Abstract
PurposeProbe-based dynamic (4-D) imaging modalities capture breast intratumor heterogeneity both spatially and kinetically. Characterizing heterogeneity through tumor sub-populations with distinct functional behavior may elucidate tumor biology to improve targeted therapy specificity and enable precision clinical decision making.MethodsWe propose an unsupervised clustering algorithm for 4-D imaging that integrates Markov-Random Field (MRF) image segmentation with time-series analysis to characterize kinetic intratumor heterogeneity. We applied this to dynamic FDG PET scans by identifying distinct time-activity curve (TAC) profiles with spatial proximity constraints. We first evaluated algorithm performance using simulated dynamic data. We then applied our algorithm to a dataset of 50 women with locally advanced breast cancer imaged by dynamic FDG PET prior to treatment and followed to monitor for disease recurrence. A functional tumor heterogeneity (FTH) signature was then extracted from functionally distinct sub-regions within each tumor. Cross-validated time-to-event analysis was performed to assess the prognostic value of FTH signatures compared to established histopathological and kinetic prognostic markers.ResultsAdding FTH signatures to a baseline model of known predictors of disease recurrence and established FDG PET uptake and kinetic markers improved the concordance statistic (C-statistic) from 0.59 to 0.74 (p = 0.005). Unsupervised hierarchical clustering of the FTH signatures identified two significant (p < 0.001) phenotypes of tumor heterogeneity corresponding to high and low FTH. Distributions of FDG flux, or Ki, were significantly different (p = 0.04) across the two phenotypes.ConclusionsOur findings suggest that imaging markers of FTH add independent value beyond standard PET imaging metrics in predicting recurrence-free survival in breast cancer and thus merit further study.
Highlights
Cancer heterogeneity is well-established, with inter- and intratumor manifestations recognized as key prognostic andThis article is part of the Topical Collection on Advanced Image Analyses (Radiomics and Artificial Intelligence) predictive factors [1,2,3,4,5]
We have developed a method to characterize 4-D functional tumor heterogeneity (FTH) by capturing aspects of both spatial and kinetic tumor heterogeneity seen in dynamic imaging
The temporal signal of an ROI over dynamic positron emission tomography (PET) scans is first summarized using functional principal component analysis (FPCA), with each voxel represented using functional principal components (FPC) capturing greater than 85% of the variance seen in its dynamic behavior
Summary
Cancer heterogeneity is well-established, with inter- and intratumor manifestations recognized as key prognostic andThis article is part of the Topical Collection on Advanced Image Analyses (Radiomics and Artificial Intelligence) predictive factors [1,2,3,4,5]. Cancer heterogeneity is well-established, with inter- and intratumor manifestations recognized as key prognostic and. Increased intratumor heterogeneity is associated with adverse outcomes [6]. Quantitative characterization of intratumor heterogeneity could allow for novel precision prognostic and predictive indicators. Molecular and functional imaging modalities permit 4-D sampling of disease burden, capturing both spatial and temporal information that could illuminate various physiologic behaviors. Dynamic positron emission tomography (PET) imaging can quantify specific facets of tumor molecular biology [4, 7, 8] and can provide information beyond that of static imaging [9, 10]. Dynamic PET imaging of the glucose analog, 18Ffluorodeoxyglucose (FDG), can provide simultaneous information on substrate delivery and metabolism [9].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
