Delta Radiomic Features Predict Resection Margin Status and Overall Survival in Neoadjuvant-Treated Pancreatic Cancer Patients

Authors

Kai Wang
John D Karalis
Ahmed Elamir
Alessandro Bifolco
Megan Wachsmann
Giovanni Capretti
Paola Spaggiari
Sebastian Enrico
Kishore Balasubramanian
Nafeesah Fatimah
Giada Pontecorvi
Martina Nebbia
Adam Yopp
Ravi Kaza
Ivan Pedrosa
Herbert Zeh
Patricio Polanco
Alessandro Zerbi
Jing Wang
Todd Aguilera
Matteo Ligorio

Language

English

Publication Date

4-1-2024

Journal

Annals of Surgical Oncology

DOI

10.1245/s10434-023-14805-5

PMID

38151623

PMCID

PMC10908610

PubMedCentral® Posted Date

12-27-2023

PubMedCentral® Full Text Version

Post-print

Abstract

Background: Neoadjuvant therapy (NAT) emerged as the standard of care for patients with pancreatic ductal adenocarcinoma (PDAC) who undergo surgery; however, surgery is morbid, and tools to predict resection margin status (RMS) and prognosis in the preoperative setting are needed. Radiomic models, specifically delta radiomic features (DRFs), may provide insight into treatment dynamics to improve preoperative predictions.

Methods: We retrospectively collected clinical, pathological, and surgical data (patients with resectable, borderline, locally advanced, and metastatic disease), and pre/post-NAT contrast-enhanced computed tomography (CT) scans from PDAC patients at the University of Texas Southwestern Medical Center (UTSW; discovery) and Humanitas Hospital (validation cohort). Gross tumor volume was contoured from CT scans, and 257 radiomics features were extracted. DRFs were calculated by direct subtraction of pre/post-NAT radiomic features. Cox proportional models and binary prediction models, including/excluding clinical variables, were constructed to predict overall survival (OS), disease-free survival (DFS), and RMS.

Results: The discovery and validation cohorts comprised 58 and 31 patients, respectively. Both cohorts had similar clinical characteristics, apart from differences in NAT (FOLFIRINOX vs. gemcitabine/nab-paclitaxel; p < 0.05) and type of surgery resections (pancreatoduodenectomy, distal or total pancreatectomy; p < 0.05). The model that combined clinical variables (pre-NAT carbohydrate antigen (CA) 19-9, the change in CA19-9 after NAT (∆CA19-9), and resectability status) and DRFs outperformed the clinical feature-based models and other radiomics feature-based models in predicting OS (UTSW: 0.73; Humanitas: 0.66), DFS (UTSW: 0.75; Humanitas: 0.64), and RMS (UTSW 0.73; Humanitas: 0.69).

Conclusions: Our externally validated, predictive/prognostic delta-radiomics models, which incorporate clinical variables, show promise in predicting the risk of predicting RMS in NAT-treated PDAC patients and their OS or DFS.

Keywords

Humans, Pancreatic Neoplasms, Antineoplastic Combined Chemotherapy Protocols, Neoadjuvant Therapy, Retrospective Studies, Margins of Excision, Radiomics, Carcinoma, Pancreatic Ductal

Published Open-Access

yes

Recommended Citation

Wang, Kai; Karalis, John D; Elamir, Ahmed; et al., "Delta Radiomic Features Predict Resection Margin Status and Overall Survival in Neoadjuvant-Treated Pancreatic Cancer Patients" (2024). Faculty, Staff and Student Publications. 6404.
https://digitalcommons.library.tmc.edu/uthgsbs_docs/6404