Advanced Diagnostic System: We have developed an AI-based Lung Cancer Diagnostic System that integrates PET/CT scan analysis, histopathological information, mutation analysis, and clinical data. This system utilizes deep learning algorithms and image recognition techniques for accurate and comprehensive diagnoses.

Published Research: Our research has been published in reputable medical journals, including Lancet Regional Health, Journal of Clinical Oncology, and Annals of Oncology. These publications demonstrate the effectiveness of our diagnostic system in transforming lung cancer care.

Diverse Dataset: We have a diverse dataset of 2000 Indian lung cancer patients, including annotated PET/CT scans, genomics/mutational data, histopathological information, clinical data, and diagnoses. We continuously expand the dataset to improve the accuracy of our diagnostic system.

Collaborations with Healthcare Organizations: We collaborate with renowned healthcare organizations such as Rajiv Gandhi Cancer Institute (RGCI), Max Healthcare, Delhi State Cancer Institute, Apollo Hospitals, and Medanta. These collaborations provide access to patient data, imaging facilities, and expertise, fostering a multidisciplinary approach to research.

Iterative Model Refinement: We continuously refine our diagnostic system based on feedback from healthcare professionals, patients, and field testing. Our goal is to enhance accuracy, efficiency, and user experience, optimizing patient outcomes.

Clinical Trials and Real-World Deployment: We plan to conduct larger-scale clinical trials in collaboration with healthcare institutions worldwide to evaluate the system's performance. Our aim is to deploy the diagnostic system across 300+ hospitals and oncology settings in India.

Mitigating Bias and Equitable Use: We prioritize data diversity, inclusivity, and performance across patient demographics. Our research focuses on mitigating bias through diverse data collection, rigorous preprocessing, and anonymization protocols. We strive for equitable performance across subgroups, providing accessible diagnostics for all.