Deep Radiotranscriptomics of Non-Small Cell Lung Carcinoma for Assessing Molecular and Histology Subtypes with a Data-Driven Analysis.

Apostolos Karantanas,John Souglakos,Kostas Marias,Eleftherios Trivizakis

doi:10.3390/diagnostics11122383

Abstract

Radiogenomic and radiotranscriptomic studies have the potential to pave the way for a holistic decision support system built on genomics, transcriptomics, radiomics, deep features and clinical parameters to assess treatment evaluation and care planning. The integration of invasive and routine imaging data into a common feature space has the potential to yield robust models for inferring the drivers of underlying biological mechanisms. In this non-small cell lung carcinoma study, a multi-omics representation comprised deep features and transcriptomics was evaluated to further explore the synergetic and complementary properties of these diverse multi-view data sources by utilizing data-driven machine learning models. The proposed deep radiotranscriptomic analysis is a feature-based fusion that significantly enhances sensitivity by up to 0.174 and AUC by up to 0.22, compared to the baseline single source models, across all experiments on the unseen testing set. Additionally, a radiomics-based fusion was also explored as an alternative methodology yielding radiomic signatures that are comparable to several previous publications in the field of radiogenomics. Furthermore, the machine learning multi-omics analysis based on deep features and transcriptomics achieved an AUC performance of up to 0.831 ± 0.09/0.925 ± 0.04 for the examined molecular and histology subtypes analysis, respectively. The clinical impact of such high-performing models can add prognostic value and lead to optimal treatment assessment by targeting specific oncogenes, namely the response of tyrosine kinase inhibitors of EGFR mutated or predicting the chemotherapy resistance of KRAS mutated tumors.

Highlights

The highest mortality rate worldwide has been estimated as being among lung cancer patients, according to a recent report [1] by the World Health Organization (WHO [2]).Therapeutic decisions for non-small cell lung carcinoma (NSCLC) in contemporary clinical practice are based on empirical observations of clinicians in association with histological, genomic, clinical, laboratory and other routine imaging data [3]
The final cohorts of EGFR (PEGFR = LEGFR ∩ PRG = 92), KRAS (PKRAS = LKRAS ∩ PRG = 93) and histology (PHS = LHS ∩ PRG = 112) subtypes were considered for the proposed radiotranscriptomic analyses
The same experimental protocol and data stratification methodology applied across all experiments, with the key differentiating factors being the feature fusion were applied across all experiments, with the key differentiating factors being the feature, oversampling technique and classifier

Summary

Introduction

Therapeutic decisions for non-small cell lung carcinoma (NSCLC) in contemporary clinical practice are based on empirical observations of clinicians in association with histological, genomic, clinical, laboratory and other routine imaging data [3]. The molecular characteristics of NSCLC should be considered in treatment decisions as they are involved in the crucial mechanisms of lesion progression [5]. The effectiveness of radiomics is based on the hypothesis that medical image analysis can quantify the underlying disease. In this context, radiogenomic/radiotranscriptomic analysis [6] has two main goals: (a) the correlation of imaging with genomic/transcriptomic features, and (b) the combination of the aforementioned data sources to improve robustness for increased predictive power. The accurate prediction of the genetic alterations of targeted oncogenes has a high clinical significance in precision medicine as they have the potential to uncover prognostic drivers for treatment response [7,8,9,10,11,12,13,14,15,16]

Methods

Results

Discussion

Conclusion