Dogs Are Teaching Machines to Sniff Out Cancer

In a proof-of-concept study, researchers used dogs’ diagnoses of prostate cancer to inform a machine learning algorithm with the goal of one day detecting cancers with canine-level accuracy.

asher jones
| 5 min read
dogs, olfaction, smell, prostate cancer, volatiles, diagnosis, disease, canine

Register for free to listen to this article
Listen with Speechify
0:00
5:00
Share

ABOVE: Midas sniffs a urine sample.
EMMA JEFFERY, MEDICAL DETECTION DOGS

With their legendary sense of smell, dogs are adept at identifying the characteristic scents of cancers from breath, urine, and poop. But with trained cancer-sniffing pups in short supply, animals are unlikely to become widely available for routine diagnostics. Instead, Andreas Mershin wants man’s best friend to teach machine learning algorithms to sniff out diseases, and he plans to put this technology into your pocket. Mershin, a research scientist at the MIT Center for Bits and Atoms, says his eventual goal is to build electronic nose capability into smartphones.

The detection of a cancer signal by electronic noses isn’t a new concept, but those that have been developed so far still can’t match the accuracy of dog’s, says Mershin. To get closer to that ability, Mershin and his interdisciplinary team establish a proof-of-concept method for the integration of canine olfaction ...

Interested in reading more?

Become a Member of

The Scientist Logo
Receive full access to more than 35 years of archives, as well as TS Digest, digital editions of The Scientist, feature stories, and much more!
Already a member? Login Here

Keywords

Meet the Author

  • asher jones

    Asher Jones

    Asher is a former editorial intern at The Scientist. She completed a PhD in entomology from Penn State University, and she was a 2020 AAAS Mass Media Fellow at Voice of America. You can find more of her work here.

Share
May digest 2025 cover
May 2025, Issue 1

Study Confirms Safety of Genetically Modified T Cells

A long-term study of nearly 800 patients demonstrated a strong safety profile for T cells engineered with viral vectors.

View this Issue
iStock

TaqMan Probe & Assays: Unveil What's Possible Together

Thermo Fisher Logo
Meet Aunty and Tackle Protein Stability Questions in Research and Development

Meet Aunty and Tackle Protein Stability Questions in Research and Development

Unchained Labs
Detecting Residual Cell Line-Derived DNA with Droplet Digital PCR

Detecting Residual Cell Line-Derived DNA with Droplet Digital PCR

Bio-Rad
How technology makes PCR instruments easier to use.

Making Real-Time PCR More Straightforward

Thermo Fisher Logo

Products

fujirebio-square-logo

Fujirebio Receives Marketing Clearance for Lumipulse® G pTau 217/ β-Amyloid 1-42 Plasma Ratio In-Vitro Diagnostic Test

The Scientist Placeholder Image

Biotium Launches New Phalloidin Conjugates with Extended F-actin Staining Stability for Greater Imaging Flexibility

Leica Microsystems Logo

Latest AI software simplifies image analysis and speeds up insights for scientists

BioSkryb Genomics Logo

BioSkryb Genomics and Tecan introduce a single-cell multiomics workflow for sequencing-ready libraries in under ten hours