AI Microscopy: Franklin.ai Glass

Book a DEMO

Franklin.ai Glass integrates with traditional histopathology, enhancing tissue analysis and diagnostic precision in AI Microscopy.

Predictions indicate that the number of new cases of prostate cancer will reach 35 million by 2050 (77% increase)*.
With pathologists responsible for diagnosing 100% of all cancers, their workloads are set to increase.

* Global cancer statistics 2022: GLOBOCAN estimates and mortality worldwide for 36 cancers in 185 countries.

Franklin.ai Glass: Integrated AI for traditional microscopy.

Franklin.ai Glass seamlessly integrates AI with traditional Microscopy, enhancing the efficiency and accuracy of pathology workflows. By providing AI-powered analysis directly from glass slide samples, Franklin.ai Glass eliminates the need for costly digital scanners while still enabling advanced tissue assessment. With real-time insights, automated detection of clinically relevant findings, and support for pathologists at every stage, Franklin.ai Glass brings the power of AI Microscopy into everyday practice.

Helping Pathologists save time with AI-assisted microscopy.

Did you know it can take over 10 years to train a pathologist? Whilst we can seek to address the shortage of pathologists, there's going to be a lag between the next generation of these much needed clinicians.

With rising caseloads in mind, Franklin.ai exists to streamline and scale the work pathologists can do. AI-assisted microscopy solutions help optimise workflows, reducing diagnostic turnaround times while maintaining accuracy. Our goal is to help unlock more healthcare capacity.

We want to create a world where more patients are on the right treatment pathway, thanks to the speed and precision of AI-powered diagnosis.

This technology story begins with a human story.

Harrison.ai was founded in 2018 by Dr Aengus Tran and Dimitry Tran. Prior to that, Dimitry had spent over a decade working in global healthcare and strategy; Aengus completed his medical training with distinction at the University of New South Wales in Sydney.

Witnessing first hand the gap between capacity of expert clinicians and demand they founded Harrison.ai. Their mission? To urgently scale global healthcare capacity, using A.I. automation. Their passion for computer science combined with deep medical expertise and the desire to change the world drove them onto the next chapter in the story - the founding of Franklin.ai in 2022, bringing AI-assisted microscopy to the forefront of digital pathology.

Changing healthcare for the better, with AI-Assisted Microscopy.

Every clinician, lab, hospital, technician, and member of the medical device community that works with us is helping to create a world where pathologists can perform at their best. By integrating AI-assisted microscopy into traditional workflows, we’re enhancing diagnostic precision and efficiency, ensuring more patients receive the timely, accurate care they deserve.

With the growing demand for pathology services and rising caseloads, solutions like Franklin.ai Glass are critical in expanding healthcare capacity. By providing AI-powered analysis directly from glass slides, our technology eliminates the need for costly digital scanners. Franklin.ai Glass supports pathologists with real-time insights, automated detection of clinically relevant findings, and seamless collaboration across teams. Alongside our Decision Support AI solutions, Franklin.ai is transforming pathology workflows to improve speed, accuracy, and accessibility in diagnostics.

Learn more about our Pathology AI solutions.

FAQs

Some microscope AI solutions break with scanning white space. Does Franklin Glass do this?
While using Franklin Glass you may encounter issues scanning across large areas of white space. To resolve this, you will need to pause the scan and resume scanning with tissue inside the field of view. We are currently working on improvements to make this a more seamless experience for the next release – we’d love to hear your feedback!
We have already decided to move towards 100% digital. Why would we adopt Franklin Glass?
If your lab is intending to move towards a 100% digital clinical workflow in the next 12-24 months, Franklin Digital may be best suited and give you additional workflow benefits including case triaging and integration with your IT systems. However, if your pathologists are excited to access the benefits of AI today and your lab perhaps doesn’t have the budget or business case to move to full digital pathology, Franklin Glass may be suitable for you. You can think of Franklin Glass as merely another type of ‘scanner’ (albeit a manual one!); you still get the benefits of the same Franklin Digital AI model and platform to support your lab.
What cameras and microscopes is this compatible with?
During testing, Franklin Glass was shown to be compatible with Basler Ace 2 in combination with the Olympus CX43 microscope. We intend to broaden Franklin Glass compatibility to include common camera and microscope models in the near future. Please get in touch to discuss how you can access Franklin Glass AI for your camera and microscope model.
What happens if we flip objectives?
AI analysis output will be accurate only on a 10X or equivalent objective level. Flipping objectives during a scan may result in a poorly scanned image. We recommend completing a full scan on the 10X objective only (by pressing ‘Start’ and ‘Stop’ only over sections of a scan being performed on 10X) for best performance. We aim to provide support for 4X analysis and other magnification levels in future releases of Glass.
How will this deal with different levels of focus? How will this account for blur and bias? How reproducible are the results?
AI analysis will be optimal when the scanned image and tissue are in-focus. You can adjust focus or rescan areas that are out-of-focus during scanning. The product has been designed such that the best quality frames are used in the final scan image. Preliminary internal testing has shown comparable AI performance on microscope-acquired images to whole-slide scanned images.
How long do I have to wait to get an AI result?
AI analysis turnaround time will depend on the amount of tissue sent for analysis. For a full slide of three cores and three levels, it may take approximately 10 minutes for AI analysis. For a single core, this would go down to a couple of minutes.
Stylised graphic of the Harrision logo
Built with Harrison.ai’s
proven AI technology.

By leveraging Harrison.ai's stable and proven A.I. technology, we can accelerate future product development at the highest levels of quality. We are building a platform at Franklin.ai that aims to improve efficiencies across all areas of pathology, starting with histopathology.

Your vendor neutral partner

We understand laboratories want choices in the vendors they work with. We partner and integrate with your suppliers of choice to ensure a seamless digital pathology solution.

Company logo of SectraCompany logo of Path-aiCompany logo of LeicaCompany logo of PhilipsCompany logo of 3DHistechCompany logo of HammamatsuCompany log of Amazon AWS