Molecular Characterization and Xenotransplantation of Pancreatic Cancer Using Endoscopic Ultrasound-Guided Fine Needle Aspiration (EUS-FNA).

Pancreatic cancer has one of the worst prognoses among all malignancies and few available treatment options. Patient-derived xenografts can be used to develop personalized therapy for pancreatic cancer. Endoscopic ultrasound fine-needle aspiration (EUS-FNA) may provide a powerful alternative to surgery for obtaining sufficient tissue for the establishment of patient-derived xenografts. In this study, EUS-FNA samples were obtained for 30 patients referred to the Ottawa Hospital, Ottawa, Ontario, Canada. These samples were used for xenotransplantation in NOD-SCID mice and for genetic analyses. The gene expression of pancreatic-cancer-relevant genes in xenograft tumors was examined by immunohistochemistry. Targeted sequencing of both the patient-derived tumors and xenograft tumors was performed. The xenografts' susceptibility to oncolytic virus infection was studied by infecting xenograft-derived cells with VSV∆51-GFP. The xenograft take rate was found to be 75.9% for passage 1 and 100% for passage 2. Eighty percent of patient tumor samples were successfully sequenced to a high depth for 42 cancer genes. Xenograft histological characteristics and marker expression were maintained between passages. All tested xenograft samples were susceptible to oncoviral infection. We found that EUS-FNA is an accessible, minimally invasive technique that can be used to acquire adequate pancreatic cancer tissue for the generation of patient-derived xenografts and for genetic sequencing.

Artificial Intelligence-Assisted Cancer Status Detection in Radiology Reports.

Cancer research is dependent on accurate and relevant information of patient's medical journey. Data in radiology reports are of extreme value but lack consistent structure for direct use in analytics. At Memorial Sloan Kettering Cancer Center (MSKCC), the radiology reports are curated using gold-standard approach of using human annotators. However, the manual process of curating large volume of retrospective data slows the pace of cancer research. Manual curation process is sensitive to volume of reports, number of data elements and nature of reports and demand appropriate skillset. In this work, we explore state of the art methods in artificial intelligence (AI) and implement end-to-end pipeline for fast and accurate annotation of radiology reports. Language models (LM) are trained using curated data by approaching curation as multiclass or multilabel classification problem. The classification tasks are to predict multiple imaging scan sites, presence of cancer and cancer status from the reports. The trained natural language processing (NLP) model classifiers achieve high weighted F1 score and accuracy. We propose and demonstrate the use of these models to assist in the manual curation process which results in higher accuracy and F1 score with lesser time and cost, thus improving efforts of cancer research. SIGNIFICANCE: Extraction of structured data in radiology for cancer research with manual process is laborious. Using AI for extraction of data elements is achieved using NLP models' assistance is faster and more accurate.