In the quiet, high-stakes minutes after a CT scan is taken, a patient's fate is often decided by a radiologist's weary eyes and a ruler on a screen. It is a manual, time-consuming process, and for the oncologist waiting to plan treatment, every second of delay is a tangible weight. Nucleo, a San Francisco startup founded in 2025, is betting that the critical first read of a cancer patient's scan should be handled not by human fatigue, but by a consistent, near-instantaneous AI. The company's software ingests a CT scan and, in seconds, returns a detailed analysis of tumor lesions and body composition, a foundational step in oncology care that its founders claim is 2,500 times faster than manual methods and shows 98% agreement with medical experts [Y Combinator].
For Angelica Iacovelli and Luca Pegolotti, the co-founders, the goal is not to replace the clinician but to build a reliable infrastructure layer beneath them. The platform automates three specific, protocol-driven tasks that are essential yet tedious: measuring fat and muscle mass for sarcopenia assessment, sizing tumor lesions, and classifying those lesions as target or non-target under the standardized RECIST criteria used in cancer trials [Nucleo homepage]. By handling this quantitative grunt work, Nucleo aims to free up specialists for higher-order diagnostic reasoning and patient communication, while ensuring measurements are standardized and reproducible across a care team.
The Clinical Wedge: RECIST, Sarcopenia, and Speed
Nucleo's product strategy is a classic clinical wedge, targeting well-defined, measurement-intensive workflows where automation offers clear and immediate value. In oncology, treatment decisions and clinical trial eligibility often hinge on precise, consistent tracking of tumor size changes over time,the core of the RECIST framework. Manual segmentation and measurement are not only slow but prone to inter-observer variability. Similarly, assessing a patient's muscle mass (sarcopenia) from a CT scan is a strong prognostic indicator for chemotherapy tolerance and outcomes, but it is rarely done in routine practice due to the time required.
Nucleo's reported validation metrics speak directly to these pain points. The claim of 98% agreement with expert reads addresses the paramount concern of accuracy in a regulated field [Y Combinator]. The staggering 2,500x speed improvement is not just a technical boast; it translates to a scan analysis that takes seconds instead of hours, potentially collapsing the timeline from imaging to treatment planning [Y Combinator]. This combination allows the tool to slot into existing hospital workflows as a productivity aid, rather than demanding a radical overhaul of clinical practice.
Founders with a Foot in Two Worlds
The company's technical credibility is anchored by the backgrounds of its two founders, who bridge the worlds of academic medicine and applied industry AI.
- Angelica Iacovelli, the CEO, brings experience from Stanford and a track record that earned a spot on a Forbes profile list for YC founders [Forbes, 2026].
- Luca Pegolotti, the CTO, was a postdoctoral researcher in Stanford's Cardiovascular Imaging Research Group before joining Apple's Health AI team in Zürich [Luca Pegolotti personal website, 2026].
This blend of deep medical imaging research and experience at a tech giant known for its focus on user privacy and robust systems is a deliberate signal. It suggests a team capable of navigating the dual challenges of building clinically valid algorithms and engineering a secure, scalable platform fit for hospital integration.
Early Traction in Prestigious Hallways
For a company that only launched in Y Combinator's Fall 2025 batch, Nucleo has secured a notably impressive roster of early clinical partners. The startup reports its tools are already in use at institutions including Stanford Hospital, Cedars-Sinai, Weill Cornell Medicine, and UCI Health [Y Combinator]. These are not pilot agreements with community clinics, but deployments within leading U.S. academic medical centers known for their rigorous vetting of new technologies. This early adoption provides critical real-world validation and a funnel for refining the product alongside top-tier oncologists and radiologists.
The company is also generating revenue, according to its Product Hunt page, indicating these hospital relationships have progressed beyond research collaborations to commercial deployments [Product Hunt]. With an estimated $4 million in seed funding and a team of 2-10 employees, Nucleo is operating at the intersection of a promising clinical need and demonstrable early execution [LinkedIn].
The Road to Regulation and Reimbursement
The path forward, however, is paved with the complex realities of medical technology. While the 98% agreement statistic is compelling, the gold standard for adoption in this space is regulatory clearance from bodies like the U.S. Food and Drug Administration. Nucleo's current tools may be marketed as clinical decision support software, but any claim that moves toward autonomous diagnosis would likely trigger a FDA review process. The company has not yet publicized any regulatory submissions, which will be a key milestone to watch.
Competition is another factor. The field of AI-powered medical image analysis is crowded, with well-funded players like Nucleai and Brainomix also targeting oncology with advanced segmentation and biomarker discovery platforms. Nucleo's focused approach on core CT quantification tasks is a defensible starting point, but it will need to continually demonstrate superior accuracy, smooth integration, and a clear path to affecting patient outcomes to maintain its edge.
- Algorithmic drift. The performance of AI models can degrade over time or behave unexpectedly on scans from new hospital imaging equipment. Continuous monitoring and validation on diverse datasets are non-negotiable.
- Reimbursement motion. For widespread hospital adoption, Nucleo must prove its tool doesn't just save time but also improves care metrics in a way that justifies its cost, potentially influencing billing codes and insurance reimbursement.
- Clinical workflow fit. The most accurate tool fails if it disrupts a radiologist's established routine. Deep integration with major picture archiving and communication systems (PACS) is essential.
What Standard Care Looks Like Today
For a patient with a solid tumor, today's standard of care involves a radiologist manually scrolling through hundreds of CT scan slices, using software calipers to measure select lesions, and visually estimating body composition. This process is slow, subjective, and often inconsistently applied between different readers or even by the same reader at different times. The result can be delays in treatment decisions and variability in clinical trial data. Nucleo's bet is that by automating this quantitative foundation, it can bring a new level of speed, consistency, and depth to the care of every cancer patient facing a CT scan. The next twelve months will likely see the company working to convert its prestigious hospital partnerships into broader commercial contracts, while navigating the early stages of the regulatory pathway that will define its scale and impact in the years to come.
Sources
- [Y Combinator] Nucleo: Automated Cancer Diagnostics | https://www.ycombinator.com/launches/Okn-nucleo-automated-cancer-diagnostics
- [Nucleo homepage] Nucleo Research | https://nucleoresearch.com
- [Forbes, 2026] Angelica Iacovelli | https://www.forbes.com/profile/angelica-iacovelli/
- [Luca Pegolotti personal website, 2026] Luca Pegolotti | https://lucapegolotti.com
- [Product Hunt] Nucleo: Automated cancer diagnostics | https://www.producthunt.com/products/nucleo-research-inc
- [LinkedIn] Nucleo Research Company Page | https://www.linkedin.com/company/nucleoresearch