Impact of COVID-19 Pandemic on Radiology Department Employees and Trainees in Al-Qassim, 2021.

Objectives This study aimed to assess the impact of the COVID-19 pandemic on radiology department employees and trainees. It also compared the impact of COVID-19 to the pre-COVID-19 era in the Al-Qassim region. Methods This was a quantitative observational analytical cross-sectional study conducted in the largest government hospitals under the Ministry of Health (MOH) in Al-Qassim. A pre-determined questionnaire was distributed among radiology staff that included demographic characteristics, the impact of the COVID-19 pandemic among radiology staff, the behavior of staff related to COVID-19 infection, and the assessment of mental health using the patient health questionnaire (PHQ-9). Results Eighty-four radiology staff were recruited (64.3% males vs 35.7% females). Of these, 66.7% were trainees and the rest were employees (33.3%). Of the trainees, 32.1% and 42.9% thought that elective imaging, procedures, and outpatient/clinic exposures were reduced during the pandemic, and 37.5% indicated that their training had been affected negatively. The prevalence of depression among radiology staff was 36.9%. The prevalence of depression was substantially higher among radiology trainees (p=0.038), those who were not infected with COVID-16 (p=0.041), and those who indicated that their studying time increased at the time of the pandemic (p=0.047). However, after conducting multivariate regression analysis, these variables did not seem to have significantly affected depression (p>0.05). Conclusion Training and medical education have been affected negatively because of the outbreak. Studying time and research activities of employees and trainees slowed down, which could be critical to their careers. Trainees complained about the significant reduction in their exposure to clinics and imaging procedures. Therefore, a method to safeguard the well-being of employees and trainees in the radiology department is necessary to limit the impact of such pandemics.

Predicting stereotactic radiosurgery outcomes with multi-observer qualitative appearance labelling versus MRI radiomics.

Qualitative observer-based and quantitative radiomics-based analyses of T1w contrast-enhanced magnetic resonance imaging (T1w-CE MRI) have both been shown to predict the outcomes of brain metastasis (BM) stereotactic radiosurgery (SRS). Comparison of these methods and interpretation of radiomics-based machine learning (ML) models remains limited. To address this need, we collected a dataset of n = 123 BMs from 99 patients including 12 clinical features, 107 pre-treatment T1w-CE MRI radiomic features, and BM post-SRS progression scores. A previously published outcome model using SRS dose prescription and five-way BM qualitative appearance scoring was evaluated. We found high qualitative scoring interobserver variability across five observers that negatively impacted the model's risk stratification. Radiomics-based ML models trained to replicate the qualitative scoring did so with high accuracy (bootstrap-corrected AUC = 0.84-0.94), but risk stratification using these replicated qualitative scores remained poor. Radiomics-based ML models trained to directly predict post-SRS progression offered enhanced risk stratification (Kaplan-Meier rank-sum p = 0.0003) compared to using qualitative appearance. The qualitative appearance scoring enabled interpretation of the progression radiomics-based ML model, with necrotic BMs and a subset of heterogeneous BMs predicted as being at high-risk of post-SRS progression, in agreement with current radiobiological understanding. Our study's results show that while radiomics-based SRS outcome models out-perform qualitative appearance analysis, qualitative appearance still provides critical insight into ML model operation.

Dual-center validation of using magnetic resonance imaging radiomics to predict stereotactic radiosurgery outcomes.

Background: MRI radiomic features and machine learning have been used to predict brain metastasis (BM) stereotactic radiosurgery (SRS) outcomes. Previous studies used only single-center datasets, representing a significant barrier to clinical translation and further research. This study, therefore, presents the first dual-center validation of these techniques. Methods: SRS datasets were acquired from 2 centers (n = 123 BMs and n = 117 BMs). Each dataset contained 8 clinical features, 107 pretreatment T1w contrast-enhanced MRI radiomic features, and post-SRS BM progression endpoints determined from follow-up MRI. Random decision forest models were used with clinical and/or radiomic features to predict progression. 250 bootstrap repetitions were used for single-center experiments. Results: Training a model with one center's dataset and testing it with the other center's dataset required using a set of features important for outcome prediction at both centers, and achieved area under the receiver operating characteristic curve (AUC) values up to 0.70. A model training methodology developed using the first center's dataset was locked and externally validated with the second center's dataset, achieving a bootstrap-corrected AUC of 0.80. Lastly, models trained on pooled data from both centers offered balanced accuracy across centers with an overall bootstrap-corrected AUC of 0.78. Conclusions: Using the presented validated methodology, radiomic models trained at a single center can be used externally, though they must utilize features important across all centers. These models' accuracies are inferior to those of models trained using each individual center's data. Pooling data across centers shows accurate and balanced performance, though further validation is required.