19.11.2019 Hype, hope and reality DÜSSELDORF | TUESDAY 19.11.2019 Artificial intelligence (AI) opens up a host of new diagnostic methods and treatments. Almost daily we read about physicians, researchers or companies that are developing an AI system to identify malignant lesions or dangerous cardiac patterns, or that can personalise healthcare. ‘Currently, we are too focused on the topic,’ observes Professor Christian Johner, of the Johner Institute for Healthcare IT. At the same time he does recognize the enormous potential of AI. However, to leverage the technology, several challenges must be mastered and a proper framework established. things than a human. That’s how we should look at AI: it is a tool that can perform certain tasks better than we Fujitsu Smart Hospital Solutions Asked which AI methods are cur- rently being applied in healthcare, the professor said: ‘The best known methods are machine learning meth- ods that detect patterns in existing data pools and can thus find solu- tions autonomously. One of these methods is Deep Learning, which uses neuronal networks. Today we use it in imaging, for example. More recently, boosting procedures such as XGBoost, which is also a machine learning approach, have been quickly gaining ground. ‘Moreover, AI is used to detect depression by analysing language and movement patterns. Other areas of application are production, selec- tion and dosage of pharmaceuticals, error detection in patient records and signal detection in ECG to recognise arrhythmias. These are diagnostic methods that have been approved and are commercially available. Additionally, AI methods are used in therapy, for example in triage, where they support decision-making processes.’ Which types of AI innovations will have the greatest impact on healthcare? ‘Hard to tell. Any prognosis has to consider the hype curve. AI has reached peak hype in imaging. I’m sure that in other areas the hype is still to come. AI will sweep over us in waves at different points. The next focus will be on false diagnoses and treatments, which will generate con- siderable attention. These AI applica- tions will become part of medical practice sooner or later, without the patient ever noticing their existence, a bit like anti-lock brakes in the car.’ Which regulations must manufac- turers of AI healthcare applica- tions meet? ‘The legislator neither can, nor wants to, adopt a separate set of laws for each medical device category. The Medical Device Directive, in the near future the Medical Device Regulation, defines the requirements. This legal framework has to be adjusted for the current AI procedures with a focus on verification and validation of the systems, stability and reproducibil- ity as well as fitness for use – issues that are already regulated. The law demands that benefits of the systems be proven quantitatively and that they outweigh the inherent risks of the systems. ‘This regulatory framework pro- vides good guidance. We are cur- rently working on specific stand- ards for AI. In cooperation with the notified bodies, such as TÜV, I drafted a guideline covering these requirements. This not only refers to the devices themselves, but also to organisations – inter alia they must define and prove staff competen- cies.’ What limitations does or should AI have? ‘AI should not cement bias – some- thing that happens quite eas- ily depending on the data pool the developers use to train their algo- rithms. Furthermore, AI methods must not be used when there is no clear evidence of their benefit and when the risks outweigh the ben- efits. ‘We also have to discuss whether we need to regulate the econom- ic framework together with the AI methods. For instance: Should health insurers be allowed to use AI for reimbursement decisions?’ Some people fear AI will replace physicians, particularly in imag- ing. Could this happen? ‘There’s already a shortage of physi- cians and healthcare will not become easier in the future. I hope that AI will ease physicians’ workload – after all, these systems are programmed to support them in routine tasks. In some areas, AI is more powerful than the human brain, but that’s not a new experience. A truck, we all agree, is better at transporting h o t n e k / k c o t s r e t t u h S © humans. AI will give physicians more time to actually deal with patients. ‘This means we need physicians who can use the information culled from AI in a meaningful way, in the diagnostic workup, or who can assess and implement therapy sug- gestions made by an AI system. These skills create an added value for human intelligence.’ Professor Christian Johner, physician and founder/owner of the Johner Institut GmbH, a consultancy for manufacturers of medical devices, teaches software architecture, software engineering, software quality assurance and medical IT at the University of Constance, Germany. At Stanford University, USA, in 2010-11 he was a research associate contributing to the development of the ontology editor named Protégé and he taught Modelling of Biomedical Systems. Fujitsu IoT Connectivity Solutions for Hospitals More info: www.fujitsu.com/IoT WWW. H E A LT H C A R E - I N - E U R O P E . C O M ISO 13485:2016LATEX GLOVESMAKE GREAT BALLOONS BUT THEY MAKELOUSY PROBE COVERS.AD 38-1 REV 3Sure, exam gloves are “handy”, but using one as a probe cover isawkward, especially with a large3D/4D probe. It also allows for wasted ultrasound gel, can bemessy, and if the glove is latex,may cause an allergic reaction inpatient, clinician, or both. That’s why we developed the Eclipse®3DProbe Cover, specially designedfor 3D/4D probes.So you can save your examgloves for iheir iniended use, or for decoraiing ihe nexi office pariy. Like our original Eclipse® ProbeCover, Eclipse 3D is laiex-free andconvenienily pre-gelled wiih Aquasonic® 100, ihe world siandardfor medical ulirasound procedures. Visit us at Hall 9 Stand D41© 2018 Psrker Lsborstories, Inc. The sound choice in pstient csre is strsdemsrk of Psrker Lsborstories, Inc.Hall 10B60

T U E S D AY @ M E D I C A 3 tion and structure that allow them to adapt to the characteristics of the fluid they are moving through. For instance, if they encounter a change in viscosity or osmotic concentration, they modify their shape to main- tain their speed and manoeuvrability without losing control of the direc- tion of motion.’ While currently at the research stage, the next step for the scientists is to test them in ex vivo animal tis- sue. However, they remain confident that their robots can be inexpensive and be manufactured relatively easily. Brad Nelson has been Professor of Robotics and Intelligent Systems at ETH Zürich since 2002, conducting research on microrobotics, nanorobotics, and medical robotics. His key interest lies in how to make tiny intelligent machines of millimetres to nanometres size, with applications in medicine. Research: Microrobots to re-shape drug delivery ransforming minuscule ‘swimmers’ or inserted into human veins to deliver drug therapies directly to diseased body areas. Scientists have developed minute flexible robots that could help revolutionise drug delivery in the future, Mark Nicholls reports. These ‘microrobots’ are so small that they could be ingested, to unblock a thrombosis or to fill an aneurysm.’ Additionally, Sakar, Assistant Professor Institute of Mechanical Engineering at EPFL, said: ‘Our robots have a special composi- the in new fabrication technologies,’ he pointed out adding that, in terms of healthcare, particularly in respect of targeted drug delivery, ‘They are able to swim through tortuous blood vessels to deliver drugs, for example Z H T E / L F P E 9 1 0 2 © which can change their shape to escape physical traps. To control and manoeuvre them, we embed mag- netic particles in the materials and then externally generate magnetic fields to create forces on them to propel them through liquid.’ To create the robot devices, the team used stimuli-responsive hydro- gels made of N-Isopropylacrylamide and polyethylene glycol diacrylate with iron-oxide magnetic nanopar- ticles embedded within them. The magnetic nanoparticles allow them to be controlled via an electromag- netic field, though the microro- Z H T E / L F P E 9 1 0 2 © bots have been designed in such a way that they can also utilise the fluid flow to navigate on their own through cavities. In their findings the researchers suggest that the ‘development of microscopic artificial swimmers that can cross biological barriers, move through bodily fluids, and access remote pathological sites can revolu- tionise targeted therapies.’ Transformation inspired by nature Professor Nelson added: ‘In nature, there is a multitude of microorgan- isms that change shape as their envi- ronmental conditions change. We have been inspired by this basic principle in the development of our microrobots. ‘The key challenge for us was to develop the physics that describe the types of changes we were interested in, and then to integrate this with Z H T E / L F P E 9 1 0 2 © EH @ MEDICA No 2 2019

T U E S D AY @ M E D I C A 5 The end of medicine as we know it The physician is no longer the lone master of diagnosis Physician, chemist and pharmacist Professor Harald Schmidt chairs the Department of Pharmacology and Personalised Medicine, at the Faculty for Health, Medicine and Life Sciences, University of Maastricht. As advanced investigator of the European Research Council (ERC) he also leads various research programmes, among them a Proof-of-Concept study on strokes; the COST Action OpenMultiMed on system medicine and the Horizon 2020 programme REPO-TRIAL. Schmidt was co-founder and managing director of Vasopharm GmbH, is co-publisher of the journal Systems Medicine and has written more than 200 refereed international publications, summary articles and books. lone master of diagnosis – he cannot be that any more. The networked data analysis necessary to analyse big data will be possible everywhere. Nonetheless there will still be precise ad hoc diagnoses and manual thera- pies, such as the surgical specialties. However, there will be big changes in the field of chronic illnesses.’ AI will not make a therapy decision ‘Currently, the most common cause of death is physician’s error – we already have the problem. The com- puter does not administer therapy; AI proposes a diagnosis with a probabil- ity of x and the therapy appropriate to it. The decision as to which way to go is reserved for the medical team, the patients and their priorities.’ treats a patient based on his personal current knowledge are now already over. ‘A research phase will precede these changes. But, it’s clear to see that such a medicine will lead to sig- nificantly more interdisciplinary hos- pital structures. Thus, the first clinics have already introduced immune dis- ease boards. In these boards, illnesses such as psoriasis, asthma, colitis or rheumatoid arthritis are treated by a team, working like the familiar tumour boards for oncological issues. Even experts agree that these disease designations are obsolete. These are essentially immune system diseases that have to be defined molecu- larly and not by clinical morphological means. ‘We also have to bid farewell to classical pathology, currently exhaust- ed by histology and the detailed description of cell changes. More than anything we need a molecular pathology that leads to molecular dis- ease definitions and thus permits pre- cise diagnosis and therapy. To attain this, we have to work more in terms of systems and more holistically. ‘Once we have penetrated deeply enough to identify the disease mech- anisms, then we can apply a precisely suited medication – possibly one that has already been approved. ‘In the not too distant future there will be at least one appropriate medi- cation for all the disease mechanisms so defined, the number of which will be between 160 and 200. Thus, a research and development phar- maceutical industry is obsolete; only manufacturers and distributors will still be needed. Only those pharma- ceutical enterprises that heal rather than treat will survive. ‘The first steps have been taken in this direction. In 2018, the USA’s FDA approved tumour medications that are no longer approved to treat an organ tumour – but for an oncologi- cal mechanism, which means they are approved for the specific mechanism, regardless of where the tumour is found. That is a small turning point for medication therapy.’ The AI or big data impact on health systems ‘Despite necessary changes, initially, the treatment cycle will naturally stay the same: as a rule the patient with organ-based symptoms will look for a physician, only his diagnosis will be strongly supported by artificial intelligence. Perhaps AI will propose to the physician additional measure- ment parameters, digital imaging or genetic examinations and thus deter- mine a molecular illness diagnosis. Then just like today it will be the task of the medical team to support the patient in choosing the optimum therapy for him. ‘The physician is no longer the Currently, many researchers and experts assume that the next great socio-economic revolution will include a completely new definition of health and how we define ill- nesses and therapies. According to Professor Harald Schmidt, head of the Department of Pharmacology and Personalised Medicine, Faculty for Health, Medicine and Life Sciences at the University of Maastricht, ‘Our health system today can no longer be sustained in its existing form. It has become too expensive and too ineffective.’ The end of medicine, as we know it? Asked for a fuller explanation of his prediction, he pointed to a fun- damental problem. ‘Our definition of illness is based on organ localisation or individual symptoms. All medicine, as we teach it, in the way we train specialists, the way our clinics are structured, is divided according to organs. There is a specialist physician and clinic for every organ. ‘However, illnesses do not function that way, rather we experience dis- ruptions in the signal systems in our cells – put more precisely, in certain hotspots that are disturbed and cause symptoms. In most cases these signal disruptions occur in more than one organ and produce different symp- toms. Thanks to the organ-based divi- sion, we do not see that though. And thus there are hardly any systematic or holistic approaches to medicine. ‘The pharmaceutical industry is also contributing to the end of medi- cine as we know it, doomed in its current form. In the list of the world’s ten largest companies there is not a single pharmaceutical company any more. That is somehow logical because why should we be forever discovering new medicines? ‘One reason why, after 100 years of pharmaceutical industry, we are still researching for new medicines is the lack of precise illness definitions and the chronic treatment of symp- toms instead of healing. To date, we know the molecular causes of very few illnesses and therefore cannot treat them.’ Medical education must change ‘Medical education will have to change along with hospital struc- tures. Physicians will have to work in interdisciplinary teams more often, together with bioinformatics special- ists and system physicians. Actually the days when the medical specialist EH @ MEDICA No 2 2019

T U E S D AY @ M E D I C A 7 See the GrossPath GP-1500 live in action! More safety for blood banks is permanently Laboratory staff exposed to harmful formalin vapors. The GrossPath GP-1500 reduces this risk to a bare minimum as contami- nated air is being extracted immedi- ately downward and also backwards. Additionally, the tissue grossing sta- tion complies with MAC (maximum allowable concentration) values for formalin. Convince yourself of the advantages of a GrossPath The No. 1 solution for eco-friendly tissue grossing stations is coming to Düsseldorf. Visit our booth and let us convince you of all the advantages that our GrossPath has to offer. The special worktable designed to ensure a pollution-free, laboratory- grade working environment for slicing and preparing histological slide prep- arations. Its compact design makes the GrossPath Special Worktable the perfect laboratory equipment, espe- cially for small facilities. As a product of our ECO-line, this worktable was designed with a special view to con- serving energy and resources while delivering outstanding air extraction results. Buy it, set it up and power it on: thanks to its active-carbon air recirculation system, the GrossPath is ready for immediate use – no need for installing a costly, separate air ventilation system! As a result, a customer-supplied ventilation is not necessary, which can reduce invest- ment and even overheads by up to 30 %. A permanganate carbon filter intercepts and efficiently purifies contaminated air and directs the clean air back to the labora- tory. Thanks to the down-draft and additional backdraft system, formalin con- c e n t r a t i o n even will be signifi- cantly below the MAC value throughout the entire extraction zone. Additionally, the GrossPath has a soundproofed exhaust fan that substantially keeps the noise level to KUGEL medical is at Medica Hall 13 / Stand E09 a minimum. Thanks to its large per- manganate carbon filter, the table can be in use for up to 800 working hours* * operating time varies between 600 and 800 working hours Hettich provides transparency and traceability Hettich is at Medica Hall 3 / Stand B69 Ensuring the quality of blood dona- tions is vital. Data collected dur- ing the various processes involved must be fully traceable and docu- mented, the company Andreas Hettich GmbH emphasises. Based in Tuttlingen, Germany, the com- pany has produced laboratory equip- ment for 115 years, today focusing on centrifuges and incubators and employing 420 people worldwide. Its new HettInfo II documents all steps before and during centrifuga- tion. ‘The touch display guides the user step-by-step through the process, from scanning the blood bags to centrifu- gation,’ Hettich reports. ‘The blood bag ID, operator and program are entered using a barcode scanner. The running parameters are recorded in the background during centrifuga- tion and can later be exported as a CSV file to a USB stick or, alternatively, directly to the network. The export can take place cyclically after each run or time-controlled.’ Trailblazers in medical solutions Taiwanese excellence on display at Medica From Augmented Reality to Robotics, and all exciting technol- ogies in between, the Taiwanese companies present at Medica always manage to impress visitors with health tech innovations. In co-opera- tion with the Bureau of Foreign Trade (BOFT) of the Taiwanese Ministry of Economics and the Taiwan External Trade Development Council (TAITRA), 20 elite healthcare companies put on display their achievements in Artificial Intelligence (AI), Virtual Reality (VR), 5G and more. Growing economic importance At Medica, Taiwanese companies showcase their focus on innovative manufacturing and in-house ICT, which have increased the efficiency and quality of production. Today, Taiwan has become the market lead- er with its concept of ‘Asian Silicon Valley’. The government wants to further strengthen this key position by independently developing medi- EH @ MEDICA No 2 2019 cal products that meet the high demands of international markets at attractive terms. The future of healthcare relies on Big Data and its collection, transmis- sion and evaluation. The develop- ment and implementation of 5G net- works now enables the immediate transfer of large image and monitor- Intelligence AmCad BioMed Artificial innovation expertise company with professional clinical experience, AmCad BioMed has created an ultrasound-based obstructive sleep apnea (OSA) detec- tion system, AmCAD®-UO. According to a recent survey, around one billion people in the Taitra is at Medica Taiwan Pavilion Hall 17 / A40 ing data sets to specialists at remote locations. This reduces the amount of travel required for patient care. The AI supports the time-consum- ing and expensive data evaluation that is becoming increasingly impor- tant in the diagnostic process. The enormous potential of AR/VR offers advantages in the training of medical staff, the performance of complicat- ed operations and the treatment of mental disorders. Robotics has also made the jump into the realm of healthcare and is now used for the benefit of patients and care- givers. Medica visi- tors will have the opportunity to meet – among others – the following innovative Taiwanese manu- facturers and their products: world suffer from OSA, 80% of them remain undiagnosed. The most com- mon method of diagnosis is a poly- somnography (PSG), which requires an overnight stay at a sleep center. However, the limited availability of sleep tests may lead to long waiting times. While PSG helps diagnosing sleep disorders through physiological index overnight, AmCAD-UO provides effi- cient anatomical OSA detection for patients within 10 minutes – with- out the need for the patient to be asleep. With laser-guided position- ing, the device precisely scans the upper airway and analyzes the dif- ference between normal breathing and Müller’s Maneuver (mimicking snoring model). AmCAD-UO system standardizes ultrasound transducer scanning to make the assessment more consistent and avoid highly operator-dependent variations. The president further pointed out that “through our patented laser- guided system, intra-observer vari- ability is largely reduced.” iHelper ChiliGO AI Robot Kiosk and iCart from manufacturer iHelper offer many advantages and more useful features than other mobile kiosk robots. With its pleasant robot design and intuitive user-friendly interface, users of the ChiliGO will have a faster and more satisfying experience get- ting the information they need, while the iCart handling robot can be used in hospitals or all other fields where items need to be transported. The ChiliGO uses facial recogni- tion technology to analyze user infor- mation like gender and age, which can be used to enhance a company’s marketing based on key consumer demographics. It also features AI voice interaction. iCart operates independent of tracks, instead using opti- cal radar (LiDar) and ultra- sonic sensors with AI self- optimized path correction technology to achieve automatic navigation and smart obstacle avoidance, to iHelper ChiliGO has a faster and more satisfying experience getting the information they need, while the iCart handling robot can be used in hospitals or all other fields where items need to be transported. quickly complete equipment delivery tasks. IEI Industrial computer provider IEI Integration Corp., presents its solu- tions for AI in healthcare at Medica. These include a global platform for health management and real-time medical data collection to offer a flexible way and enhance work effi- ciency for daily hospital routine. This year at Medica, IEI will show- case its latest AI ready hardware – a POCm Series Panel PC with hot-swapped batteries, a box PC solution for endoscopy and AI an all- in-one terminal. Further new prod- ucts include solutions for big data management, AI training (machine learning and accelerator cards) and AI decision support. Conclusion Take advantage of this unique setting during the upcoming Medica to feel the pulse of these leaps forward in 5G, AI, VR/AR and robotics. Medica is a premier opportunity for Taiwanese companies to develop relationships throughout the year. Staff and rep- resentatives of these innova- tive companies wel- come the chance to engage, exchange and demonstrate their advances in hall 17, stand A40. For more information, please visit: https://www. taiwanexcel- lence.org/de

9 l / s d a o p u / p p a / g r o . r s e y m . i a / / : s p t t h : e c r u o S g n p . e i p o K - y b o T - h s l a W World-renowned artificial intelligence professor at the University of South Wales and Data61, Toby Walsh was named by the media as a ‘rock star’ of the digital revolution and has been included on a list of the 100 most important digital innovators in Australia. He is the author of the books ‘IT’s Alive’, ‘Android Dreams’ and the soon to be published release ‘Machines That Think’ and ‘2062: The World that AI Made’. The professor is a sought-after keynote speaker on how AI influences business, education, warfare, personal development, and finance, and more. Together with Pope Francis, he was voted runner up in the Person of the Year Award by the Arms Control Association, recognising his work in ensuring the safe use of AI in warfare. working for four years. That brought down the human performance. Actually, there was one experienced radiologist who did better than the machine,’ he said. People should read through stud- ies carefully, because obviously some authors might be looking for fund- ing. Caution should also prevail upon hearing provocative quotes, such as Geoffrey Hinton’s famous line about stopping radiologists’ training. ‘Geoffrey is extremely bright, but he is also famous for saying provocative things to get people’s attention. He also said that you couldn’t predict more than five years out. I agree. There is still some distance to go,’ Walsh concluded, ‘before you can get much faith and confidence in equalling humans.’ T U E S D AY @ M E D I C A to fold a towel. Easy things for us are often surprisingly hard for com- puters. What’s more, we have made almost no progress in artificial gener- al intelligence that matches humans in their full capabilities.’ Computers can do narrow tasks, but nothing approaches the human brain yet. Machines are not going to take over anytime soon. ‘We have 50, 100 or maybe 200 more years before it can match the human brain, if ever. So, we should not worry about it,’ he said. Instead, people should look into the exciting new opportunities and just learn about the field. This starts with differentiating between AI and machine learning. ‘People often mix up these terms. But there’s a lot more to your intelligence than learning.’ Other types of intelligence include, for instance, perception, speech and speech recognition, NLP, vision and reasoning. A lot of AI research focus- es on machine learning, but much more could be done in workflow, image optimisation, etc. All these fields are interesting to explore for medical imaging. Provocation for attention The rule of thumb is that AI can now do most things a radiologist can do in a moment’s thought. ‘You can see an image and recognise it. The com- puter has been trained to do this. It can now also label images – i.e. a man dances dressed in black; a girl plays the violin, etc. – and that works pretty well. So, we can also start labelling X-rays,’ he explained. In 2017, AI researcher Andrew Y Ng, from Stanford University, claimed he and his team had developed an algorithm that could diagnose pneu- monia at a level exceeding practic- ing radiologists. Such claims need to be taken with precaution, Walsh insisted, because studies may show some limitations. ‘In this case researchers trained on 6,351 images and reported results on 420, but they only used frontal imag- es and no patient history. Although the machine was more accurate on average than four human radiolo- gists, one of them had only been AI? We shouldn’t worry about it – yet Will machines be taking over? No – at least not in the foreseeable future, according to AI expert Toby Walsh. While certain algorithms today come close to, or even surpass, humans in narrowly defined tasks, it should be another 50, 100, maybe even 200 years before artificial intelligence will match the complexity of the human brain. in 2010, one in 10 objects were clas- sified properly. Since then, perfor- mance has been doubled every two years, and now it recognises objects better than the average human does. Last but not least, investment has doubled every two years over the past decade, allowing skyrocketing advances in AI. The impact on radiology AI started to make headlines in 2015, when humans lost against machines in a Go competition. Nonetheless, and despite all the progress made, it is remarkable how slowly the machine learns compared to humans, even with unlimited resources of time, Walsh underlined. ‘There are still many things that machines can’t do as well as humans, some of which are plain trivial. A robot developed by a colleague at Berkley University takes 25 minutes Humanity is not doomed to submit to machines as in the Terminator movies – or at least not yet. Artificial intelligence (AI) systems are still far from capable to imitate the human brain in all its complexity. Yet there is no doubt that AI will have a global and huge impact, particularly for professionals such as radiologists, who should look at AI critically and focus on the many new opportunities that will arise, advises Australian AI expert Professor Toby Walsh. Report: Mélisande Rouger ‘People have woken up to the idea that AI is going to be interesting and transformative because it will impact on every aspect of our lives,’ explained Toby Walsh, a profes- sor of AI at the University of New South Wales, speaking at the AI Premium meeting organised by the European Society of Radiology and the European School of Radiology in Barcelona. AI will have a major impact on global economy, according to audit giant PwC, which predicted it could generate 15.7 trillion USD and account for 26.1% of GDP in China, 14.5% in North America and 10% in Europe by 2030. ‘That’s an inflation just in terms,’ said Walsh, who is dubbed ‘the rock star of the digital revolution’ and has published many books on the topic. ‘16 trillion USD is China and India’s GDP put together. It’s like we’ve dis- covered a whole new continent. Last time that happened, it had big rami- fications for the world’s economy.’ Walsh’s last work, ‘2062: The World that AI made’, is an optimistic vision of how to help mankind benefit from AI, rather than helplessly suffer the consequences ‘Every profession and particularly data intensive professions, such as radiology, will be affected,’ he said. Four exponentials Walsh shared a brief history of AI, which was boosted by four exponen- tials, including Moore’s law, accord- ing to which the number of tran- sistors in computers double almost every two years. This observation has accurately guided projection rates and technological developments for the past 50 years, all of which have led to immense computing power. ‘Things that we dreamed about doing, we just do now because we have more computing power. We have more computing power in our smartphones than was once used to fly a man to the moon,’ he observed. Moore’s law is now officially dead and scientists need to design new architecture to increase computing power. One trend is to design speci- fied chips to do AI and do more on the device energy, he says. Along the doubling of transistors count, there has been a doubling in data. ‘We’re collecting more and more data, and have the ability to store more and more data. This con- tinues to help expand AI,’ Walsh pointed out. The third exponential was a dou- bling in performance of algorithms to recognise objects and limits. Back EH @ MEDICA No 2 2019

T U E S D AY @ M E D I C A 1 1 Lithuanian chemist advances cell research Crafting new molecular tools Recently, chemist Aurimas Vyšniauskas a 31-year-old Oxford and Imperial College London graduate, was featured in the European journal Chemistry because he and his research team have changed the structure of viscosity sensors and enhanced their viscosity-sensitivity range by a very significant margin. Put simply, viscosity sensors are small molecules used to measure surrounding viscosity; they are used as tools to study events inside a liv- ing cell. Various diseases, such as Alzheimer’s and diabetes, cause vis- cosity changes in cells. With sensors of improved sensitivity, it will be possible to improve determination of what adverse effects arrive with changed cell viscosity. ‘I call myself a craftsman of tools – molecular kind of tools,’ Vyšniauskas explains. ‘Personally, I will not cure Alzheimer’s, nor diabetes; but, if I’m successful, I will finally manage to create a tool that would help other scientists to treat these and other incurable diseases, popularly called civilizational epidemics.’ In early-stage diabetes, the viscos- ity of the membrane of liver cells increases. The receptors of insulin in the membrane of these cells con- tinually deliver signals and connect with one another, but the increase in viscosity leads to poor connections, g n i r p s t h g i L / k c o t s r e t t u h S © the regular cell activity is disrupted, and the cells are no longer able to recognise insulin. ‘Up to this point, the most popu- lar viscosity sensor could measure cell viscosity from five to 1,500 vis- cosity units of measurement, or cP,’ Vyšniauskas adds. ‘We managed to increase this – our method can measure viscosity in the range of 0.5 to 50,000 cP. That’s a big accom- plishment. Imagine a thermometer that could only measure tempera- ture from 10 to 20 degrees Celsius. work. I also cooperate with other chemists, particularly those who syn- thesise molecules. Biologists are also involved, because the implementa- tion of our research would be in their field, biology. The collaborative process is fascinating.’ The decision to head home after gaining his doctorate in the UK was pretty straightforward, he explains. ‘A couple of reasons were at play when deciding where to continue my career after the studies. For one, the Department of Molecular Compound Physics, where I now work, employs several excellent sci- entists who produce international- level results. Being a young scientist, it is a privilege to work hand in hand with these experienced researchers. Also, it’s a more stable environment for a scientist here than in the UK. Extremely high competition in the UK science community causes unneces- sary stress, while here, I can focus on my research and feel valued. Finally, we have state-of-the-art facilities and favourable all-round conditions.’ The scientific achievement of Vyšniauskas and colleagues is not an isolated case of success for Vilnius- based scientists. Just this year, Vilnius physicists have developed a laser that possibly could solve the nuclear waste problem, while other scientists from the Centre for Physical Sciences and Technology, the same institution in which Vyšniauskas works, have developed a cheaper and faster DNA testing method. i o d u t S a m i x o r P / k c o t s r e t t u h S © Metaphorically speaking, we have created a new thermometer with a measurement range from -10 to 60 degrees Celsius.’ Currently, viscosity sensors are only used by scientists who study them, but this scientist has no doubt: once this method develops to become a reliable tool, it will be used by bio- chemists and cell biologists alike. This breakthrough in viscosity measurement resulted from a collab- oration between many scientists from the Centre for Physical Sciences and Technology and Vilnius University, in Lithuania, where Vyšniauskas now works. ‘Since physical chemistry is an interdisciplinary field, we needed knowledge from various scientific fields to make this achievement pos- sible,’ he points out. ‘As a chemist, I need to consult with theoretical physicists who are specialists in theo- retical calculations, which are cru- cial to explain how viscosity sensors Imaging robot for spinal surgery Brainlab recently unveiled its flagship Loop-X mobile intraoperative imaging robot that is specifically designed for spinal surgical procedures. Developed by medPhoton, an Austrian company, the device is now the core of Brainlab’s the outer edge of the scanner. The highly integrated device is designed for 2D and 3D imaging, com- bining ultra-high resolution with extra- low doses, and proprietary technology to image with interlaced energies for soft-tissue visualization. Loop-X imaging robot can be inte- grated with Brainlab technology as well as third party products through an open interface, maximizing inter- operability and data integration. “For Brainlab, Loop-X is a critical milestone in contributing disruptive innovations in spinal surgery,” said Stefan Vilsmeier, President and Chief Executive Officer, Brainlab. “It provides us with an even stronger foundation for leveraging emerging technologies such as AI, big data, cloud computing, augmented reality and spatial computing.” Loop-X-positioning imaging offerings. The Loop-X robotic architecture intro- duces a new standard in flexibility, add- ing additional degrees of freedom to any surgical procedure: By automating imaging workflow steps and roboti- cally moving with the procedure and on command, the system is in sync with other devices like robotic arms and with the surgeon and staff. One interesting feature of the Loop-X is the non-isocentric move- ment of the X-ray source and detector. Unlike in other CT imagers, the two are not always directly across from each other, and the X-ray beam turns to always point toward the detector. This allows the device to better target the specific anatomy of interest while minimizing the delivered radiation dose. Additionally, the capability can be used to better view anatomy at a larger scale by widely sweeping the beam closer to EH @ MEDICA No 2 2019