Keep up with the latest news from the NCI Center for Biomedical Informatics and Information Technology (CBIIT) and the data science communities.

Data scientists, informaticists, and medical physicists are invited to develop the best, most generalizable models, algorithms, and approaches for breast density estimation using image-based distributed or federated learning.

IMPROVE focuses on improving deep learning models to predict the efficacy of cancer treatments. The research community, including data scientists and informaticists, is asked to respond to an RFI for creating protocols to evaluate model performance by April 15, 2022, at 5:00 p.m. ET. Additionally, they are encouraged to respond to an RFP for improving model comparison by May 9, 2022.

Do you work on a project funded by an active NIH grant? Is this project rooted in artificial intelligence, machine learning, and/or ethics components? Apply to this Notice of Special Interest by March 31, 2022.

Over the past several years, scientists have made exciting advances in the realm of artificial intelligence (AI) and its integration into the cancer imaging field. New AI tools could make cancer imaging faster, more accurate, and more informative. But are they ready for real-world implementation?

Cancer researchers, check out this opportunity to receive supplemental support for collaborations that bring together expertise in biomedicine, data management, and artificial intelligence/machine learning (AI/ML)! Improve the AI/ML-readiness of data generated from NIH-funded research that will then be shared through repositories, knowledge bases, or other data resources.

NCI’s Office of Cancer Clinical Proteomics Research’s new blog highlights recent findings from scientists in the Clinical Proteomic Tumor Analysis Consortium. It describes a proof-of-concept approach to identifying fraudulent data in biological data sets.

In RAS-related diseases, such as cancer, mutations in the RAS genes or their regulators render RAS proteins persistently active. Investigating RAS activation events is challenging when using conventional techniques. An unprecedented multiscale platform is using machine learning to change that.

NCI’s Center for Cancer Research invites applicants with image processing, machine learning, and deep learning experience to be considered for a federal image bioinformatics scientist position supporting the Artificial Intelligence Resource. The successful candidate will develop and implement automated imaging and data processing workflows to analyze large image data sets generated by confocal microscopes.

Drs. Emily Greenspan and Eric Stahlberg of NCI’s CBIIT and Frederick National Laboratory for Cancer Research, respectively, recently contributed to an article, “Digital twins for predictive oncology will be a paradigm shift for precision cancer care,” published in Nature Medicine. The commentary examines the vision that members of NCI’s Envisioning Computational Innovations for Cancer Challenges (ECCIC) community have for developing cancer patient digital twins. Such a platform could revolutionize how clinicians and policymakers approach cancer care and further advance precision medicine.

In a recent podcast, NCI leaders from CBIIT and the Small Business Innovation Research Development Center shared how technological developments have enhanced cancer research and have helped usher in new diagnostics, treatments, and patient care.