In the field of lung cancer research, obtaining molecular information often requires sending tissue out for sequencing—a process that is slow, costly, and can consume precious biopsy material. Pulmogene-Predict, developed by Imagenomix, offers a compelling alternative by using artificial intelligence to predict EGFR mutations directly from routine hematoxylin and eosin (H&E) whole-slide images. This approach not only saves time and resources but also preserves limited tissue for confirmatory testing, making it a valuable tool for research and clinical trial enrichment.
Pulmogene-Predict is part of the Imagenomix IGX Predict platform and is designed to integrate seamlessly with Techcyte Fusion AP, an enterprise digital pathology platform. Pathologists can send H&E slides from a Fusion AP case to Imagenomix’s cloud for analysis, and results return as a mutation score, a spatial heatmap showing where the biomarker signal is strongest, and a PDF prediction report. This workflow fits naturally into existing slide review processes, allowing molecular insights to be explored without disrupting routine practice.
What is Pulmogene-Predict?
Pulmogene-Predict is a research-use-only AI application that predicts cancer genetics from standard pathology slides. It focuses initially on EGFR mutation prediction in lung cancer, with plans to expand to other biomarkers such as KRAS and TP53. The tool works from existing H&E images, meaning no additional stains, sections, or tissue consumption is required.
Also worth a look: A&D Medical Direct Connect Review: Secure BP Monitoring for MyChart and Hensley / Elam Review: AI-Enabled IT & Cybersecurity.
By bringing molecular prediction into the digital pathology workflow, Pulmogene-Predict helps address a significant gap: many lung cancer patients never receive molecular testing due to limited biopsy material or slow turnaround times. The tool enables a screen-then-confirm research approach, where the AI prediction can guide subsequent confirmatory testing, making the overall process more efficient and tissue-sparing.
Key Features and Benefits
Pulmogene-Predict offers several standout features that make it a noteworthy addition to the pathology research toolkit. Its ability to work from routine H&E slides without consuming additional tissue is a major advantage, especially when dealing with small biopsies. The integration with Techcyte Fusion AP ensures a smooth, end-to-end digital workflow.
- AI-Powered Prediction: Uses deep learning to predict EGFR mutations from whole-slide H&E images, returning actionable scores and spatial heatmaps.
- No Additional Tissue Required: Works from existing slides, preserving limited biopsy material for necessary confirmatory tests like NGS or IHC.
- Seamless Integration: Designed to plug into Techcyte Fusion AP, allowing pathologists to send images and receive results within their existing case management system.
- Research and Trial Enrichment: Can screen archived H&E slides to identify potential biomarker-positive cohorts, supporting retrospective studies and clinical trial enrichment.
- Future-Proof Design: The platform is built to expand to additional biomarkers, including KRAS, TP53, and more, as research evolves.
Who It’s For
Pulmogene-Predict is primarily intended for pathologists and researchers working in lung cancer molecular research and clinical trial settings. It is especially valuable for laboratories that handle small biopsies where conserving tissue is critical. Biopharma partners conducting translational research or seeking to enrich trial cohorts with biomarker-positive patients will also find the tool useful.
The product is not a clinical diagnostic and does not replace next-generation sequencing or immunohistochemistry. Instead, it serves as a research aid that can streamline workflows and provide early molecular insights. Labs already using Techcyte Fusion AP will benefit from the native integration, while others may adopt it as part of a broader digital pathology strategy.
What Makes It Worth Considering
Pulmogene-Predict stands out because it addresses a real bottleneck in lung cancer research: the gap between routine histology and molecular testing. By enabling pathologists to explore mutation profiles from the same H&E slide they are already reviewing, the tool reduces the need for reflex testing and can accelerate research timelines.
The spatial heatmap is a particularly useful feature, showing where in the tissue the biomarker signal is strongest, which can help guide microdissection or confirmatory testing. Additionally, the ability to screen archived slides opens up new possibilities for retrospective studies and cohort identification without consuming additional tissue. While the tool is currently limited to research use, its potential to improve efficiency and accessibility in molecular profiling is significant.
Verdict
Pulmogene-Predict offers a groundbreaking way to explore molecular signals from routine H&E slides, preserving tissue and accelerating research workflows. Its integration with Techcyte Fusion AP makes it a practical addition for labs already using digital pathology, and its focus on EGFR mutation prediction addresses a key need in lung cancer research. For pathologists and researchers looking to get more from their H&E slides without additional tissue consumption, Pulmogene-Predict is a promising and innovative tool.
Frequently asked questions
It uses AI to predict EGFR mutations from routine H&E whole-slide images, returning a mutation score, spatial heatmap, and PDF report.
No, it is intended for research, translational, and trial-enrichment use only, and does not replace next-generation sequencing or immunohistochemistry.
Pathologists can send H&E slides from a Fusion AP case to Imagenomixu2019s cloud for analysis, and results return directly to the case.
It starts with EGFR mutation prediction, with future expansion planned for KRAS, TP53, and other biomarkers.
No, it works from existing H&E images, so no additional stains or sections are needed, preserving biopsy material.
Pathologists, researchers, and biopharma partners working on lung cancer research and clinical trial enrichment.
