Machine learning and deep learning for classifying the justification of brain CT referrals.

OBJECTIVES: To train the machine and deep learning models to automate the justification analysis of radiology referrals in accordance with iGuide categorisation, and to determine if prediction models can generalise across multiple clinical sites and outperform human experts. METHODS: Adult brain computed tomography (CT) referrals from scans performed in three CT centres in Ireland in 2020 and 2021 were retrospectively collected. Two radiographers analysed the justification of 3000 randomly selected referrals using iGuide, with two consultant radiologists analysing the referrals with disagreement. Insufficient or duplicate referrals were discarded. The inter-rater agreement among radiographers and consultants was computed. A random split (4:1) was performed to apply machine learning (ML) and deep learning (DL) techniques to unstructured clinical indications to automate retrospective justification auditing with multi-class classification. The accuracy and macro-averaged F1 score of the best-performing classifier of each type on the training set were computed on the test set. RESULTS: 42 referrals were ignored. 1909 (64.5%) referrals were justified, 811 (27.4%) were potentially justified, and 238 (8.1%) were unjustified. The agreement between radiographers (κ = 0.268) was lower than radiologists (κ = 0.460). The best-performing ML model was the bag-of-words-based gradient-boosting classifier achieving a 94.4% accuracy and a macro F1 of 0.94. DL models were inferior, with bi-directional long short-term memory achieving 92.3% accuracy, a macro F1 of 0.92, and outperforming multilayer perceptrons. CONCLUSION: Interpreting unstructured clinical indications is challenging necessitating clinical decision support. ML and DL can generalise across multiple clinical sites, outperform human experts, and be used as an artificial intelligence-based iGuide interpreter when retrospectively vetting radiology referrals. CLINICAL RELEVANCE STATEMENT: Healthcare vendors and clinical sites should consider developing and utilising artificial intelligence-enabled systems for justifying medical exposures. This would enable better implementation of imaging referral guidelines in clinical practices and reduce population dose burden, CT waiting lists, and wasteful use of resources. KEY POINTS: Significant variations exist among human experts in interpreting unstructured clinical indications/patient presentations. Machine and deep learning can automate the justification analysis of radiology referrals according to iGuide categorisation. Machine and deep learning can improve retrospective and prospective justification auditing for better implementation of imaging referral guidelines.

Retrospective analysis of radiological investigation of surgically excised head and neck lipomas.

PURPOSE: Differentiating benign lipomas from malignant causes is challenging and preoperative investigative guidelines are not well-defined. The purpose of this study was to retrospectively identify cases of head and neck lipomas that were surgically resected over a 5-year period and to identify the radiological modality chosen and features discussed in the final report. Multidisciplinary outcomes and pathology reports were examined with a view to identifying high risk features of a lipoma to aid in future risk stratification. METHODS: Retrospective chart review of pathology characteristics, radiological features (modality, size, calcifications, septations, globular/nodular foci), multidisciplinary discussion and history of presenting complaint was performed. RESULTS: Two liposarcomas and 138 lipomas were identified. Twenty-two percent of all lipomas received radiological investigation. Twenty-two percent of imaging referrals were possibly inappropriate. Furthermore, radiological features suggestive of malignancy were not present in the final radiology report, X2 = 28.8, p < 0.0001. CONCLUSION: As expected, the incidence of liposarcoma is low. There is limited awareness of radiology referral guidelines superimposed with a tendency to over-investigate lipomas. Furthermore, radiological features suggestive of malignancy were inconsistently reported on and not documented in multidisciplinary discussions. Therefore, we propose a multidisciplinary checklist for referring physicians and radiologists to aid in diagnostic work-up.

Image-guided navigation in posterior orbital tumour surgery: a comparative cohort study.

PURPOSE: The posterior orbit is a confined space, harbouring neurovascular structures, frequently distorted by tumours. Image-guided navigation (IGN) has the potential to allow accurate localisation of these lesions and structures, reducing collateral damage whilst achieving surgical objectives. METHODS: We assessed the feasibility, effectiveness and safety of using an electromagnetic IGN for posterior orbital tumour surgery via a comparative cohort study. Outcomes from cases performed with IGN were compared with a retrospective cohort of similar cases performed without IGN, presenting a descriptive and statistical comparative analysis. RESULTS: Both groups were similar in mean age, gender and tumour characteristics. IGN set-up and registration were consistently achieved without significant workflow disruption. In the IGN group, fewer lateral orbitotomies (6.7% IGN, 46% non-IGN), and more transcutaneous lid and transconjunctival incisions (93% IGN, 53% non-IGN) were performed (p = .009). The surgical objective was achieved in 100% of IGN cases, with no need for revision surgery (vs 23% revision surgery in non-IGN, p = .005). There was no statistically significant difference in surgical complications. CONCLUSION: The use of IGN was feasible and integrated into the orbital surgery workflow to achieve surgical objectives more consistently and allowed the use of minimal access approaches. Future multicentre comparative studies are needed to explore the potential of this technology further.

iSPAN: Explainable prediction of outcomes post thrombectomy with Machine Learning.

PURPOSE: This study aimed to develop and evaluate a machine learning model and a novel clinical score for predicting outcomes in stroke patients undergoing endovascular thrombectomy. MATERIALS AND METHODS: This retrospective study included all patients aged over 18 years with an anterior circulation stroke treated at a thrombectomy centre from 2010 to 2020 with external validation. The primary outcome was day 90 mRS ≥3. Existing clinical scores (SPAN and PRE) and Machine Learning (ML) models were compared. A novel clinical score (iSPAN) was derived by adding an optimised weighting of the most important ML features to the SPAN. RESULTS: 812 patients were initially included (397 female, average age 73), 63 for external validation. The best performing clinical score and ML model were SPAN and XGB (sensitivity, specificity and accuracy 0.290, 0.967, 0.628 and 0.693, 0.783, 0.738 respectively). A significant difference was found overall and our XGB model was more accurate than SPAN (p < 0.0018). The most important features were Age, mTICI and total number of passes. The addition of 11 points for mTICI of ≤2B and 3 points for ≥3 passes to the SPAN achieved the best accuracy and was used to create the iSPAN. iSPAN was not significantly less accurate than our XGB model (p > 0.5). In the external validation set, iSPAN and SPAN achieved sensitivity, specificity, and accuracy of (0.735, 0.862, 0.79) and (0.471, 0.897, 0.67) respectively. CONCLUSION: iSPAN incorporates machine-derived features to achieve better predictions compared to existing clinical scores. It is not inferior to our XGB model and is externally generalisable.

A Radiomic "Warning Sign" of Progression on Brain MRI in Individuals with MS.

BACKGROUND AND PURPOSE: MS is a chronic progressive, idiopathic, demyelinating disorder whose diagnosis is contingent on the interpretation of MR imaging. New MR imaging lesions are an early biomarker of disease progression. We aimed to evaluate a machine learning model based on radiomics features in predicting progression on MR imaging of the brain in individuals with MS. MATERIALS AND METHODS: This retrospective cohort study with external validation on open-access data obtained full ethics approval. Longitudinal MR imaging data for patients with MS were collected and processed for machine learning. Radiomics features were extracted at the future location of a new lesion in the patients' prior MR imaging ("prelesion"). Additionally, "control" samples were obtained from the normal-appearing white matter for each participant. Machine learning models for binary classification were trained and tested and then evaluated the external data of the model. RESULTS: The total number of participants was 167. Of the 147 in the training/test set, 102 were women and 45 were men. The average age was 42 (range, 21-74 years). The best-performing radiomics-based model was XGBoost, with accuracy, precision, recall, and F1-score of 0.91, 0.91, 0.91, and 0.91 on the test set, and 0.74, 0.74, 0.74, and 0.70 on the external validation set. The 5 most important radiomics features to the XGBoost model were associated with the overall heterogeneity and low gray-level emphasis of the segmented regions. Probability maps were produced to illustrate potential future clinical applications. CONCLUSIONS: Our machine learning model based on radiomics features successfully differentiated prelesions from normal-appearing white matter. This outcome suggests that radiomics features from normal-appearing white matter could serve as an imaging biomarker for progression of MS on MR imaging.

Impact of point-of-care clinical decision support on referrer behavior, imaging volume, patient radiation dose exposure, and sustainability.

OBJECTIVES: When referring patients to radiology, it is important that the most appropriate test is chosen to avoid inappropriate imaging that may lead to delayed diagnosis, unnecessary radiation dose, worse patient outcome, and poor patient experience. The current radiology appropriateness guidance standard at our institution is via access to a standalone web-based clinical decision support tool (CDST). A point-of-care (POC) CDST that incorporates guidance directly into the physician workflow was implemented within a subset of head and neck cancer specialist referrers. The purpose of this audit was to evaluate the imaging pathway, pre- and post-implementation to assess changes in referral behavior. METHODS: CT and MRI neck data were collected retrospectively to examine the relationship between imaging referrals pre- and post-POC CDST implementation. Effective radiation dose and estimated carbon emissions were also compared. RESULTS: There was an overall reduction in absolute advanced imaging volume by 8.2%, and a reduction in duplicate CT and MRI imaging by 61%, p < 0.0001. There was also a shift in ordering behavior in favor of MRI (OR [95% CI] = 1.50 [1.02-2.22], p = 0.049). These changes resulted in an effective radiation dose reduction of 0.27 mSv per patient, or 13 equivalent chest x-rays saved per patient, p < 0.0001. Additionally, the reduction in unnecessary duplicate imaging led to a 13.5% reduction in carbon emissions, p = 0.0002. CONCLUSIONS: Implementation of the POC CDST resulted in a significant impact on advanced imaging volume, saved effective dose, and reduction in carbon emissions. CRITICAL RELEVANCE STATEMENT: The implementation of a point-of-care clinical decision support tool may reduce multimodality ordering and advanced imaging volume, manifesting in reduced effective dose per patient and reduced estimated carbon emissions. Widespread utilization of the point-of-care clinical decision support tool has the potential to reduce imaging wait times. KEY POINTS: • Implementation of the point-of-care clinical decision support tool reduced the number of patients who simultaneously had a CT and MRI ordered for the same clinical indication compared to a standalone web-based clinical decision support tool. • The point-of-care clinical decision support tool reduced the absolute number of CT/MRI scans requested compared to the standalone web-based clinical decision support tool. • Utilization of the point-of-care clinical decision support tool led to a significant reduction in the effective dose per patient compared to the standalone web-based clinical decision support tool.

Cybersecurity considerations for radiology departments involved with artificial intelligence.

Radiology artificial intelligence (AI) projects involve the integration of integrating numerous medical devices, wireless technologies, data warehouses, and social networks. While cybersecurity threats are not new to healthcare, their prevalence has increased with the rise of AI research for applications in radiology, making them one of the major healthcare risks of 2021. Radiologists have extensive experience with the interpretation of medical imaging data but radiologists may not have the required level of awareness or training related to AI-specific cybersecurity concerns. Healthcare providers and device manufacturers can learn from other industry sector industries that have already taken steps to improve their cybersecurity systems. This review aims to introduce cybersecurity concepts as it relates to medical imaging and to provide background information on general and healthcare-specific cybersecurity challenges. We discuss approaches to enhancing the level and effectiveness of security through detection and prevention techniques, as well as ways that technology can improve security while mitigating risks. We first review general cybersecurity concepts and regulatory issues before examining these topics in the context of radiology AI, with a specific focus on data, training, data, training, implementation, and auditability. Finally, we suggest potential risk mitigation strategies. By reading this review, healthcare providers, researchers, and device developers can gain a better understanding of the potential risks associated with radiology AI projects, as well as strategies to improve cybersecurity and reduce potential associated risks. CLINICAL RELEVANCE STATEMENT: This review can aid radiologists' and related professionals' understanding of the potential cybersecurity risks associated with radiology AI projects, as well as strategies to improve security. KEY POINTS: • Embarking on a radiology artificial intelligence (AI) project is complex and not without risk especially as cybersecurity threats have certainly become more abundant in the healthcare industry. • Fortunately healthcare providers and device manufacturers have the advantage of being able to take inspiration from other industry sectors who are leading the way in the field. • Herein we provide an introduction to cybersecurity as it pertains to radiology, a background to both general and healthcare-specific cybersecurity challenges; we outline general approaches to improving security through both detection and preventative techniques, and instances where technology can increase security while mitigating risks.

Using deep learning-derived image features in radiologic time series to make personalised predictions: proof of concept in colonic transit data.

OBJECTIVES: Siamese neural networks (SNN) were used to classify the presence of radiopaque beads as part of a colonic transit time study (CTS). The SNN output was then used as a feature in a time series model to predict progression through a CTS. METHODS: This retrospective study included all patients undergoing a CTS in a single institution from 2010 to 2020. Data were partitioned in an 80/20 Train/Test split. Deep learning models based on a SNN architecture were trained and tested to classify images according to the presence, absence, and number of radiopaque beads and to output the Euclidean distance between the feature representations of the input images. Time series models were used to predict the total duration of the study. RESULTS: In total, 568 images of 229 patients (143, 62% female, mean age 57) patients were included. For the classification of the presence of beads, the best performing model (Siamese DenseNET trained with a contrastive loss with unfrozen weights) achieved an accuracy, precision, and recall of 0.988, 0.986, and 1. A Gaussian process regressor (GPR) trained on the outputs of the SNN outperformed both GPR using only the number of beads and basic statistical exponential curve fitting with MAE of 0.9 days compared to 2.3 and 6.3 days (p < 0.05) respectively. CONCLUSIONS: SNNs perform well at the identification of radiopaque beads in CTS. For time series prediction our methods were superior at identifying progression through the time series compared to statistical models, enabling more accurate personalised predictions. CLINICAL RELEVANCE STATEMENT: Our radiologic time series model has potential clinical application in use cases where change assessment is critical (e.g. nodule surveillance, cancer treatment response, and screening programmes) by quantifying change and using it to make more personalised predictions. KEY POINTS: • Time series methods have improved but application to radiology lags behind computer vision. Colonic transit studies are a simple radiologic time series measuring function through serial radiographs. • We successfully employed a Siamese neural network (SNN) to compare between radiographs at different points in time and then used the output of SNN as a feature in a Gaussian process regression model to predict progression through the time series. • This novel use of features derived from a neural network on medical imaging data to predict progression has potential clinical application in more complex use cases where change assessment is critical such as in oncologic imaging, monitoring for treatment response, and screening programmes.

DNMT1-associated sensory neuropathy and cerebellar ataxia: A novel variant and review of genotype-phenotype correlation.

AIM: Hereditary sensory neuropathy (HSN) 1E is a neurodegenerative disorder caused by pathogenic variants in DNA methyltransferase 1 (DNMT1). It is characterised by sensorineural deafness, sensory neuropathy and cognitive decline. Variants in DNMT1 are also associated with autosomal dominant cerebellar ataxia, deafness and narcolepsy. METHODS: A 42-year-old man presented with imbalance, lancinating pain, numerous paucisymptomatic injuries, progressive deafness since his mid-20s, mild cognitive decline and apathy. Examination revealed abnormalities of eye movements, distal sensory loss to all modalities, areflexia without weakness and lower limb ataxia. MRI brain and FDG-PET scan demonstrated biparietal and cerebellar atrophy/hypometabolism. Whole exome sequencing detected a heterozygous likely pathogenic missense variant in DNMT1, c.1289G > A, p.Cys430Tyr. Cochlear implant was performed at 44 years for the bilateral high frequency sensorineural hearing loss with improvement in hearing and day-to-day function. RESULTS AND CONCLUSION: We describe a novel variant in DNMT1 and confirm that an overlapping HSN1E-cerebellar phenotype can occur. Only one prior case of cochlear implant in HSN1E has been reported to date but this case adds to that literature, suggesting that cochlear implant can be successful in such patients. We further explore the clinical and radiological signature of the cognitive syndrome associated with this disorder.

How to apply evidence-based practice to the use of artificial intelligence in radiology (EBRAI) using the data algorithm training output (DATO) method.

OBJECTIVE: As the number of radiology artificial intelligence (AI) papers increases, there are new challenges for reviewing the AI literature as well as differences to be aware of, for those familiar with the clinical radiology literature. We aim to introduce a tool to aid in this process. METHODS: In evidence-based practise (EBP), you must Ask, Search, Appraise, Apply and Evaluate to come to an evidence-based decision. The bottom-up evidence-based radiology (EBR) method allows for a systematic way of choosing the correct radiological investigation or treatment. Just as the population intervention comparison outcome (PICO) method is an established means of asking an answerable question; herein, we introduce the data algorithm training output (DATO) method to complement PICO by considering Data, Algorithm, Training and Output in the use of AI to answer the question. RESULTS: We illustrate the DATO method with a worked example concerning bone age assessment from skeletal radiographs. After a systematic search, 17 bone age estimation papers (5 of which externally validated their results) were appraised. The paper with the best DATO metrics found that an ensemble model combining uncorrelated, high performing simple models should achieve error rates comparable to human performance. CONCLUSION: Considering DATO in the application of EBR to AI is a simple systematic approach to this potentially daunting subject. ADVANCES IN KNOWLEDGE: The growth of AI in radiology means that radiologists and related professionals now need to be able to review not only clinical radiological literature but also research using AI methods. Considering Data, Algorithm, Training and Output in the application of EBR to AI is a simple systematic approach to this potentially daunting subject.

DEEP MOVEMENT: Deep learning of movie files for management of endovascular thrombectomy.

OBJECTIVES: Treatment and outcomes of acute stroke have been revolutionised by mechanical thrombectomy. Deep learning has shown great promise in diagnostics but applications in video and interventional radiology lag behind. We aimed to develop a model that takes as input digital subtraction angiography (DSA) videos and classifies the video according to (1) the presence of large vessel occlusion (LVO), (2) the location of the occlusion, and (3) the efficacy of reperfusion. METHODS: All patients who underwent DSA for anterior circulation acute ischaemic stroke between 2012 and 2019 were included. Consecutive normal studies were included to balance classes. An external validation (EV) dataset was collected from another institution. The trained model was also used on DSA videos post mechanical thrombectomy to assess thrombectomy efficacy. RESULTS: In total, 1024 videos comprising 287 patients were included (44 for EV). Occlusion identification was achieved with 100% sensitivity and 91.67% specificity (EV 91.30% and 81.82%). Accuracy of location classification was 71% for ICA, 84% for M1, and 78% for M2 occlusions (EV 73, 25, and 50%). For post-thrombectomy DSA (n = 194), the model identified successful reperfusion with 100%, 88%, and 35% for ICA, M1, and M2 occlusion (EV 89, 88, and 60%). The model could also perform classification of post-intervention videos as mTICI < 3 with an AUC of 0.71. CONCLUSIONS: Our model can successfully identify normal DSA studies from those with LVO and classify thrombectomy outcome and solve a clinical radiology problem with two temporal elements (dynamic video and pre and post intervention). KEY POINTS: • DEEP MOVEMENT represents a novel application of a model applied to acute stroke imaging to handle two types of temporal complexity, dynamic video and pre and post intervention. • The model takes as an input digital subtraction angiograms of the anterior cerebral circulation and classifies according to (1) the presence or absence of large vessel occlusion, (2) the location of the occlusion, and (3) the efficacy of thrombectomy. • Potential clinical utility lies in providing decision support via rapid interpretation (pre thrombectomy) and automated objective gradation of thrombectomy outcomes (post thrombectomy).

Automated vetting of radiology referrals: exploring natural language processing and traditional machine learning approaches.

BACKGROUND: With a significant increase in utilisation of computed tomography (CT), inappropriate imaging is a significant concern. Manual justification audits of radiology referrals are time-consuming and require financial resources. We aimed to retrospectively audit justification of brain CT referrals by applying natural language processing and traditional machine learning (ML) techniques to predict their justification based on the audit outcomes. METHODS: Two human experts retrospectively analysed justification of 375 adult brain CT referrals performed in a tertiary referral hospital during the 2019 calendar year, using a cloud-based platform for structured referring. Cohen's kappa was computed to measure inter-rater reliability. Referrals were represented as bag-of-words (BOW) and term frequency-inverse document frequency models. Text preprocessing techniques, including custom stop words (CSW) and spell correction (SC), were applied to the referral text. Logistic regression, random forest, and support vector machines (SVM) were used to predict the justification of referrals. A test set (300/75) was used to compute weighted accuracy, sensitivity, specificity, and the area under the curve (AUC). RESULTS: In total, 253 (67.5%) examinations were deemed justified, 75 (20.0%) as unjustified, and 47 (12.5%) as maybe justified. The agreement between the annotators was strong (κ = 0.835). The BOW + CSW + SC + SVM outperformed other binary models with a weighted accuracy of 92%, a sensitivity of 91%, a specificity of 93%, and an AUC of 0.948. CONCLUSIONS: Traditional ML models can accurately predict justification of unstructured brain CT referrals. This offers potential for automated justification analysis of CT referrals in clinical departments.

Traumatic open brachial plexus injuries: The importance of interdisciplinary collaboration.

Open traumatic brachial plexus injuries are rare, yet can be life threatening and require rapid clinic assessment. Early interdisciplinary collaboration is critical to achieve superior patient outcomes. This case of a 24-year-old female of a traumatic neck injury with contralateral brachial plexus injury demonstrates the limitations of early clinical assessment due to the potential for haemodynamic instability and highlights the priority of patient stabilisation. Early and active interdisciplinary collaboration in this case demonstrates its importance in accurate diagnosis and timely intervention to achieve better patient outcomes. As published in recent guidelines, this report shows the importance of early interdisciplinary involvement following stabilisation and resuscitation of the patient.

Radiology artificial intelligence: a systematic review and evaluation of methods (RAISE).

OBJECTIVE: There has been a large amount of research in the field of artificial intelligence (AI) as applied to clinical radiology. However, these studies vary in design and quality and systematic reviews of the entire field are lacking.This systematic review aimed to identify all papers that used deep learning in radiology to survey the literature and to evaluate their methods. We aimed to identify the key questions being addressed in the literature and to identify the most effective methods employed. METHODS: We followed the PRISMA guidelines and performed a systematic review of studies of AI in radiology published from 2015 to 2019. Our published protocol was prospectively registered. RESULTS: Our search yielded 11,083 results. Seven hundred sixty-seven full texts were reviewed, and 535 articles were included. Ninety-eight percent were retrospective cohort studies. The median number of patients included was 460. Most studies involved MRI (37%). Neuroradiology was the most common subspecialty. Eighty-eight percent used supervised learning. The majority of studies undertook a segmentation task (39%). Performance comparison was with a state-of-the-art model in 37%. The most used established architecture was UNet (14%). The median performance for the most utilised evaluation metrics was Dice of 0.89 (range .49-.99), AUC of 0.903 (range 1.00-0.61) and Accuracy of 89.4 (range 70.2-100). Of the 77 studies that externally validated their results and allowed for direct comparison, performance on average decreased by 6% at external validation (range increase of 4% to decrease 44%). CONCLUSION: This systematic review has surveyed the major advances in AI as applied to clinical radiology. KEY POINTS: • While there are many papers reporting expert-level results by using deep learning in radiology, most apply only a narrow range of techniques to a narrow selection of use cases. • The literature is dominated by retrospective cohort studies with limited external validation with high potential for bias. • The recent advent of AI extensions to systematic reporting guidelines and prospective trial registration along with a focus on external validation and explanations show potential for translation of the hype surrounding AI from code to clinic.

Adherence with reporting of ethical standards in COVID-19 human studies: a rapid review.

BACKGROUND: Patients with COVID-19 may feel under pressure to participate in research during the pandemic. Safeguards to protect research participants include ethical guidelines [e.g. Declaration of Helsinki and good clinical practice (GCP)], legislation to protect participants' privacy, research ethics committees (RECs) and informed consent. The International Committee of Medical Journal Editors (ICMJE) advises researchers to document compliance with these safeguards. Adherence to publication guidelines has been suboptimal in other specialty fields. The aim of this rapid review was to determine whether COVID-19 human research publications report compliance with these ethical safeguards. METHODS: A rapid systematic literature review was conducted in MEDLINE using the search term 'COVID-19'. The search was performed in April 2020 with no start date and repeated to include articles published in November 2020. Filters were 'Full free text available' and 'English Language'. Two reviewers assessed article title, abstracts and full texts. Non-COVID-19 articles and non-clinical studies were excluded. Independent reviewers conducted a second assessment of a random 20% of articles. The outcomes included reporting of compliance with the Declaration of Helsinki and GCP, REC approval, informed consent and participant privacy. RESULTS: The searches yielded 1275 and 1942 articles of which 247 and 717 were deemed eligible, from the April  search and November respectively. The majority of journals had editorial policies which purported to comply with ICMJE ethical standards. Reporting of compliance with ethical guidelines was low across all study types but was higher in the November search for case series and observational studies. Reporting of informed consent for case studies and observational studies was higher in the November search, but similar for case series. Overall, participant confidentiality was maintained but some case studies included a combination of details which would have enabled participant identification. Reporting of REC approval was higher in the November search for observational studies. CONCLUSIONS: While the majority of journal's editorial policies purported to support the ethical safeguards, many COVID-19 clinical research publications identified in this rapid review lacked documentation of these important safeguards for research participants. In order to promote public trust, ethical declarations should be included consistently.

PET/CT Variants and Pitfalls in Head and Neck Cancers Including Thyroid Cancer.

PET/CT imaging is a dual-modality diagnostic technology that merges metabolic and structural imaging. There are several currently available radiotracers, but 18F-FDG is the most commonly utilized due to its widespread availability. 18F-FDG PET/CT is a cornerstone of head and neck squamous cell carcinoma imaging. 68Ga-DOTA-TOC is another widely used radiotracer. It allows for whole-body imaging of cellular somatostatin receptors, commonly expressed by neuroendocrine tumors and is the standard of reference for the characterization and staging of neuroendocrine tumors. The normal biodistribution of these PET radiotracers as well as the technical aspects of image acquisition and inadequate patient preparation affect the quality of PET/CT imaging. In addition, normal variants, artifacts and incidental findings may impede accurate image interpretation and can potentially lead to misdiagnosis. In order to correctly interpret PET/CT imaging, it is necessary to have a comprehensive knowledge of the normal anatomy of the head and neck and to be cognizant of potential imaging pitfalls. The interpreter must be familiar with benign conditions which may accumulate radiotracer potentially mimicking neoplastic processes and also be aware of malignancies which can demonstrate low radiotracer uptake. Appropriate use of structural imaging with either CT, MR or ultrasound can serve a complimentary role in several head and neck pathologies including local tumor staging, detection of bone marrow involvement or perineural spread, and classification of thyroid nodules. It is important to be aware of the role of these complementary modalities to maximize diagnostic accuracy and patient outcomes. The purpose of this article is to outline the basic principles of PET/CT imaging, with a focus on 18F-FDG PET/CT and 68Ga-DOTA PET/CT. Basic physiology, variant imaging appearances and potential pitfalls of image interpretation are presented within the context of common use cases of PET technology in patients with head and neck cancers and other pathologies, benign and malignant.

Molecular and Anatomical Imaging of Dementia With Lewy Bodies and Frontotemporal Lobar Degeneration.

Dementia with Lewy bodies (DLB) and frontotemporal lobar degeneration (FTLD) are common causes of dementia. Early diagnosis of both conditions is challenging due to clinical and radiological overlap with other forms of dementia, particularly Alzheimer's disease (AD). Structural and functional imaging combined can aid differential diagnosis and help to discriminate DLB or FTLD from other forms of dementia. Imaging of DLB involves the use of 123I-FP-CIT SPECT and 123I-metaiodobenzylguanidine (123I-MIBG), both of which have an established role distinguishing DLB from AD. AD is also characterised by more pronounced atrophy of the medial temporal lobe structures when compared to DLB and these can be assessed at MR using the Medial Temporal Atrophy Scale. 18F-FDG-PET is used as a supportive biomarker for the diagnoses of DLB and can distinguish DLB from AD with high accuracy. Polysomnography and electroencephalography also have established roles in the diagnoses of DLB. FTLD is a heterogenous group of neurodegenerative disorders characterised pathologically by abnormally aggregated proteins. Clinical subtypes include behavioral variant FTD (bvFTD), primary progressive aphasia (PPA), which can be subdivided into semantic variant PPA (svPPA) or nonfluent agrammatic PPA (nfaPPA) and FTD associated with motor neuron disease (FTD-MND). Structural imaging is often the first step in making an image supported diagnoses of FTLD. Regional patterns of atrophy can be assessed on MR and graded according to the global cortical atrophy scale. FTLD is typically associated with atrophy of the frontal and temporal lobes. The patterns of atrophy are associated with the specific clinical subtypes, underlying neuropathology and genetic mutations although there is significant overlap. 18F-FDG-PET is useful for distinguishing FTLD from other forms of dementia and focal areas of hypometabolism can often precede atrophy identified on structural MR imaging. There are currently no biomarkers with which to unambiguously diagnose DLB or FTLD and both conditions demonstrate a wide range of heterogeneity. A combined approach of structural and functional imaging improves diagnostic accuracy in both conditions.