Radiomics-based decision support tool assists radiologists in small lung nodule classification and improves lung cancer early diagnosis.

BACKGROUND: Methods to improve stratification of small (≤15 mm) lung nodules are needed. We aimed to develop a radiomics model to assist lung cancer diagnosis. METHODS: Patients were retrospectively identified using health records from January 2007 to December 2018. The external test set was obtained from the national LIBRA study and a prospective Lung Cancer Screening programme. Radiomics features were extracted from multi-region CT segmentations using TexLab2.0. LASSO regression generated the 5-feature small nodule radiomics-predictive-vector (SN-RPV). K-means clustering was used to split patients into risk groups according to SN-RPV. Model performance was compared to 6 thoracic radiologists. SN-RPV and radiologist risk groups were combined to generate "Safety-Net" and "Early Diagnosis" decision-support tools. RESULTS: In total, 810 patients with 990 nodules were included. The AUC for malignancy prediction was 0.85 (95% CI: 0.82-0.87), 0.78 (95% CI: 0.70-0.85) and 0.78 (95% CI: 0.59-0.92) for the training, test and external test datasets, respectively. The test set accuracy was 73% (95% CI: 65-81%) and resulted in 66.67% improvements in potentially missed [8/12] or delayed [6/9] cancers, compared to the radiologist with performance closest to the mean of six readers. CONCLUSIONS: SN-RPV may provide net-benefit in terms of earlier cancer diagnosis.

Assessment of the levels of termination of the conus medullaris and thecal sac in the pediatric population.

PURPOSE: This study assessed the position of the termination of the conus medullaris (the point where the spinal cord tapers to an end) and thecal sac (the sheath of dura mater that surrounds the spinal cord and caudal nerve roots) in a large pediatric population, to characterise the nature of the pediatric Gaussian distribution and assess whether age affected the distribution. The study further aimed to assess the effect of gender on termination positions. METHODS: A total of 520 MRI spine studies of children aged between 1 month and 19 years old were collected from two pediatric tertiary referral centres in the UK and Italy. Studies with pathological findings were excluded, and normal scans were found using keyword search algorithms on a database of radiologists' reports. The reported scans were individually assessed and reviewed by two experienced neuroradiologists. The termination points of the conus medullaris and thecal sac were determined for each study. Local IRB approvals were sought. RESULTS: The results showcased a Gaussian distribution in both conus medullaris (r=0.8997) and thecal sac termination levels (r=0.9639). No statistically significant results were noted with increasing age for the termination positions of the conus medullaris or thecal sac (p = 0.154, 0.063). No statistical significance was observed with gender variation with either anatomical landmark. A weak positive correlation was observed between the termination levels of the conus medullaris and the thecal sac (r=0.2567) CONCLUSION: Termination levels across all pediatric age range followed a Gaussian distribution. Knowledge of normal termination levels has relevant clinical implications, including the assessment of patients with suspected spinal dysraphism.

2021 WHO classification of tumours of the central nervous system: a review for the neuroradiologist.

The fifth edition of the World Health Organization Classification of Tumours of the Central Nervous System (WHO CNS5) published in 2021 builds on the 2016 edition and incorporates output from the Consortium to Inform Molecular and Practical Approaches to CNS Tumour Taxonomy (cIMPACT-NOW). WHO CNS5 introduces fundamental changes to brain tumour classification through the introduction of new tumour families and types, especially in the paediatric population, and a revision of diagnostic criteria for some of the existing neoplasms. Neuroradiologists are central to brain tumour diagnostics, and it is therefore essential that they become familiar with the key updates. This review aims to summarise the most relevant updates for the neuroradiologist and, where available, discuss the known radiophenotypes of various new tumour types to allow for increased accuracy of language and diagnosis. Of particular importance, WHO CNS5 places greater emphasis on organising tumours by molecular type to reflect biology, as well as to allow for better planning of treatment. The principal updates in adult tumours concern the molecular definition of glioblastoma, restructuring of diffuse gliomas, and the introduction of several new tumour types. The updates to the paediatric classification are protean, ranging from the introduction of new types to establishing separate tumour families for paediatric-type gliomas. This review summarises the most significant revisions and captures the rationale and radiological implications for the major updates.

Anti-NMDAR encephalitis complicating pregnancy.

Anti-N-methyl-D-aspartate receptor (NMDAR) encephalitis was first reported in 2005 in four patients with ovarian teratomas; there have been many further cases reported since the antigen for the NMDAR antibody was confirmed in 2007. Patients characteristically have a well-defined set of features, characterised by psychiatric disturbance, seizures and cognitive disturbance, followed by movement disorders, disorders of consciousness and dysautonomia. To date, 14 cases of NMDAR encephalitis have been described in the context of pregnancy. We report a case of NMDAR encephalitis in a 34-year-old woman at 8 weeks' gestation. She had a turbulent clinical course and was initially admitted to a psychiatric unit. She was successfully treated with first-line immunomodulatory therapies and surgical resection of an ovarian teratoma. Following discharge she delivered a healthy baby and made a complete clinical recovery.

Imaging Spectrum of HTLV-1-Related Neurologic Disease: A Pooled Series and Review.

Purpose of Review: Human T-cell lymphotropic virus type 1 (HTLV-1)-associated myelopathy (HAM) is a well-recognized neurologic complication of HTLV-1. Beyond HAM, several other neurologic manifestations are increasingly recognized, including acute myelopathy, encephalopathy, and myositis. The clinical and imaging features of these presentations are less well understood and potentially underdiagnosed. In this study, we summarize the imaging features of HTLV-1-related neurologic disease, providing both a pictorial review and pooled series of the less well-recognized presentations. Recent Findings: 35 cases of acute/subacute HAM and 12 cases of HTLV-1-related encephalopathy were found. In subacute HAM, cervical and upper thoracic longitudinally extensive tranverse myelitis was noted, while in HTLV-1-related encephalopathy, confluent lesions in the frontoparietal white matter and along the corticospinal tracts were the most prevalent finding. Summary: There are varied clinical and imaging presentations of HTLV-1-related neurologic disease. Recognition of these features aids early diagnosis where therapy may have the greatest benefit.

Real-world evaluation of Brainomix e-Stroke software.

BACKGROUND AND PURPOSE: Brainomix e-Stroke is an artificial intelligence-based decision support tool that aids the interpretation of CT imaging in the context of acute stroke. While e-Stroke has the potential to improve the speed and accuracy of diagnosis, real-world validation is essential. The aim of this study was to prospectively evaluate the performance of Brainomix e-Stroke in an unselected cohort of patients with suspected acute ischaemic stroke. METHODS: The study cohort included all patients admitted to the University College London Hospital Hyperacute Stroke Unit between October 2021 and April 2022. For e-ASPECTS and e-CTA, the ground truth was determined by a neuroradiologist with access to all clinical and imaging data. For e-CTP, the values of the core infarct and ischaemic penumbra were compared with those derived from syngo.via, an alternate software used at our institution. RESULTS: 1163 studies were performed in 551 patients admitted during the study period. Of these, 1130 (97.2%) were successfully processed by e-Stroke in an average of 4 min. For identifying acute middle cerebral artery territory ischaemia, e-ASPECTS had an accuracy of 77.0% and was more specific (83.5%) than sensitive (58.6%). The accuracy for identifying hyperdense thrombus was lower (69.1%), which was mainly due to many false positives (positive predictive value of 22.9%). Identification of acute haemorrhage was highly accurate (97.8%) with a sensitivity of 100% and a specificity of 97.6%; false positives were typically caused by areas of calcification. The accuracy of e-CTA for large vessel occlusions was 91.5%. The core infarct and ischaemic penumbra volumes provided by e-CTP strongly correlated with those provided by syngo.via (ρ=0.804-0.979). CONCLUSION: Brainomix e-Stroke software provides rapid and reliable analysis of CT imaging in the acute stroke setting although, in line with the manufacturer's guidance, it should be used as an adjunct to expert interpretation rather than a standalone decision-making tool.

Cerebral microhaemorrhage in COVID-19: a critical illness related phenomenon?

BACKGROUND: Cerebral microhaemorrhages are increasingly being recognised as a complication of COVID-19. This observational retrospective study aims to further investigate the potential pathophysiology through assessing the pattern of microhaemorrhage and clinical characteristics of patients with COVID-19 and microhaemorrhage. By comparing with similar patterns of microhaemorrhage in other non-COVID-19 disease, this study aims to propose possible common pathogenic mechanisms. METHODS: A retrospective observational case series was performed identifying all patients with COVID-19 complicated by cerebral microhaemorrhage on MRI. The distribution and number of microhaemorrhages were recorded using the microbleed anatomical scale, and patients' baseline characteristics and salient test results were also recorded. RESULTS: Cerebral microhaemorrhages were noted to have a predilection for the corpus callosum, the juxtacortical white matter and brainstem. All patients had a preceding period of critical illness with respiratory failure and severe hypoxia necessitating intubation and mechanical ventilation. DISCUSSION: This study demonstrates a pattern of cerebral microhaemorrhage that is similar to the pattern reported in patients with non-COVID-19 related critical illness and other causes of severe hypoxia. This raises questions regarding whether microhaemorrhage occurs from endothelial dysfunction due the direct effect of SARS-CoV-2 infection or from the secondary effects of critical illness and hypoxia.