Nucleai Launches New Multiplex Imaging Spatial Analysis Solution to Increase Reliability and Speed of Immunofluorescence Analysis

Nucleai, a leader in AI-powered spatial biology, announced the expansion of its spatial biology platform to include a new generation of multiplex immunofluorescence (mIF) analysis that uses deep learning to establish new levels of accuracy, speed, and generalizability, further unlocking the power of mIF data for drug discovery and development. Nucleai will present new data demonstrating the power of its new mIF pipeline to correlate spatial features with patient outcomes in colorectal cancer (CRC) at the Society for Immunotherapy of Cancer (SITC) conference in Boston this week.

Browse The Complete News About Blockchain : Blockchain Partnership: PraSaga and Metahug Gamify Web3 Education Via Roblox

“Nucleai’s platform will revolutionize the reliability and speed of mIF analysis conducted by translational researchers”

While mIF is a powerful technology for cancer research, current tools for mIF image analysis are time-consuming, manual, and not robust enough to generalize across different platforms, markers and indications. Nucleai addresses these challenges, bringing 40% improvement in accuracy compared to other solutions, while also reducing mIF analysis time-to-results from months to only weeks. Nucleai’s mIF pipeline, built and trained on millions of annotations across different staining platforms, indications and markers, provides the most comprehensive mIF deep-learning based solution available on market today.

“Nucleai’s platform will revolutionize the reliability and speed of mIF analysis conducted by translational researchers,” said Dr. Ken Bloom, Head of Pathology at Nucleai. “Our deep learning approach will enable the standardization of mIF-based analysis and help establish multiplex as common practice throughout drug R&D.”

Latest Aithority Insights: Got It AI Announces AutoFlows, a Breakthrough Autonomous Conversational AI

Nucleai’s cutting-edge AI spatial models, which are optimized for multiplex assays, derive new insights from tissue biopsies, including novel drug targets, mechanisms of action, and potential biomarkers to advance the field of precision medicine. The tumor microenvironment is a highly complex ecosystem, and spatial biology can be used to unlock the important relationships and interactions. The spatial analysis that run through Nucleai’s platform enables the discovery of novel tumor microenvironment cell patterns and signatures. The platform is agnostic to staining and scanning platforms and is currently available as a comprehensive service, providing fast turnaround times for large datasets of mid to high plex images.

New Data from CRC Study using Nucleai’s Spatial Biology Platform

Nucleai applied a novel end-to-end deep learning pipeline to mIF tumor-microarray images to predict outcome based on the tumor microenvironment (TME) composition. This novel deep learning pipeline for mIF analysis demonstrated high accuracy on the Nucleai platform in classifying cell types and phenotypic markers, thus enabling the identification of multiple cellular and spatial features associated with prognosis in CRC.

Cell typing model reached a 91.9% accuracy and strong performance by qualitative assessment in 97.7% of cores (>75% accuracy), thereby vastly outperforming current clustering-based cell typing approaches which demonstrated 65.9% accuracy in a paper published in Cell.

Red Hat and IBM Research :  Red Hat and IBM Research Advance IT Automation with AI-Powered Capabilities for Ansible

[To share your insights with us, please write to sghosh@martechseries.com]