A new £21 million fund for AI was announced by the UK government in June, with the intention of providing NHS trusts with at least some of the tools needed to deliver faster, more accurate diagnoses for patients.

The urgency to get these tools in place, means that many NHS trusts and imaging networks will now be engaged in developing bids, ahead of what is a tight September deadline.

But what will those bids contain, and how can successful organisations start to make the most of funds? Here are five things some of those organisations bidding for funding might consider: 

1. Have you identified the problem you need to solve?

With a significant focus expected on tools to help radiology teams as they report on many thousands of chest x-rays, NHS organisations do have the option to apply for funding for almost any AI application that supports diagnostics. But they also need to demonstrate value for money and a return on investment to be successful.

Doing that starts with defining the problem that needs to be addressed. If healthcare professionals are not clear what an AI tool is trying to solve, it is unlikely to demonstrate improvements.

Clear goals need to be established that might mean improving patient outcomes or clinical efficiency, and that will also ideally have a monetary value associated.

For example, that might mean clearing a backlog of chest x-rays, reducing workloads for diagnostic teams under pressure, increasing the number of cases a radiologist is able to review, or improving turnaround times to support early diagnosis in particular areas. 

2. How will you measure that?

To demonstrate value for money there needs to be something to measure before and after – particularly in relation to the problem you are trying to solve.

Many algorithms will have compelling case studies. But you need to know if it works in your clinical environment, and for your population.

Every patient population is unique and there have been examples of AI working well in some places, whilst failing to work effectively for other patient cohorts or demographics.

Most organisations would choose a period of clinical validation. They might start with a retrospective study, and run it for a time period in test scenarios, whilst also creating milestones and KPIs to check and evaluate performance. If it works well, you can demonstrate the value to your organisation and others, and potentially scale deployment. If it doesn’t you might need to adjust your approach or try something new. 

3. Can trusted evidence help to cut through the noise?

There is a rapidly growing number of AI vendors out there. New algorithms for healthcare seem to emerge almost every week.

Any opportunities that can help your organisation to get a head start on what is likely to work, could help to deliver effective tools into clinical practice sooner.

This can mean more than glancing at small scale case studies.

Strong peer-reviewed evidence of the efficacy of AI driven approaches to diagnostics, in some cases backed by substantial samples, is now being published.

One of our customers in Sweden recently made international headlines for a detailed research study involving more than 80,000 women, that showed significant potential for AI in helping to reduce workload for breast radiologists by as much as 44%.

Such peer reviewed studies are not likely to replace the need for local validation, but they can help to narrow the field from a large choice of proven and unproven tools.

4. What can you do to leverage regional resources?

The government’s funding announcement focussed on trusts deploying AI tools. But that doesn’t mean those trusts need to work in isolation.

Imaging networks and regional consortia are continuing to mature in the NHS, and several of those regions we work with are electing to utilise their resources collaboratively.

For example, this could mean one trust out of five or six within a consortium, trialling an AI to detect lung cancers on chest x-rays, and sharing learnings with its partner trusts. Other trusts in the network might choose to trial other AI applications that perform a similar task, cutting down the time it takes to find the best tool for the job. Or they might trial AI applications in different areas and share what they learn. 

5. Could your suppliers do some of the hard work for you?

NHS organisations will ultimately be responsible for investing the time needed to determine which AI tools are clinically effective for their patients.

But a lot of time and energy could be saved in other areas. Many trusts for example lack the resource to manage commercial relationships with multiple suppliers. They might also not have enough bandwidth to manage the technical, data, integration and infrastructure complexities that can come with individual AI procurements.

The answer for many is to allow core system suppliers to carry some of this burden for them. In the case of imaging, trusts might wish to examine if their picture archiving and communication system (PACS) vendor can help to accelerate the deployment of AI, without the need for new contracts with additional suppliers.

Customers in the NHS using our Amplifier Service, for example, have told us that this approach has provided an ability to introduce AI easily and seamlessly into the radiology workflow, whist saving months of time and effort on IT and infrastructure work.

The post NHS AI Diagnostic Funding Five Things to Consider if you are Applying appeared first on .

AI is well-established in some sectors of the health care industry as well. Pharmaceutical researchers are using it to discover new drugs with greater speed and efficiency than before. Hospital systems are using it to study their patients’ journey from the point of admission to the point of release, with the goal of making the process more efficient and satisfying.

But one of the most important health care specialties of all – cardiology – is just beginning to recognize the benefits that AI can bring to its field. As we know, heart disease is the leading cause of death in the United States. By 2035, more than 130 million adults, or 45% of the U.S. population, are projected to have some form of cardiovascular diseases (CVD). In 2035 total costs of CVD are expected to reach $1.1 trillion. Direct medical costs are projected to reach $748.7 billion. Indirect costs are estimated to reach $368 billion.

Cardiology has adopted various imaging technologies over recent decades, and the use of imaging technologies is linked to improved patient outcomes. But the millions of images being captured every day are still being analyzed manually, placing heavier and heavier workloads on clinicians, increasing the risk of diagnostic errors, disagreements among experts, and eventual human burnout. Cardiologists at the top of their profession agree that they need more ways to provide better care and improve outcomes. It is time to recognize the emergence of additional technologies like AI and move this vital medical field even more forward.

By combining cardiac imaging analysis with artificial intelligence, we can tap the insights of multiple experts, improve the quality of analysis, shorten the time spent waiting for diagnoses, and lower costs in our health care system. AI will not replace humans, of course, but it can provide an immediately available second opinion and help researchers and clinicians make even better decisions. AI is a consistent, quantifiable, readily available tool that will better equip us in the lifesaving work of cardiology.

Let’s look at how this could work

Researchers seeking to improve the use of stents in opening clogged coronary arteries can look at a series of images collected through Intravascular Optical Coherence Tomography, or IVOCT, and input their analysis into AI-enabled software. The more images they analyze, the more they can teach the software what to look for when stents fail to expand properly, when they fail to completely cover diseased segments of an artery, or when dissections at the stents’ edges go untreated. Armed with this hard data, the researchers can recommend ways to improve products, procedures, or both.

Or imagine a clinician performing an echocardiogram on a patient and seeing a potential problem with the patient’s ejection fraction (EF), a measure of the volume of blood the heart is pushing into the body. It would take hours for the clinician to manually trace the hundreds of image frames needed to accurately quantify the patient’s EF, evaluate the heart strain, and make a diagnosis. Instead, clinicians today quickly “eyeball” the images, leaving a diagnosis dependent on the physician’s experience, alertness, and access to second opinions. AI-enabled software, having learned from the insights of many experts diagnosing many similar cases, can automatically interpret the images, save the clinicians precious time, and give them and their patients added confidence in the diagnosis and course of treatment.

Artificial Intelligence and Cardiac Imaging

These types of AI advances in cardiology are not far off in the distant future.

Dyad Medical Inc., a Boston-based medical technology startup, has developed the Libby  software platform to use artificial intelligence to help interpret three- and four-dimensional medical images in intravascular OCT and additional other primary modalities for cardiac imaging.  A global community of clinicians have shared their expertise to train Dyad’s artificial-intelligence model, effectively offering thousands of second opinions. The U.S. Food and Drug Administration recently cleared Dyad’s Libby platform for viewing and quantifying intravascular OCT images. The FDA clearance is an important milestone that will give researchers, imaging centers and hospital systems another tool to automate their ability to see inside blood vessels.

In training its artificial intelligence software to help interpret cardiac images, Dyad also has accumulated what it believes is the largest repository of cardiac imaging data held by a private company, allowing its software to learn from the insights of many experts analyzing this large trove of data.

Other advantages of the Libby platform include that it is cloud-based, so users can access results from anywhere, at any time of day or night, and on any device. The platform also integrates into a hospital’s existing information technology, so any new applications can be added easily to the platform and the existing systems and workflows.

FDA clearance in hand, a leading research hospital will soon begin using the platform to research ways to improve clinical conclusions based on intravascular OCT. By the end of 2022, we expect to see the platform and the intravascular modality in use in hospital settings. We cannot predict when the FDA will act on the use of Libby for other modalities, but the company is currently submitting for FDA clearance the platforms for multiple future modality support.

In the ideal future, every practitioner around the world will consult Dyad technology every time they interpret any medical images. This will continue to train Dyad’s AI-enabled software to become an even more accurate, more efficient, and more valuable tool for everyone involved in the diagnosis of heart disease globally.

About the author

Ronny Shalev holds a Ph.D. in electrical engineering and computer science from Case Western Reserve University and is CEO and founder of Dyad Medical Inc.

The post It’s Time to Combine Artificial Intelligence with Cardiac Imaging appeared first on .

POCUS provides patients the opportunity to see their images with their clinicians, helping them to understand their diagnosis, which can lead to greater engagement and compliance. From a healthcare provider’s perspective, the technology offers a way to reduce costs, avoid the need to move a patient across the facility and bring a more collaborative approach to patient care.

However, to truly fulfil its potential, the POCUS solution must offer not only medical functionality and accuracy but also fit seamlessly into the healthcare provider’s wider Imaging IT systems or Picture Archiving and Communications System (PACS). It is only then that healthcare professionals can acquire the complete and accurate medical imaging record they need to ensure quality of outcome and care for each patient.

Healthcare professionals can improve their ultrasound skills by taking POCUS certification from Zedu Ultrasound Training Academy or other reputable training centers. 

POCUS certification courses provide comprehensive training in various ultrasound applications, including abdominal, vascular, musculoskeletal, cardiac, and obstetric/gynecologic. These programs enhance your knowledge of ultrasound principles, techniques, and interpretation skills, granting you credentials for higher levels of work while providing the latest insights in the field.

Overcoming metadata issues

Unfortunately, not all POCUS technology can do what’s described above. Some, for example, don’t possess the worklist features that are typically common to larger departments, for example, radiology. This means that images captured on POCUS devices cannot be easily or automatically incorporated into core enterprise systems, such as the electronic medical record (EMR) or PACS. While PACSs, for instance, may be good at managing the flow of DICOM images within departments, it’s much less effective when it comes to assimilating non-DICOM assets.

Any attempt to migrate data manually between systems is time-consuming and likely to lead to errors in transcription, with the consequent inclusion of ‘rough data’ into a patient’s records.

However, this kind of functionality gap can be removed if the POCUS platform has the capability to automatically resolve issues relating to incomplete or incorrect metadata, for example involving order or accession numbers, then index and forward the revised studies to the appropriate destination. Automating the indexing of POCUS images, which often lack a formal radiology order, allows them to be indexed to the patient record in the EMR.

Avoiding clinical blind spots

Having the capacity to do this is a much better solution than being forced to create multiple PACS or siloed imaging systems for different specialities, which fails to address the longer-term issue of greater accessibility and interoperability.

When separate imaging systems develop across an organisation, this inevitably leads to the ‘siloing’ of data and disparate image archives, which then limits access to these clinically relevant images and may lead to information being omitted from the bigger diagnostic or clinical picture. It’s not unusual, for instance, for organisations to find that important clinical imaging material is scattered across any number of locations, applications and solutions. These comprise of a myriad of PACS, CDs, non-networked hard drives and other removable storage.

This is a particular problem in proprietary, vendor-controlled environments, which is why it is important to seek out a vendor-neutral platform that allows you to integrate POCUS content with enterprise systems.

To avoid the creation of potential clinical blind spots Hyland’s POCUS solution uses industry-standard protocols, API’s and formats, to ensure that POCUS studies can be captured and managed across an enterprise, alongside images from DICOM modalities, e.g. Radiology, Cardiology as well as visible light image and videos from specialities such as, gastroenterology, dermatology, wound care, and all other departments.

Recognising the viewer preferences of different departments, such as radiology and cardiology, ensures there is no disruption to a healthcare organisation’s existing approach to referential or interpretive viewing. So once POCUS studies are stored in Hyland’s Acuo VNA, they can be made available enterprise-wide through the web-based NilRead enterprise, diagnostic viewer, allowing images from any modality to be accessed and referenced by clinicians on any personal computer or mobile device.

This allows clinicians to retain autonomy over access to an image and its manipulation and sharing, while contributing to cross-disciplinary, patient-centred care.

Scale and flexibility

The use of point-of-care imaging is only going to increase as technology evolves and clinicians become more confident using it. As it is, POCUS images already make up a significant portion of clinically relevant data that needs to be incorporated into wider systems.

So, it’s critical that healthcare organisations recognise the importance of having a common enterprise-wide imaging framework that can be easily expanded and reshaped to changing needs. That requires a degree of interoperability that can’t be achieved without an open, standards based, vendor neutral archive system.

As we’ve seen, there’s an opportunity to do this if a solution is chosen with collaboration among key stakeholders in mind. That way POCUS can make a significant contribution to the enterprise-wide imaging picture that aims to improve patient outcomes, which after all is the whole point of caring.

Article by Saduf Ali-Drakesmith is director, Global Strategy, Enterprise Imaging at Hyland. www.hyland.com

The post Make time to Focus on POCUS appeared first on .

Leeds Teaching Hospitals went live with the Sectra picture archiving and communication system (PACS) in October – allowing pathology images to be interrogated by professionals electronically from a range of devices.

With many pathology departments across the country still reliant on microscopes and glass slides, the new system is allowing pathologists to work more quickly, gain easier access to opinions from colleagues and manage rising demand.

Bigger benefits are expected as more hospitals in the NPIC co-operative go live with the system later in the year and into 2021. The programme is part of a £17m partnership between industry, the NHS and academia and funded by UK Research and Innovation and industry partners to connect pathology services across the region using technology. This will lead to the full digitisation of NHS laboratories covering a population of three million people, allowing hospitals to pool resources, balance workload, and enable easier access to specialists across the region whose expertise may be quickly needed to make a clinical diagnosis.

Trusts to follow Leeds will include Bradford Teaching Hospitals NHS Foundation Trust, Harrogate and District NHS Foundation Trust, Calderdale and Huddersfield NHS Foundation Trust, The Mid Yorkshire Hospitals NHS Trust, and Airedale NHS Foundation Trust.

Dr Darren Treanor, NPIC’s director, and a practising pathologist at Leeds Teaching Hospitals NHS Trust, said: “Leeds is the first of our six sites to go fully digital. Collectively, we are modernising our pathology services to become amongst the most advanced and interconnected anywhere in the world, and we hope to share our experience to help others across the NHS and beyond.

“The days of using glass slides and paper notes to determine and communicate a patient’s diagnosis are numbered. As we move to digital ways of working we can improve quality and create a more structured digital workflow.”

The project will also see the consortium deliver a Vendor Neutral Archive from Sectra. This will allow the trusts to pool imaging and build a platform for artificial intelligence crucial to improving diagnoses for cancers and other illnesses.

Jane Rendall, UK managing director for Sectra, one of the NPIC industry partners, said: “Digital pathology is about far more than replacing microscopes with computers. It’s about fundamentally changing how pathology services can be configured across regions and across the country, so that patients can receive faster diagnoses, services can become more intelligent, and the NHS can make best use of its valuable pathologists. NPIC is at the forefront of this transformation.”

The post Leeds Deploys Imaging Tech for Advanced Digital Pathology Network appeared first on .

A recent study found that obstetrics (OB) and gynecology (GYN) clinicians in the United States have some of the highest burnout rates among physicians, with the leading factor being bureaucratic tasks like paperwork, charting, and patient data capture. In today’s COVID-19 pandemic environment, these clinicians are now facing additional pressures to see more patients and perform exams quickly to limit possible patient exposure to the coronavirus.

To help combat these constraints and improve clinical outcomes, GE Healthcare gathered input from 200 women’s health practitioners worldwide to develop the all-new Voluson SWIFT that is designed to help make clinician’s daily work more manageable. New features allow users to customise the system to their personal preferences and the system comes with guided workflows to help new users learn the technology faster and use it more effectively.

“The Voluson SWIFT is intuitive to use and comes with many options to personalize your preferences on the system and auto-measurement tools that allow you to focus on the examination rather than time-consuming adjustments,” said Dr. Ralf Menkhaus, Gynecologist at Kinderwunschzentrum in Minden, Germany. “It’s like the machine is helping do some of the thinking for you which has allowed me to seamlessly integrate it for any obstetric and gynecological exams I need to do.”

The new ultrasound system features an embedded artificial intelligence platform, including the new SonoLyst application, the industry’s first fully integrated AI tool that recognises the 20 views recommended by the International Society of Ultrasound in Obstetrics and Gynecology mid-trimester practice guidelines for fetal imaging, optimising the scan workflow by 73 percent when compared to manual 2D workflow.

“Voluson SWIFT has redefined one of the most essential tools obstetrics and gynecology clinicians rely on, delivering a contemporary design, intuitive user interface, and intelligent workflow supported by AI,” said Roland Rott, General Manager of Women’s Health Ultrasound at GE Healthcare. “In today’s environment where cleanliness and time savings opportunities are critical for clinicians, we’re proud to offer a solution that makes our customers’ work easier and gives them time back with their patients.”

The post GE Healthcare Unveils AI-Enhanced Women’s Health Ultrasound appeared first on .

From ambulance or landing pad to scanner in minutes

Located just off the busy M6 motorway and treating patients who can be airlifted from as far away as North Wales, the Royal Stoke University Hospital deals with high volumes of patients every day.

The hospital, part of University Hospitals North Midlands NHS Trust, or UHNM, was recognised for having the best survival rates of any major trauma centre in the country in a 2017 independent report. Today, the role of the imaging department is key to continuing to get patients appropriate care quickly.

Within minutes of landing on the tarmac or leaving the ambulance, trauma patients can find themselves under a scanner that can capture detailed diagnostic images from head to toe in just seconds.

And as soon as a scan is complete, the trust’s radiologists and reporting radiographers are on the case, using a sophisticated picture archiving and communication system – or PACS – to interrogate the images and to inform a detailed diagnostic report that is fed to hospital clinicians in as little as 20 minutes, allowing appropriate clinical decisions to be made quickly.

Dr Suchi Gaba, a consultant musculoskeletal radiologist, says: “It’s a major trauma centre here. That is one of the reasons we are so busy. A great many patients who come to the hospital will have some radiological procedure, whether that’s an x-ray, MRI, or ultrasound, for example. Radiology is at the heart of the hospital and it makes a huge difference if you have good systems and good IT set up.”

The diagnostic backbone

It’s not just trauma patients that keep diagnostic professionals busy. In usual circumstances, the UHNM imaging department sees more than 9,500 patients – capturing and reporting on a wide range of medical imaging from simple x-rays to more complex CT and MRI scans.

“This makes us one of the busiest NHS imaging departments in England in terms of patient throughput and the volume of cutting-edge machines,” says Dr Marius Grima, consultant paediatric radiologist and clinical information officer for the children’s, women’s & diagnostics division. “But in terms of radiologists, our number is small compared to other places.”

The PACS, implemented by medical imaging provider Sectra in 2017, has been key in enabling radiologists to cope with a 10% year on year rise in demand.

“The PACS is the backbone of our department and we have been using it in innovative and extensive ways to help our patients.” says Dr Grima.

Notifying cancer patients more quickly

One of those innovative approaches has been to transform how quickly patients are notified if they do or do not have bowel cancer, by drawing on functionality in the PACS and transforming pathways.

Dr Ingrid Britton, consultant gastrointestinal radiologist, says: “We can now identify patients with colorectal cancer whilst they are still on the scanner. Previously the radiographer would perform the scan, and then place imaging in a queue to be reported by a radiologist, before the report would be sent onto a multi-disciplinary team.

“Now, when radiographers see something during the scan, they alert the imaging team immediately, and using a simultaneous viewing feature in our PACS, radiologists can immediately look at the imaging from their own location and report as the image is generated, before notifying the referring clinician the same day when a patient is positive.”

Patients are also being notified more quickly and discharged sooner when they don’t have bowel cancer.  Traditionally if a CTC scan, or virtual colonoscopy, doesn’t show signs of cancer, imaging joins a queue to be reported, before going through an administrative process that can take three to four weeks. A pilot programme at the trust has seen this reduced to 16 days, simply by the radiologist sending a letter from the multi-disciplinary team (MDT) to the patient when the radiologist can see from the image that the patient doesn’t have cancer – something not traditionally done.

Dr Britton explains the trust’s approach has resonated with the national Getting It Right First Time programme. And she believes it’s the fact that the technology “just works” that has given her and colleagues the capacity to stop worrying about IT and to focus on transforming the patient experience.

“If a patient knows straight away, they have faith in the service,” she says. “Getting this right from the beginning gives the patient confidence. This wouldn’t work with a system where the technology doesn’t load quickly enough.”

A big difference in breast care

Breast radiologists are equally as impressed. “The PACS has made an obviously huge difference in breast,” says Dr Seema Salehi-Bird, a consultant radiologist in imaging and breast care. “We can more easily look at every aspect of a mammogram systematically,” she adds. “Imaging is now just there. We can more easily annotate areas for colleagues to look at. And we no longer need to work across three specialist systems. All of this has made our work far more streamlined. We can more effectively present information to surgeons, allowing them to make important decisions, and in MDT meetings we can bring up relevant images at the click of a button.”

Improving data integrity and strategic innovation

Innovation with the PACS continues to pick up pace. Martin Dale, the University Hospitals North Midlands trust’s PACS manager, says that, since working with Sectra, the increased stability and functionality of the PACS has seen a significant reduction in firefighting that has freed up more time within his team to focus on strategic work. This includes moving more diagnostic specialities into the PACS, bringing in artificial intelligence and a more flexible approach to responding to clinical needs and service improvement strategies.

The team are now much better equipped to deal with routine problems like data errors and have even been able to commence a project in resolving legacy errors not easily visible in previous solutions. Since bringing in the Sectra, the team have been able to significantly enhance the data integrity of the system; eliminating duplication and reducing misfiled studies, with a big focus on a rapid response to errors and education of users (whilst cases are still fresh in their minds).

“We are adding more power to the solution,” he says. “We want to bring in tools that add value, where the radiologists no longer waste time with things like measurements, which are just done by the system.

“Radiologists come back from conferences with ideas about how we can move forward – and we can accommodate them. We used to have to say ‘no’, now we can say ‘yes’ which is not only better for the service, but has really improved what we take away from the role personally.”

Real partnership

Dr Grima says this willingness to do things extends to the trust’s relationship with the technology provider. “Sometimes a CT scan might supersede an x-ray,” he says. “We wanted something in the PACS that identifies when this happens, so that our reporters can report on what is actually going to add value to the patient’s care and save a lot of time.”

Within weeks of describing the idea to Sectra, the company started working on a solution. “Talking directly with the technical person helps,” adds Dr Grima. “If we identify an area that can be developed, they take it on board.”

Improving working lives and the next generation of radiologists

Implementing the PACS has improved working lives in many ways. Radiologists now have the ability to work from home, and they are connected across multiple sites through a single PACS.

Whether an image is captured at the hospital in Stoke, in the community, or at University Hospitals North Midlands’ County Hospital in Stafford, it can be quickly accessed and interrogated by professionals regardless of their location.

Chat functionality, which operates in a similar way to consumer instant messaging, is also allowing staff to access second opinions from colleagues who could be located miles away, very quickly.

Radiologists are also saving time in preparation for MDT meetings, adding in reports and images to lists within a few clicks.

Julia Astbury, a reporting radiographer who has seen a progression from working with film, through to a range of different PACS, says: “It’s easier to use than other systems. It’s easy to negotiate and access a history of images, and connects me to colleagues across different sites.”

The future generation of radiologists is also realising benefits. Dr Shaun Neal, a trainee radiologist, says: “If it wasn’t for the speed the of the system, we wouldn’t be able to keep up with demand. The chat function on Sectra is also fantastic. If you have any questions you can send a link to the image you are looking at to a consultant who can check it. This works really well for junior trainees.”

And staff are using the system to equip future radiologists through teaching. Dr Zafar Hashim, a consultant neuro-radiologist at the trust, says: “I’ve used several PACS and Sectra allows me to create teaching files and anonymise images very easily. We use Sectra workstations for our courses and I can build teaching files when I’m sitting at home. We no longer need to download images and place them on a separate computer for teaching. It’s now so easy.”

It’s not about the IT

Ingenuity demonstrated by healthcare professionals at University Hospitals of North Midlands is what technology in the NHS should be about. It’s not about IT. It’s about how people can use it to deliver better patient care, and a better patient experience.

The post Coping with Rising Demand: How Radiologists are Fighting Back with Tech appeared first on .

Region Västra Götaland, serving 1.6 million citizens, was the first region in Sweden to establish a coordinated effort for digital processes across its pathology units. This transformation has driven a need for solutions that can deliver speed, quality, and accuracy of diagnoses for pathologists, patients and healthcare organisations.

By understanding the value that digital pathology brings to the table, TietoEVRY and Hyland can combine and leverage their unique offerings into one Laboratory Information Management System (LIMS) to deliver services covering the fully digital diagnostic process.

PATOS is a solution delivered by TietoEVRY, integrating technology infrastructure, instrumentation and diagnostic analysis from a consortium of five partnering companies of which Hyland is one.

Hyland’s Acuo vendor neutral archive (VNA) and NilRead enterprise viewer are central components of the solution providing both storage and management of digital pathology images. Hyland’s solution will also contribute with functionality for the industry standard, DICOM, formatting the images that are produced by scanning the slides, ensuring the interoperability and full flexibility for the digital pathology solution in the future.

Hyland´s Acuo VNA can manage larger data sets at higher speeds than traditional archive systems, a must for pathology images that are several times larger than typical radiology studies. The vendor-neutrality of Acuo also allows pathology images to be stored and accessed alongside other types of imaging studies, providing added convenience and enhancing diagnosis.

“Hyland has been a good partner in this solution, and we are very happy to continue looking for ways to deepen our collaboration. With digital pathology, there is an ever-increasing need for improved image resolution and that is creating demands on storage capacity. Effectively storing a growing number of these images is a key challenge where TietoEVRY as a Nordic leader of infrastructure offerings can provide a cost-efficient storage solution for the digital images”, says Patric Nilson, Head of Healthcare Solutions and Specialist Products, TietoEVRY.

TietoEVRYs Lifecare Pathology LIMS supports a fully digital pathology process, both the laboratory process and the diagnostics, including possible integrations with viewers and image analysis.

“Digital pathology is an emerging area in medical imaging and TietoEVRY and Hyland Healthcare are at the forefront of delivering working solutions that address the modern healthcare landscape.” By helping pathologists accelerate analysis via digitisation, we’re helping them make quicker diagnoses and potentially save lives.  It’s rewarding when technology has a very real human impact”, says Mark Groesch, Director of EMEA Sales at Hyland Healthcare.

The post Hyland Healthcare and TietoEVRY Extend Partnership for Revolutionary Digital Pathology Solutions appeared first on .

Patients undergoing CT colonography scans are being quickly notified if they do or do not have bowel cancer, following the implementation of imaging technology that has given staff at University Hospitals of North Midlands NHS Trust the opportunity to redesign pathways.

The trust first went live with its picture archiving and communication system, or PACS, from Sectra in 2017– providing healthcare professionals with much faster access to imaging necessary for making important diagnoses.

Radiologists have found the imaging technology so reliable and easy to use, that it has freed up their time to get the most out of the system.

And this now means that referring clinicians are being consistently notified on the same day as the patient’s CTC scan, also known as a virtual colonoscopy, if their patients test positive for bowel cancer.

Dr Ingrid Britton, consultant gastrointestinal radiologist, at University Hospitals of North Midlands NHS Trust, said: “We can now identify patients with colorectal cancer whilst they are still on the scanner. Previously the radiographer would perform the scan, and then place imaging in a queue to be reported by a radiologist, before the report would be sent onto a multidisciplinary team.

“Now, when radiographers see something during the scan, they alert the imaging team immediately, and using a simultaneous viewing feature in our PACS, radiologists can immediately look at the imaging from their own location and report as the image is generated, before notifying the referring clinician the same day when a patient is positive.

“If a patient knows straight away, they have faith in the service. Getting this right from the beginning gives the patient confidence. This wouldn’t work with a system where the technology doesn’t load quickly enough.”

Patients who show no signs of bowel cancer are also being notified and discharged weeks sooner in a new pilot project at the trust – helping to avoid any unnecessary anxiety for the patient.

Traditionally if a scan doesn’t show signs of cancer, the imaging joins a queue to be reported. Once a radiologist has done the report it is sent to a surgeon’s secretary, who then gives it to the surgeon. The surgeon dictates a letter, which is written by the secretary and eventually sent to the patient.

“That whole loop can take around three to four weeks, or in some cases months, during which time patients are worried they may have cancer,” said Dr Britton. “The 97% of patients we see who don’t have cancer need to know quicker. Our pilot project is changing that. If I know the patient doesn’t have cancer at the point of my report, I now issue a standard letter directly to the patient from our multi-disciplinary team telling them so. We are now discharging patients from scan to report in around 16 days – meaning patients know they don’t have cancer days or even weeks earlier, putting their mind at ease, and saving time as the patient isn’t chasing their GP.”

The developments come as recruitment challenges and continually growing demand are leaving many NHS imaging departments struggling to manage reporting backlogs.

A 2018 report from the Royal College of Radiologists found that 98% of trusts were unable to meet their reporting requirements within radiologists’ contracted hours, and that demand for complex imaging scans such as CT and MRI had increased by 10% per year for the previous five years. And a separate report from the Care Quality Commission found huge variation in reporting delays, calling for local and national action to address the problem and to keep people safe from harm.

The new approaches also come as a new national target for patients to be told whether they have cancer is set to be put in practice by NHS England and NHS Improvement in 2020.

Dr Marius Grima, consultant paediatric radiologist and clinical information officer for children’s, women’s & diagnostics division at University Hospitals of North Midlands NHS Trust, said: “This is about making the most of imaging technology so that we can cope with growing demand, meet national requirements and help to improve care – escalating patients who do have colorectal cancer, and quickly de-escalating those who don’t. Our imaging technology works so well, and is so reliable that we no longer need to think about IT. This means that we have the bandwidth to think about using the system to the full, and to change our pathways to improve the patient’s experience.”

Jane Rendall, managing director for UK and Ireland at Sectra, said: “Ingenuity demonstrated by healthcare professionals at University Hospitals of North Midlands is what technology in the NHS should be about. It’s not about IT. It’s about how people can use it to deliver better patient care, and a better patient experience. I hope other hospitals can replicate this success to spread the same benefits to many more patients.”

The post Redesigned Cancer Pathway Delivers Faster Results Using Innovative Imaging Tech appeared first on .

This is exacerbated by other pressures on healthcare systems including budgetary constraints, the increase in ageing populations and the number if people living with chronic long-term conditions. Further challenges come from new technology disrupting the provision of care, an imperative to improve patient outcomes, and a need to do more with less. However, there is also a real opportunity to use technology to provide a solution to the imaging capacity gap.

So, how bad is the crisis in medical imaging?

Across Europe, there is a huge shortage of trained radiologists, with the UK experiencing the worst capacity constraints, having the lowest number of practicing radiologists per capita.  There are currently 4.7 radiologists per 100,000 people in the UK. This would need to rise to 8 FTE radiologists per 100,000 to fill the gap [1].

The Royal College of Radiologists (RCR) released a recent report which found that just 2% of radiology departments were able to fulfil their imaging reporting requirements within contracted hours in 2018. [2] Most radiology clinical directors say they do not have enough radiologists to deliver effective patient care.  At any one time across the U.K., 250,000 patients will be waiting for more than 30 days on average for results on their imaging study, according to Dr. Nicola Strickland, President of the RCR. Demand for complex imaging scans such as CT and MRI has increased by 10% p.a. for the past five years, leading to Trusts outsourcing reporting in order to address backlogs. This estimated expenditure on outsourcing and insourcing has trebled to £165m since 2014.

As more complex images become available, reporting will become even more challenging, placing more demands on the radiology workforce, which will require higher levels of expertise. Training and recruiting large number of new radiologists alone cannot address this challenge.

Only by harnessing new technology can we adapt to the complexity of the situation and evolve our working practices and expand our resources to meet growing needs.  While it is often easy to get embroiled in the detail of technology and the many avenues it can open up, what is needed is a clear focus on the end goal, delivering better health outcomes for patients. For the patient this means being treated as an individual with a speedy diagnosis and rapid access to targeted, effective treatments. This should mean no more waiting times, no more back logs, no disconnects in their treatment and an integrated approach between diagnosis and treatment.

The potential of AI

There has been much hype about the potential for AI in medical imaging, but the key question now is how it can be applied in practice to deliver better health outcomes. The answer is to use it to accelerate the diagnostic process and provide targeted effective treatments. Machine learning can process information faster than humans and enhance human-led clinical decision making by providing accurate contextualised information quickly to the right experts. Clinicians’ jobs can be improved by enabling them to focus their expertise on the most complex of cases.  The diagnostic process can then be accelerated ensuring patients have access to the right treatments quickly.

What practical improvements can AI bring to medical imaging?

AI can also help in dealing with the problem that humans are limited by their experience. Radiologists rely on the images they have seen before and the experiences they have had in their clinical field. Applying machine learning on large image databanks can compare individual cases to large global databanks to provide insights on diagnosis, disease trajectory and treatment options. It can provide additional information by combining multiple data sources, such as longitudinal and genomic data, as well as individual electronic health records. The radiologist can gain access to similar cases on an international level and learnings from other specialists in the field. This increases the radiologist’s bank of expertise.

The patient benefits from a highly informed and rapid diagnostic process and insights gained from others’ treatment pathways, accelerating access to targeted effective, more personalised treatments. The radiologist’s own experience can be improved as they can apply their time to more complex cases.

Machine learning can automate parts of the image reading and reporting process and improve analysis and reporting times.  AI is also a tool which can enhance the clinical workflow, can automate simple repetitive tasks, distinguish between healthy and abnormal cases, triage and prioritise cases which require urgent referral. The combination of machine and human input and interpretation provides a way to increase the capacity and skills of the radiologist practice of the future. It empowers humans to keep pace with the rise the complexity and number of images and to harness these to deliver better patient outcomes.

The broader health system can benefit from efficiencies by making better use of hospital equipment and clinician time and improved quality of reporting by reducing the number of errors. In addition, AI based applications can play a role in training radiologists and provide a richer data source and deeper expertise.

The use of AI in medical imaging can then support a shift to informed, predictive healthcare, away from reactive healthcare

What does the future look like?

AI in medical imaging is in early development phase and there are still hurdles to be overcome related to reliability, user confidence, and adoption.  However, advances are being made by many players across industry and the healthcare system.

Established players in the field of medical imaging, such as the large PACs (picture archiving and communications systems vendors) are taking a platform approach, incorporating AI solutions into their offerings on an application-model basis. They are embracing proprietary in-house AI solutions as well as third party solutions. Innovators are focusing on disease-specific fields, as no one innovator could possibly provide a solution across all clinical areas. Healthcare systems are trialling AI in medical imaging and providing compelling evidence of its effectiveness.

All these developments are encouraging but to make this new approach in medical imaging a reality will require collaboration from many stakeholder groups, including Government, industry, innovators, healthcare delivery systems, payers and regulators.

Humans, whether as patients or clinicians, will also be required to take a leap of faith, to embrace AI as an enhancement to current practices, to adopt it into clinical pathways and to accept its potential as an essential ingredient for delivering better health outcomes for all.

References

1 EUROPE’S LOOMING RADIOLOGY CAPACITY CHALLENGE A COMPARATIVE STUDY C. SILVESTRIN

2 RCR Clinical Radiology Workforce Consensus Report 2018.

By Valerie Phillips, healthcare consultant at PA Consulting

The post AI has Huge Potential to Address the Crisis in Medical Imaging appeared first on .

Algorithms developed by Imbio, which has offices in the states of Minnesota and Wisconsin, enable clinicians to quickly analyse a patient’s lung density and texture. This includes using advanced computer vision to transform a standard chest CT into a detailed map of lung textures in order to identify cases of interstitial lung disease (ILD) and other fibrotic conditions.

The company also has a range of additional algorithms currently at research stage, as well as partnerships with a number of leading clinics and universities, including the University of Michigan, Oregon Health & Science University and the prestigious Mayo Clinic, a US academic medical centre based in Rochester, Minnesota.

Imbio is the latest provider to make its technology available through Wellbeing Software’s AI Connect platform, which enables hospitals to embed their chosen algorithms into their radiology workflow, no matter what RIS or PACS they’re running.

As the leading provider of Radiology Information Systems to the NHS, Wellbeing’s expertise in radiology workflow has already enabled trusts and organisations to speed up their adoption of AI. This has included the deployment of AI at Dartford & Gravesham NHS Trust, where Wellbeing’s AI Connect platform has enabled the introduction of algorithms from AI provider behold.ai that are helping clinicians to triage imaging and prioritise workloads. AI Connect also provides a standard framework for the roll-out of multiple algorithms from multiple providers.

David Hannes, COO at Imbio, said: “More than one billion imaging studies are requested in the US and EU alone every year. But this explosion hasn’t come with the tools clinicians need to see and interpret all of the information in each patient’s images.

“With big data analysis and computer vision, our algorithms are able to turn standard medical images into rich visual maps of a patient’s condition and reports that provide detailed data on the type and extent of abnormalities found in the patient images. This enables clinicians to see hidden information in the images and drive data-based, personalised patient care decisions from diagnosis, to therapy tracking, to planning for procedures.

“Wellbeing Software’s understanding of radiology workflow within the NHS is unrivalled and their AI Connect platform will provide a quick way for trusts and organisations to see the benefits of our technology in action.”

Graham Ridgway, CEO at Wellbeing Software, added: “We’re committed to giving NHS organisations the best choice when it comes to the adoption of AI and are pleased to welcome Imbio and its pioneering algorithms to the AI Connect Programme and our newly launched AI Market Place, which highlights the different applications of AI we are making available.

“Algorithms, such as those created by Imbio, have the ability to drastically improve clinical workloads and patient care, but this only becomes a reality when the technology is matched with existing workflows and practices. By enabling this we hope to make the roll-out of AI as simple as possible.”

The post Pioneering Algorithms to offer NHS Organisations AI Support for Lung Condition Imaging appeared first on .