Most artificial intelligence imaging startups focus on building one model per disease, tailoring their algorithms to detect or monitor a single condition. Qureight, a Cambridge-based company, is taking a fundamentally different approach: it has raised $20 million to build a single, general-purpose AI model for the entire chest. The idea is that from that foundational model, the company can rapidly spin off models for specific diseases, dramatically reducing the time and cost of developing new diagnostic tools for clinical trials.
The Series B round was led by Molten Ventures, a London-based venture capital firm with a strong track record in deep tech. The investment brings Qureight's total funding to over €27 million, as reported by Tech.eu. The company plans to use the capital to establish an AI imaging lab centered around its chest foundation model, expand its team, and develop new disease-specific applications for asthma, lung cancer, pulmonary hypertension, and bronchiectasis, in addition to its existing work on lung fibrosis.
The foundation model advantage
Qureight's core innovation is a 3D model of the chest that captures the complex anatomy and pathology of the lungs, heart, and surrounding structures. By training this model on a vast amount of chest CT scans, the company has created a base that can be fine-tuned for specific diseases with relatively little additional data and effort. According to Qureight, building a disease-specific model from scratch typically takes about a year. Using the foundation model, that timeline shrinks to one or two months. This speed is critical in the competitive landscape of AI in medicine, where first-mover advantage can determine a company's survival.
The foundation model approach mirrors the recent trend in natural language processing and computer vision, where large pre-trained models like GPT and DALL-E are fine-tuned for specific tasks. In medical imaging, this is still a relatively novel concept. Most AI startups train their models on datasets for a single disease, such as breast cancer or diabetic retinopathy, and then seek regulatory approval and commercial adoption for that narrow use case. Qureight's strategy is more ambitious: it aims to create a platform that can address multiple diseases across the chest, serving as a versatile tool for pharmaceutical companies conducting clinical trials.
How Qureight speeds up drug trials
The company's pitch to drugmakers centers on speed and efficiency. Clinical trials for lung and heart diseases often rely on imaging to assess how a drug is affecting the disease. Traditionally, central reading of these images can take about two weeks, as multiple radiologists review scans and reconcile their interpretations. Qureight has developed an AI tool that reduces this timeline to just 48 hours, enabling faster decision-making for trial sponsors.
Additionally, Qureight offers a technology that builds 3D maps of airways and blood vessels. These maps allow researchers to track how a drug changes the structure of the lungs over time, providing quantitative biomarkers that can be more sensitive than traditional measurements like lung function tests. The company also provides "synthetic control arms," a technique increasingly used in clinical trials to reduce the need for a placebo group. By using AI to generate a virtual control group from historical data, drug companies can lower the cost and complexity of their trials, accelerate enrollment, and potentially bring life-saving therapies to market faster.
Major pharmaceutical companies have already taken notice. AstraZeneca and Bristol Myers Squibb are among the firms using Qureight's tools, according to Tech Funding News. The market Qureight is targeting – lung and heart clinical trials – is substantial and growing. It is forecast to reach $27.5 billion by 2030, driven by an aging population, the prevalence of chronic diseases like chronic obstructive pulmonary disease (COPD) and heart failure, and the increasing use of imaging biomarkers as surrogate endpoints in regulatory approvals.
From a doctor's uncertainty to a company
Qureight's origin story is unusual for an AI imaging firm. The company was founded in 2018 not by engineers or computer scientists, but by two doctors. Chief executive Muhunthan Thillai is a chest physician who still sees patients. He started Qureight after encountering a CT scan that he could not confidently read. That moment of clinical uncertainty led him to envision an AI system that could augment human interpretation and, more importantly, serve as a consistent tool in drug development.
To compensate for the founders' lack of technical background, Qureight hired a deep senior bench of experts. The team includes a former global platform head at HP and a machine-learning professor from Imperial College London. This blend of medical and technical expertise has enabled the company to build robust, clinically validated AI models that meet the rigorous standards of the pharmaceutical industry. Qureight's closest European rival, Oxford's Brainomix, focuses on diagnostic software for hospitals, primarily for stroke and lung cancer. Qureight sits earlier in the value chain, embedded directly within the clinical trial process rather than in clinical care. This distinction shapes its business model: it charges pharmaceutical companies for the use of its imaging tools in their trials, rather than selling software to healthcare providers.
Keeping the round in London
The raise also reflects a broader trend in where AI-in-medicine money is flowing. Two years ago, Qureight approached Molten Ventures and was turned down. This time around, the company received term sheets from three investors within six weeks, a sign of the heightened interest in AI for drug discovery and biology. Notably, Qureight received offers from US investors but chose to keep the round with a London-based fund. This decision likely reflects a desire to maintain operational and strategic control close to home, as well as the strengthening of the European deep-tech ecosystem.
The surge of capital into AI for drug discovery is part of a larger wave of health-tech raises. Companies like BenevolentAI, Exscientia, and Recursion have raised billions to apply AI to early-stage drug development, but Qureight is focused on the later stage of clinical trials, an area that has seen less attention but is equally critical. The company's technology addresses a pain point that drug developers have struggled with for decades: how to reliably measure disease progression and drug effect using imaging, especially in heterogeneous diseases like lung fibrosis and asthma.
Looking ahead, Qureight plans to double its staff to 100 by December. The company will need to scale quickly to meet the demand from pharmaceutical partners and to develop the new disease-specific models it has promised. Whether its chest foundation model becomes a standard tool in clinical trials or remains a niche application depends on the partnerships it lands next. The company's success could also encourage other startups to adopt a foundation model approach for other parts of the body, potentially transforming the way medical AI is built.
But challenges remain. AI models in medicine must navigate complex regulatory pathways. Qureight's tools are currently used as research-use-only software in clinical trials, which does not require FDA clearance or CE marking. As the company moves toward diagnostic applications, it will need to seek regulatory approvals, a process that can take years and significant capital. Moreover, the foundation model must demonstrate consistent performance across diverse patient populations and imaging protocols. If it fails to do so, the promise of rapid model development may not be realized.
Nonetheless, the $20 million raise is a strong vote of confidence in Qureight's vision. The company is betting that a single, powerful model of the chest can unlock efficiencies across multiple therapeutic areas, from asthma to pulmonary hypertension. In an industry where speed and precision are increasingly valuable, Qureight's platform could become an essential tool for drug developers looking to cut costs and accelerate timelines.