IIT Indore develops AI algorithms for early cancer detection:Tools show high accuracy in breast, cervical screening

Researchers at IIT Indore have developed advanced Artificial Intelligence (AI) algorithms that can detect breast and cervical cancers in medical images with high accuracy, offering a potential solution to India’s shortage of trained radiologists. Breast and cervical cancers remain among the leading causes of cancer-related deaths among women in India. Early detection through imaging is critical, but limited access to specialists, especially in rural areas, often delays diagnosis. Advanced algorithms for breast cancer detection The research has been led by Prof. Kapil Ahuja at the Math of Data Science and Simulation (MODSS) Lab in the Department of Computer Science and Engineering. His team includes Ph.D. scholar Saurabh Saini, former postdoctoral researcher Dr. Deepti Tamrakar, and former doctoral student Dr. Aditya A. Shastri. For breast cancer screening, the team analyzed mammogram images, focusing on subtle texture patterns that become irregular when cancer develops. They introduced a specialized method called the Histogram of Oriented Texture (HOT) descriptor, which studies fine texture directions to distinguish between healthy and cancerous tissues even in dense breast cases. Deep learning model for cervical cancer For cervical cancer, where colposcopy images are examined, texture alone is not sufficient. Doctors must evaluate color, edges, shapes and structural patterns simultaneously. To address this, the researchers developed a deep learning model known as Block-Fused Attention-Driven Adaptively-Pooled ResNet (BF-AD-APResNet). This model captures both detailed and abstract features, improving the system’s ability to identify suspicious regions in images. The algorithms were tested on four international datasets and achieved accuracy levels in the mid-to-high nineties, outperforming several existing methods reported in scientific studies. Technology-driven solutions for healthcare challenges Prof. Suhas Joshi, Director of IIT Indore, said the research reflects the institute’s commitment to addressing critical healthcare challenges through technology. “This research reflects the institute’s commitment to developing technology-driven solutions for critical national healthcare challenges. The team also ensured that these AI systems clearly explain how they arrive at their decisions. This transparency has helped doctors understand and trust the results,” he said. Prototype for Indian patients under development Prof. Kapil Ahuja noted that the current models were largely trained on global datasets dominated by patients of European ancestry. “Our AI algorithms have been trained on global datasets predominantly from patients with European ancestry. We are currently working on developing a prototype that would be trained and subsequently used on Indian patients,” he said. He added that the team has partnered with Dr. Renu Dubey Sharma, senior oncologist at HCG Cancer Hospital, Indore, for clinical collaboration. The initiative is supported by the DRISHTI Cyber Physical Systems Foundation at IIT Indore as part of a lab-to-market effort. Prof. Ahuja further said the team plans to extend the AI framework to other major cancers, including thyroid, lung, oral, colorectal and esophageal cancers, which are among the leading causes of cancer-related deaths in India.