This page shows the documentation available for CHAVI.


One of the unique aspects of the CHAVI databank is an unified, relational, broad, common database which is used to store de-identified demographic, clinical, pathological, molecular biological, treatment and outcome data for all patients. This database can be queried flexibly and therefore is a powerful tool for exploring image sets across cancer sites. This feature allows an interested researcher to potentially interrogate radiological images in a cancer site agonistic fashion.

De-identification System

CHAVI was built ground up to ensure protection of patient privacy. In order to ensure correct de-identification of DICOM and tabular clinical data a custom de-identification software has been developed which ensures that data is de-identified while retaining the longitudinal temporal integrity.

Information about CHAVI

CHAVI - The Comprehensive Archive of Imaging is the first imaging biobank from India with an exclusive focus on Oncological Imaging. CHAVI was designed as a research collaboration between Tata Medical Center, Kolkata and Indian Institute of Technology, Kharagpur. Researchers, academicians and industry are welcome to collaborate and use the wealth of imaging data available in CHAVI subject to our terms and conditions of use.


The motivation behind CHAVI is to develop a image biobank in India which not only is available across the country but is also a foundation for future collaborative research efforts amongst major cancer institutes nationally.