RadNet Acquires CIMAR UK, Empowering DeepHealth to Accelerate AI-Powered Imaging, Reporting and Image-Based Screening

Acquisition supplements CIMAR’s cloud-native infrastructure with DeepHealth’s AI-powered informatics to deliver connected, efficient and accessible care

LOS ANGELES and LONDON, November 4, 2025 — RadNet, Inc. (NASDAQ: RDNT) (“RadNet”), a US leader in providing high-quality, cost-effective diagnostic imaging services and digital health solutions, announced today the acquisition of CIMAR UK, a leading provider of cloud-native healthcare image management solutions.  CIMAR will be integrated into DeepHealth, RadNet’s wholly owned subsidiary and a global leader in AI-powered health informatics, to advance connected imaging-based care.

“Imaging and diagnostics sit at the forefront of care, serving as the gateway to treatment and disease management,” said Kees Wesdorp, CEO and President of RadNet’s Digital Health division, DeepHealth.  “Radiologists and care teams are under immense pressure, often working with outdated or siloed tools, and are not set up to keep pace with rising demand.  By acquiring CIMAR, DeepHealth is taking a powerful step in redefining imaging-based care through a portfolio of solutions that connect clinical and operational intelligence to enable faster, more accurate diagnoses and improve efficiency.”

CIMAR deploys an extensive image management infrastructure that provides data connectivity and interoperability to enable vendor-neutral solutions, such as clinical AI, across more than 50% of National Health Service Trusts and 80% of UK private hospital groups.  As imaging volumes continue to rise and fragmented technologies create barriers to efficient, coordinated care, CIMAR’s model of a centralized image infrastructure has demonstrated its capability to deliver connected healthcare.

The acquisition combines complementary capabilities, CIMAR’s cloud-native infrastructure and services—which enhance data connectivity and interoperability across public and private healthcare systems in the UK—with DeepHealth’s leading end-to-end informatics and population health applications, from patient engagement tools and AI-based reporting to viewing and workflow applications.  Together, they can create a richer solution for advancing efficient, coordinated and accessible imaging-based care across the UK.

“This acquisition marks a pivotal moment for CIMAR,” said Howard Jenkinson, Co-Founder and Chief Executive Officer of CIMAR.  “Through our integration with DeepHealth, we can scale our impact and expand access to services and solutions that provide a more seamless, connected, and intelligent imaging experience.  Together, we aim to empower healthcare providers with the tools they need to stay at the forefront of medical imaging innovation, supporting them in delivering the highest standard of care.”

Today, an existing partnership between DeepHealth and CIMAR underpins the NHS England’s Lung Cancer Screening Program. CIMAR provides the digital infrastructure connecting DeepHealth’s AI lung solution across more than 90% of the program’s screening sites.  The Program has demonstrated early success. UK Government data show that more than three-quarters (76%) of lung cancers detected through the program are now caught at earlier, more treatable stages compared to only 29% historically.1

This stage shift highlights how connected, AI-powered screening programs can enable earlier disease detection, expand access to timely care and advance better patient outcomes.  With this acquisition, DeepHealth aims to scale digitally enabled new and more efficient care models across the UK and Europe for other screening and diagnostic programs.  The expansion would bring this connected healthcare model of image-based care programs to more patients and healthcare systems.

 

 

About RadNet

RadNet, Inc. is a leading national provider of freestanding, fixed-site diagnostic imaging services in the United States based on the number of locations and annual imaging revenue. RadNet has a network of 405 owned and/or operated outpatient imaging centers. RadNet’s imaging center markets include Arizona, California, Delaware, Florida, Maryland, New Jersey, New York and Texas.  In addition, RadNet provides radiology information technology and artificial intelligence solutions marketed under the DeepHealth brand, teleradiology professional services and other related products and services to customers in the diagnostic imaging industry.  Together with contracted radiologists, and inclusive of full-time and per diem employees and technologists, RadNet has a total of over 11,000 employees. For more information, visit http://www.radnet.com.

 

About DeepHealth

DeepHealth is a wholly owned subsidiary of RadNet, Inc. (NASDAQ: RDNT) and serves as the umbrella brand for all companies within RadNet’s Digital Health segment. DeepHealth provides AI-powered health informatics with the aim of empowering breakthroughs in care through imaging.  Building on the strengths of the companies it has integrated and is rebranding (e.g., eRAD Radiology Information and Image Management Systems and Picture Archiving and Communication System, Aidence lung AI, DeepHealth, Kheiron, and iCAD breast AI, Quantib prostate and brain AI, and See-Mode thyroid and breast AI), DeepHealth leverages advanced AI for operational efficiency and improved clinical outcomes in brain, breast, chest, prostate, and thyroid health.  At the heart of DeepHealth’s portfolio is a cloud-native operating system – DeepHealth OS – that unifies data across the clinical and operational workflow and personalizes AI-powered workspaces for everyone in the radiology continuum.  Thousands of radiologists at imaging centers and radiology departments around the world use DeepHealth solutions to enable earlier, more reliable, and more efficient disease detection, including in large-scale cancer screening programs. DeepHealth’s human-centered, intuitive technology aims to push the boundaries of what’s possible in healthcare. https://deephealth.com/

 

Forward Looking Statements

This communication contains certain “forward-looking statements” within the meaning of the safe harbor provisions of the U.S. Private Securities Litigation Reform Act of 1995, Section 27A of the Securities Act of 1933, as amended, and Section 21E of the Securities Exchange Act of 1934, as amended. Forward-looking statements can be identified by words such as: “anticipate,” “believe,” “could,” “estimate,” “expect,” “forecast,” “intend,” “may,” “outlook,” “plan,” “potential,” “possible,” “predict,” “project,” “seek, “should,” “target,” “will” or “would,” the negative of these words, and similar references to future periods.  Examples of forward-looking statements include statements regarding the anticipated benefits of the acquisition, the impact of the acquisition on RadNet’s business and future financial and operating results and prospects and the amount and timing of synergies from the acquisition are based on the current estimates, assumptions and projections of RadNet, and are qualified by the inherent risks and uncertainties surrounding future expectations generally, all of which are subject to change.  Actual results could differ materially from those currently anticipated due to a number of risks and uncertainties, many of which are beyond RadNet’s control.

Forward-looking statements are neither historical facts nor assurances of future performance.  Instead, they are based only on management’s current beliefs, expectations and assumptions regarding the future of RadNet’s business, future plans and strategies, projections, anticipated events and trends, the economy and other future conditions. Because forward-looking statements relate to the future, they are subject to inherent uncertainties, risks and changes in circumstances that are difficult to predict and many of which are outside of RadNet’s control.  RadNet’s actual results and financial condition may differ materially from those indicated in the forward-looking statements as a result of various factors.  None of RadNet, CIMAR or any of their respective directors, executive officers, or advisors, provide any representation, assurance or guarantee that the occurrence of the events expressed or implied in any forward-looking statements will actually occur, or if any of them do occur, what impact they will have on the business, results of operations or financial condition of RadNet.  Should any risks and uncertainties develop into actual events, these developments could have a material adverse effect on RadNet’s business and the ability to realize the expected benefits of the acquisition.  Risks and uncertainties that could cause results to differ from expectations include, but are not limited to: (1) the ability to recognize the anticipated benefits of the acquisition, which may be affected by, among other things, the ability of RadNet or CIMAR to maintain relationships with its vendors, customers, the NHS and providers and retain its management and key employees, (2) the ability of RadNet to achieve the synergies contemplated by the acquisition or such synergies taking longer to realize than expected, (3) costs related to the acquisition, (4) the ability of RadNet to execute successfully its strategic plans, (5) the ability of RadNet to promptly and effectively integrate CIMAR into its business, (6) the risk of litigation related to the acquisition, (7) the diversion of management’s time and attention from ordinary course business operations to integration matters, and (8) the risk of legislative, regulatory, economic, competitive, and technological changes.  The foregoing review of important factors should not be construed as exhaustive and should be read in conjunction with the other cautionary statements that are included elsewhere.  Additional information concerning risks, uncertainties and assumptions can be found in RadNet’s filings with the Securities and Exchange Commission (the “SEC”), including the risk factors discussed in RadNet’s most recent Annual Report on Form 10-K, as updated by its Quarterly Reports on Form 10-Q and future filings with the SEC.

Forward-looking statements included herein are made only as of the date hereof and, except as required by applicable law, RadNet does not undertake any obligation to update any forward-looking statements, or any other information in this communication, as a result of new information, future developments or otherwise, or to correct any inaccuracies or omissions in them which become apparent.  All forward-looking statements in this communication are qualified in their entirety by this cautionary statement.

 

RadNet Contact

Mark Stolper
Executive Vice President and Chief Financial Officer
+1 310-445-2800

 

Jane Mazur
Senior Vice President, Corporate Communications
+1 585-355-5978
jane.mazur@radnet.com

 

DeepHealth Contact

Andra Axente
Director of Communications
+31614440971
andra.axente@deephealth.com

 

 

References

World’s Biggest Medical Imaging Project Reaches Major Target

The impact of advances in medical imaging technology, particularly in the wake of machine learning and increased training data, is found both in individual diagnoses as well as wider trends in health, medicine and an understanding of how the human body changes as it ages.

The single biggest medical imaging project in the world, the UK Biobank, has completed its goal of scanning the whole bodies of 100,000 volunteers, with an impact that has already been felt throughout the medical world.

Taking place over the course of a decade, the UK Biobank involved the collection of an extensive corpus of MRI scans, with 12,000 scans being undertaken in each five-hour session with every person.

The project took ten years to complete, with a second phase following up on 60,000 participants set to continue until 2029.

This information has become extremely vital training data for medical scanners, allowing for dedicated diagnostic tools powered by machine learning to provide more accurate, faster diagnoses, particularly of complex and difficult-to-detect diseases.

For example, the UK Biobank has already allowed for dementia to be more accurately diagnosed, something that can potentially prolong and save lives as more rapid interventions lead to more positive prognoses.

Another result of the project was a tool that can scan the heart in less than a second, compared to a 15-minute scan that was more common prior to the UK Biobank project. This tool can help find potential warning signs of heart disease, further preventing premature death.

In the future, the Biobank could replace a biopsy scan to diagnose fatty liver disease with an MRI scan, which could avoid it progressing into potentially life-threatening conditions such as cirrhosis.

It also helps to illuminate certain variables that affect how people remain healthy as they age, including predicting the early onset of disease, how alcohol consumption affects the brain and how people store fat in different ways, leading to different risks of disease.

These insights, as well as countless others made possible with the anonymised database of information, have already saved lives and will have a progressively larger impact going forward.

Why The Cloud Can Help Maximise Diagnostic Scan Advances

If ever two developments should go hand-in-hand, it is the growing effectiveness of medical scans in detecting problems and making early diagnosis possible, and the development of the cloud to make this crucial information accessible to all who need it.

This point should never be overlooked, because at a time when developments like AI are enabling diagnostic scans to be more effective than ever before, the capacity to maximise the benefit lies in ensuring that the accessibility to the data is as easy to obtain as possible for those who need to know. Medical cloud storage offers exactly this.

Some of the latest diagnostic developments in the UK alone offer great encouragement. The BBC recently reported on the introduction of AI by West Yorkshire NHS Trust, which will be used to help diagnose conditions like lung cancer and infections faster when examining X-rays.

Speaking to the broadcaster, project lead and consultant radiologist Dr Fahmid Chowdhury said: The real benefit will be once we start using the AI to flag the abnormal reads we will see over time, and the abnormal X-rays will get reported more quickly.”

Needless to say, the benefit of earlier diagnosis can mean an earlier start to treatment, which may make the difference between life and death in cases such as cancer.

However, the capacity of staff to access such information via the cloud means that in circumstances such as a patient moving to a different hospital, essential data like this will be easy to access and not lost through any lack of communication.

Other new developments in the UK include a study co-led by the London Health Sciences Centre Research Institute and published in the Lancet Neurology, which revealed that carrying out heart scans quickly after a stroke patient arrives in hospital improves the chances of establishing the underlying reasons for the episode.

This will not only help the stroke patient at the time, but can aid recovery by enabling future treatment and medication to be tailored towards preventing a recurrence arising from the identified root cause.

Fluorescent Imaging May Aid Musculoskeletal Treatments

The importance of medical imaging sharing has been well established for years, but the value of using the cloud and other innovations to facilitate easier access to images for all who need them will only increase as new developments provide better image data.

A new form of imaging could add significantly to this by advancing the field of care for musculoskeletal disorders.

As Science X reports, researchers in Japan have developed a technique for tracking two genes in mice that are associated with the foetal stage development of the musculoskeletal system. These have provided insights into how the tendons, ligaments and cartilage form connections during fetal development.

It was done because one gene expressed red proteins and the other green, enabling the imaging of these to produce a clear picture of the development taking place in the embryonic stage. The work was published in the journal Development.

This imaging provides a 3D view of this development in a way that other imaging methods cannot. This could prove useful not only in detecting problems in foetal development, but also in adult musculoskeletal disorders and regeneration, especially when age or sporting injury is involved. This could, in turn, help inform and develop treatments.

“Traditional methods using thin tissue sections have limitations in preserving structural integrity, which makes it difficult to study the 3D organisation of these tissues,” said Professor Chisa Shukunami of Hiroshima University, where the work was carried out.

He added: “Our approach overcomes these challenges by combining tissue clearing of a newly established double fluorescent reporter mouse model with high-resolution fluorescence imaging.”

Data produced by the World Health Organization in 2022 indicated that 1.7 billion people around the world had musculoskeletal disorders, indicating that this form of imaging may prove valuable for a significant proportion of the global population, not least in countries like the UK, where life expectancy is greater and thus age-related issues are more common.

Medical Imaging Reveals Why Music Affects People So Strongly

There are few art forms that affect people emotionally and physically as much as music and a recent study used multiple medical imaging technologies to find out why.

The first line of William Shakespeare’s Twelfth Night described music as the “food of love” but whilst the power of music can be fairly easily intuited, it is far more difficult to ascertain exactlyhow it affects people.

The answer might be found in a study by a team from the University of Turku in Finland, published in the European Journal of Nuclear Medicine.

Through the use of positron emission tomography (PET) and functional magnetic resonance imaging (fMRI), the team led by Vesa Putkinen noted that the reaction engages the same hedonic systems of the brain as delicious food and positive social interactions, which triggers a neurochemical reaction to reward and reinforce that behaviour.

The neurochemical reactions in similar areas may explain why when people listen to music they like, they can get strong physical reactions such as accumulating goosebumps, feeling chills, and crying tears of joy.

As it turns out, Mr Shakespeare may have been right to compare music to food; certainly, they affect the pleasure circuitry of the brain in a similar way according to this study.

The results, particularly those found using the PET scan, found a direct connection between music and the brain’s opioid system, and this discovery could have greater implications for treatment and pain relief.

The opioid system plays a role not only in pleasure sensations but also in pain relief, which means potentially that listening to music one enjoys could affect the sensation of pain.

There have been previous studies in that field but they have focused on distraction, stress relief and more general dopamine regulation, rather than the specific neurochemical processes that make music so powerful.

By contrast, medical imaging allowed researchers to see the specific processes involved.

Study Highlights Role Of AI In Improving Scan Diagnostics

The importance of medical image sharing will be well known to many involved in patient care, with the ease with which this information can be transmitted between different settings enabling greater access for all those delivering treatment or seeking to carry out a diagnosis.

Since early and accurate diagnosis is so often the key to successful treatment outcomes, the usefulness of medical images produced by scans can be increased further by enhancements in diagnostics. This is an area in which the use of artificial intelligence has produced some exciting developments, often spotting problems the human eye would usually miss.

These have been highlighted in a new study conducted by India-based healthcare technology researcher Sriram Sitaraman, Tech Bullion reports.

His research, published in the International Journal of Scientific Research, highlighted just how much advancement AI is bringing to the area of medical diagnostics.

Perhaps the most telling finding was that suspicious lesions are now detected 2.3 years earlier on average when AI is used than when it is not.

It is not just the all-important early diagnosis rate that has been improved, but workflows for busy staff, with the typical time taken to interpret an image falling from 6.5 minutes to 3.2 minutes, while maintaining a diagnostic accuracy of 96.2 per cent. Anatomical segmentation rates are also high, at 89.2 per cent accuracy.

The report highlighted that while upfront costs for such AI systems are high, they will pay for themselves in two or three years. Such a concern may apply most to the private medical sector, but within a state-run body like the NHS it may be considered that it brings the wider social and economic value of a healthier population.

Indeed, as Public Technology recently reported, the NHS is planning to set up a £180 million framework to enable health bodies to invest in AI for diagnostics. It is set to start taking bids this summer.

Does Medical Imaging Show That Athletes Think Differently?

There are a lot of uses for medical imaging in research, but one of the most unusual recent studies has explored the neurological differences between elite-level athletes and those who play sports at an amateur or recreational level.

The study, published in the Journal of Exercise Science and Fitness, used MRI scans on 60 different people. This included 20 professional-level basketball players, 20 intermediate-skilled amateur players and 20 people of the same age who were not athletes and had no experience in basketball.

The team measured the voxel-mirrored homotopic connectivity (VMHC) of each person, as well as their grey matter density (GM) and amplitude of low-frequency fluctuations, which are quantitative indicators linked to the motor skills, coordination and executive function seen as vital to sporting success.

Compared to the 20 non-athletes, basketball players of both skill groups were shown to have a greater connection between areas that were responsible for control, motor function and decision-making ability, all factors vital for success in a team sport.

The key to a player doing well in a team sport is not just the ability to think quickly but to think clearly and coordinate with other players during a playing or training session.

This could have significant implications for athletes at all levels, as the difference between skill levels could be seen as much in the brain as it is in the body, in a way that can be seen through imaging and quantified.

This is not necessarily a new phenomenon; the National Football League has regularly used cognitive ability testing as part of its scouting and recruitment process, with certain playing positions seen as more mentally taxing than others.

There have historically been issues with cognitive testing, as whilst it can determine a form of basic general intelligence, it is not always suited for determining the types of intelligence needed in an elite player.

Using MRI or another imaging benchmark could potentially be a better alternative, but a lot more research needs to be done to determine this.

Could A Tracing Compound Reveal Treatment-Resistant Tumours?

One of the most important parts of any cancer treatment is diagnosis, which starts with effective, regular medical imaging techniques.

These help to show the location of tumours, but cannot always be used to diagnose a cancerous tumour’s characteristics, something that can fundamentally change the types of treatment that are suitable for a patient.

Given that some forms of cancer treatment such as chemotherapy take a long time, a delay caused by a treatment-resistant tumour could be potentially life-threatening.

However, a team at King’s College London led by Tim Witney, believe that they might have found a solution by taking advantage of a system regularly used for clinical trials known as a radiotracer.

A radioactive tracer is commonly used to trace biochemical reactions such as metabolic processes, but using a molecule that is designed to target a tumour-associated protein named xCT, researchers noticed that cancer cells resistant to treatment would light up brighter on imaging systems.

This means that it could reduce the amount of time it takes to see if an aggressive cancerous growth is resistant to treatment from 12 weeks to a matter of hours.

Given that with aggressive cancers time is everything, this means that months might no longer be wasted with treatments that are ultimately found to be unnecessary, allowing for contingencies for treatment resistance to be used as soon as possible to ensure they are at their most effective.

This not only has a lot of benefits in terms of treatment prognosis but also in terms of the mental health of patients, who all too often are left devastated and worried that the treatment they have endured for months at a time has been meaningless.

It also potentially could provide even more hope for the future, as a type of targeted therapy known as antibody-drug conjugate (ADC) could be used to selectively kill the resistant cells without harming healthy tissue alongside it.

What Does Elon Musk Medical Image Request Say About AI?

There are not many things Elon Musk says or does these days that escape attention, so a request made by the owner of X (formerly Twitter) may raise attention about the growing use of AI in providing medical imaging solutions.

Mr Musk asked X users to upload their medical scans in order that Grok, the platform’s AI tool, could learn to interpret them, Fortune Magazine reported. Many did so, uploading MRI and CT scans.

“This is still early stage, but it is already quite accurate and will become extremely good. Let us know where Grok gets it right or needs work.” Mr Musk said. However, the report added, Grok actually made a lot of errors in interpretation early on.

Given his proximity to power as Donald Trump’s new best friend, some may wonder what the ultimate motive of the Tesla owner is, while there have been concerns expressed about whether patient identities will be compromised by allowing X and Grok access to such data.

However, what this exercise may also do is help to highlight the growing importance of AI in interpreting medical imaging scans, which in turn makes facilities enabling their storage and transmission all the more valuable.

At its best, an AI interpretation can help spot signs of illnesses such as cancer that will usually be missed by a human eye. This can then enable a more accurate and, crucially, early diagnosis, which in many cases can make the difference between whether a patient survives or not.

It may turn out, however, that it will always require specialised AI tools to carry out this work, rather than asking a bot like Grok, which is designed for different purposes, to adapt its role to such a function.

Others, however, may want to give Grok a break, as it has apparently identified who one of the biggest spreaders of misinformation on X is, in response to a user query – Elon Musk himself.

Who Was The First Person To Be Scanned Using MRI?

One of the main medical imaging tools that has become vital for helping to diagnose and plan potential medical procedures is magnetic resonance imaging, but unlike computed tomography scans, its history is far more condensed and characterised by fairly rapid progress.

An MRI scan is a common tool used to diagnose a wide variety of medical conditions using strong magnetic fields and radio waves to create three-dimensional images of the body without using radiation.

Outside of people who are claustrophobic, have metal implants or have a pacemaker that will not allow them to enter an MRI scanner, they are often a preferred tool for scanning the human body, particularly when planning cancer treatments.

Unlike CT, which was theorised half a century before it was first attempted, the discovery of the potential for MRI to distinguish tumours from normal tissue was in 1971. Within three years the first image had been taken of Dr Andrew Maudsley’s finger by Sir Peter Mansfield, and within four years of that, the first full-body scan of a human being was made.

This scan, undertaken by Raymond Damadian, Larry Minkoff and Michael Goldsmith, was interesting, but it would take another three years for this concept to be taken further and actually be used in the treatment of a disease.

A team led by Professor John Mallard used an MRI machine on 28th August 1980 to scan a patient for the first time to actively look for disease at the University of Aberdeen. The scan found a chest tumour, which had spread to the patient’s bones, alongside an abnormal liver.

Whilst the theory behind MRI’s effectiveness had been largely proven by his point, this scan and the full-body machine that performed it led to the widespread application and introduction of MRI throughout the 1980s, fundamentally transforming diagnostics in the process.