Unsupervised deconvolution of dynamic imaging reveals intratumor vascular heterogeneity

TL;DR

This paper introduces an unsupervised computational method called tissue-specific compartment modeling (TSCM) that deconvolves dynamic imaging data to reveal intratumor vascular heterogeneity, improving vascular phenotyping.

Contribution

The paper presents TSCM, a novel unsupervised approach for analyzing dynamic imaging data to uncover vascular heterogeneity within tumors.

Findings

TSCM identified characteristic intratumor vascular heterogeneity.

TSCM detected therapeutic responses undetectable by other methods.

Application to breast cancer MRI demonstrated clinical relevance.

Abstract

Intratumor heterogeneity is often manifested by vascular compartments with distinct pharmacokinetics that cannot be resolved directly by in vivo dynamic imaging. We developed tissue-specific compartment modeling (TSCM), an unsupervised computational method of deconvolving dynamic imaging series from heterogeneous tumors that can improve vascular phenotyping in many biological contexts. Applying TSCM to dynamic contrast-enhanced MRI of breast cancers revealed characteristic intratumor vascular heterogeneity and therapeutic responses that were otherwise undetectable.