets; excluding the ‘test’ set given the smaller portion of patients with known HPV status.

Discussion

Findings

Methods and Analysis