Clinical Focus

  • Body Imaging
  • Oncologic Imaging
  • Cardiovascular Imaging
  • Radiology and Pathology Integration
  • Diversity, Equity and Inclusion

Academic Appointments

  • Clinical Assistant Professor, Radiology

Honors & Awards

  • Chief, Body Imaging Fellowship, Stanford University (7/2018-6/2019)

Professional Education

  • Fellowship: Stanford University Advanced Cardiovascular Imaging Fellowship (2020) CA
  • Board Certification: American Board of Radiology, Diagnostic Radiology (2019)
  • Fellowship: Stanford University Body Imaging Fellowship (2019) CA
  • Residency: Harbor UCLA Medical Center Radiology Residency (2018) CA
  • Internship: Arrowhead Regional Medical Center Internal Medicine Residency (2014) CA
  • Medical Education: Boston University School of Medicine (2013) MA

All Publications

  • Automated Identification and Measurement Extraction of Pancreatic Cystic Lesions from Free-Text Radiology Reports Using Natural Language Processing. Radiology. Artificial intelligence Yamashita, R., Bird, K., Cheung, P. Y., Decker, J. H., Flory, M. N., Goff, D., Morimoto, L. N., Shon, A., Wentland, A. L., Rubin, D. L., Desser, T. S. 2022; 4 (2): e210092


    Purpose: To automatically identify a cohort of patients with pancreatic cystic lesions (PCLs) and extract PCL measurements from historical CT and MRI reports using natural language processing (NLP) and a question answering system.Materials and Methods: Institutional review board approval was obtained for this retrospective Health Insurance Portability and Accountability Act-compliant study, and the requirement to obtain informed consent was waived. A cohort of free-text CT and MRI reports generated between January 1991 and July 2019 that covered the pancreatic region were identified. A PCL identification model was developed by modifying a rule-based information extraction model; measurement extraction was performed using a state-of-the-art question answering system. The system's performance was evaluated against radiologists' annotations.Results: For this study, 430426 free-text radiology reports from 199783 unique patients were identified. The NLP model for identifying PCL was applied to 1000 test samples. The interobserver agreement between the model and two radiologists was almost perfect (Fleiss kappa = 0.951), and the false-positive rate and true-positive rate were 3.0% and 98.2%, respectively, against consensus of radiologists' annotations as ground truths. The overall accuracy and Lin concordance correlation coefficient for measurement extraction were 0.958 and 0.874, respectively, against radiologists' annotations as ground truths.Conclusion: An NLP-based system was developed that identifies patients with PCLs and extracts measurements from a large single-institution archive of free-text radiology reports. This approach may prove valuable to study the natural history and potential risks of PCLs and can be applied to many other use cases.Keywords: Informatics, Abdomen/GI, Pancreas, Cysts, Computer Applications-General (Informatics), Named Entity Recognition Supplemental material is available for this article. © RSNA, 2022See also commentary by Horii in this issue.

    View details for DOI 10.1148/ryai.210092

    View details for PubMedID 35391762