Researchers at the Post Graduate Institute of Medical Education and Research (PGIMER) in Chandigarh have achieved a clinical breakthrough by introducing a novel gallbladder cancer detection AI model. Specifically, this artificial intelligence tool utilizes routine, radiation-free ultrasound images to accurately identify early malignant signs. Consequently, this innovation offers an accessible diagnostic option for regions with limited medical infrastructure.

Gallbladder cancer remains a major public health menace in north India, particularly among women. Unfortunately, common gallstones serve as a primary risk factor for this highly aggressive disease. Since early malignancy signs are subtle, smaller peripheral centers often miss them due to a lack of specialized radiologists. Consequently, clinicians often diagnose these patients at advanced stages, which severely restricts treatment options.

How the Gallbladder Cancer Detection AI Works

Specifically, the PGIMER team designed a unique model that mirrors real-world clinical workflows. Unlike conventional systems, this software evaluates multiple ultrasound scans from a single patient simultaneously. Furthermore, this multi-image analysis delivers a unified "cancer" or "non-cancer" diagnosis along with a mathematical probability score. Crucially, the system highlights the exact visual areas that influenced its decision. This visual feedback allows local medical officers to quickly verify the machine's findings.

Multi-Center Validation and Free Global Access

Led by Dr. Pankaj Gupta, this pioneering study appeared in "The Lancet Regional Health – Southeast Asia". For this reason, researchers successfully tested the model on clinical data from four prominent north Indian hospitals. Additionally, team computer scientist Kartik Bose developed a user-friendly, free-access computer application based on this research. Consequently, researchers and frontline clinicians worldwide can immediately access this technology. Ultimately, the PGIMER team plans prospective clinical trials to integrate this software directly into routine hospital workflows.

Frequently Asked Questions

Q1: How does the new AI model differ from standard medical AI tools?

Unlike conventional systems that look at single-view images, this model simultaneously reviews multiple ultrasound images from the same patient to generate a single diagnostic probability score.

Q2: Why is early gallbladder cancer detection particularly challenging in rural India?

Although basic ultrasound equipment is highly accessible, smaller rural health centers often lack the specialized radiologists required to identify subtle, early signs of malignant tumors.

Disclaimer: This content is for informational and educational purposes only. It does not constitute medical advice or replace professional judgment. Refer to the latest local and national guidelines for clinical practice.

References

1. PGI combines AI and ultrasound for early gallbladder cancer detection - ETHealthworld


2. Gupta P, Bose K, Mudgil P, et al. Multiple instance learning approach for automated gallbladder cancer detection using ultrasound imaging: multi-center validation of a deep learning model with the public dataset contribution. The Lancet Regional Health – Southeast Asia. 2026;47:100737. doi:10.1016/j.lansea.2026.100737