Weijie Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Weijie Chen has a total of 120 co-authors. Here are the top co-authors by number of shared publications:
- Nicholas Petrick
U.S. Food and Drug Administration
15 shared publications - Brandon D. Gallas
U.S. Food and Drug Administration (United States)
10 shared publications - Berkman Sahiner
Univ. of Michigan (United States)
8 shared publications Berkman Sahiner
Office of Science and Engineering Laboratories, Center for Devices and Radiological Health, US Food and Drug Administration
7 shared publications- Maryellen Lissak Giger
The University of Chicago, Department of Radiology, Chicago, Illinois, United States
6 shared publications - Frank W. Samuelson
U.S. Food and Drug Administration
5 shared publications
Latest Publications
- 1 May 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 13 (03) , 1-17
Methodological considerations for evaluating deep learning segmentation models in digital pathology whole-slide images
PurposeAutomated whole-slide image (WSI) analysis, specifically applications of deep learning (DL)-based algorithms, has been enabling automated detection, classification, segmentation, and prognosis for various diseases. Performance evaluation plays an important role in the success of these complex big-data-based technologies. Our purpose is to conduct a performance evaluation of DL segmentation models applied to a breast cancer WSI dataset provided by the Tumor InfiltratinG lymphocytes in breast cancER challenge and investigate methodological issues in the assessment of WSI segmentation models.ApproachWe evaluated the performance of DL models in the segmentation of tumoral and stromal regions and the effect of color normalization on improving the performance of these models when the training and testing data are from different sources. One important issue is the aggregation of image segmentation performance when the reference standard includes annotations only from selected regions of interest (ROIs). We introduced three different methods for aggregating performance based on different units of analysis (pixels, ROIs, and slides) and a bootstrap method to estimate the variance of the performance results at the slide level.ResultsWe found that using different units of analysis can produce not just different mean performance estimates but also different levels of uncertainty. Our results also showed that color normalization significantly improved DL model performance when the training and testing data are from different sources.ConclusionsOur study demonstrates the importance of image acquisition, study design, and statistical analysis methods used in the performance evaluation of computational pathology applications.
- 1 May 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 13 (03) , 1-17
Methodological considerations for evaluating deep learning segmentation models in digital pathology whole-slide images
PurposeAutomated whole-slide image (WSI) analysis, specifically applications of deep learning (DL)-based algorithms, has been enabling automated detection, classification, segmentation, and prognosis for various diseases. Performance evaluation plays an important role in the success of these complex big-data-based technologies. Our purpose is to conduct a performance evaluation of DL segmentation models applied to a breast cancer WSI dataset provided by the Tumor InfiltratinG lymphocytes in breast cancER challenge and investigate methodological issues in the assessment of WSI segmentation models.ApproachWe evaluated the performance of DL models in the segmentation of tumoral and stromal regions and the effect of color normalization on improving the performance of these models when the training and testing data are from different sources. One important issue is the aggregation of image segmentation performance when the reference standard includes annotations only from selected regions of interest (ROIs). We introduced three different methods for aggregating performance based on different units of analysis (pixels, ROIs, and slides) and a bootstrap method to estimate the variance of the performance results at the slide level.ResultsWe found that using different units of analysis can produce not just different mean performance estimates but also different levels of uncertainty. Our results also showed that color normalization significantly improved DL model performance when the training and testing data are from different sources.ConclusionsOur study demonstrates the importance of image acquisition, study design, and statistical analysis methods used in the performance evaluation of computational pathology applications.
- 1 April 2026
- Published by Springer Nature
- p. 595-607
Restorable Segmentation Synthesis Using Fourier Descriptors
- 1 April 2026
- Published by Springer Nature
- p. 595-607
Restorable Segmentation Synthesis Using Fourier Descriptors
- 24 November 2025
- Published by SAGE Publications in Medical Decision Making
- Vol. 46 (3) , 321-333
Use of Expected Utility to Evaluate Artificial Intelligence–Enabled Rule-out Devices for Mammography Screening
Background: An artificial intelligence (AI)–enabled rule-out device may autonomously remove patient images unlikely to have cancer from radiologist review. Many published studies evaluate this type of device by retrospectively applying the AI to large datasets and use sensitivity and specificity as the performance metrics. However, these metrics have fundamental shortcomings because sensitivity will always be negatively affected in retrospective studies of rule-out applications of AI. Method: We reviewed 2 performance metrics to compare the screening performance between the radiologist-with-rule-out-device and radiologist-without-device workflows: positive/negative predictive values (PPV/NPV) and expected utility (EU). We applied both methods to a recent study that reported improved performance in the radiologist-with-device workflow using a retrospective US dataset. We then applied the EU method to a European study based on the reported recall and cancer detection rates at different AI thresholds to compare the potential utility among different thresholds. Results: For the US study, neither PPV/NPV nor EU can demonstrate significant improvement for any of the algorithm thresholds reported. For the study using European data, we found that EU is lower as AI rules out more patients including false-negative cases and reduces the overall screening performance. Conclusions: Due to the nature of the retrospective simulated study design, sensitivity and specificity can be ambiguous in evaluating a rule-out device. We showed that using PPV/NPV or EU can resolve the ambiguity. The EU method can be applied with only recall rates and cancer detection rates, which is convenient as ground truth is often unavailable for nonrecalled patients in screening mammography. Highlights: Sensitivity and specificity can be ambiguous metrics for evaluating a rule-out device in a retrospective setting. PPV and NPV can resolve the ambiguity but require the ground truth for all patients. Based on utility theory, expected utility (EU) is a potential metric that helps demonstrate improvement in screening performance due to a rule-out device using large retrospective datasets. We applied EU to a recent study that used a large retrospective mammography screening dataset from the United States. That study reported an improvement in specificity and decrease in sensitivity when using their AI as a rule-out device retrospectively. In terms of EU, we cannot conclude a significant improvement when the AI is used as a rule-out device. We applied the method to a European study that reported only recall rates and cancer detection rates. Since there is no established EU baseline value in European mammography screening workflow, we estimated the EU baseline using data from previous literature. We cannot conclude a significant improvement when the AI is used as a rule-out device for the European study. In this work, we investigated the use of EU to evaluate rule-out devices using large retrospective datasets. This metric, used with retrospective clinical data, could be used as supporting evidence for rule-out devices.
- 24 November 2025
- Published by SAGE Publications in Medical Decision Making
- Vol. 46 (3) , 321-333
Use of Expected Utility to Evaluate Artificial Intelligence–Enabled Rule-out Devices for Mammography Screening
Background: An artificial intelligence (AI)–enabled rule-out device may autonomously remove patient images unlikely to have cancer from radiologist review. Many published studies evaluate this type of device by retrospectively applying the AI to large datasets and use sensitivity and specificity as the performance metrics. However, these metrics have fundamental shortcomings because sensitivity will always be negatively affected in retrospective studies of rule-out applications of AI. Method: We reviewed 2 performance metrics to compare the screening performance between the radiologist-with-rule-out-device and radiologist-without-device workflows: positive/negative predictive values (PPV/NPV) and expected utility (EU). We applied both methods to a recent study that reported improved performance in the radiologist-with-device workflow using a retrospective US dataset. We then applied the EU method to a European study based on the reported recall and cancer detection rates at different AI thresholds to compare the potential utility among different thresholds. Results: For the US study, neither PPV/NPV nor EU can demonstrate significant improvement for any of the algorithm thresholds reported. For the study using European data, we found that EU is lower as AI rules out more patients including false-negative cases and reduces the overall screening performance. Conclusions: Due to the nature of the retrospective simulated study design, sensitivity and specificity can be ambiguous in evaluating a rule-out device. We showed that using PPV/NPV or EU can resolve the ambiguity. The EU method can be applied with only recall rates and cancer detection rates, which is convenient as ground truth is often unavailable for nonrecalled patients in screening mammography. Highlights: Sensitivity and specificity can be ambiguous metrics for evaluating a rule-out device in a retrospective setting. PPV and NPV can resolve the ambiguity but require the ground truth for all patients. Based on utility theory, expected utility (EU) is a potential metric that helps demonstrate improvement in screening performance due to a rule-out device using large retrospective datasets. We applied EU to a recent study that used a large retrospective mammography screening dataset from the United States. That study reported an improvement in specificity and decrease in sensitivity when using their AI as a rule-out device retrospectively. In terms of EU, we cannot conclude a significant improvement when the AI is used as a rule-out device. We applied the method to a European study that reported only recall rates and cancer detection rates. Since there is no established EU baseline value in European mammography screening workflow, we estimated the EU baseline using data from previous literature. We cannot conclude a significant improvement when the AI is used as a rule-out device for the European study. In this work, we investigated the use of EU to evaluate rule-out devices using large retrospective datasets. This metric, used with retrospective clinical data, could be used as supporting evidence for rule-out devices.
- Open Access
- 1 August 2025
- Published by Springer Nature in Scientific Data
- Vol. 12 (1) , 1-10
Multimodal data curation via interoperability: use cases with the Medical Imaging and Data Resource Center
Interoperability (the ability of data or tools from non-cooperating resources to integrate or work together with minimal effort) is particularly important for curation of multimodal datasets from multiple data sources. The Medical Imaging and Data Resource Center (MIDRC), a multi-institutional collaborative initiative to collect, curate, and share medical imaging datasets, has made interoperability with other data commons one of its top priorities. The purpose of this study was to demonstrate the interoperability between MIDRC and two other data repositories, BioData Catalyst (BDC) and National Clinical Cohort Collaborative (N3C). Using interoperability capabilities of the data repositories, we built two cohorts for example use cases, with each containing clinical and imaging data on matched patients. The representativeness of the cohorts is characterized by comparing with CDC population statistics using the Jensen-Shannon distance. The process and methods of interoperability demonstrated in this work can be utilized by MIDRC, BDC, and N3C users to create multimodal datasets for development of artificial intelligence/machine learning models.
- 1 August 2025
- Published by Springer Nature in Scientific Data
- Vol. 12 (1) , 1-10
Open AccessMultimodal data curation via interoperability: use cases with the Medical Imaging and Data Resource Center
Interoperability (the ability of data or tools from non-cooperating resources to integrate or work together with minimal effort) is particularly important for curation of multimodal datasets from multiple data sources. The Medical Imaging and Data Resource Center (MIDRC), a multi-institutional collaborative initiative to collect, curate, and share medical imaging datasets, has made interoperability with other data commons one of its top priorities. The purpose of this study was to demonstrate the interoperability between MIDRC and two other data repositories, BioData Catalyst (BDC) and National Clinical Cohort Collaborative (N3C). Using interoperability capabilities of the data repositories, we built two cohorts for example use cases, with each containing clinical and imaging data on matched patients. The representativeness of the cohorts is characterized by comparing with CDC population statistics using the Jensen-Shannon distance. The process and methods of interoperability demonstrated in this work can be utilized by MIDRC, BDC, and N3C users to create multimodal datasets for development of artificial intelligence/machine learning models.
- 3 April 2024
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12933, 26-198
Deep learning-based ROI detection of AEH and EC on histopathology WSIs for predicting hormonal treatment response
Endometrial cancer (EC) is the most common gynecologic malignancy in the United States. Hormone therapies and hysterectomy are viable treatments for early-stage EC and atypical endometrial hyperplasia (AEH), a high-risk precursor to EC. Prediction of patient response to hormonal treatment is useful for patients to make treatment decisions. We have previously developed a mix-supervised model: a weakly supervised deep learning model for hormonal treatment response prediction based on pathologist-annotated AEH and EC regions on whole slide images of H&E stained slides. The reliance on pathologist annotation in applying the model to new cases is cumbersome and subject to inter-observer variability. In this study, we automate the task of ROI detection by developing a supervised deep learning model to detect AEH and EC regions. This model achieved a patch-wise AUROC performance of 0.974 (approximate 95% CI [0.972, 0.976]). The mixsupervised model yielded a patient-level AUROC of 0.76 (95% CI [0.59, 0.92]) with ROIs detected by our new model on a hold-out test set in the task of classifying patients into responders and non-responders. As a comparison, the original model as tested on pathologist-annotated ROIs achieved an AUROC of 0.80 with 95% CI [0.63, 0.95]. Our results demonstrate the potential of using weakly supervised deep learning and supervised ROI detection model for predicting hormonal treatment response in endometrial cancer patients.
- 3 April 2024
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12933, 26-198
Deep learning-based ROI detection of AEH and EC on histopathology WSIs for predicting hormonal treatment response
Endometrial cancer (EC) is the most common gynecologic malignancy in the United States. Hormone therapies and hysterectomy are viable treatments for early-stage EC and atypical endometrial hyperplasia (AEH), a high-risk precursor to EC. Prediction of patient response to hormonal treatment is useful for patients to make treatment decisions. We have previously developed a mix-supervised model: a weakly supervised deep learning model for hormonal treatment response prediction based on pathologist-annotated AEH and EC regions on whole slide images of H&E stained slides. The reliance on pathologist annotation in applying the model to new cases is cumbersome and subject to inter-observer variability. In this study, we automate the task of ROI detection by developing a supervised deep learning model to detect AEH and EC regions. This model achieved a patch-wise AUROC performance of 0.974 (approximate 95% CI [0.972, 0.976]). The mixsupervised model yielded a patient-level AUROC of 0.76 (95% CI [0.59, 0.92]) with ROIs detected by our new model on a hold-out test set in the task of classifying patients into responders and non-responders. As a comparison, the original model as tested on pathologist-annotated ROIs achieved an AUROC of 0.80 with 95% CI [0.63, 0.95]. Our results demonstrate the potential of using weakly supervised deep learning and supervised ROI detection model for predicting hormonal treatment response in endometrial cancer patients.
- 3 April 2024
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12933, 41-289
Assessment of machine learning algorithms for TILs scoring using whole slide images: comparison with pathologists
Machine learning (ML) based whole slide imaging biomarkers have great potential to improve the efficiency and consistency of biomarker quantification, thereby facilitating the development of prognosis models for personalized medicine. Assessment methods in this area are still under-developed. Using the public TiGER (Tumor InfiltratinG lymphocytes in breast cancER) challenge data, we developed a deep neural network-based algorithm for automated tumorinfiltrating lymphocytes (TILs) scoring from whole slide images (WSIs) of biopsies and surgical resections of human epidermal growth factor receptor-2 positive (HER2+) and triple-negative breast cancer (TNBC) patients. The purpose of this study is to assess our model’s performance on a new independent dataset. Seven pathologists independently assessed 320 pre-selected regions of interests (ROIs) across 32 WSIs for TILs scoring. Our results show that there is substantial variability among pathologists in scoring TILs density. We also observed a systematic discrepancy between the ML-based TILs scoring and the pathologists’ manual scoring that led us to develop a calibration between the two. Our calibration reduced the discrepancy, increasing the intra-class-correlation coefficient (ICC) from 0.35 (95% CI [-0.062, 0.625]) for uncalibrated scores to 0.67 (95% CI [0.6, 0.736]) after calibration.
- 3 April 2024
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12933, 41-289
Assessment of machine learning algorithms for TILs scoring using whole slide images: comparison with pathologists
Machine learning (ML) based whole slide imaging biomarkers have great potential to improve the efficiency and consistency of biomarker quantification, thereby facilitating the development of prognosis models for personalized medicine. Assessment methods in this area are still under-developed. Using the public TiGER (Tumor InfiltratinG lymphocytes in breast cancER) challenge data, we developed a deep neural network-based algorithm for automated tumorinfiltrating lymphocytes (TILs) scoring from whole slide images (WSIs) of biopsies and surgical resections of human epidermal growth factor receptor-2 positive (HER2+) and triple-negative breast cancer (TNBC) patients. The purpose of this study is to assess our model’s performance on a new independent dataset. Seven pathologists independently assessed 320 pre-selected regions of interests (ROIs) across 32 WSIs for TILs scoring. Our results show that there is substantial variability among pathologists in scoring TILs density. We also observed a systematic discrepancy between the ML-based TILs scoring and the pathologists’ manual scoring that led us to develop a calibration between the two. Our calibration reduced the discrepancy, increasing the intra-class-correlation coefficient (ICC) from 0.35 (95% CI [-0.062, 0.625]) for uncalibrated scores to 0.67 (95% CI [0.6, 0.736]) after calibration.
- 29 March 2024
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12929, 139-143
Use of equivalent relative utility to evaluate artificial intelligence-based rule-out devices
We investigated the use of equivalent relative utility (ERU) to evaluate the effectiveness of artificial intelligence (AI)-based rule-out algorithms designed to autonomously remove non-cancer patient images from radiologist review. Two evaluation metrics are explored: positive/negative predictive values and ERU. We applied both methods to a recent US study that concluded an improved specificity by retrospectively applying their AI algorithm to analyze a large mammography dataset. The ERU values are also calculated given the recall and cancer detection rates from a European mammography screening study. Without large prospective studies, ERU may provide insights in the effectiveness of a rule-out algorithm.
- 29 March 2024
- Published by SPIE-Intl Soc Optical Eng
- Vol. 12929, 139-143
Use of equivalent relative utility to evaluate artificial intelligence-based rule-out devices
We investigated the use of equivalent relative utility (ERU) to evaluate the effectiveness of artificial intelligence (AI)-based rule-out algorithms designed to autonomously remove non-cancer patient images from radiologist review. Two evaluation metrics are explored: positive/negative predictive values and ERU. We applied both methods to a recent US study that concluded an improved specificity by retrospectively applying their AI algorithm to analyze a large mammography dataset. The ERU values are also calculated given the recall and cancer detection rates from a European mammography screening study. Without large prospective studies, ERU may provide insights in the effectiveness of a rule-out algorithm.
- 1 January 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (01) , 017502-11
End-to-end deep learning method for predicting hormonal treatment response in women with atypical endometrial hyperplasia or endometrial cancer
PurposeEndometrial cancer (EC) is the most common gynecologic malignancy in the United States, and atypical endometrial hyperplasia (AEH) is considered a high-risk precursor to EC. Hormone therapies and hysterectomy are practical treatment options for AEH and early-stage EC. Some patients prefer hormone therapies for reasons such as fertility preservation or being poor surgical candidates. However, accurate prediction of an individual patient’s response to hormonal treatment would allow for personalized and potentially improved recommendations for these conditions. This study aims to explore the feasibility of using deep learning models on whole slide images (WSI) of endometrial tissue samples to predict the patient’s response to hormonal treatment.ApproachWe curated a clinical WSI dataset of 112 patients from two clinical sites. An expert pathologist annotated these images by outlining AEH/EC regions. We developed an end-to-end machine learning model with mixed supervision. The model is based on image patches extracted from pathologist-annotated AEH/EC regions. Either an unsupervised deep learning architecture (Autoencoder or ResNet50), or non-deep learning (radiomics feature extraction) is used to embed the images into a low-dimensional space, followed by fully connected layers for binary prediction, which was trained with binary responder/non-responder labels established by pathologists. We used stratified sampling to partition the dataset into a development set and a test set for internal validation of the performance of our models.ResultsThe autoencoder model yielded an AUROC of 0.80 with 95% CI [0.63, 0.95] on the independent test set for the task of predicting a patient with AEH/EC as a responder vs non-responder to hormonal treatment.ConclusionsThese findings demonstrate the potential of using mixed supervised machine learning models on WSIs for predicting the response to hormonal treatment in AEH/EC patients.
- 1 January 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 11 (01) , 017502-11
End-to-end deep learning method for predicting hormonal treatment response in women with atypical endometrial hyperplasia or endometrial cancer
PurposeEndometrial cancer (EC) is the most common gynecologic malignancy in the United States, and atypical endometrial hyperplasia (AEH) is considered a high-risk precursor to EC. Hormone therapies and hysterectomy are practical treatment options for AEH and early-stage EC. Some patients prefer hormone therapies for reasons such as fertility preservation or being poor surgical candidates. However, accurate prediction of an individual patient’s response to hormonal treatment would allow for personalized and potentially improved recommendations for these conditions. This study aims to explore the feasibility of using deep learning models on whole slide images (WSI) of endometrial tissue samples to predict the patient’s response to hormonal treatment.ApproachWe curated a clinical WSI dataset of 112 patients from two clinical sites. An expert pathologist annotated these images by outlining AEH/EC regions. We developed an end-to-end machine learning model with mixed supervision. The model is based on image patches extracted from pathologist-annotated AEH/EC regions. Either an unsupervised deep learning architecture (Autoencoder or ResNet50), or non-deep learning (radiomics feature extraction) is used to embed the images into a low-dimensional space, followed by fully connected layers for binary prediction, which was trained with binary responder/non-responder labels established by pathologists. We used stratified sampling to partition the dataset into a development set and a test set for internal validation of the performance of our models.ResultsThe autoencoder model yielded an AUROC of 0.80 with 95% CI [0.63, 0.95] on the independent test set for the task of predicting a patient with AEH/EC as a responder vs non-responder to hormonal treatment.ConclusionsThese findings demonstrate the potential of using mixed supervised machine learning models on WSIs for predicting the response to hormonal treatment in AEH/EC patients.
- Open Access
- 23 July 2023
- Published by Springer Nature
- p. 705-752
A Regulatory Science Perspective on Performance Assessment of Machine Learning Algorithms in Imaging
This chapter presents a regulatory science perspective on the assessment of machine learning algorithms in diagnostic imaging applications. Most of the topics are generally applicable to many medical imaging applications, while brain disease-specific examples are provided when possible. The chapter begins with an overview of US FDA’s regulatory framework followed by assessment methodologies related to ML devices in medical imaging. Rationale, methods, and issues are discussed for the study design and data collection, the algorithm documentation, and the reference standard. Finally, study design and statistical analysis methods are overviewed for the assessment of standalone performance of ML algorithms as well as their impact on clinicians (i.e., reader studies). We believe that assessment methodologies and regulatory science play a critical role in fully realizing the great potential of ML in medical imaging, in facilitating ML device innovation, and in accelerating the translation of these technologies from bench to bedside to the benefit of patients.
- 23 July 2023
- Published by Springer Nature
- p. 705-752
Open AccessA Regulatory Science Perspective on Performance Assessment of Machine Learning Algorithms in Imaging
This chapter presents a regulatory science perspective on the assessment of machine learning algorithms in diagnostic imaging applications. Most of the topics are generally applicable to many medical imaging applications, while brain disease-specific examples are provided when possible. The chapter begins with an overview of US FDA’s regulatory framework followed by assessment methodologies related to ML devices in medical imaging. Rationale, methods, and issues are discussed for the study design and data collection, the algorithm documentation, and the reference standard. Finally, study design and statistical analysis methods are overviewed for the assessment of standalone performance of ML algorithms as well as their impact on clinicians (i.e., reader studies). We believe that assessment methodologies and regulatory science play a critical role in fully realizing the great potential of ML in medical imaging, in facilitating ML device innovation, and in accelerating the translation of these technologies from bench to bedside to the benefit of patients.
- Open Access
- 18 July 2023
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 10 (06) , 061105-15
Longitudinal assessment of demographic representativeness in the Medical Imaging and Data Resource Center open data commons
Since the first identification of the SARS-CoV-2 coronavirus (and its associated infectious disease, COVID-19) in late 2019, there have been reports of differences in disease health outcomes by race, ethnicity, sex, and other demographics.1 – 14 Additionally, the relative difference in impact of COVID-19 to demographic subgroups has also changed over time.15,16 Furthermore, differences in the utilization of medical imaging in healthcare have been observed in various demographic subgroups over the course of the pandemic.17 – 19 As a result, the use of medical imaging among different demographic subpopulations can be expected to change over time.
- 18 July 2023
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 10 (06) , 061105-15
Open AccessLongitudinal assessment of demographic representativeness in the Medical Imaging and Data Resource Center open data commons
Since the first identification of the SARS-CoV-2 coronavirus (and its associated infectious disease, COVID-19) in late 2019, there have been reports of differences in disease health outcomes by race, ethnicity, sex, and other demographics.1 – 14 Additionally, the relative difference in impact of COVID-19 to demographic subgroups has also changed over time.15,16 Furthermore, differences in the utilization of medical imaging in healthcare have been observed in various demographic subgroups over the course of the pandemic.17 – 19 As a result, the use of medical imaging among different demographic subpopulations can be expected to change over time.