Tushar Lab

Resources

Open-source tools, datasets, and models from the lab — freely available to the research community.

iTrialSpace

iTrialSpace

Cohort-by-specification engine for lung-CT AI: declare a virtual trial by prevalence, nodule size, lobe distribution, and demographics; synthesize anatomically grounded CTs; evaluate CADe/CADx/VLMs under controlled conditions. 13 trial modes, 44K+ synthetic volumes, and a zero-shot VLM benchmark.

View on Hugging Face →
HAID

HAID

A curated dataset for health AI research and development, enabling training and evaluation of medical imaging models.

View on GitHub →
AI in Lung Health Detection and Classification Models

AI in Lung Health Detection and Classification Models

AI-driven models for lung health detection and classification, supporting early diagnosis and clinical decision-making.

View on Zenodo →