Nucleo
Nucleo Research, Inc. · AI Assistant
Nucleo is an AI platform from Nucleo Research that automates CT scan analysis for oncology care. It reads an imported scan and extracts the metrics cancer teams use most, including body composition and sarcopenia, tumor lesion sizing, and target versus non-target lesion classification under RECIST criteria. The company says its segmentation runs about 2,500x faster than manual work, with 98% agreement between Nucleo and medical experts in its validation studies. It's aimed at hospitals and clinical research teams rather than individual consumers, and there's no self-serve sign-up for someone who just wants to poke around the platform on their own.
About Nucleo
What Is Nucleo
Nucleo is a clinical software product focused on one narrow job: turning a raw CT scan into the oncological measurements a care team needs, without a radiologist hand-tracing every slice. The platform combines automated segmentation with measurement and classification tools, and then it returns structured results a clinician can review before anything reaches a patient's file.
The problem it targets is time. According to Nucleo Research's Y Combinator profile, a typical American cancer patient waits roughly 9 to 11 weeks between diagnosis and the start of therapy. The company argues that automating the scan-reading steps is one way to compress that window. Instead of a display tool, Nucleo behaves like an assistant that does the repetitive measurement work first.
The biggest limit is access. Nucleo isn't a self-serve app you can download and try tonight. It's sold to hospitals and research groups, so a solo user or a small clinic without an existing imaging workflow won't get far. There's no public pricing page, and no consumer sign-up. So who ends up using it? Mostly teams that already run volume through a CT scanner every day.
Getting Started
- Book a demo through the Nucleo Research site to discuss your imaging workflow and volume.
- Set up your organization's access with the Nucleo team, since the product runs as a clinical deployment rather than a public download.
- Import a CT scan into the platform.
- Let the AI run segmentation and measurement, then review the body composition, lesion size, and RECIST classification output.
- Export or record the measurements into your existing reporting process.
Product Information
A quick look at Nucleo's pricing, supported platforms, and performance.
Best for
The users, tasks, and scenarios where this tool fits best.
Users
- Oncology care teams
- Clinical research groups
- Body composition researchers
Tasks
- Reading oncology CT scans
- Staging and tracking lesions
- Reducing measurement variance
Scenarios
- High-volume imaging departments where manual segmentation is the bottleneck between scan and treatment decision.
- Multi-site studies that need the same measurement logic applied everywhere.
- Research on cancer treatment side effects, where muscle and fat changes need to be tracked over time.
Key features
Automated CT Segmentation
Nucleo's core function is automatic segmentation of CT scans. It replaces the slice-by-slice tracing that manual analysis requires. Per Nucleo Research, this runs about 2,500x faster than the manual process. For a clinician, that's the difference between a task that shapes the day and one that runs in the background.
Body Composition and Sarcopenia Assessment
The platform detects and quantifies fat and muscle mass automatically, and it flags sarcopenia. Cancer teams care about this because muscle loss affects how patients tolerate treatment, which is exactly the kind of slow, hard-to-spot change that gets missed when nobody stops to measure it. The company reports state-of-the-art performance on sarcopenia detection in its own evaluation.
Tumor Lesion Sizing
Nucleo measures tumor lesions in a CT scan and returns consistent numbers. Measurement consistency matters more than raw speed here. When sizing shifts between scans because two people traced it differently, it's hard to tell whether the tumor changed or the reading did. That's a real problem for treatment decisions.
RECIST Lesion Classification
Lesions get classified as target or non-target according to RECIST criteria. That's the standard oncology trials and many treatment decisions use. Automating that step means the classification follows a fixed rule set instead of a reader's judgment call on a busy day, and in a trial setting that consistency can matter as much as the measurement itself.
Expert-Level Agreement
In validation studies cited by Nucleo Research, measurements from the platform agreed with medical experts 98% of the time. That number comes from the company. Treat it as a vendor figure, not an independent benchmark. It's still the claim most buyers will want to test.
Clinical Workflow Integration
Nucleo is built to slot into an existing oncology workflow rather than replace it. A doctor imports the scan and the software returns metrics. That's a deliberately small footprint, which lowers the change-management burden on a department already stretched thin. It also means adoption depends on how well it plays with the systems a hospital already owns.
Pros and cons
Pros
- Cuts segmentation from a manual job to an automatic one, which is the slowest step in many scan-reading workflows.
- Covers three high-value oncology measurements in one tool: body composition, lesion sizing, and RECIST classification.
- Reports strong agreement with expert readers, so the output is designed to be reviewed rather than blindly trusted.
- Built by a team with real research backgrounds in medical AI, including work that ended up in NVIDIA's scientific libraries.
Cons
- There's no public pricing and no self-serve trial, so you can't evaluate it without going through a sales conversation.
- It's aimed at institutions. That means individual clinicians and small practices are effectively priced out of even testing it.
- The company's performance numbers are its own, and independent validation isn't easy to find, so claims should be verified in your own data.
- Details on API access and EHR integration aren't published. Teams that need automated pipelines will have to ask directly.
Frequently asked questions
Nucleo automates the analysis of oncology CT scans. It segments the scan, measures body composition and tumor lesions, and classifies lesions as target or non-target under RECIST criteria. In practice, that means a scan goes in and a set of measurements comes out that a clinician can review against their own read.
Related content
Explore related tools, skills, and articles for Nucleo.
Nucleo Alternatives
Agibot
Agibot · Productivity · AI Assistant · ChatbotAgibot is a personal AI agent for Mac that keeps running after you close the window, runs routines on a schedule, and works from Telegram or Slack with your own API keys.
Foley
Hanamori Labs, LLC · Voice & Language · Productivity · AI AssistantFoley is a voice to-do list that turns a spoken sentence into a filed task, complete with project, date and time, then helps you plan the day around what is already there.
Ghost Core
Ghost · Productivity · AI AssistantGhost Core is a $3,499 screenless personal AI computer that runs local AI models on its own hardware, builds context from your apps and devices, and acts without waiting for a prompt.