Imagene AI to Demonstrate Real-Time Biomarker Detection From H&E Images at ASCO 2022

Imagene will also present its poster, "Image-based detection of FGFR3-fusion in urothelial bladder cancer"

CHICAGO, June 01, 2022 (GLOBE NEWSWIRE) -- Imagene AI, an emerging leader in the field of AI-based precision medicine for cancer, today announced that it will demonstrate its molecular and spatial intelligence platform at the 2022 American Society of Clinical Oncology (ASCO) conference. Imagene’s deep learning models have been shown to detect a wide range of cancer biomarkers in real time, using only a digitally scanned Hematoxylin and Eosin (H&E) image.

Imagene’s molecular classifier platform currently detects 28 cancer biomarkers, spanning seven organs, including lung, thyroid, breast, ovary, CNS, bladder, and hematologic malignancies. When compared to gold standard genomic testing methods, Imagene’s validation demonstrated, on average, sensitivity of 94.8%, greater than 90% specificity, and an AUC over 0.95. Imagene has demonstrated the capability to identify a spectrum of alterations, including mutations (e.g., EGFR), fusions and other structural variants (e.g., NTRK), differential gene expression (e.g., HER2), and cancer signatures (e.g., HRD).

Imagene leadership team will offer individual presentations in its ASCO booth, #2086, June 4-6 during exhibiting hours (9:00 a.m. to 5:00 p.m. CDT) at McCormick Place in Chicago.

“Imagene’s deep-learning technology, which continues to detect a growing number of cancer biomarkers in real time using only an H&E image, has the potential to truly democratize access to precision medicine, allowing for both improved quality of care and stratification of patients into clinical trials,” said Dean Bitan, co-founder and CEO at Imagene. “We look forward to participating at ASCO and demonstrating how our technology unlocks valuable information to support oncologists and pathologists, as well as drug developers and researchers.”

As example of Imagene’s biomarker detection capabilities, its abstract, “Image-based detection of FGFR3-fusion in urothelial bladder cancer,” was accepted for ASCO poster presentation (Abstract No. 3072; Poster No. 64), June 5, at 4:00 CDT.

The FGFR3 classification model was validated on a cohort of 150 patients from 19 different medical centers. FGFR3 is a prognostic, predictive, and therapeutic target in urothelial bladder cancer, directing targeted treatment such as BALVERSA® (erdafitinib) in locally advanced or metastatic urothelial carcinoma. The initial research shows that FGFR3 alteration (mutations and fusions) accounts for up to 80% of the cases (depending on grade and stage). Screening these patients using an image-based solution has potential to dramatically speed-up diagnosis time and improve diagnostic accuracy, leading to well-timed, personalized treatment.


Imagene AI is a precision oncology diagnosis company. Its molecular and spatial intelligence platform delivers real-time biomarker reports using only digitized biopsy images, leading to faster diagnosis and better identification of treatment for patients. Its multidisciplinary team is composed of a diverse group of experts from the fields of science, clinical, and deep learning.

Imagene collaborates with top-tier medical centers and pharmaceutical companies worldwide, making therapeutic decisions for cancer more accurate and accessible, profiling patients for clinical trials, and accelerating the drug development process.

For more information, visit

The mentioned products are currently used for research purposes only and subject to regulatory clearances in the applicable markets.

A photo accompanying this announcement is available at


Image-based detection of FGFR3 fusion in urothelial bladder cancer

Contact Data