AI algorithm automates analysis of cystic fibrosis scans

By Jenni Spinner

- Last updated on GMT

(TefiM/iStock via Getty Images Plus)
(TefiM/iStock via Getty Images Plus)

Related tags Medical imaging Artificial intelligence analytical Lung Software

Artificial intelligence software company Thirona has released PRAGMA-AI, technology that automates and accelerates CT scans in cystic fibrosis analysis.

Thirona, an artificial intelligence (AI) software firm centered on medical-image analysis has released PRAGMA-AI, a new AI algorithm designed to streamline and accelerate the analysis of CT scans. The technology can help in the detection and quantification of lung abnormalities related to cystic fibrosis (CF).

Carla Kalkhoven, business development manager with Thirona, spoke with Outsourcing-Pharma about the PRAGMA-AI algorithm, and the implications for the advancement of future CF treatments and therapies.

OSP: Could you please talk about the evolution of CF research and drug discovery in recent years?

CK: In recent years, CF research has led to the availability of so-called Highly Effective Modulator Therapy (HEMT) for patients. These drugs are indeed highly effective but extremely expensive and can only be justified when they halt or substantially reduce the progression of CF-related lung diseases in patients.

OSP: What are some of the key challenges researchers face when looking for CF treatments and solutions?

CK: Although HEMTs have reached the clinical market, they face challenges in the adoption due to high price and variability in effectiveness. To move forward, it will be necessary to find ways of selecting and targeting patient subpopulations which will respond positively to different treatments, and to substantiate treatment claims with precise description of the mechanisms of action. PRAGMA-AI can support this process.

Currently, the most common way to measure lung disease severity and treatment outcome is lung function tests. These tests are useful for the detection of major changes in lung condition, but they are insensitive to small, clinically relevant progression of lung structure abnormalities. For the sensitive monitoring of structural lung disease, automated quantitative analysis is necessary.

Moreover, the introduction of HEMT potentially allows to withdraw other currently used maintenance therapies. To do this safely, sensitive monitoring of the progression of CF lung disease is needed.

OSP: Could you please describe Thirona in ‘elevator presentation’ form—who you are, what you do, key capabilities, and what sets you apart?

CK: Thirona is a high-tech company focusing on the development of artificial intelligence solutions for medical image analysis. Our focus is on the analysis of chest CT scans, chest X-ray, and retinal images, for disease diagnosis, treatment planning, and drug development.

Thirona combines its state-of-the-art knowledge of innovative deep learning technology with clinical expertise to develop effective analysis solutions that have direct clinical impact. Thirona believes in continuous innovation and has strong collaborations with clinical and scientific partners to remain at the forefront of new developments in the field of medical image analysis.

Besides having several certified medical software products, Thirona also offers an image analysis service by trained medical analysts for customized solutions and high-quality results.

OSP: Could you please tell us what makes PRAGMA-AI so innovative, how it complements your LungQ software, and what you hope it can accomplish for CF researchers that wasn’t possible before?

CK: Thirona's LungQ software suite already focused on the analysis of lung tissue, blood vessels and airway abnormalities on CT scans in a variety of diseases, including COPD, asthma, Bronchiectasis and COVID-19. The PRAGMA-AI algorithm combines this expertise in an analysis of the most important, clinically relevant abnormalities for CF lung disease and therefore fits perfectly in the proposition of LungQ.

It is revolutionary to use a precise, quantitative method for disease assessment on CT scans in clinical practice and research, as opposed to expert-based or time-consuming semi-quantitative readings. With PRAGMA-AI, it is possible to monitor with accuracy and precision the effects of treatment and disease progression in individuals over longer time intervals, while at the same time being cost-effective.

OSP: Do you have anything you’d like to add about your CF solutions, the disease itself, or anything else you’d want our readers to know?

The availability of PRAGMA-AI algorithm also allows the accurate and sensitive analysis of large numbers of chest CTs. In this way clinically relevant information of lung structure can be added to registries such as the ECFS patient registry; this allows evaluation of the efficacy of novel therapies in real life in large numbers of patients to improve our understanding of the strengths and weaknesses of novel therapies.

Related news

Show more

Related products

show more

The Right CDMO Can Unlock Faster Drug Development

The Right CDMO Can Unlock Faster Drug Development

Content provided by Lonza Small Molecules | 15-May-2023 | Interview

Drug development presents biotech companies with ever-changing challenges. Enabling a faster end-to-end process requires seamless flexibility and extensive...

SDTM supplemental qualifiers explained

SDTM supplemental qualifiers explained

Content provided by Formedix | 12-May-2023 | White Paper

What are SDTM supplemental qualifiers? In short, these are variables in non-CDISC datasets that cannot be mapped to a variable that matches the SDTM standard....

Plan for success with process liquid and buffer preparation

Plan for success with process liquid and buffer preparation

Content provided by Thermo Fisher Scientific - Process Liquid Preparation Services | 25-Apr-2023 | White Paper

Setting the groundwork for successful scale-up is essential for getting a therapeutic to market quickly and efficiently, but navigating the unknowns associated...

Related suppliers

Follow us


View more