PGI Chandigarh doctors develop AI model to detect gallbladder cancer using ultrasound
Chandigarh- In a significant development, a multidisciplinary team of researchers at the Post Graduate Institute of Medical Education and Research (PGIMER), Chandigarh, has developed an Artificial Intelligence (AI)-based model that accurately detects gallbladder cancer using routine ultrasound images.
The team was led by Dr Pankaj Gupta from the Department of Radiodiagnosis and Imaging. The pioneering study has been published in “The Lancet Regional Health – Southeast Asia”, marking a major breakthrough in the early diagnosis of gallbladder cancer.
The PGIMER team has developed a specialised model that closely mirrors real-world clinical practice. Unlike conventional AI tools, which typically analyse only a single image, this novel model simultaneously analyzes multiple ultrasound scans of the same patient to provide a definitive "cancer" or "non-cancer" diagnosis in a single step, while also generating a corresponding mathematical probability score, as per the TOI report.
To ensure a widespread impact within the medical field, the team's computer scientist, Kartik Bose, under the guidance of Dr Gupta, developed a user-friendly and free computer application, making this technology immediately available to researchers and frontline clinicians across the country.
The model's diagnostic accuracy was successfully verified using patient data collected from four major hospitals across Northern India.
The PGIMER team is now planning to validate this model through a prospective clinical trial and integrate this software directly into the hospital's routine ultrasound workflow.
Most importantly, this system highlights the precise visual regions that influenced its decision, thereby helping local doctors validate these findings.
In Northern India, particularly among women, gallbladder cancer poses a significant threat to public health, with common gallstones serving as a primary risk factor. Although affordable and radiation-free ultrasound machines are widely available in rural areas, small and remote health centres typically lack the specialised expertise required to identify the early and subtle symptoms of cancer.
Consequently, most cases are detected only when the disease has advanced significantly, at which stage treatment options remain very limited.
