Published
Senescence, measured where care already happens
Deep learning of nuclear morphology, applied to tissues and biofluids.
- Aging biology from biofluids
- Disease risk from routine images
- Treatment-linked senescence readouts
Health risk from image-based AI.
Senescope reads subtle signals in images of routine samples,
then turns that biology into risk and treatment insight.
- Nature Aging 2022
- The Lancet Digital Health 2024
- Nature Aging 2024
- Breast Cancer Research 2025
- GeroScience 2025
01 — Scope
Senescence signals, turned into actionable risk.
The company is built on key biological signals underlying aging and many chronic diseases.
02 — Applications
Where the signal has been tested.
-
01
Aging and place
Senescence from blood smears: aging and altitude shift cellular appearance.
-
02
Future breast cancer risk
Senescence-associated nuclear morphology in breast tissue from healthy donors, associated with a later cancer diagnosis.
-
03
Benign breast disease
The same class of model on biopsy images from women with benign breast disease, aimed at future cancer risk.
-
04
COPD, in sputum
Senescence assessment inside a randomized trial of nicotinamide riboside, based on sputum.
03 — Method
From a slide to a risk readout.
01
Collect
Standard clinical material. Biopsies, blood smears, biofluids. No consumable required.
02
Read
Models recognize senescence-linked nuclear morphology and image-based signals.
03
Use
Risk context for clinicians, set next to the scores and markers they already trust.
04 — Research
Selected publications.
Peer-reviewed work from our scientific team.
Nuclear morphology is a deep learning biomarker of cellular senescence
Neural networks read senescence from nuclear shape in culture and in tissue. Rates rise with age and track health outcomes in medical records.
Deep learning assessment of senescence-associated nuclear morphologies in mammary tissue from healthy female donors to predict future risk of breast cancer
In a retrospective cohort, senescence scores on normal breast biopsies were associated with a later diagnosis. Combining models improved on the Gail score alone.
Effect of nicotinamide riboside on airway inflammation in COPD: a randomized, placebo-controlled trial
A randomized trial in COPD. Our team contributed senescence assessment in sputum alongside the inflammatory endpoints.
Cellular senescence predicts breast cancer risk from benign breast disease biopsy images
Senescence scored on biopsy images from women with benign breast disease, as a marker of later breast cancer risk.
Deep learning reveals diverging effects of altitude on aging
Blood smears, read with deep learning, showing that aging and altitude affect cellular appearance.
About Senescope
Our mission is to enhance lives by empowering clinicians and patients with actionable insights. Founded by a team of healthcare entrepreneurs and AI experts, we leverage our innovative AI platform to analyze complex biological data, uncovering subtle patterns that enable risk prediction, often years before symptoms emerge. Using standard clinical samples, our automated technology rapidly quantifies biomarkers of aging and disease, making advanced diagnostics widely available.
Senescope is transforming health risk assessment by combining advanced artificial intelligence with deep biological expertise. Our scalable technology enables earlier disease detection, more precise risk assessment, and personalized treatment guidance, helping optimize outcomes while minimizing unnecessary interventions and side effects. By turning routinely collected clinical data into meaningful insights, we aim to advance a new generation of accessible precision medicine.
Summaries on this page describe published research. They are not a claim that a Senescope product is cleared to diagnose, treat, or prevent disease, and they are not medical advice.
Contact
Bring a cohort or a question.
Partnerships, studies, and pilots. Senescence projects and broader clinical risk work both belong here.
info@senescope.com