Thirona, a Dutch start-up company specialising in AI to analyse medical images, is offering one of their products for free to medical imaging specialists in an effort to combat the COVID-19 pandemic. International Hospital speaks to Dr Eva van Rikxoort, the Managing Director and founder of Thirona, about the company and its products.
International Hospital: Thirona is a Dutch company established in 2014. Can you give our readers a bit of background about the company?
Eva van Rikxoort: Thirona started in 2014 as a spin-off from the Radboud University in Nijmegen. We started with two full-time employees and we have built our company to 25 full-time employees and 20 part-time medical analysists. Together, we developed artificial intelligence software to analyse chest CT scans, chest X-ray images and retina images. Healthcare specialists around the world use our AI software for diseases like asthma, COPD, tuberculosis and diabetic retinopathy.
IH: What led you to set it up?
EVR: I was doing research on chest CT analysis at the Radboud University with my co-founder Prof. Bram van Ginneken. We saw that there was a gap between research that was being done on potential clinical solutions and putting those into clinical practice; Thirona was founded with the vision to bridge that gap.
IH: What products did you have at that time?
EVR: We started with two launching customers for one solution – our AI solution for chest CT analysis.
IH: Where does the name Thirona come from?
EVR: The name Thirona comes from the Celtic goddess named Thirona, worshipped for healing. Although more commonly spelled as ‘Sirona’ in the Latin alphabet, the spelling Thirona was chosen to reflect our roots in thoracic image analysis.
IH: Delft Imaging appears to be part of Thirona. Can you tell us a bit more about Delft Imaging and the relationship between Thirona and Delft Imaging?
EVR: Technically, Thirona and Delft Imaging are separate companies, although we collaborate extensively and practically work together as sister companies. Where Thirona specialises in artificial intelligence software for medical imaging, Delft Imaging specialises in diagnostic innovations that can be used in developing countries. For example, our AI solution for chest X-ray analysis (CAD4TB) is developed by Thirona and distributed by Delft Imaging.
IH: Can you tell us briefly about your key products and where they are being used?
EVR: We essentially offer three categories of products. AI software for chest CT analysis focusing on COPD and asthma, called LungQ; AI software for X-ray analysis – focusing on tuberculosis, called CAD4TB; and AI software for the analysis of retinal images – focusing on DR, AMD and Glaucoma, called RetCAD. LungQ allows for the quantification of chest CTs and is used for patient monitoring, treatment planning and clinical trial analysis.It is mostly used across the United States and European Union. CAD4TB is used in 40 countries around the world and has screened more than 6 million people for tuberculosis. RetCAD is being rolled out across Europe and Asia.
IH: If we look at how the company has grown over the past 5-6 years — can you explain what has been the driving force behind the growth?
EVR: As a spin-off of the Radboud University, our company (and our solutions) is rooted in science. Every software product we develop is thoroughly validated (through 150+ publications to date) and that level of validation drives our growth, I believe; our customers know the type of quality we aim to offer.
IH: What guided your research and development? In other words, why did you take the product development route you have taken?
EVR: We are a demand-driven organisation. Meaning, we develop and work on where our customers and partners have needs to be supported. That has led us on the route we have been on for the past sevearl years.
IH: What are the main challenges have you faced and how have you overcome them?
EVR: One of the main challenges was keeping the same culture in the company during the growth from a small team of a few people with similar backgrounds to a larger more diverse team. We did this by installing a management team structure. By making it a focus for each team allowed us to overcome any difficulties.
IH: Most recently, you are offering a free AI-powered COVID-19 tool – the CAD4COVID-Xray. I understand it has been developed on the back of your successful TB-screening AI tool, CAD4TB. Can you explain how the CAD4TB tool works and how you adapted it for COVID-19 screening.
EVR: Yes, we developed two AI-powered COVID-19 tools actually: one for chest X-ray analysis and one for chest CT. Both have been built on the technical foundation of our existing and proven CAD4TB and LungQ solutions. Because there were underlying algorithms already in place, we were able to rapidly pivot these for the detection of COVID-19.
IH: How will this tool help healthcare facilities and COVID-19 patients?
EVR: CAD4COVID-XRay and CAD4COVID-CT automatically detect COVID-19 related abnormalities and thereby help with triage before any follow-up testing, like RT-PCR. This helps to reduce the workload of healthcare personnel and alleviate the burden on RT-PCR tests. Furthermore, both solutions show the percentage of affected lung tissue, thereby helping to track disease progress and recovery.
IH: How has the AI tool been validated? Has it been approved for use in Europe? In which other countries / regions has it been approved?
EVR: We have done several studies for both solutions (a publication on CAD4COVID-XRay was recently published in Radiology), through which we were able to prove that the software performs on par with expert human readers. For both solutions we have applied for class IIa CE certification, which we expect to receive soon.
IH: Are the CAD4COVID tools specific to certain platforms?
EVR: Both solutions are system agnostic. They process DICOM images which can be from any type of system.
IH: Are you receiving many requests for the CAD4COVID-Xray AI tool?
EVR: The response has been tremendous, which is probably also because we made the software available free-of-charge. CAD4COVIDXRay was launched first (March 31st) and has since been made available to 30+ healthcare facilities across more than 20 countries. We are especially focusing on resource-constrained settings (mostly in developing countries) because in those settings CT often has limited availability, making X-ray all the more important. CAD4COVID-CT was launched a month later and is available at 15+ facilities across 10 countries. We are also integrating it in several platforms through collaborations with partner companies like Smart Reporting.
IH: Why are you offering it for free?
EVR: We knew that for CAD4COVID to have the biggest impact during the pandemic and provide the most support to healthcare specialists globally, we needed to roll it out rapidly. In order to do that, we wanted to avoid as many hurdles as possible that could cause a delay in facilities being able to use the software. We believe cost is a big factor in that. That’s why we, supported by several organisations, have made it available to use free-of-charge.
IH: Can it be shared easily with healthcare facilities that want to use it?
EVR: Yes, people can fill in a form on www.delft.care/cad4covid (for CAD4COVID-XRay) and www.thirona.eu/cad4covid (for CAD4COVID-CT) and our team will reach out to them to help them set it up for their facility.
IH: Is any training required to use the CAD4COVID tools?
EVR: The tool is designed to be very intuitive, but we have developed an onboarding tool to guide new users on how to use the software effectively.
IH: Lastly, what’s in the pipeline for Thirona and how do you envisage development of the field of AI in medical imaging?
EVR: We are quickly expanding into other areas like cystic fibrosis on chest CT analysis, silicosis on chest X-ray analysis and cataract on retinal images. I believe that AI still has to prove itself in many settings, for many different use cases, but that it will become more and more accepted over time, and we already see this happening at incredible speed. In time, AI will leverage the efforts of our healthcare specialists, helping them to diagnose and determine treatment planning quicker, more effectively and reduce their workload in the meantime.

The German Federal Government asked domestic vehicle manufacturers to produce medical equipment, such as masks and ventilators, to help fight Covid-19.
In a statement, the Volkswagen Group announced 20 March it will be providing about 200,000 category FFP-2 and FFP-3 protective face masks for public health protection in the near future. The donation is being made in close cooperation with Federal Minister of Health Jens Spahn.
A spokesperson said the company has more than 125 industrial 3-D printers which could be repurposed to make respirators or other necessary devices, once they receive the required info.
Kathrin Schnurr, spokesperson for Daimler AG Human Resources and External Affairs Communications told International Hospital: “We have inquiries from the medical technology sector. We are currently examining how we can contribute, for example by providing 3D printers or our production expertise.
“In addition, we are in constant communication with the authorities about how and where we can help, for example to sustain the supply infrastructure.”
This follows a trend across Europe as companies unrelated to the medical-device industry offer to retool factories to help make equipment to combat the shortage of devices such as respirators and face masks.

Even as the world grapples with COVID-19, there is another looming public health problem. Antibiotic resistance, according to some experts, may turn out as bad, or even worse, than the current pandemic.

Similarities in European and US fatalities

In November 2018, the Stockholm-based European Centre for Disease Prevention and Control (ECDC) released a study which estimated that about 33,000 people died each year in Europe, due to anti-microbial resistance (AMR).
One of the most disturbing findings was that 39 percent of the burden is caused by infections with bacteria which had resistant to last-line antibiotics such as carbapenems and colistin. This, the ECDC observed, was worrying as the latter antibiotics were often the last treatment options available. When these are no longer effective, it is extremely difficult or, in many cases, impossible, to treat infections.
The ECDC report also explained that 75% of the burden of disease due to resistant bacteria was due to healthcareassociated infections (HAIs), and that this could be reduced through adequate infection prevention and control measures.
Fatalities in the United States due to AMR are similar to those in Europe. In early March, just as COVID-19 was beginning to gain momentum in Europe, the Centers for Disease Control and Prevention (CDC) stated that more than 35,000 people die as a result of AMR in the US each year.

Not a new challenge

The problem of antibiotic-resistant bacteria is not new. Awareness of the fast-emerging challenge, and its scale, has been present for decades. It is also routinely re-kindled.
In March 1994, ‘Newsweek’ magazine highlighted the threat in a cover story titled ‘End of the Miracle Drugs.’ A few months later, in September, ‘Time’ magazine followed up with a feature titled ‘Revenge of the Killer Microbes.’
The challenge moved to the centre of global attention in April 2011, when the World Health Organization (WHO) warned that indiscriminate use of antibiotics was giving rise to resistant ‘superbugs’, which could render the drugs useless. Also that same year, the EU warned that anti-microbial resistance was a public health priority, with the Commission adopting an action plan against the rising AMR threat.
Three years later, the WHO warned about the impending arrival of a ‘post-antibiotic era.’
In 2016, the O’Neill report, commissioned by the UK government, suggested that, without action, AMR will cause the deaths of 10 million people a year by 2050.

COVID-19 and bacterial infections

It is now over a quarter century since the dramatic warnings by ‘Time’ and ‘Newsweek’.
Given the high levels of awareness about infection and hygiene at present due to COVID-19, some believe that this is the best moment to launch a concerted campaign to control the growth of antibioticresistant bacteria.
One of the factors which would favour such timing is a report from Stanford University School of Medicine. This found that secondary infections to be commonplace in hospitalized COVID-19 patients.
The authors note that though much more data would be required, severely ill patients are ten times more likely to have bacterial or fungal secondary infections than viral. They also observed that “ICU patients with prolonged illness/intubation have more frequent detection of multidrug-resistant Gram-negative pathogens, likely reflecting hospital-acquired infection.”

Air travel, animals would spread bacterial pandemics too

It is now evident that one of the factors behind the speed at which COVID-19 became a global pandemic was air travel. The impact of increasing antibiotic resistance is no different. For example, the blaNDM-1 ‘superbug’ gene was detected in India in 2007 but was found shortly thereafter in hospital patients in Sweden and Germany. In 2013, it was found at Svalbard in the Arctic.
Once again, just as with COVID-19, variants of blaNDM-1 have appeared locally, evolving with time as they move.
Such dispersal, in both bacteria and viruses, are not only caused by human travel. Wildlife, such as migratory birds, not only carry ‘bird flu’, but also resistant bacteria and genes from contaminated water or soils.

Antibiotic use

One of the most problematic aspects of the AMR challenge is inappropriate antibiotic use.
In 2016, the EU Council issued advice under its One Health approach and called on the Commission and Member States to develop EU-wide guidelines on prudent use of antibiotics.
Once again, the gap between threat perception and action is large.
At the turn of the previous decade, the ‘British Medical Journal’ urged authorities to harmonize antibiotic prescribing practices in order to tackle resistance. This followed a multi-year effort by the EU Commission to study community-acquired lower respiratory tract infections (CA-LRTI), which were resistant to antibiotics.
The Network of Excellence project, which was called GRACE (Genomics to combat Resistance against Antibiotics Communityacquired LRTI in Europe), identified wide variations in antibiotic use, in spite of little impact on patients’ recovery times. Although the GRACE website (www.grace-lrti.org) no longer exists, some of its findings were alarming.
For coughs, for example, antibiotic prescribing by physicians ranged from 20 percent in some countries to 90 percent in others. Ressitance levels were confirmed to be especially high. Some 70 percent of bacteria responsible for HAIs were resistant to at least one of the drugs most commonly used to treat infections. Some organisms were resistant to all approved antibiotics and needed to be treated with experimental and potentially toxic drugs.

Variations in impact of resistant bacteria

The impact of antibiotic-resistant bacteria varies greatly between countries. As a result, EU strategies to prevent and control antibiotic-resistant bacteria require coordination at both European and global level.
Since 2014, the ECDC has sough to monitor antibiotic consumption in the EU via the European Surveillance of Antimicrobial Consumption Network (ESAC-Net). Towards this, it has has been using the number of packages per 1,000 inhabitants per day (ipd), as a surrogate for prescriptions, to make comparisons.
At the end of 2017, a study in ‘Eurosurveillance’ using ECDC data showed consumption of antibiotics across Europe ranged from 1.0 to 4.7 packages per 1,000 ipd. However, further analysis revealed that “consumption of antibiotics for systemic use per 1,000 ipd was on average 1.3 times greater in France than in Belgium when considering prescriptions in the numerator” and “2.5 times greater when considering packages.”

Lessons from below

In reality, resistance has been with us ever since antibiotics began to be used, and resistant strains of bacteria have been with us since life began. Resistance has, however, recently accelerated due to use, or rather over-use. Antibiotics typically kill the majority of bacteria at an infection site, but not all. Some bacteria are naturally resistant. Others acquire the genes which carry resistance from other bacteria, especially from our digestive and respiratory systems.
Knowledge of antibiotic resistance development pathways in bacteria has been revolutionised after a research expedition by microbiologists 500 meters below the earth’s surface a cave at Carlsbad Caverns National Park in the US State of New Mexico. The researchers, whose discoveries were described in April 2012 by ‘National Geographic’ magazine, found no fewer than 100 types of bacteria coating the cave walls.
Until that moment, the bacteria had no contact with humans. This was due to geology. Between 4 and 7 million years ago, the cave had been isolated by a massive mantle of rock. Even water takes some 10,000 years to reach the depths of the cave.
Though the bacteria in the cave are non-pathogenic, researchers subsequently discovered that they were resistant to many classes of antibiotics. This held up the possibility that the bacteria would offer new means to investigate the genetic pathways by which resistance to antibiotics is developed.

Insights for new antibiotic development

Until recently, studies had suggested that the bulk of antibioticresistant genes ought to take at least several thousand years to develop. However, resistance to new antibiotics begins within months or even weeks of their launch. Microbiologists have long suspected that this is because bacteria not only routinely exchange genes from other bacteria but that benign bacteria may provide a huge pool of ancient antibiotic-resistance genes ready to be transferred to their pathogenic cousins.
The isolated bacteria in the New Mexico cave have begun providing clues about such theories – and provide new insights into designing the next generation of antibiotics. One of the biggest is that the internally-hardwired resistance is true only for natural antibiotics. The cave bacteria are sensitive to man-made antibiotics.

Turning around antibiotics

More work continues in the Carlsbad Caverns. Barely weeks ago, it was reported that the researchers came across an underground pool of water which is likely to contain other microbial organisms.
So far, the pharmaceutical industry has responded to increasing resistance by developing new and stronger antibiotics. However, given the fact that bacteria evolve rapidly, and even new antibiotics quickly lose their effectiveness, less attention has been paid to new antibiotic development. It is hoped that the findings at Carlsbad Caverns will provide lessons and show us ways to turn such a process around.

New research provides cause for encouragement

Recent findings from academic research in the US and Europe give cause for encouragement that we may soon see a new class of antibiotics.
In early June, a team of Princeton University researchers reported that a compound, SCH-79797, simultaneously punctured the walls of Gram negative bacteria and destroyed the folate in their cells, while being immune to antibiotic resistance.
Gram-negative bacteria are protected by an outer layer which neutralises most antibiotics. Indeed, for almost three decades, there has been no new class of drugs against them.
SCH-79797 is described as being akin to a poisoned arrow, providing synergy between two ways of attack – an arrow to break the wall and poison against folate. The compound is expected to inspire new derivatives and has been named Irresistin, since it can be used against even the toughest opponents – from E. coli to MRSA (methicillin resistant Staphylococcus aureus).
A few days after the discoveries from Princeton University were reported, the journal ‘Nature Communications’ described efforts by scientists at Britain’s University of Liverpool and the University of Utrecht in the Netherlands to develop a viable drug based on teixobactin – a new class of potent antibiotic capable of killing superbugs.
Teixobactin was hailed as a ‘game changer’ after it was discovered in 2015, due to its ability kill multi-drug resistant bacterial pathogens such as MRSA without developing resistance.

Medtronic said 18 March it plans to more than double its capacity to make and supply ventilators to fight the global pandemic.
Medtronic, an industry leader in respiratory care and device innovation, said that they had already increased production by more than 40 percent and were on track to more than double its capacity to manufacture and supply ventilators.
The company said it recognizes the acute need for ventilators as life-saving devices in the management of COVID-19 infections. High-performance ventilators play a critical role in the management of patients with severe respiratory illness, such as COVID-19. Without ventilation support, some patients with severe respiratory disease might not survive.
“Medtronic recognizes the demand for ventilators in this environment has far outstripped supply,” said Bob White, executive vice president and president of the Minimally Invasive Therapies Group at Medtronic. “No single company will be able to fill the current demands of global healthcare systems. However, with all manufacturers increasing their production and through partnerships with governments, hospitals and global health organizations, Medtronic is committed to getting more ventilators into the market and to the right locations in the world to help doctors and patients dealing with COVID-19.”
Medtronic produces high performance ventilators for a variety of care settings, including the acute segment (in-hospital patients in intensive care units, emergency departments or on the general care floors) and the sub-acute segment (out of hospital, long-term care facilities or home-ventilated patients).
Medtronic manufactures the Puritan Bennett 980 (PB 980) and Puritan Bennett 840 (PB 840) high performance ventilators in Galway, Ireland, which are primarily designed for critically ill patients in high acuity setting, such as some Covid-19 patients.
In the company’s Ireland ventilator manufacturing facility, the company currently has over 250 employees dedicated to ventilator manufacturing and plans to more than double that number, including transferring staff from other Medtronic sites to support ramp up activities.
Ventilator manufacturing is a complex process that relies on a skilled workforce, a global supply chain and a rigorous regulatory regime to ensure patient safety.
Medtronic said it is prioritizing high risk/high needs areas for ventilator allocation on a weekly basis for global distribution through its supply chain. Covid-19 is a dynamic global issue, and Medtronic will continue to monitor the situation.