This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.
Life Sciences
Case Studies
An increasing number of biopharma companies are looking for an imaging strategy. Combined with AI techniques, imaging can predict which patients will respond to a drug, finding the right candidates for clinical studies, detect patients at risk, and accelerate drug development programs.
Applications
Oncology
Our tissue-agnostic AI methods are applied at each stage of drug development programs. First we apply our AI techniques to harmonize image quality across hospitals and scanner models, then we perform automated organ and lesion detection. A tissue characterization follows to extract a signature based on the most relevant radiomics-based and deep features. These features are then used to develop predictive models of tumor growth, treatment response, overall survival, disease free survival, among many other patient outcomes.
Immunology
Our AI-based tools provide patients with an early diagnosis for rheumatic diseases in the main imaging modalities. We support the digital transformation of therapy indication either during drug-development phases or in post-approval scenarios, deploying an integrated offering to healthcare providers.
Neuroscience
We apply our AI-based methods for automated segmentation and quantification of brain tissues and abnormal lesions. We assess differences in the volume of brain regions in neurodegenerative and inflammatory diseases and in metabolic disorders, extracting surrogate imaging biomarkers.
Hematology
We provide automated segmentation methods for lesions and organs in whole body PET/CT examinations. The most frequent clinical scenarios are lymphoma and multiple myeloma, extracting lesion-level features, which, combined at the patient level, can help in predicting treatment response in standard or advanced therapies as well as other phenomena like cytokine release syndrome (CRS) in cell therapies such as Chimeric Antigen Receptor T-cell therapies (CAR-T).
-
Drug revival: Prediction of treatment response to immunotherapy in NSCLC
-
Post-approval: Identifying patients suffering from axial spondyloarthritis (axSpA) at an early stage, candidates for an approved drug
-
Managing, storing and analyzing large-scale imaging and multi-omics datasets through QP-Discovery® platform
-
Early detection of localized colon cancer relapse using an AI-based predictive model