Our lab has secured $20,000 from Google and $15,000 in support from OpenAI to accelerate our work
Read AnnouncementCRASH Lab · Ashoka University
Active research projects, benchmarks, and accepted papers — with evaluation grounded in clinical reality, not presentation-friendly metrics alone.
The flagship benchmark establishing the current human-AI gap in high-stakes radiology reasoning.
by Dr. Suvrankar Datta et al.RSNA 2025 Cutting Edge Oral Presentation2025Benchmarkradiology, benchmark, multimodal AI
Evaluation framework for autonomous report-writing systems in head CT and chest radiography.
by Dr. Suvrankar Datta et al.RSNA 20252025Paperreport generation, NLP, radiology
Human factors and workflow design principles for responsible AI adoption in radiology.
by Dr. Suvrankar Datta et al.MICCAI Workshop 20252025Paperhuman AI collaboration, radiology
Blueprint for privacy-preserving clinical data collaboration across Indian institutions.
by Dr. Suvrankar Datta et al.NeurIPS Datasets and Benchmarks 20252025Paperdata commons, federated learning
Evidence on why diagnostic AI degrades when moved into Indian clinical environments.
by Dr. Suvrankar Datta et al.RSNA 20252025AbstractIndia healthcare, benchmark, computer vision
Governance framework for evaluating responsibility in medical AI misdiagnosis scenarios.
by Dr. Suvrankar Datta et al.Health AI Policy Forum 20252025Talkgovernance, policy
We began securing support from leading national bodies, including ANRF, DST, and the IndiaAI Mission, to advance responsible healthcare AI research.
Supported by Koita Foundation
Funding for the lab is provided by the Koita Foundation and Google, alongside contributions from institutional partners and private philanthropy
