Purpose: Tumor-associated vasculature differs from healthy blood vessels by
its chaotic architecture and twistedness, which promotes treatment resistance.
Measurable differences in these attributes may help stratify patients by likely
benefit of systemic therapy (e.g. chemotherapy). In this work, we present a new
category of radiomic biomarkers called quantitative tumor-associated
vasculature (QuanTAV) features, and demonstrate their ability to predict
response and survival across multiple cancers, imaging modalities, and
Experimental Design: We segmented tumor vessels and computed mathematical
measurements of twistedness and organization on routine pre-treatment radiology
(CT or contrast-enhanced MRI) from 558 patients, who received one of four
first-line chemotherapy-based therapeutic intervention strategies for breast
(n=371) or non-small cell lung cancer (NSCLC, n=187).
Results: Across 4 chemotherapy-based treatment strategies, classifiers of
QuanTAV measurements significantly (p<.05) predicted response in held out
testing cohorts alone (AUC=0.63-0.71) and increased AUC by 0.06-0.12 when added
to models of significant clinical variables alone. QuanTAV risk scores were
prognostic of recurrence free survival in treatment cohorts chemotherapy for
breast cancer (p=0.002, HR=1.25, 95% CI 1.08-1.44, C-index=.66) and
chemoradiation for NSCLC (p=0.039, HR=1.28, 95% CI 1.01-1.62, C-index=0.66).
Categorical QuanTAV risk groups were independently prognostic among all
treatment groups, including NSCLC patients receiving chemotherapy (p=0.034,
HR=2.29, 95% CI 1.07-4.94, C-index=0.62).
Conclusions: Across these domains, we observed an association of vascular
morphology on radiology with treatment outcome. Our findings suggest the
potential of tumor-associated vasculature shape and structure as a prognostic
and predictive biomarker for multiple cancers and treatments.
Nathaniel Braman, Prateek Prasanna, Kaustav Bera, Mehdi Alilou, Mohammadhadi Khorrami, Patrick Leo, Maryam Etesami, Manasa Vulchi, Paulette Turk, Amit Gupta, Prantesh Jain, Pingfu Fu, Nathan Pennell, Vamsidhar Velcheti, Jame Abraham, Donna Plecha, Anant Madabhushi