Simulated daily readout for maintaining nuclear medicine education in residency training amidst declining case volume: evidence from the COVID-19 pandemic.

BACKGROUND: Simulated daily readout (SDR) is a teaching initiative in radiology and nuclear medicine developed to simulate a resident's experience during periods of case volume reduction. SDR was employed by many training centers during the coronavirus disease 2019 (COVID-19) pandemic. This study aimed to evaluate the perception of radiology residents on the effectiveness of SDR. METHOD: The SDR was conducted in the nuclear medicine rotations from 2019 to 2020 during the shutdown of the radionuclide imaging facilities using a combination of strategies including case selection, assignment, reporting and feedback. A brief 8-item questionnaire with Likert scale values was completed by radiology residents who participated in the SDR-based nuclear medicine rotations. RESULTS: Thirty-five of 54 residents returned the questionnaire. The majority of residents affirmed the negative impact of the reduction in case volume on their training experiences and perceived that SDR could alleviate the effects. The SDR strategies perceived as more effective were targeted case selection, in-advanced assignment, verbal interpretation and reporting, and verbal feedback. CONCLUSION: The radiology residents perceived the SDR as an effective tool to preserve their training experiences. The SDR has the potential to be a useful initiative when teaching centers face the threat of declining case volume.

Lesion segmentation in lung CT scans using unsupervised adversarial learning.

Lesion segmentation in medical images is difficult yet crucial for proper diagnosis and treatment. Identifying lesions in medical images is costly and time-consuming and requires highly specialized knowledge. For this reason, supervised and semi-supervised learning techniques have been developed. Nevertheless, the lack of annotated data, which is common in medical imaging, is an issue; in this context, interesting approaches can use unsupervised learning to accurately distinguish between healthy tissues and lesions, training the network without using the annotations. In this work, an unsupervised learning technique is proposed to automatically segment coronavirus disease 2019 (COVID-19) lesions on 2D axial CT lung slices. The proposed approach uses the technique of image translation to generate healthy lung images based on the infected lung image without the need for lesion annotations. Attention masks are used to improve the quality of the segmentation further. Experiments showed the capability of the proposed approaches to segment the lesions, and it outperforms a range of unsupervised lesion detection approaches. The average reported results for the test dataset based on the metrics: Dice Score, Sensitivity, Specificity, Structure Measure, Enhanced-Alignment Measure, and Mean Absolute Error are 0.695, 0.694, 0.961, 0.791, 0.875, and 0.082 respectively. The achieved results are promising compared with the state-of-the-art and could constitute a valuable tool for future developments.

COVID-19 pneumonia detected by parathyroid scintigraphy.

We report a case of incidental diagnosis of COVID-19 pneumonia by parathyroid scintigraphy. A 53-year-old woman who had severe fatigue, and mild dyspnea underwent parathyroid scintigraphy due to increased serum parathyroid hormone (PTH) and serum calcium levels. Parathyroid scan was negative for abnormal parathyroid tissue. Although the patient had three negative results of COVID-19 PCR tests, significant 99m Tchexakis-2-methoxyisobutylisonitrile ([99mTc]MIBI) uptake is noticed in both lungs that was suspicious for Covid-19 pneumonia. The patient underwent CT scan of the chest for further evaluation. Diffuse groundglass opacities were identified in both lungs which were interpreted as typical feature for COVID-19 pneumonia.

Human-level COVID-19 diagnosis from low-dose CT scans using a two-stage time-distributed capsule network.

Reverse transcription-polymerase chain reaction is currently the gold standard in COVID-19 diagnosis. It can, however, take days to provide the diagnosis, and false negative rate is relatively high. Imaging, in particular chest computed tomography (CT), can assist with diagnosis and assessment of this disease. Nevertheless, it is shown that standard dose CT scan gives significant radiation burden to patients, especially those in need of multiple scans. In this study, we consider low-dose and ultra-low-dose (LDCT and ULDCT) scan protocols that reduce the radiation exposure close to that of a single X-ray, while maintaining an acceptable resolution for diagnosis purposes. Since thoracic radiology expertise may not be widely available during the pandemic, we develop an Artificial Intelligence (AI)-based framework using a collected dataset of LDCT/ULDCT scans, to study the hypothesis that the AI model can provide human-level performance. The AI model uses a two stage capsule network architecture and can rapidly classify COVID-19, community acquired pneumonia (CAP), and normal cases, using LDCT/ULDCT scans. Based on a cross validation, the AI model achieves COVID-19 sensitivity of [Formula: see text], CAP sensitivity of [Formula: see text], normal cases sensitivity (specificity) of [Formula: see text], and accuracy of [Formula: see text]. By incorporating clinical data (demographic and symptoms), the performance further improves to COVID-19 sensitivity of [Formula: see text], CAP sensitivity of [Formula: see text], normal cases sensitivity (specificity) of [Formula: see text] , and accuracy of [Formula: see text]. The proposed AI model achieves human-level diagnosis based on the LDCT/ULDCT scans with reduced radiation exposure. We believe that the proposed AI model has the potential to assist the radiologists to accurately and promptly diagnose COVID-19 infection and help control the transmission chain during the pandemic.

Supraclavicular and Axillary Lymphadenopathy Induced by COVID-19 Vaccination on 18F-Fluorthanatrace, 68Ga-DOTATATE, and 18F-Fluciclovine PET/CT.

ABSTRACT: COVID-19 vaccination has started in most countries, and postvaccination imaging is inevitable in the oncologic population. The immune response to the vaccination in the form of reactive lymphadenopathy has been well documented on 18F-FDG PET/CT. We present the imaging findings of 3 patients who have undergone non-FDG PET/CT imaging including 18F-fluorthanatrace, 68Ga-DOTATATE, and 18F-fluciclovine PET/CT. It is crucial to recognize the timing and laterality of immunization to avoid false-positive findings.

Artifact from 131I-Contaminated Mask in Postradioiodine Therapy Scintigraphy.

A patient wearing the mandatory face mask because of the ongoing coronavirus disease 2019 pandemic underwent postradioiodine therapy scintigraphy. The spot view of the neck showed an area of uptake that was later demonstrated to be caused by contamination of the mask. This finding has led to updating the scan procedure for posttherapy scintigraphy by replacing the patients' masks before the scan acquisition.