Medical Image De-Identification Automation and Validation
The theme of June’s NCI Imaging and Informatics Community Webinar will focus on DICOM medical image de-identification (MIDI). Patient privacy rules require the removal of protected health information (PHI) prior to sharing medical images publicly. With the growing volume of imaging data, manually removing PHI is inefficient. In this presentation, speakers will disclose how their teams assessed the accuracy of automated de-identification algorithms and cloud services in removing PHI.
“A DICOM Data Set for Evaluation of Medical Image De-Identification” |1:00–1:20|
Dr. Fred Prior, the Chair of the Department of Biomedical Informatics at the University of Arkansas for Medical Sciences, will share the Cancer Imaging Archive (TCIA) team’s efforts to develop a DICOM data set that can be used to evaluate the performance of de-identification algorithms.
“Medical Image De-Identification Using Cloud Services” |1:20–1:40|
Dr. Benjamin Kopchick and Ms. Dina Mikdadi from the Deloitte Biomedical Data Science team will present on the use of a cloud service for automated MIDI. Their team tested the Google Cloud Platform’s Healthcare API service leveraging data sets with synthetic PHI generated by the TCIA team.
This event is free and open to the public.
Dr. Prior is the Professor and Inaugural Chair of the Department of Biomedical Informatics and Professor of Radiology at the University of Arkansas for Medical Sciences (UAMS).
Dr. Kopchick is a member of the Biomedical Data Science team at Deloitte. His current focus is on machine learning and artificial intelligence using medical images.
Ms. Mikdadi is a data scientist at Deloitte focused on clinical, imaging, and bioinformatics serving clients in the life science and healthcare space. Much of Ms. Mikdadi’s work lies at the intersection of science and technology, testing and validating cloud-native, cutting-edge solutions (AI/ML) for biomedicine.
- Cancer Research Data Commons and Other NCI Infrastructures in Support of Data ScienceSeptember 19, 2021AttentiveChrome: Deep Learning for Predicting Gene Expression from Histone ModificationsSeptember 22, 2021“Le Grand et Le Petit”: Splicing Factors SF3B1 and SUGP1 and Their Cancer Mutations Leading to Aberrant Acceptor UsageSeptember 22, 2021The Future of Clinical Trial Data Sharing.... The Art of The PossibleSeptember 23, 2021Genomic Data Commons Single Cell RNA-Seq SupportSeptember 27, 2021Virtual Workshop on Next-Generation Sequencing and Radiomics: Resource Requirements for Acceleration of Clinical Applications Including AISeptember 29, 2021 - September 30, 2021