Phillip Ming-Da Cheng

Phillip Ming-Da Cheng, MD is a Professor of Clinical Radiology and Medical Director of Radiology at Norris Hospital, part of the Keck School of Medicine of the University of Southern California. His clinical work focuses on abdominal imaging and image-guided interventions at the Norris Comprehensive Cancer Center.

Dr. Cheng's primary research interests lie at the intersection of radiology and artificial intelligence. He has pioneered work in applying machine learning and informatics to solve practical problems in radiology, with a particular focus on abdominal imaging. His research spans several key areas including deep learning for medical image analysis, natural language processing for radiology reports, CT dose monitoring and optimization, and software tools to improve radiology workflow. His highly-cited educational articles in Radiographics have become essential resources for radiologists navigating the AI revolution in medical imaging.

• RSNA 2016 Certificate of Merit for research on Transfer Learning with Convolutional Neural Networks
• RSNA 2015 Magna Cum Laude award for ReportDiff: Analyzing Attending Edits of Radiology Trainee Reports
• RSNA 2013 Cum Laude award for PrelimCheck: Software to Facilitate Follow-Up of Resident Preliminary Reports
• 3rd place entry in the RSNA Pneumonia Detection Machine Learning Challenge (2018)

Dr. Cheng leads a productive research group that has developed numerous open-source tools addressing real-world challenges in radiology departments. His team has created practical software solutions including NeedlePath for CT-guided procedures, ReportDiff for analyzing resident report edits, PrelimCheck for tracking preliminary reports, RadQRCode for teaching file metadata management, and DoseRetriever for CT dose monitoring. These tools demonstrate his commitment to improving clinical workflow, education, and patient safety through technology innovation.