UMMON HealthTech develops AI-based pathology software that analyzes digitized biopsy images to identify morphological anomalies and predict tumor molecular alterations. This technology enhances diagnostic accuracy and accelerates access to targeted therapies, reducing the time to initiate treatment by up to 60 days.
Funding
Funding not disclosed
Founders
Product
Problem
Traditional pathology relies on manual analysis of biopsy images, which can be time-consuming and subjective, potentially leading to diagnostic inaccuracies and delays in treatment. Access to molecular biology platforms for identifying potential therapeutic targets can be limited, delaying access to targeted therapies.
Solution
UMMON HealthTech offers AI-powered pathology software that analyzes digitized biopsy images to identify morphological anomalies and predict tumor molecular alterations. The software integrates diagnostic information, molecular biology, and therapeutic recommendations directly onto the digitized biopsy image, supporting multidisciplinary team meetings and optimizing cancer patient management. By identifying morphological anomalies undetectable by standard pathology classifications, UMMON's deep-learning algorithms refine diagnoses and predict patient responses to available therapies. The technology aims to optimize access to molecular biology platforms by prioritizing patients who may benefit from targeted therapies, reducing the time to initiate treatment.
Target Audience
The primary target audience includes pathologists, oncologists, surgeons, and radiotherapists involved in cancer diagnosis and treatment, as well as hospitals and diagnostic laboratories.
Features
- AI-driven analysis of digitized pathology slides for automated detection of morphological anomalies.
- Prediction of tumor molecular alterations (NGS, transcriptomics, epigenetics) from image analysis.
- Integration of diagnostic, molecular, and therapeutic data for multidisciplinary team review.
- Algorithms designed to support oncologists, surgeons, radiotherapists, and pathologists.
- p16/Ki67 AutoReader for automated cytology in cervical cancer screening.
- Ummon Crawler to identify patients who would benefit from molecular testing.
- Chemo-prAIdict to predict tumor chemosensitivity and relapse risk.
- Quality control tools to monitor the performance of AI algorithms in real-world settings.