From e-commerce to cancer diagnosis, AI start-up bets big on image-understanding

Developing artificial intelligence markers at the University of Manchester, the UK, as a student, Atul Rai realised he wanted to be a disruptor — to build applications with AI that would help create sophisticated systems. Many years later, Rai is living his dream, working with artificial intelligence to help locate cancer cells.

Rai is the co-founder and CEO of Staqu, a start-up that aims to revolutionise the fashion e-tail, mobile and e-commerce industries with its bidirectional image-understanding technology, as well as engage with AI algorithms to benefit the healthcare sector.

“Back in 2008, AI was not popular with researchers,” says Rai. He reminisces the initial days spent in understanding how AI was set to create new benchmarks in almost every sector.

“I was working on an algorithm that would help physically disabled people control computers without touching them — a system that could recognise human gestures and provide a new way for people with physical disabilities to interact with computers.”

Rai went on to publish a paper on his research in France in 2010. Today, the same research on image detection has provided a strong foundation to detect cancerous cells at Staqu. Rai insists diagnosing cancer is about to get more accurate with the help of AI.

Digitising images and using machine-learning is helping the firm make more accurate diagnosis, says Rai, adding that researchers are using a machine-learning algorithm that has been used for a range of applications, including speech recognition and image recognition.

“70 per cent of data is in the form of images. Few can extract data from images. We have algorithms that can do it. Certain cells in the human body have a cancerous tendency, and this data is very sensitive. We are researching it,” Rai says.

With a Master’s degree in AI from the University of Manchester, Rai had worked as a Research Associate at University of Szeged, Hungary, and as a Research Consultant at the University of Hertfordshire, the UK. He had earlier worked on a collaborative mobile computer vision project to develop a 3D vision model for mobile devices.

Talking of Staqu co-founders Chetan Rexwal, Anurag Saini and Pankaj Sharma, Rai says. “Both Saini and Sharma are inclined towards AI, while Rexwal is skilled in mobile technology.

“Two big trends prompted us to team up. Smartphones cameras have triggered image-based content on the internet and everywhere else. We realised that businesses would increasingly need deep-learning technologies to understand and analyse visual content.”

The firm uses AI, deep-learning and image-search technologies that powers fashion e-tailers to simplify catalogue search, drive customer engagement and get higher conversions. The same technology is helping provide more accurate disease diagnosis.

COMMENT NOW