DeepHealth Unifies Imaging AI to Tackle Europe’s Radiology Challenges
23rd March, 2026
A key milestone in this journey is DeepHealth’s acquisition of Gleamer, which expands its capabilities in X-ray interpretation and automated reporting
As healthcare systems across Europe grapple with rising imaging volumes, workforce shortages, and increasingly complex diagnostic demands, radiology is at a critical inflexion point. The expansion of population-scale screening programmes, coupled with fragmented workflows and growing data burdens, has intensified the need for more integrated, intelligent solutions that can deliver consistent and timely clinical outcomes.
Against this backdrop, DeepHealth is advancing a unified, AI-powered imaging platform designed to streamline radiology workflows across modalities, including MR, CT, X-ray, mammography, and ultrasound. By integrating screening, detection, interpretation, and follow-up into a single ecosystem, the platform aims to reduce operational friction, enhance diagnostic accuracy, and support clinicians in managing increasing workloads.
A key milestone in this journey is DeepHealth’s acquisition of Gleamer, which expands its capabilities in X-ray interpretation and automated reporting. Combined with an open ecosystem approach through AI Studio—featuring over 140 algorithms from more than 75 partners the company is positioning itself to drive scalable, enterprise-wide adoption of AI in radiology.
In this interview with MedTech Spectrum, Kees Wesdorp, President & CEO of DeepHealth, discusses how the company’s integrated platform is addressing core clinical challenges in Europe, the strategic significance of the Gleamer acquisition, and the evolving role of AI in enabling more efficient, standardised, and equitable diagnostic care at scale.
DeepHealth introduced an integrated platform of AI-powered solutions across multiple imaging modalities. What key clinical challenges in radiology is this platform designed to address for healthcare providers in Europe?
European healthcare systems face similar challenges we see globally — disconnected patient engagement, a strained workforce and growing demand gap, and fragmented technology, data, and workflows that can lead to inconsistent clinical outcomes. European healthcare systems are also expanding screening programs, and that means more scans, more data, and higher expectations for consistency.
What we've built at DeepHealth is a direct response to this reality. Our integrated portfolio of AI-powered solutions and services spans MR, CT, X-ray, Mammography, and Ultrasound, supporting screening, detection, interpretation and follow-up across many of the most prevalent cancer types, as well as neurodegenerative and musculoskeletal conditions, including trauma and chronic conditions. These innovations are designed to help stage shift disease, drive more timely diagnostic pathways, and expand patient access. Accessible on one platform, this approach also helps alleviate the workload of care professionals and, through seamless integration into existing clinical workflows, supports more consistent adoption of AI in routine practice.
Following the acquisition of Gleamer, how does DeepHealth plan to expand AI applications beyond screening into routine imaging and acute diagnostic care?
The acquisition and integration of Gleamer into DeepHealth is a transformative milestone for us and for the industry. AI-powered screening has always been a core strength of DeepHealth — we have validated, real-world proof points of delivering impact at scale across breast, lung, and prostate cancer screening in Europe and the United States.
Gleamer’s leadership in imaging, and particularly X-ray, is unparalleled through the breadth and scale of its cloud-first AI solutions. By integrating Gleamer's technology with DeepHealth’s Clinical AI suites of solutions, we create a comprehensive portfolio unrivalled by any other radiology AI company. Moreover, Gleamer’s capabilities in automated reporting, already deployed in Europe, combined with DeepHealth’s AI and informatics portfolio, bring clinical, generative and agentic AI and imaging informatics together into an integrated offering. With this extensive expertise, DeepHealth is uniquely positioned to enable more standardized interpretation, automated draft reporting and scalable diagnostic pathways addressing the challenges aforementioned.
Our goal is to be the platform that radiology departments can rely on, whether they're running a population screening program or managing everyday imaging workload.
Your portfolio includes specialised suites for Breast, Chest, Neuro, Prostate, and Thyroid. How does consolidating these tools onto a single platform improve diagnostic workflows and efficiency for radiologists?
The feedback we hear most from radiologists is that fragmentation is exhausting. Logging into multiple different systems, reconciling outputs from disconnected tools, transferring data between platforms — that friction adds up, and it costs time that should be spent on patients. A single, unified platform that orchestrates imaging, AI, and workflows eliminates that fragmentation.
With our Breast Suite, Chest Suite, Neuro Suite, Prostate Suite, and Thyroid Suite accessible on the same platform — integrated with the worklist, the viewer, and the reporting module — the radiologist's experience is fundamentally different. AI insights surface where and when they're needed, without extra steps. Take Prostate Suite as an example: it integrates automated lesion detection, intelligent gland segmentation with PSA density calculation, and PI-RADS-compliant reporting, all in one seamless flow.
Data from real-world at-scale deployments reflects this. Our Thyroid Suite deployment across more than 200 RadNet sites showed that radiologists accepted AI-based measurements and characterisation without correction in more than 90% of cases,1 and we demonstrated up to a 30% reduction in scan slot time.2 This efficiency gain, multiplied across an entire imaging department or network, can be transformative.
Studies presented at ECR 2026 highlight improvements in detection and accuracy. How are these AI-driven insights translating into measurable clinical outcomes in real-world settings?
Everything we presented at ECR 2026 is grounded in real-world clinical data, and that distinction matters enormously to the healthcare systems we work with. Our research spans lung nodule detection, thyroid characterisation, white matter hyperintensity quantification, breast cancer detection and screening protocols, and prostate MRI interpretation — all showing meaningful gains in key performance areas, such as measurable improvements in accuracy, interobserver agreement, and read efficiency.
A great example is the recently published paper in Nature Health, the largest real-world analysis of AI-powered breast cancer screening in the US on mammograms from over 579,000 women across 100+ community-based imaging sites, which demonstrated that DeepHealth Breast Suite applications enabled a 21 per cent increase in breast cancer detection rate. The study showed consistent benefits across dense-breast and diverse patient populations, including 23 per cent more cancers detected in women with dense breasts and 20 per cent more cancers detected in Black, non-Hispanic women.2
AI Studio integrates over 140 algorithms from more than 75 partners. How does this open ecosystem approach help healthcare institutions scale AI solutions more effectively?
One of the biggest barriers to AI adoption in healthcare is the complexity of deploying AI safely and sustainably across an enterprise. AI Studio is our answer.
By providing access to more than 140 algorithms from over 75 ecosystem partners — alongside our own clinical AI applications — AI Studio gives healthcare institutions a single, governed platform to orchestrate AI across the entire workflow.
What makes this scalable is the governance layer. AI Studio includes continuous monitoring, drift management — meaning the system can detect when an AI model’s performance begins to change over time due to shifts in data, patient populations, or imaging protocols — and AI validation in production, so institutions can be confident that the algorithms they deploy today are still performing over time.
As European healthcare systems expand screening programs and face rising workloads, what role will AI play in shaping the future of population health and early disease detection?
AI has shown the potential to help stage shift disease at the population health level in Europe, and the systems that embrace it now will be the ones that can deliver on the promise of large-scale screening across clinical domains. AI will also enable a scalable model — allowing healthcare systems to manage growing imaging volumes despite ongoing workforce shortages.
Our Chest Suite applications enable population-scale screening programs worldwide, including NHS England’s Lung Cancer Screening Program, for which UK Government data show that 76 per cent of detected cancers are now caught at earlier, more treatable stages, compared to only 29 per cent historically.3
The role AI will play going forward is to make early detection consistent and equitable — across every imaging site in a national program. It means catching lung cancer at stage one instead of stage three. It means identifying a woman's elevated breast cancer risk from a routine mammogram and getting her into supplemental screening before a tumour ever forms. It means flagging early signs of neurodegeneration while there's still a window for intervention.
That's the vision we're building toward at DeepHealth — a world where the quality of your diagnostic care doesn't depend on where you live or which hospital you happen to walk into. AI, deployed at scale and governed responsibly, is what makes that possible.
References:
-
Signify Research, Diagnostic Imaging Procedure Volumes Database – World – 2025 (Sept 2025). https://www.signifyresearch.
net/market-intelligence/ diagnostic-imaging-procedure- volumes-database-world-2025/ -
Louis, L. et al. “Equitable Impact of an AI-Driven Breast Cancer Screening Workflow in Real World US-wide Deployment.” Nature Health, 2025.
-
Mouland et al. “Targeted Lung Health Check Programme Final evaluation report.” Ipsos. November 2024.
Medtech Special
© 2023 MM Activ Sci-Tech Communications. All rights reserved | Disclaimer