The new era of artificial intelligence in neuroradiology: current research and promising tools.

Radiology has a number of characteristics that make it an especially suitable medical discipline for early artificial intelligence (AI) adoption. These include having a well-established digital workflow, standardized protocols for image storage, and numerous well-defined interpretive activities. The more than 200 commercial radiologic AI-based products recently approved by the Food and Drug Administration (FDA) to assist radiologists in a number of narrow image-analysis tasks such as image enhancement, workflow triage, and quantification, corroborate this observation. However, in order to leverage AI to boost efficacy and efficiency, and to overcome substantial obstacles to widespread successful clinical use of these products, radiologists should become familiarized with the emerging applications in their particular areas of expertise. In light of this, in this article we survey the existing literature on the application of AI-based techniques in neuroradiology, focusing on conditions such as vascular diseases, epilepsy, and demyelinating and neurodegenerative conditions. We also introduce some of the algorithms behind the applications, briefly discuss a few of the challenges of generalization in the use of AI models in neuroradiology, and skate over the most relevant commercially available solutions adopted in clinical practice. If well designed, AI algorithms have the potential to radically improve radiology, strengthening image analysis, enhancing the value of quantitative imaging techniques, and mitigating diagnostic errors.

A radiologia tem uma série de características que a torna uma disciplina médica especialmente adequada à adoção precoce da inteligência artificial (IA), incluindo um fluxo de trabalho digital bem estabelecido, protocolos padronizados para armazenamento de imagens e inúmeras atividades interpretativas bem definidas. Tal adequação é corroborada pelos mais de 200 produtos radiológicos comerciais baseados em IA recentemente aprovados pelo Food and Drug Administration (FDA) para auxiliar os radiologistas em uma série de tarefas restritas de análise de imagens, como quantificação, triagem de fluxo de trabalho e aprimoramento da qualidade das imagens. Entretanto, para o aumento da eficácia e eficiência da IA, além de uma utilização clínica bem-sucedida dos produtos que utilizam essa tecnologia, os radiologistas devem estar atualizados com as aplicações em suas áreas específicas de atuação. Assim, neste artigo, pesquisamos na literatura existente aplicações baseadas em IA em neurorradiologia, mais especificamente em condições como doenças vasculares, epilepsia, condições desmielinizantes e neurodegenerativas. Também abordamos os principais algoritmos por trás de tais aplicações, discutimos alguns dos desafios na generalização no uso desses modelos e introduzimos as soluções comercialmente disponíveis mais relevantes adotadas na prática clínica. Se cautelosamente desenvolvidos, os algoritmos de IA têm o potencial de melhorar radicalmente a radiologia, aperfeiçoando a análise de imagens, aumentando o valor das técnicas de imagem quantitativas e mitigando erros de diagnóstico.

Mechanism of molecular interaction of sitagliptin with human DPP4 enzyme - New Insights.

PURPOSE: Dipeptidyl peptidase 4 (DPP4) inactivates a range of bioactive peptides. The cleavage of insulinotropic peptides and glucagon-like peptide 1 (GLP1) by DPP4 directly influences glucose homeostasis. This study aimed to describe the mode of interaction between sitagliptin (an antidiabetic drug) and human DPP4 using in silico approaches. MATERIALS AND METHODS: Docking studies were conducted using AutoDock Vina, 2D and 3D schematic drawings were obtained using PoseView and PLIP servers, and the DPP4-sitagliptin complex was visualized with Pymol software. RESULTS: The best affinity energy to form the DPP4-sitagliptin complex was E-value â€‹= â€‹- 8.1 â€‹kcal â€‹mol-1, as indicated by docking simulations. This result suggests a strong interaction. According to our observations, hydrophobic interactions involving the amino acids residues Tyr663 and Val712, hydrogen bonds (Glu203, Glu204, Tyr663, and Tyr667), π-Stacking interactions (Phe355 and Tyr667), and halogenic bonds (Arg123, Glu204, and Arg356) were prevalent in the DPP4-sitagliptin complex. Root Mean Square Deviation prediction also demonstrated that the global structure of the human DPP4 did not have a significant change in its topology, even after the formation of the DPP4-sitagliptin complex. CONCLUSION: The stable interaction between the sitagliptin ligand and the DPP4 enzyme was demonstrated through molecular docking simulations. The findings presented in this work enhance the understanding of the physicochemical properties of the sitagliptin interaction site, supporting the design of more efficient gliptin-like iDPP4 inhibitors.

Vascular Myelopathies.

There are many vascular disorders that can affect the spinal cord, and their prevalence and etiology are highly influenced by age, sex, and risk factors. This article reviews the embryology and anatomy of the spinal cord, as well as several vascular conditions, describing their clinical and imaging presentation, emphasizing the different imaging modalities' contributions to increasing specificity and better defining the most appropriate therapy strategy for improving the patient's prognosis.

Imaging Aspects of Toxic and Metabolic Myelopathies.

Metabolic and toxic myelopathies usually occurs due to several different causes. Metabolic myelopathy usually occurs due to deficiency of a nutrient, such as vitamin B12. Toxic myelopathy occurs secondary to the exposure to an external toxic agent. Although they may have a difficult diagnosis, determination of the specific cause of myelopathy is of utmost importance, because many causes are amenable to treatment. Although they have many clinical, electrophysiologic, and neuropathologic similarities, imaging may aid in the suspicion of toxic or metabolic myelopathy. The aim of this article, is to review the imaging features of the main toxic and metabolic myelopathies.

"Bunch of acai berries sign": a new radiological sign in patients with CNS involvement in Chagas disease.

Chagas disease is an infection caused by Trypanosoma cruzi, a parasite endemic in Latin America. Acute involvement of the CNS by Chagas has been considered rare, but presumed reactivation of chronic disease in immunosuppressed patients has been the subject of recent reports. Our objective is to describe the clinical and imaging characteristics of four patients with Chagas disease and CNS involvement, and the patients had to have available MRI and a diagnosis confirmed by biopsy. The imaging findings were similar, highlighting the presence of focal cerebral lesions with hypointensity on T2-WI, and these lesions assume a "bunch of acai berries appearance", a fruit involved in the transmission of T. cruzi. The post Gd T1-WI shows punctate enhancement. Knowledge of this pattern may be crucial to recognize this disease in immunocompromised patients from endemic areas.

Brain MRI Abnormalities, Epilepsy and Intellectual Disability in LAMA2 Related Dystrophy - a Genotype/Phenotype Correlation.

BACKGROUND: LAMA2-related muscular dystrophy is a disorder that causes muscle weakness and varies in severity, from a severe, congenital type to a milder, late-onset form. However, the disease does not only affect the muscles, but has systemic involvement and can lead to alterations such as brain malformation, epilepsy and intellectual disability. OBJECTIVE: Describe the frequency of cortical malformations, epilepsy and intellectual disability in LAMA2-RD in a Brazilian cohort and correlate the neurological findings to genetic and motor function. METHODS: This is an observational study of 52 LAMA2-RD patients, who were divided into motor function subgroups and compared based on brain MRI findings, epilepsy, intellectual disability, and type of variants and variant domains. RESULTS: 44 patients (84.6%) were only able to sit, and 8 patients (15.4%) were able to walk. 10 patients (19.2%) presented with cortical malformations (polymicrogyria, lissencephaly-pachygyria, and cobblestone),10 patients (19.2%) presented with epilepsy, and 8 (15.4%) had intellectual disability. CNS manifestations correlated with a more severe motor phenotype and none of the patients able to walk presented with cortical malformation or epilepsy. There was a relation between gene variants affecting the laminin-α2 LG-domain and the presence of brain malformation (P = 0.016). There was also a relation between the presence of null variants and central nervous system involvement. A new brazilian possible founder variant was found in 11 patients (21,15%) (c.1255del; p. Ile419Leufs*4). CONCLUSION: Cortical malformations, epilepsy and intellectual disability are more frequent among LAMA2-RD patients than previously reported and correlate with motor function severity and the presence of variants affecting the laminin-α2 LG domain. This brings more insight fore phenotype-genotype correlations, shows the importance of reviewing the brain MRI of patients with LAMA2-RD and allows greater attention to the risk of brain malformation, epilepsy, and intellectual disability in those patients with variants that affect the LG domain.

Intracranial vessel wall magnetic resonance imaging features of infectious vasculitis.

Vasculitis is a complication of several infectious diseases affecting the central nervous system, which may result in ischemic and/or hemorrhagic stroke, transient ischemic attack, and aneurysm formation. The infectious agent may directly infect the endothelium, causing vasculitis, or indirectly affect the vessel wall through an immunological mechanism. The clinical manifestations of these complications usually overlap with those of non-infectious vascular diseases, making diagnosis challenging. Intracranial vessel wall magnetic resonance imaging (VWI) enables the evaluation of the vessel wall and the diseases that affect it, providing diagnostic data beyond luminal changes and enabling the identification of inflammatory changes in cerebral vasculitis. This technique demonstrates concentric vessel wall thickening and gadolinium enhancement, associated or not with adjacent brain parenchymal enhancement, in patients with vasculitis of any origin. It permits the detection of early alterations, even before a stenosis occurs. In this article, we review the intracranial vessel wall imaging features of infectious vasculitis of bacterial, viral, and fungal etiologies.

Arterial Spin Labeling: Techniques, Clinical Applications, and Interpretation.

Arterial spin labeling (ASL) is an emerging noninvasive MRI technique for assessing cerebral perfusion. An important advantage of ASL perfusion is the lack of a requirement for an exogenous tracer. ASL uses magnetically labeled water protons from arterial blood as an endogenous diffusible tracer. For this reason, ASL is an attractive perfusion imaging modality for children and for patients with contraindications or adverse reactions to gadolinium, patients with renal failure, and those who need repeated follow-up imaging. Another advantage of ASL is the possibility of quantifying cerebral blood flow, which provides an opportunity for comparative analysis among multiple longitudinal studies, unlike other MR perfusion techniques, which are semiquantitative and yield relative perfusion parameters. Advances in MRI technology and pulse sequence design have translated ASL beyond the research arena to successful clinical implementation. However, ASL is still underused in routine clinical practice. Some disadvantages of ASL include a lower signal-to-noise ratio and a longer acquisition time than those with dynamic susceptibility contrast-enhanced MRI. Additional factors limiting the use of ASL include variations in existing techniques and pulse sequence design, the complexity of implementation and postprocessing, insufficient experience with and/or knowledge of the potential clinical applications, and the absence of interpretation guidelines. The authors review the technical and physiologic basis of ASL perfusion, as well as artifacts, pitfalls, and its current clinical applications. A practical approach for interpreting ASL findings is also suggested.

Extra-pituitary midline structural abnormalities associated with ectopic posterior pituitary detected on a new rapid MRI protocol (FAST1.2)

ABSTRACT Objective: Test if the MRI FAST1.2 protocol can detect extra-pituitary midline structural brain abnormalities in patients with ectopic posterior pituitary (EPP), and highlighting their radiological-laboratory correlations. Subjects and methods: Cross-sectional study of patients with EPP and control group. All individuals were submitted to FAST1.2, which combines the FAST1 protocol developed by our group with 3D T2DRIVE imaging. Results: We evaluated 36 individuals with EPP and 78 as control group. Pituitary stalk (PS) was identified in 7/36 patients in EPP group by FAST1, and in 24/36 patients in FAST1.2 (p < 0.001). FAST1 failed to detect PS in one individual in the control group, while the FAST1.2 defined the PS in all individuals. In EPP group, eleven had interhypothalamic adhesion (IHA), three septo-optic dysplasia, and one cerebellar malformation. We didn't observe higher frequency of panhypopituitarism or developmental delay in patients with IHA. In control group, three had pars intermedia cysts, one hydrocephalus, and one hypothalamic hamartoma. Conclusions: FAST1.2 allows confident recognition of midline structural abnormalities, including the pituitary stalk and IHA, thereby making MRI acquisition faster and with no need for contrast administration. IHA could be associated with defects in neuronal migration, as occur in patients with EPP, with no clinical significance.

Forging Connections in Latin America to Advance AI in Radiology.

The 1° Encontro Latino-Americano de IA em Saúde (1st Latin American Meeting on AI in Health) was held during the 2022 Jornada Paulista de Radiologia, the annual radiology meeting in the state of São Paulo. The event was created to foster discussion among Latin American countries about the complexity, challenges, and opportunities in developing and using artificial intelligence (AI) in those countries. Technological improvements in AI have created high expectations in health care. AI is recognized increasingly as a game changer in clinical radiology. To counter the fear that AI would "take over" radiology, the program included activities to educate radiologists. The development of AI in Latin America is in its early days, and although there are some pioneer cases, many regions still lack world-class technological infrastructure and resources. Legislation, regulation, and public policies in data privacy and protection, digital health, and AI are recent advances in many countries. The meeting program was developed with a broad scope, with expertise from different countries, backgrounds, and specialties, with the objective of encompassing all levels of complexity (from basic concepts to advanced techniques), perspectives (clinical, technical, ethical, and business), and specialties (both informatics and data science experts and the usual radiology clinical groups). It was an opportunity to connect with peers from other countries and share lessons learned about AI in health care in different countries and contexts. Keywords: Informatics, Use of AI in Education, Impact of AI on Education, Social Implications © RSNA, 2022.

Extra-pituitary midline structural abnormalities associated with ectopic posterior pituitary detected on a new rapid MRI protocol (FAST1.2).

Objective: Test if the MRI FAST1.2 protocol can detect extra-pituitary midline structural brain abnormalities in patients with ectopic posterior pituitary (EPP), and highlighting their radiological-laboratory correlations. Subjects and methods: Cross-sectional study of patients with EPP and control group. All individuals were submitted to FAST1.2, which combines the FAST1 protocol developed by our group with 3D T2DRIVE imaging. Results: We evaluated 36 individuals with EPP and 78 as control group. Pituitary stalk (PS) was identified in 7/36 patients in EPP group by FAST1, and in 24/36 patients in FAST1.2 (p < 0.001). FAST1 failed to detect PS in one individual in the control group, while the FAST1.2 defined the PS in all individuals. In EPP group, eleven had interhypothalamic adhesion (IHA), three septo-optic dysplasia, and one cerebellar malformation. We didn't observe higher frequency of panhypopituitarism or developmental delay in patients with IHA. In control group, three had pars intermedia cysts, one hydrocephalus, and one hypothalamic hamartoma. Conclusion: FAST1.2 allows confident recognition of midline structural abnormalities, including the pituitary stalk and IHA, thereby making MRI acquisition faster and with no need for contrast administration. IHA could be associated with defects in neuronal migration, as occur in patients with EPP, with no clinical significance.

Adding T2-Weighted Images to FAST1 Protocol to Evaluate the Anatomy of the Hypothalamic-Pituitary Region.

INTRODUCTION: Ectopic posterior pituitary (EPP) is a malformation of the hypothalamic-pituitary region presented as a spectrum from isolated growth hormone deficiency (GHD) to multiple pituitary hormone deficiencies (MPHDs). Our goal was to establish whether the FAST1.2 protocol, which combines the FAST1 protocol with 3D-T2 DRIVE images, could identify the pituitary stalk (PS) and the regional anatomy more accurately. METHODS: A retrospective study of 36 individuals with EPP and hypopituitarism and a control group of 78 individuals with eutopic posterior pituitary was conducted. All individuals were submitted to FAST1.2. The position and size of the pituitary lobes were described, and the presence/absence of the PS was confirmed. RESULTS: FAST1 identified the PS in 19% of individuals with EPP, while FAST1.2 identified the PS in 67% (p < 0.001). In the FAST1.2 protocol, the PS was visible in all control individuals. All EPP patients with isolated GHD had visible PS in FAST1.2, while only 58.6% of MPHD cases had visible PS. The size of the anterior lobe and the anteroposterior length of the posterior pituitary were smaller in the EPP group versus controls (p < 0.001). We noticed a reduced anterior pituitary lobe in both diameters in MPHD patients (p < 0.05). Six patients acquired new pituitary hormone deficiencies not recognized at the time of MRI; in this group, only 1 patient had a PS not visible in FAST1.2. DISCUSSION/CONCLUSION: The FAST1.2 protocol could prevent the misdiagnosis of idiopathic GHD in patients with short stature and could also be important in the progression to MPHD. The PS could be considered a predictor of hypopituitarism, but its use as an isolated indicator for the progression to MPHD is not recommended. Our results reinforce the use of the size of the anterior lobe as a predictor of hypopituitarism and a possible predictor of the degree of pituitary insufficiency. The FAST1.2 protocol could be used as an alternative to gadolinium administration, as a cheaper and faster method, while eliminating the potential risks associated with the administration of contrast media.

Neurological imaging findings in hospitalized COVID-19 patients: a retrospective observational study in two Brazilian reference centers / Achados de neuroimagem em pacientes hospitalizados por COVID-19: um estudo retrospectivo e observacional em dois serviços brasileiros de referência

ABSTRACT Background: A variety of neurological manifestations have been attributed to COVID-19. Objective: To investigate the occurrence of neurological symptoms and neuroimaging findings in patients hospitalized in two Brazilian reference centers. Methods: We performed a retrospective cohort study of patients who had laboratory-confirmed COVID-19 presenting in two hospitals in Brazil between March 4 and July 7, 2020, who underwent brain imaging. Results: We recorded 1,359 patients with laboratory-confirmed COVID-19. Brain imaging was performed in 250 (18.4%) patients with neurological symptoms, and nine of them (3.6%) had acute or subacute ischemic stroke neuroimaging findings. Six of the nine patients initially presented with respiratory symptoms while the other three patients presented to the emergency room with acute stroke signs. Conclusions: We described the neuroimaging findings of patients infected with COVID-19 who presented with neurological symptoms in two major hospitals in Brazil. We reinforce the importance of being aware of cerebrovascular complications, both in severe hospitalized patients and in patients who present to the emergency room with acute neurological symptoms, even in the elderly.

RESUMO Introdução: Diversas manifestações neurológicas têm sido atribuídas à COVID-19. Objetivo: Investigar a ocorrência de sintomas neurológicos e achados de neuroimagem em pacientes internados em dois centros de referência brasileiros. Métodos: Estudo retrospectivo que avaliou pacientes internados em dois hospitais no Brasil entre 4 de março e 7 de julho de 2020, com confirmação laboratorial de infecção pelo COVID-19 e que foram submetidos a tomografia computadorizada ou ressonância magnética do crânio em razão de sintomas neurológicos. Resultados: Obtivemos 1.359 pacientes com confirmação laboratorial de infecção pelo COVID-19. Deles, 250 (18,4%) apresentaram sintomas neurológicos e foram submetidos a exames de imagem do crânio e nove (3,6%) demonstraram achados de neuroimagem compatíveis com acidente vascular cerebral (AVC) isquêmico agudo ou subagudo. Em seis dos nove pacientes, observaram-se inicialmente tosse e dispneia graves, enquanto outros três chegaram ao pronto-socorro com sinais de AVC agudo. Conclusões: Foram descritos os achados de neuroimagem em pacientes infectados com COVID-19 em dois grandes centros de referência brasileiros. Reforçamos a importância de estar atento aos quadros neurológicos, especialmente de AVC, tanto em pacientes graves hospitalizados quanto em pacientes que chegam ao pronto-socorro com sintomas neurológicos agudos, mesmo em idosos.

Neurological imaging findings in hospitalized COVID-19 patients: a retrospective observational study in two Brazilian reference centers.

BACKGROUND: A variety of neurological manifestations have been attributed to COVID-19. OBJECTIVE: To investigate the occurrence of neurological symptoms and neuroimaging findings in patients hospitalized in two Brazilian reference centers. METHODS: We performed a retrospective cohort study of patients who had laboratory-confirmed COVID-19 presenting in two hospitals in Brazil between March 4 and July 7, 2020, who underwent brain imaging. RESULTS: We recorded 1,359 patients with laboratory-confirmed COVID-19. Brain imaging was performed in 250 (18.4%) patients with neurological symptoms, and nine of them (3.6%) had acute or subacute ischemic stroke neuroimaging findings. Six of the nine patients initially presented with respiratory symptoms while the other three patients presented to the emergency room with acute stroke signs. CONCLUSIONS: We described the neuroimaging findings of patients infected with COVID-19 who presented with neurological symptoms in two major hospitals in Brazil. We reinforce the importance of being aware of cerebrovascular complications, both in severe hospitalized patients and in patients who present to the emergency room with acute neurological symptoms, even in the elderly.