Our science at AACR: SABCS
Deep learning-based identification and characterization of HER2-low tumors
A pre-screen approach for MSI from digitized H&E slides
Biomarker of response to immunotheraphy in NSCLC
A biomarker of outcome prediction in Mesothelioma
Revealing interpretable signatures of whole slide images
Deep learning to reduce sample size requirement for adjuvant HCC trials
Prediction of gene expression from H&E slides
Identifying pancreatic adenocarcinoma molecular subtypes from routine histology slides
Prediction of patient’s TLS status from H&E whole slide images in pan-cancer cohort
Prediction of patient prognosis from digitized pathology slides in early Breast Cancer (ER+/HER2-)
Robust Evaluation of Deep Learning-based Representation Methods for Survival and Gene Essentiality Prediction on Bulk RNA-seq Data
Jan 26, 2024
Subgroup analysis methods for time-to-event outcomes in heterogeneous randomized controlled trials
Jan 22, 2024
Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery
Journal of Pathology Informatics
Dec 29, 2023
View all publications
Understand how MSIntuit® CRC pre-screens for Microsatellite Instability directly from digitized H&E slides.
MSIntuit® CRC demo | Sectra
MSIntuit® CRC integrated into Sectra’s digital pathology solution, see how it works.
Discover the science behind our AI diagnostic tool.
Increasing the security of federated learning.
MOSAIC is the world’s largest spatial multiomics dataset in oncology.
Owkin combines cutting-edge machine learning and biology to advance drug discovery.
Meet the people at the heart of AI-augmented healthcare.
Prof Miriam Merad on the impact of building MOSAIC, the world’s largest spatial omics atlas in cancer.
External control arms
Data-driven prognostic covariates for adjustment to improve statistical power and broaden the eligibility criteria of randomized control trials.
What is spatial omics and how it works, with Margaret Hoang, Associate Director of Research at NanoString.
An open source federated learning software developed by Owkin for healthcare research.
Meet FLamby – the world’s largest open-source federated learning-ready datasets designed to bridge the gap between federated learning theory and practice, while tackling multiple healthcare data modalities.
A solution to help normalize real-world data distributed across multiple data centers in a federated manner, without compromising data privacy or security.
Voice as a biomarker
Artificial intelligence may soon help doctors diagnose and treat diseases, including cancer and depression, based on the sound of a patient’s voice.
A research project to develop new biomarkers to improve the targeting of antiangiogenic drugs.
We select data-driven prognostic covariates for adjustment to improve statistical power without sacrificing power of randomized control trials.
At Owkin we develop deep learning models to leverage crucial information captured in pathology images.
We develop interpretable AI models to identify clinically relevant biomarkers from multimodal data, such as omics, imaging, histology and clinical data.