Bio

Clinical Focus


  • Abdominal Imaging
  • Diagnostic Radiology

Academic Appointments


  • Clinical Assistant Professor, Radiology

Administrative Appointments


  • Interim Director, Body Imaging Fellowship (2021 - Present)
  • Assistant Director, Body Imaging Fellowship (2018 - 2021)

Honors & Awards


  • Chief Resident, Department of Radiology, University of Illinois Hospital & Health Sciences System (2016-2017)
  • Chief Fellow, Body Imaging Division, Department of Radiology, Stanford University (2017-2018)

Professional Education


  • Fellowship: Stanford University Radiology Fellowships (2018) CA
  • Board Certification: American Board of Radiology, Diagnostic Radiology (2018)
  • Fellowship, Stanford University School of Medicine, Body Imaging (2018)
  • Residency: University of Illinois Hospital and Health Sciences System (UIC) (2017) IL
  • Internship: Louis A Weiss Memorial Hospital (2013) IL
  • Medical Education: University of Illinois at Chicago College of Medicine (2012) IL

Publications

All Publications


  • Human-machine partnership with artificial intelligence for chest radiograph diagnosis. NPJ digital medicine Patel, B. N., Rosenberg, L. n., Willcox, G. n., Baltaxe, D. n., Lyons, M. n., Irvin, J. n., Rajpurkar, P. n., Amrhein, T. n., Gupta, R. n., Halabi, S. n., Langlotz, C. n., Lo, E. n., Mammarappallil, J. n., Mariano, A. J., Riley, G. n., Seekins, J. n., Shen, L. n., Zucker, E. n., Lungren, M. n. 2019; 2: 111

    Abstract

    Human-in-the-loop (HITL) AI may enable an ideal symbiosis of human experts and AI models, harnessing the advantages of both while at the same time overcoming their respective limitations. The purpose of this study was to investigate a novel collective intelligence technology designed to amplify the diagnostic accuracy of networked human groups by forming real-time systems modeled on biological swarms. Using small groups of radiologists, the swarm-based technology was applied to the diagnosis of pneumonia on chest radiographs and compared against human experts alone, as well as two state-of-the-art deep learning AI models. Our work demonstrates that both the swarm-based technology and deep-learning technology achieved superior diagnostic accuracy than the human experts alone. Our work further demonstrates that when used in combination, the swarm-based technology and deep-learning technology outperformed either method alone. The superior diagnostic accuracy of the combined HITL AI solution compared to radiologists and AI alone has broad implications for the surging clinical AI deployment and implementation strategies in future practice.

    View details for DOI 10.1038/s41746-019-0189-7

    View details for PubMedID 31754637

    View details for PubMedCentralID PMC6861262

  • Detection of Primary Malignancy and Metastases with FDG PET/CT in Patients with Cholangiocarcinomas: Lesion-based Comparison with Contrast Enhanced CT. World journal of nuclear medicine Elias, Y. n., Mariano, A. T., Lu, Y. n. 2016; 15 (3): 161–66

    Abstract

    The current National Comprehensive Cancer Network (NCCN) Guidelines consider the role of 2-deoxy-2-(18)F-fluoro-d-glucose positron emission tomography/computer tomography (FDG PET/CT) in the evaluation of cholangiocarcinoma (CCA) as "uncertain," and have recommended contrast enhanced computed tomography (CECT) but not FDG PET/CT as a routine imaging test for CCA workup. We set out to compare the diagnostic performance of FDG PET/CT and CECT in patients with CCA. The retrospective study included patients with CCA who underwent FDG PET/CT and CECT within 2-month interval between 2011 and 2013 in our hospital. Lesion-based comparison was conducted. Final diagnoses were made based on the composite clinical and imaging data with minimal 6-month follow-up. A total of 18 patients with 28-paired tests were included. There is a total of 142 true malignant lesions as revealed by the 6-paired pre-treatment and 22-paired post-treatment tests. On a lesion-based analysis, the sensitivities, specificities, positive predictive values (PPVs), negative predictive values (NPVs), and accuracies of PET/CT and CECT for detection of CCA were 96.5%, 55.5%, 97.2%, 50.0%, 94.1% and 62.2%, 66.7%, 96.7%, 10.0%, 62.5%, respectively. FDG PET/CT detected more intrahepatic malignant and extrahepatic metastases; and had significant higher sensitivity, NPV, and accuracy than CECT, while similar in specificity and PPV. No true positive lesion detected on CECT that was missed on PET/CT, and none of the false negative lesions on PET/CT were detected on CECT. Six patients had paired pretreatment tests, and FDG PET/CT results changed planned management in three patients. Our data suggest that FDG PET/CT detect more primary and metastatic lesions and lead to considerable changes in treatment plan in comparison with CECT.

    View details for DOI 10.4103/1450-1147.167605

    View details for PubMedID 27651736

    View details for PubMedCentralID PMC5020788

Latest information on COVID-19