Advanced medical imaging can change the course of a patient’s care, but access is not always simple. A PET scan can help doctors understand disease activity inside the body, especially in cancer care. The challenge is that PET imaging often depends on expensive machines, radioactive tracers, specialist facilities, and appointment availability. For many hospitals and patients, that creates delays at exactly the moment when faster answers matter.
That is the problem Sean Walsh, also styled publicly as Dr. Seán Walsh, is trying to solve through RADiCAIT. As CEO and co-founder, Walsh is leading a medical imaging company focused on a bold idea: using AI to turn routine CT scans into PET-like functional imaging insights. Instead of making every patient wait for a traditional PET scan, RADiCAIT wants to help clinicians get more value from scans they already order every day.
The company’s core technology, Insilico PET®, is built around this practical shift. CT scans are common, fast, and widely available. PET scans are powerful, but more limited. RADiCAIT is trying to bring the value of PET-level imaging closer to the scale of CT, making advanced diagnostics easier to reach for hospitals, radiologists, oncologists, and patients.
Who is Sean Walsh
Sean Walsh is a medical imaging entrepreneur with a background that fits naturally into the world RADiCAIT is trying to reshape. His public profiles describe him as a medical physicist and radiology AI leader, with experience across medical physics, data science, radiomics, and healthcare entrepreneurship.
That mix matters because RADiCAIT is not simply building another software tool for hospitals. It sits at the crossing point of imaging science, clinical decision-making, and AI model development. To lead that kind of company, a founder needs to understand more than technology. They also need to understand what clinicians need, what hospitals can adopt, and where current imaging systems create friction for patients.
Walsh’s earlier work in radiomics is especially relevant. Radiomics is the study of how medical images can reveal hidden patterns, measurements, and signals that may not be easy for the human eye to see. In simple terms, it is about making images more informative. That same idea runs through RADiCAIT’s mission. The company is asking whether routine CT scans can carry more clinical value than the healthcare system currently extracts from them.
The problem RADiCAIT is trying to solve
To understand why RADiCAIT matters, it helps to look at the difference between CT and PET.
A CT scan is widely used because it is fast, familiar, and available in many hospitals and imaging centers. It gives doctors detailed anatomical information. It can show the size, shape, and location of structures in the body. That makes CT useful across emergency care, cancer diagnosis, surgery planning, and follow-up imaging.
A PET scan works differently. It helps show biological activity, such as how tissues use glucose or how disease behaves at a functional level. In oncology, that kind of information can be valuable for detecting cancer, staging disease, choosing treatment, and monitoring response.
The problem is that PET imaging is harder to scale. It can require radioactive tracer production, nuclear medicine infrastructure, highly trained staff, and expensive equipment. Patients may need to travel to larger medical centers, wait longer for appointments, or go through extra steps before doctors can make decisions.
RADiCAIT is built around a straightforward but ambitious question. What if hospitals could get PET-like functional insight from the CT scans they already perform?
What RADiCAIT is building
RADiCAIT is developing AI-powered imaging technology that transforms routine CT scan data into PET-like functional maps. Its product, Insilico PET®, is designed to create in silico PET imaging without requiring radioactive tracers, new scanner hardware, or an additional patient appointment.
The phrase “in silico” means something is generated or modeled computationally. In RADiCAIT’s case, the idea is to use deep learning to understand the relationship between CT and PET imaging patterns, then create a PET-like output from CT data.
For clinicians, the value is not just that the image looks more advanced. The value is the possibility of getting functional insight more quickly and at lower cost. That could make a difference in several parts of the cancer care pathway, including detection, staging, treatment planning, and monitoring.
The practical appeal is clear. If a hospital already has CT scanners, it may not need to build or access full PET infrastructure for every imaging question. RADiCAIT’s model could help smaller clinics, regional hospitals, and resource-constrained systems benefit from richer diagnostic information without the same logistical burden.
How AI connects CT scans and PET-level insight
RADiCAIT’s work depends on deep learning, a form of AI that can learn complex patterns from large sets of data. In medical imaging, deep learning models can be trained on paired imaging examples, such as CT scans and PET scans, to understand how anatomical patterns may relate to functional information.
This does not mean the AI is guessing randomly. The goal is to teach the model to recognize relationships between structure and function. CT shows anatomy. PET shows activity. RADiCAIT is working in the space between those two forms of information.
That is why the company often frames its work as turning “anatomy into physiology.” It is a useful way to understand the idea. A CT scan may show where something is. PET-like functional mapping may help reveal what is happening there.
For radiologists, that could mean more context when interpreting scans. For oncologists, it could mean faster insight into disease behavior. For patients, it could mean fewer delays and less exposure to additional procedures in cases where the technology is clinically validated and approved for use.
Why PET-level imaging matters in cancer care
Cancer care often depends on timing. Doctors need to know whether a tumor is present, how far disease has spread, whether treatment is working, and whether a suspicious area is active or inactive. Imaging helps answer those questions.
Traditional CT can show important structural changes, but function matters too. A lesion may look similar in size while its biological activity changes. PET imaging can help reveal that activity, which is why it is widely used in oncology workflows.
The access issue is the key. A major academic hospital may have more advanced imaging resources. A smaller clinic may not. A patient in a rural area may need to travel. A hospital system may face scheduling pressure. A doctor may wait for the next available PET appointment before making a treatment decision.
This is where Sean Walsh and RADiCAIT are focusing their effort. The goal is not to make imaging more complicated. It is to make powerful imaging insight easier to access through tools hospitals already use.
Sean Walsh’s leadership role in RADiCAIT
A company like RADiCAIT needs more than a clever technical idea. It needs clinical trust, scientific discipline, regulatory awareness, and a clear understanding of hospital workflows. That is where Walsh’s background becomes part of the story.
As CEO, Sean Walsh is helping position RADiCAIT as a practical healthcare company rather than a purely academic AI project. The company’s message is built around real-world needs: faster imaging decisions, lower system cost, safer workflows, and better access to advanced diagnostics.
This leadership role also involves translating a highly technical concept into a clear value proposition. Hospitals do not adopt AI because it sounds futuristic. They adopt it when it helps clinicians make better decisions, fits into existing workflows, passes validation, and makes financial sense.
Walsh’s achievement is in connecting those pieces. He is taking a complex scientific idea and shaping it into a company aimed at one of radiology’s most visible pain points.
The team behind RADiCAIT
RADiCAIT’s work is not built around one person alone. The company’s team brings together medical, technical, operational, and clinical experience.
Alongside Sean Walsh, the company publicly lists leaders including Dr. Regent Lee, Dr. Sina Shahendeh, and JP Sampson. The combination is important because medical imaging AI requires different kinds of expertise working together.
A clinical leader can help identify what doctors actually need. A technical leader can guide model development and system performance. An operations leader can help move the company from research into deployment. A CEO with medical physics and startup experience can connect the company’s scientific foundation with its commercial path.
That type of team structure matters in healthtech because good science alone is rarely enough. Medical AI companies need to prove that their technology is accurate, useful, safe, and adoptable.
From Oxford innovation to the healthcare market
RADiCAIT has been described publicly as an Oxford spinout, which gives the company a research-driven foundation. That background helps explain why its technology is focused on a specific and difficult clinical challenge rather than a broad, vague AI promise.
The company has also gained attention as a Boston-based AI medtech startup, reflecting its move toward the US healthcare market. That matters because the United States is one of the world’s largest medical imaging markets, but it is also a demanding environment for clinical validation, regulation, reimbursement, and hospital adoption.
RADiCAIT’s reported pre-seed funding and early visibility show that investors and healthcare observers are paying attention to the problem it is trying to solve. More importantly, its work points toward a larger trend in medicine: using AI to make high-value care more scalable.
In the past, advanced diagnostics often required advanced physical infrastructure. RADiCAIT is trying to shift part of that value into software, computation, and routine scan data.
Why RADiCAIT could help hospitals work faster
Hospitals already face heavy imaging demand. Radiology departments deal with growing scan volumes, workforce pressure, and the need for faster reporting. Adding more machines, rooms, specialists, and appointments is not always simple.
RADiCAIT’s approach could reduce some of that pressure if clinical use cases are validated. Instead of sending every patient down a longer imaging pathway, clinicians may be able to extract more information from existing CT scans. That could support faster triage, earlier treatment planning, and better use of specialist imaging resources.
For radiology teams, the technology may become a form of clinical decision support. It can potentially add another layer of information to scans that are already part of the patient journey. For hospital administrators, it may offer a way to improve access without depending entirely on new infrastructure.
The broader point is simple. Healthcare systems do not only need better technology. They need technology that fits the reality of busy hospitals.
Why access is central to the RADiCAIT story
The most compelling part of RADiCAIT’s work is not only technical. It is about access.
PET imaging can be extremely valuable, but it is not equally available everywhere. Large medical centers are more likely to have advanced imaging infrastructure. Smaller hospitals may rely on referrals. Patients may face travel, waiting times, and added stress. In oncology, those delays can feel especially heavy.
By building on CT scans, RADiCAIT is working with one of the most widely used imaging tools in healthcare. CT is already part of many diagnostic pathways. It is faster to schedule, easier to access, and more common than PET.
If RADiCAIT can prove its technology in clinical settings, the result could be a more scalable model for advanced imaging. That means PET-level insight may become available to more patients, not only those who live near major centers or can access specialized facilities quickly.
A safer and more scalable imaging pathway
Another important part of RADiCAIT’s value proposition is safety. Traditional PET imaging can involve radioactive tracers. These tracers are used for good clinical reasons, but they add complexity, cost, and patient burden.
RADiCAIT’s Insilico PET® approach is designed to avoid radioactive tracers by generating PET-like maps from CT data. That does not remove the need for clinical proof, regulatory review, or careful use. But it does show why the idea is attractive.
A tracer-free workflow could make imaging easier for patients and more efficient for healthcare systems. It could also reduce dependence on nuclear medicine supply chains and specialist infrastructure. For a health system trying to serve more people with limited resources, that kind of scalability matters.
Why Sean Walsh’s work stands out in radiology AI
The radiology AI market is crowded. Many companies promise faster reporting, automated detection, or workflow support. What makes Sean Walsh and RADiCAIT stand out is the ambition of the problem they are tackling.
RADiCAIT is not only trying to help read images faster. It is trying to change what kind of information can be extracted from a routine scan. That is a deeper shift.
If CT data can be used to generate clinically useful PET-like insight, the impact could reach beyond one hospital department. It could affect oncology workflows, diagnostic access, patient scheduling, imaging costs, and the way smaller clinics participate in advanced care.
That is why Walsh’s story works as an achievement-focused profile. His work is not framed around personal publicity. It is framed around a healthcare bottleneck that many clinicians and patients can understand.
The clinical proof RADiCAIT still needs
A balanced article about RADiCAIT should also be honest about what comes next. Medical AI is not adopted on promise alone. It needs evidence.
RADiCAIT will need strong clinical validation to show where its technology works, how accurately it performs, and which patient groups benefit most. It will also need to fit regulatory requirements and earn trust from radiologists, oncologists, hospital leaders, and payers.
That is not a weakness. It is the reality of building in healthcare. A tool that influences diagnosis or treatment planning must be tested carefully. Doctors need to know when to rely on it, when to question it, and how it compares with existing standards.
This is where Walsh’s leadership will continue to matter. The next stage is not only about model performance. It is about clinical integration, regulatory progress, and real-world adoption.
What RADiCAIT could mean for smaller clinics and underserved patients
One of the most important possibilities is the effect on smaller healthcare settings. Many clinics and regional hospitals have CT access but not PET access. That gap can shape the speed and quality of care.
If RADiCAIT can help clinicians get PET-like insights from CT scans, it could make advanced diagnostic information available in places that do not have full nuclear medicine infrastructure. That could be meaningful for rural communities, community hospitals, and patients who currently need to travel for advanced imaging.
The technology could also help health systems use PET scanners more strategically. Instead of treating PET access as the only path to functional imaging insight, clinicians may have another tool for certain decisions. Traditional PET would still remain important where it is clinically required, but RADiCAIT could reduce pressure on the system.
That is the bigger achievement behind Walsh’s work. He is not simply building AI for the sake of AI. He is helping build a pathway that could make advanced diagnostics more practical.
How RADiCAIT fits into the future of medical imaging
Medical imaging is moving toward richer data, faster interpretation, and more personalized decisions. AI is a major part of that shift, but the strongest companies are usually the ones that solve a clear clinical problem.
RADiCAIT fits into that future because it focuses on a specific pain point: PET-level insight is valuable, but PET access is constrained. CT is widely available, but it does not naturally provide the same functional information. RADiCAIT is working to close that gap with deep learning.
This kind of innovation could support a more efficient imaging ecosystem. Radiologists may get more useful information from routine scans. Oncologists may make decisions faster. Hospitals may reduce unnecessary delays. Patients may avoid extra steps in parts of the pathway where the technology is approved and appropriate.
For Sean Walsh, the success story is still developing. RADiCAIT has a strong mission, a clear technical focus, and a healthcare problem that is easy to understand. The company’s future will depend on clinical results, regulatory progress, and adoption by real medical teams.
Still, the direction is important. Walsh is building RADiCAIT around a future where advanced imaging is not limited only by expensive hardware and specialized infrastructure. Instead, the company is trying to make powerful diagnostic insight faster, safer, and easier to access through the scans hospitals already use.
