Search

743 Background: The prognosis of metastatic pancreatic ductal adenocarcinoma (mPDAC) remains poor with a median survival time of 10-12 months. First-line treatment is largely influenced by performance status with fit patients more often receiving FOLFIRINOX (FFX) than Gemcitabine+Nab-Paclitaxel (GNP). Although the two regimens have improved outcomes over gemcitabine monotherapy, no biomarkers routinely used in clinical practice can predict which regimen is optimal to facilitate a precision medicine approach. We developed two signatures (V-FFX and V-GNP) associated with treatment outcomes for the respective first-line regimens using a retrospective cohort of mPDAC cases. Methods: We conducted a retrospective study of mPDAC patients treated at two institutions (UPMC and Cedars Sinai) from 2014 to 2021. Digitized histological H&E sections corresponding to 145 metastatic PDAC patients treated with either first-line FFX or GNP were included. Independent randomized training and test datasets were constructed for FFX-treated (train: 41, test: 25) and GNP-treated (train: 49, test: 30) patients. To construct the histological assay, a deep-learning algorithm then segmented nuclei to extract quantitative histological features. Features associated with disease-specific survival (DSS) for FFX and GNP were identified utilizing univariate Cox proportional hazards (CPH) models for the respective training sets and V-FFX and V-GNP signatures were constructed. DSS stratification of the V-FFX and V-GNP signatures were examined using Kaplan-Meier analysis and the log-rank test and DSS percentages at 12 months were calculated on the respective test sets. Results: The V-FFX and V-GNP signatures were found to be significantly associated with treatment outcomes stratified in the respective test sets (log-rank test, V-FFX: p=0.046, V-GNP: p=0.004). 29 of 55 patients tested positive for only one of either V-FFX and V-GNP signatures. Kaplan-Meier analysis demonstrated robust separation with hazard ratios for the V-FFX and V-GNP signatures of 3.01 (95% CI: 0.96, 9.45) and 4.81 (95% CI: 1.74, 13.3). DSS at 12 months for patients in V-FFX +ve vs -ve groups were 88% (8/9) vs 50% (7/14). DSS at 12 months for patients in V-GNP +ve vs -ve groups were 66% (8/12) vs 15% (2/13). Conclusions: AI derived V-FFX and V-GNP morphological signatures were strongly associated with treatment outcomes for first-line FFX and GNP and can potentially aid in the selection of first-line treatment for mPDAC patients.

e16295 Background: Adjuvant chemotherapy improves survival following resection of pancreatic ductal adenocarcinoma (PDAC). A modified fluorouracil/irinotecan/oxaliplatin regimen (mFOLFIRINOX) has demonstrated improved disease free survival and overall survival, though gemcitabine-based monotherapy and gemcitabine plus capecitabine are alternatives in less fit patients. Though there are several proposed biomarkers to guide treatment decisions (GATA6, hENT1, and GemPred), no biomarker is used to guide treatment selection in clinical practice. Consequently, we sought to develop an artificial intelligence-derived signature of features from digital images of routine histopathology specimens that could identify patients susceptible to routine chemotherapeutic agents. Methods: 139 whole-slide digitized histological slides corresponding to 102 resected PDAC tumors from TCGA-PAAD were used in this study. This dataset corresponded to patients that had received either gemcitabine-backbone or 5 FU-backbone chemotherapy as their first-line adjuvant treatment. We extracted nuclei images from tissue regions using segmentation models and computed geometric features of these nuclei which we then correlated with Disease Specific Survival (DSS) in order to construct a signature associated with treatment benefit. This signature was compared against two board certified pathologists using the grade of the digital slides images to classify patients into above or below average DSS buckets. Results: Among quantitative geometric features, a set of area and ellipse features describing nuclei geometry correlated most with response to gemcitabine (R̃0.4). The cox proportional hazards model using these geometric nuclei features was found to be predictive of response to gemcitabine and achieved a C-index (95% CI) of 0.69 (0.58, 0.79). The pathologist-based baseline model for above and below average DSS had a median DSS of 443 and 461 days respectively. Using the average expected lifetime as the threshold, the model divides patients receiving gemcitabine into two histological subtypes with median DSS of 586 and 394 days respectively (p < 0.05). The model appeared specific to gemcitabine. Among patients receiving 5-FU (n = 10) there was no statistical significance in median DSS between the subtypes and a c-index of 0.63 (0.27, 1.0). Conclusions: An artificial intelligence approach utilizing only routine histopathology can identify features that correlate with treatment outcomes in PDAC with classification performance (c-index:0.69) superior to the validated AJCC treatment prediction tool (0.59).