Click here to


Are you sure ?

Yes, do it No, cancel

Delta-Radiomics and Tumor Characteristic Factors as a Combined Biomarker for Chemoradiation Therapy of Locally Advanced Pancreatic Cancer

H Nasief1*, W Hall2 , C Zheng3 , S Tsai4 , L Wang5 , B Erickson6 , X Li7 , (1) Medical College of Wisconsin, Marshall, WI, (2) Medical College of Wisconsin, Milwaukee, WI, (3) University of Wisconsin Milwaukee, Milwaukee, WI, (4) Medical College of Wisconsin, Milwaukee, WI, (5) Medical College of Wisconsin, Milwaukee, WI, (6) Medical College of Wisconsin, Milwaukee, WI, (7) Medical College of Wisconsin, Milwaukee, WI


(Tuesday, 7/16/2019) 1:45 PM - 3:45 PM

Room: Stars at Night Ballroom 2-3

Purpose: The goal of this study is to investigate whether a combination of delta-radiomic-features (DRF) and the commonly used tumor characteristic factors, carbohydrate-antigen (CA19-9) and carcinoembryonic-antigen (CEA), is an improved biomarker for CRT response of locally advanced unresectable pancreatic cancer (LAUPC).

Methods: Daily non-contrast CTs (28-fractions) acquired during routine CT-guided CRT for 20 LAUPC patients, along with their CA19-9, and CEA-tests were analyzed. The pancreatic head was delineated on daily CTs and DRFs were extracted. DRFs were examined to find response correlation in LAUPC using t-test and linear-mixed-effect-models. The time from the end of treatment until endpoint of death or presence of distant metastases were used to build a survival model. Patients not reaching the endpoint were censored at their last follow-up date. Univariate and multivariate Cox regression analysis were performed to determine the effect of combining CA19-9, CEA, and DRFs on survival-probability. The effect of normalized (or a decrease) in CA19-9 and CEA-levels during treatment versus failure of CA19-9 and CEA-levels to normalize (or an increase) on survival was examined.

Results: The univariate analysis showed that patients with decreasing-CA19-9 had an improved median survival (12month) compared to those with increasing-levels (4month). Six DRFs were correlated to response in LAPC. The multivariate Cox regression analysis showed that a treatment related decrease in CA19-9 levels (p=0.03), CEA-levels (p=0.05) and DRFs (p=0.02-0.05) were predictors of survival. Incorporating CA19-9 with DRFs increased the concordance-statistic from 0.51 to 0.75. The c-index further increased to 0.81 combining CEA to CA199 and DRFs. The hazard-ratio was reduced from 0.69, p=0.03 using CA19-9 only and 0.71 using CEA only to 0.43, p=0.04 combining DRFs with CA19-9, this was further reduced to 0.27, p=0.02 combining DRFs with CA19-9 and CEA.

Conclusion: The combination of CT delta-radiomics, CA19-9 and CEA is an improved biomarker for CRT response of LAUPC.


Radiation Therapy, CT, Image-guided Therapy


IM- CT: Biomarkers

Contact Email