USCAP 2023 Annual Meeting

Tempus is advancing precision medicine through the practical application of artificial intelligence in healthcare. We are pleased to share our latest scientific and clinical research findings during USCAP 2023.

Schedule a meeting with us

Poster Presentations

Poster Presentations

March 13, 2023

Time
01:00 pm - 04:30 pm CST

Presentation Number: 119

Authors
Josh Och (Tempus), Bolesław L. Osinski (Tempus), Kshitij Ingale (Tempus), Caleb Willis (Tempus), Rohan P. Joshi (Tempus), Nike Beaubier (Tempus), Martin C. Stumpe (Tempus)

Deep Learning Identifies FGFR Alterations from H&E Whole Slide Images in Bladder Cancer

Several targeted therapies for FGFR alterations in bladder cancer are either currently in clinical trials or already FDA-approved. FGFR alterations—including activating single nucleotide variants and fusions—are common in bladder cancer and detectable via next-generation sequencing of DNA and RNA. The ability to rapidly screen patients based on routine pathology would help prioritize patients for full NGS workup. Here, researchers developed a model using H&E whole slide images to predict FGFR alterations using real-world data.

March 14, 2023

Time
09:30 am - 12:00 pm CST

Presentation Number: 100

Authors
Abbas A Rizvi (Tempus), Kunal Nagpal (Tempus), Qiyuan Hu (Tempus), Rohan Joshi (Tempus), Geoffrey Schau (Tempus), Rachel Baits (Tempus), Yoni Muller (Tempus), Martin C Stumpe (Tempus), Nike Beaubier (Tempus)

Homologous Recombination Deficiency is Detectable from H&E Whole Slide Images in Real World Prostate Needle Core Biopsies

Homologous recombination deficiency (HRD) is an increasingly important molecular phenotype given the development of targeted treatments for HRD positive tumors. While HRD is routinely assessed in breast and ovarian cancer, prostate cancer patients with homologous recombination repair gene loss may also benefit from HRD evaluation. Here, the research team applied weakly supervised deep learning to predict HRD status from H&E whole-slide images in prostate cancer as a potential screening assay for confirmatory sequencing.

Time
01:00 pm - 04:30 pm CST

Presentation Number: 126

Authors
Rohan Joshi, MD, PhD (Tempus), Irvin Ho (Tempus), Aicha BenTaieb, PhD (Tempus), Stephane Wenric (Tempus), Martin C Stumpe (Tempus)

Detection of Pancreatic Ductal Adenocarcinoma Basal-Like and Classical Subtypes from H&E Whole Slide Images

FOLFIRINOX and gemcitabine/abraxane chemotherapy regimens are first-line treatments for pancreatic ductal adenocarcinoma (PDAC). While FOLFIRINOX generally has superior efficacy, it is associated with severe side effects that often make treatment intolerable. The Moffitt subtyping schema of PDAC using RNA expression data has identified molecular subtypes with prognostic value. Here, we developed a proof-of-concept predictor of molecular subtypes of PDAC from H&E whole slide images that could be used to rapidly prioritize cases for further RNA profiling.

March 15, 2023

Time
01:00 pm - 04:00 pm CST

Presentation Number: 218

Authors
AAdam Cole (Pathnet Labs), Roberto Nussenzveig (Pathnet Labs), Abigail Gordhamer ( Pathnet Labs), Matt Leavitt (DDX Foundation), Nike Beaubier (Tempus), Martin C Stumpe (Tempus), Geoffrey Schau (Tempus), Kunal Nagpal (Tempus), Rohan Joshi (Tempus), Rachel Baits (Tempus), Sebastian Pretzer (Tempus), Irvin Ho (Tempus)

H&E-Based MSI Predictor Generalizes to External Site Stain and Scanner Characteristics

Microsatellite instability (MSI) is associated with patient response to cellular immunotherapy across several cancer types. Previous studies have shown that AI-based imaging assays can infer MSI status from H&E whole slide images but external site generalizability remains a key challenge for successful deployment of deep learning models in digital pathology. In this study, researchers develop and evaluate a model trained to predict MSI status from whole-slide H&E images of prostate cancer and evaluate stain and scanner generalizability.

Schedule a meeting with us

We'll be in touch shortly.