Context: 

• The Director of Tata Memorial Hospital(TMH), India’s largest Cancer treatment centre, expects the incidence of cancer to double, from 13 lakhs to 26 lakhs annually in the next decade.
• Growth in the number of specialists handling cancer cases cannot match with this jump in cases and here comes the role of Artificial Intelligence(AI) in early detection and control.
• TMH  had established a ‘Bio-Imaging Bank’ for cancer, utilising deep learning to craft a cancer-specific tailored algorithm that aids in early-stage cancer detection.

How does AI help in early cancer detection?

• The project’s overarching goal is to create a robust repository encompassing radiology and pathology images, intricately linked with clinical information, outcome data, treatment specifics, and additional metadata. 
• This comprehensive resource is strategically designed for the training, validation, and rigorous testing of AI algorithms.
• AI contributes to this process by emulating the human brain’s information processing. It analyses radiological and pathological images, learning from extensive datasets to recognise unique features associated with various cancers. 
• This process facilitates early detection by identifying tissue changes and potential malignancies.
• This approach allows TMH to develop algorithms for different tumours, assess treatment responses directly from images, and avoid unnecessary chemotherapy for predicted non-responders, offering clinical utility. 
• Leveraging the biobank, predictive and diagnostic models are developed using thousands of breast cancer images, undergoing AI and ML analysis with technical support from partners like IIT-Bombay. 
• The multi-institution project is funded by the Union government’s Department of Biotechnology, in collaboration with IIT- Bombay, Rajiv Gandhi Cancer Institute and Research Centre (RGCIRC)-New Delhi, AIIMS- New Delhi, and PGIMER-Chandigarh.

Other Applications:

• Alongside the creation of the data- base, the project also  involves the testing of several Al algorithms using the data to address medically relevant tasks such as screening for lymph node metastases, nucleus segmentation and classification, biomarker prediction(Eg human papillomavirus (HPV) infection in oropharyngeal (throat) cancer, and epidermal growth factor receptor (EGFR) mutation in lung cancer) and therapy response prediction.

The use of AI tools raises debates about potential replacement of human radiologists, facing regulatory scrutiny and resistance from some doctors and health institutions. Taking a comprehensive approach to address these concerns can help in effective use of AI in Cancer control.