Indian Startup Dognosis Uses AI-Assisted Cancer Detection With Dogs to Achieve 90% Accuracy

3 Sources

Share

Bengaluru-based startup Dognosis combines canine olfactory abilities with AI to create a non-invasive cancer screening tool. Using 3D-printed helmets with sensors, 15 dogs analyze human breath samples with over 90% accuracy across seven major cancer types, backed by Accel India and collaborating with government medical institutions.

News article

Dogs Sniff Cancer With AI-Assisted Method in Bengaluru

Dognosis, a Bengaluru-based startup, is pioneering AI-assisted cancer detection by equipping dogs with 3D-printed helmets with sensors to analyze human breath samples

1

. The company uses artificial intelligence to analyze dogs' brain activity, respiration and body language, converting their reaction to scent into actionable data. Co-founder Akash Kulgod, 26, who studied cognitive science at the University of California, Berkeley, explains that dogs can perform thousands of sniffs per hour, with each sniff evaluating a sample

2

. The startup employs 15 dogs, including beagles, Malinois and Shepherd mixes, all working in customized data-gathering helmets that Kulgod describes as a doggy "Iron Man" suit.

Non-Invasive Cancer Screening Tool Addresses Early Cancer Detection in India

The non-invasive cancer screening tool addresses a critical gap in India's healthcare system where early cancer detection in India remains challenging. One in nine of India's 1.4 billion people are likely to develop cancer, making it a major public health concern

3

. Many patients receive late diagnoses only after the disease has advanced, significantly reducing survival rates. The testing method is straightforward: patients breathe into a cotton mask for approximately 10 minutes, which is then sealed and transported to the lab without any direct contact between patients and dogs. This approach could provide an easy and affordable first layer of screening to be deployed at scale, identifying potential cases for further testing.

Dognosis Achieves Over 90% Accuracy in Clinical Study

Dognosis recently published a study of more than 1,500 participants involving six hospitals in Karnataka state in the Journal of Clinical Oncology. The company achieved an accuracy rate of more than 90% across seven major types of cancer

1

. This performance is built on dogs' extraordinary olfactory capabilities—they possess around 300 million scent receptors compared to about 5 million in humans. Research indicates diseases can alter the chemicals released by the body, creating distinctive odors that trained dogs can detect. The startup, backed by venture-capital firms including Accel India, is collaborating with government medical institutions for its research as it pursues commercial approval.

Expert Opinions and Commercial Launch Plans

Cancer specialists in Bengaluru independent of the project have expressed cautious optimism about the technology. Santhosh Kumar Devadas, head of oncology at Ramaiah Memorial Hospital, stated the study is "promising, as an early signal," but emphasized the need for studies with much larger groups before making definitive conclusions

2

. Neelesh Reddy, a senior consultant oncologist at Manipal Hospitals, noted that "only time will tell how this technology will be useful to the actual patients." Dognosis hopes to launch commercially next year, which would make it the third company of its kind globally, after firms from Germany and Israel.

Training Methods and Operational Model

At a facility called "Sniffspace," dogs test human breath samples on platforms equipped with automatic feeders dispensing treats. Co-founder Itamar Bitan, 28, who spent four years in an Israeli special-forces canine unit, explains the dogs are trained using positive reinforcement to detect a "specific funky smell" for a reward

3

. Dogs exhibit varied reactions—some run directly to the feeder expecting rewards, some freeze, while others scratch the sample with excitement. The AI-assisted method to detect cancer relies on the machine learning system's ability to consistently interpret these diverse canine behaviors. Dognosis maintains a strong focus on work-life balance for its canine team, limiting work time to around 30-45 minutes daily, and lists each dog as an official "sniffer" on the company website alongside their photographs.

Public Health Impact and Future Implications

Dognosis aims to advance proactive and preventative medicine while enhancing human-canine communication. The low-cost screening approach could significantly impact public health in India by enabling mass screening programs that identify cancer cases earlier when treatment is most effective. The company now plans to test the technology in real-world programs to validate its clinical utility beyond controlled research settings. If successful at scale, this AI-assisted cancer detection system could serve as a model for other countries facing similar challenges with late diagnoses and limited access to expensive screening technologies. The convergence of canine biology, sensor technology, and machine learning represents a novel approach to addressing one of healthcare's most persistent challenges: detecting cancer before it becomes life-threatening.

Today's Top Stories

© 2026 TheOutpost.AI All rights reserved