People

Samuel G. Armato, PhD

I have established my career through the development and evaluation of computerized techniques for the quantitative analysis of medical images and the assessment of tumor response to therapy. More specifically, my research has involved the computerized detection and evaluation of lung nodules in thoracic computed tomography (CT) scans, the assessment of image quality and pathologic change in temporally subtracted chest radiographic images, the computerized evaluation of mesothelioma tumor and response to therapy in CT scans, critical analyses of image-based tumor response assessment for mesothelioma, the development of objective CT-based metrics for the quantification of mucosal inflammation due to sinusitis, the application of radiomics to the pre- and post-treatment CT scans of radiation therapy patients to predict normal lung tissue complications, and the evaluation of reference standards for computer-aided diagnosis (CAD) research. As the local principal investigator for the Lung Image Database Consortium project that spanned 10 years and as the faculty director of the University of Chicago’s Human Imaging Research Office, I have extensive experience with interdisciplinary and multi-institutional image-based projects.

The University of Chicago
Chicago, IL
Ph.D. - Medical Physics
1997

The University of Chicago
Chicago, IL
B.A. - Physics
1987

Assessment of a deep learning model for COVID-19 classification on chest radiographs: a comparison across image acquisition techniques and clinical factors.
Assessment of a deep learning model for COVID-19 classification on chest radiographs: a comparison across image acquisition techniques and clinical factors. J Med Imaging (Bellingham). 2023 Nov; 10(6):064504.
PMID: 38162317

Magnetic resonance imaging preprocessing and radiomic features for classification of autosomal dominant polycystic kidney disease genotype.
Magnetic resonance imaging preprocessing and radiomic features for classification of autosomal dominant polycystic kidney disease genotype. J Med Imaging (Bellingham). 2023 Nov; 10(6):064503.
PMID: 38156331

Convolutional Neural Networks for Segmentation of Malignant Pleural Mesothelioma: Analysis of Probability Map Thresholds (CALGB 30901, Alliance).
Convolutional Neural Networks for Segmentation of Malignant Pleural Mesothelioma: Analysis of Probability Map Thresholds (CALGB 30901, Alliance). ArXiv. 2023 Nov 30.
PMID: 38076518

Best Practices for Artificial Intelligence and Machine Learning for Computer-Aided Diagnosis in Medical Imaging.
Best Practices for Artificial Intelligence and Machine Learning for Computer-Aided Diagnosis in Medical Imaging. J Am Coll Radiol. 2024 Feb; 21(2):341-343.
PMID: 37925095

Medical Physics ends print.
Medical Physics ends print. Med Phys. 2023 10; 50(10):5933-5934.
PMID: 37819174

AI in medical imaging grand challenges: translation from competition to research benefit and patient care.
AI in medical imaging grand challenges: translation from competition to research benefit and patient care. Br J Radiol. 2023 Oct; 96(1150):20221152.
PMID: 37698542

Germline Variants Incidentally Detected via Tumor-Only Genomic Profiling of Patients With Mesothelioma.
Germline Variants Incidentally Detected via Tumor-Only Genomic Profiling of Patients With Mesothelioma. JAMA Netw Open. 2023 08 01; 6(8):e2327351.
PMID: 37556141

Emphysema Detection in the Course of Lung Cancer Screening: Optimizing a Rare Opportunity to Impact Population Health.
Emphysema Detection in the Course of Lung Cancer Screening: Optimizing a Rare Opportunity to Impact Population Health. Ann Am Thorac Soc. 2023 04; 20(4):499-503.
PMID: 36490389

A Competition, Benchmark, Code, and Data for Using Artificial Intelligence to Detect Lesions in Digital Breast Tomosynthesis.
A Competition, Benchmark, Code, and Data for Using Artificial Intelligence to Detect Lesions in Digital Breast Tomosynthesis. JAMA Netw Open. 2023 02 01; 6(2):e230524.
PMID: 36821110

AAPM task group report 273: Recommendations on best practices for AI and machine learning for computer-aided diagnosis in medical imaging.
AAPM task group report 273: Recommendations on best practices for AI and machine learning for computer-aided diagnosis in medical imaging. Med Phys. 2023 Feb; 50(2):e1-e24.
PMID: 36565447

View All Publications

Fellow
Society of Photo-Optical Instrumentation Engineers (SPIE)
2018

Distinguished Investigator
Academy of Radiology Research
2016

Fellow
American Association of Physicists in Medicine
2014

Kurt Rossmann Award for Excellence in Medical Physics Teaching
The University of Chicago
2012

Raine Visiting Professor
University of Western Australia
2009

Kurt Rossmann Award for Excellence in Medical Physics Teaching
The University of Chicago
2002