Neuroimaging In Diagnosis Research Articles

STF-Net: sparsification transformer coding guided network for subcortical brain structure segmentation.

Subcortical brain structure segmentation plays an important role in the diagnosis of neuroimaging and has become the basis of computer-aided diagnosis. Due to the blurred boundaries and complex shapes of subcortical brain structures, labeling these structures by hand becomes a time-consuming and subjective task, greatly limiting their potential for clinical applications. Thus, this paper proposes the sparsification transformer (STF) module for accurate brain structure segmentation. The self-attention mechanism is used to establish global dependencies to efficiently extract the global information of the feature map with low computational complexity. Also, the shallow network is used to compensate for low-level detail information through the localization of convolutional operations to promote the representation capability of the network. In addition, a hybrid residual dilated convolution (HRDC) module is introduced at the bottom layer of the network to extend the receptive field and extract multi-scale contextual information. Meanwhile, the octave convolution edge feature extraction (OCT) module is applied at the skip connections of the network to pay more attention to the edge features of brain structures. The proposed network is trained with ahybrid loss function. The experimental evaluation on two public datasets: IBSR and MALC, shows outstanding performance in terms of objective and subjective quality.

Application of neuroimaging in diagnosis of focal cortical dysplasia: A survey of computational techniques

Focal Cortical Dysplasia (FCD) is a neurodevelopmental disorder characterized by abnormal neuronal migration, differentiation, and maturation, resulting in a range of clinical symptoms including drug-resistant epilepsy. Accurate and timely diagnosis of FCD is essential for effective treatment and management of patients with this condition. In recent years, there have been significant advances in neuroimaging and machine learning techniques, enabling automated detection of FCD lesions with increasing accuracy and efficiency.In this survey article, we provide an overview of the current state-of-the-art in computational techniques for the automated detection of FCD lesions using neuroimaging. We first introduce some common imaging findings that radiologists look for in FCD lesions, then review the automatic detection techniques studied in the last decade. These techniques have shown promising results in detecting and localizing FCD lesions, improving diagnostic accuracy and reducing misdiagnoses, diagnosis time, and cost of care.We suggest that the use of these types of quantitative image analysis tools and algorithms can play a key role in improving the overall management and outcome of patients with FCD. However, further studies are needed to validate and optimize the performance of these techniques in clinical practice. In summary, the combination of advanced neuroimaging and computational techniques has the potential to revolutionize the diagnosis and treatment of FCD, leading to better outcomes for patients with this condition.

Perinatal Stroke as It is: Updates, Insights and Challenges

Perinatal stroke comprises a heterogeneous group of focal cerebrovascular injuries that occur between 20 weeks of gestation and 28 days of postnatal life. Perinatal stroke is a leading cause of life-long disability, causing most cases of hemiparetic cerebral palsy. The intent of this article was to provide a comprehensive review of the 6 different types of perinatal stroke based on neuroimaging and clinical presentation, highlighting their similarities and distinctions in etiology and outcome, and further discuss a neuroimaging pathway for suspected perinatal stroke and follow-up imaging.Learning Objective: To provide an update on the current knowledge of the role of neuroimaging in diagnosis and long-term prognosis of perinatal stroke diseases and to understand the microglial role in perinatal arterial stroke

A case of primary adrenal insufficiency unfolding itself as a genetic syndrome

ABSTRACT Addison disease can occur at any age but most often presents during the second or third decades of life. An 11-year-old male child presented to us with complaints of pigmentation of the skin, decreased appetite, and weight loss from the last 1 year. He also had visual disturbances and learning disabilities from last 6 months. Investigations revealed the diagnosis of adrenal insufficiency and neuroimaging done was suggestive of diffuse demyelination. For further confirmation, a blood sample was sent for determination of very long chain fatty acids, which revealed accumulation of C26 fatty acids, thus confirming the diagnosis of adrenoleukodystrophy. He was treated with hydrocortisone, fludrocortisone, and anti-oxidants and was referred for bone marrow transplantation. X-linked adrenoleukodystrophy is a genetic disease, so a high index of suspicion is required to diagnose it in cases presenting primarily with non-neurological symptoms.

Breaking the amyotrophic lateral sclerosis early diagnostic barrier: the promise of general markers

Amyotrophic lateral sclerosis (ALS) is a severe neurodegenerative disease that is associated with selective and progressive loss of motor neurons. As a consequence, the symptoms of ALS are muscle cramps and weakness, and it eventually leads to death. The general markers for early diagnosis can assist ALS patients in receiving early intervention and prolonging their survival. Recently, some novel approaches or previously suggested methods have validated the potential for early diagnosis of ALS. The purpose of this review is to summarize the status of current general markers discovery and development for early diagnosis of ALS, including genes, proteins neuroimaging, neurophysiology, neuroultrasound, and machine learning models. The main genetic markers evaluated are superoxide dismutase 1 (SOD1), chromosome 9 open reading frame 72 (C9orf72), transactivation-responsive DNA binding protein 43 (TARDBP), and fused in sarcoma (FUS) genes. Among proteins, neurofilament light chain is still the most established disease-specific adaptive change in ALS. The expression of chitinases, glial fibrillary acidic protein (GFAP), and inflammatory factors are changed in the early stage of ALS. Besides, more patient-friendly and accessible feature assays are explored by the development of neuroimaging, neurophysiology, and neuroultrasound techniques. The novel disease-specific changes exhibited the promising potential for early diagnosis of ALS. All of these general markers still have limitations in the early diagnosis, therefore there is an urgent need for the validation and development of new disease-specific features for ALS.

Травматические повреждения головного мозга: классификация, клиника, нейровизуализация

Modern classification of traumatic brain injury with identification of clinical and morphological variants is provided. Neurological semiotics and neuroimaging diagnosis of concussion, mild, moderate and severe cerebral contusion, compression of the brain with epidural, subdural and intracerebral hematomas are described based on the analysis of observations of the National Medical Research Center for Neurosurgery named after Academician N.N. Burdenko.

P03.05.B PRIMARY GAMMA KNIFE RADIOSURGERY FOR PINEAL REGION TUMORS, A SYSTEMATIC REVIEW AND POOLED ANALYSIS OF AVAILABLE LITERATURE WITH HISTOLOGICAL STRATIFICATION

Abstract BACKGROUND Pineal region tumors (PTs) represent extremely rare pathologies, characterized by highly heterogeneous histological patterns. Most of the available evidence for Gamma Knife radiosurgical (GKSR) treatment of PTs arises from multimodal regimens, including GKSR as an adjuvant modality following surgery or as a salvage treatment at recurrence. We aimed to gather the existing evidence on the topic and analyze single-patient level data to address the efficacy and safety of primary GKSR when only a biopsy was attempted or biochemical or neuroimaging diagnosis was available. MATERIAL AND METHODS This is a systematic review of literature (Pubmed, Embase, Cochrane, Science Direct) and pooled analysis of single-patient-level data. A total of 1054 original works were retrieved. After excluding duplicates and irrelevant works, we included 13 papers in our final analysis comprising 64 patients. Additional 12 patients were included from the authors’ original series. RESULTS A total of 76 patients reached the final analysis. Presumptive diagnoses included intrinsic pineal low-grade (46%), glial low-grade (LGG, 5%), pineoblastoma (4%), germ cell tumors (GCTs, 4%), pineal tumors of intermediate differentiation (3%), other pineal tumors (3%), glial high-grade (HGG, 2%) and meningioma (1%). In 32% of cases, the diagnosis was unclear. Only 57% of cases received histological confirmation. The mean age at treatment was 38.7y and the mean lesional volume was 4.2 ± 4 cc. All patients received GKSR with a mean marginal dose (50% isodose) of 14.7 ± 2.1 Gy. At a median 36mo follow-up, local control was achieved in 84% of cases. Ten patients showed progression within a mean time of 24.2mo. Progression was more common in HGG and GCTs (p=0.03) compared to intrinsic pineal tumors. Overall mortality was 13.2%. The median OS was not reached for all included lesions, except high-grade gliomas (8mo). The 3y-OS was 100% for LGG, 90% for the intrinsic pineal, 60% for GCTs, 50% for HHG, and 82% for undetermined tumors. The 3y-PFS was 100% for LGG, 90% for the intrinsic pineal, 32% for GCTs, and 0% for HHG. Median PFS was 5mo for HHG and 34mo for GCTs. The radionecrosis rate was 6%, and cystic degeneration was observed in 2%. Ataxia as presenting symptom strongly predicted mortality (OR 104, p=0.02), while GCTs and HHG histology well predicted PD (OR: 13, p=0.04). CONCLUSION These results support the efficacy and safety of primary GKSR treatment of pineal region tumors. Further studies are needed to validate these results, which highlight the importance of the initial presumptive diagnosis for choosing the best therapeutic strategy.

Case Report: Pelvic Neurofibroma with Atypical Neurofibromatosis Type 1

A 23 short-stature female patient presenting initially to gynecologist for left ovarian mass and bilateral sciatica but on further investigations it had been proved to be big pelvic neurofibroma with little findings of neurofibromatosis type 1. Surgical excision had been done without any complications. We aim to discuss the manifestations of neurofibromatosis type 1 and why lack of some findings in the current case with the role of neuroimaging in diagnosis of the case.

Methylmalonic acidemia: Neurodevelopment and neuroimaging.

Methylmalonic acidemia (MMA) is a genetic disease of abnormal organic acid metabolism, which is one of the important factors affecting the survival rate and quality of life of newborns or infants. Early detection and diagnosis are particularly important. The diagnosis of MMA mainly depends on clinical symptoms, newborn screening, biochemical detection, gene sequencing and neuroimaging diagnosis. The accumulation of methylmalonic acid and other metabolites in the body of patients causes brain tissue damage, which can manifest as various degrees of intellectual disability and severe neurological dysfunction. Neuroimaging examination has important clinical significance in the diagnosis and prognosis of MMA. This review mainly reviews the etiology, pathogenesis, and nervous system development, especially the neuroimaging features of MMA.

Hepatic encephalopathy on magnetic resonance imaging and its uncertain differential diagnoses: a narrative review.

Hepatic encephalopathy (HE) is a severe neuropsychiatric abnormality in patients with either acute or chronic liver failure. Typical brain magnetic resonance imaging findings of HE are bilateral basal ganglia high signal intensities due to manganese deposition in chronic liver disease and hyperintensity in T2, fluid-attenuated inversion recovery, or diffusion-weighted imaging (DWI) with hemispheric white matter changes including the corticospinal tract. Low values on apparent diffusion coefficient mapping of the affected area on DWI, indicating cytotoxic edema, can be observed in acute HE. However, neuropsychological impairment in HE ranges from mild deficits in psychomotor abilities affecting quality of life to stupor or coma with higher grades of hepatic dysfunction. In particular, the long-lasting compensatory mechanisms for the altered metabolism in chronic liver disease make HE imaging results variable. Therefore, the clinical relevance of imaging findings is uncertain and differentiating HE from other metabolic diseases can be difficult. The recent introduction of concepts such as "acute-on-chronic liver failure (ACLF)," a new clinical entity, has led to a change in the clinical view of HE. Accordingly, there is a need to establish a corresponding concept in the field of neuroimaging diagnosis. Herein, we review HE from a historical and etiological perspective to increase understanding of brain imaging and help establish an imaging approach for advanced new concepts such as ACLF. The purpose of this manuscript is to provide an understanding of HE by reviewing neuroimaging findings based on pathological and clinical concepts of HE, thereby assisting in neuroimaging interpretation.

Protocolo diagnóstico y tratamiento de la trombosis venosa cerebral

In the diagnostic approach to cerebral venous thrombosis, both the topographic diagnosis (based on the patient's clinical manifestations, given that they can vary greatly depending on the affected venous sinus) and the neuroimaging diagnosis, in which cerebral magnetic resonance imaging and computed tomography venography or magnetic resonance imaging techniques are especially relevant, must be taken into account, without ignoring the importance of reaching an etiological diagnosis. The treatment strategies for cerebral venous thrombosis are based on anticoagulant treatment and treatment of the underlying causes, early detection, and treatment of possible complications such as epileptic seizures, intracranial hypertension, and hydrocephalus. Lastly, the high risk of recurrence of venous thrombosis that these patients present with must be considered. Therefore, it is necessary to perform an individualized evaluation and adaptation of the duration of anticoagulant treatment depending on the underlying cause.

Modern aspects to the diagnosis and non-surgical treatment of low back pain

Low back pain is one of the most common complaints in primary care. This pain is usually nonspecific and musculoskeletal. However, identification and exclusion of specific causes of pain as early as possible are important for specialists since their underestimation can sometimes lead to life-threatening consequences. The authors analyze literature data on the key facts of anamnesis («red flags»), management of patients with low back pain with emphasis on modern concepts and recommendations for diagnostics, identifying the dominant nature and cause of pain, differential diagnosis, and diagnostic significance of neuroimaging. Special attention is paid to existing options for conservative (drug and non-drug therapy) and interventional treatment methods, which have become increasingly popular in recent years.

Neuroimaging in the Diagnosis of Epilepsy

Neuroimaging is commonly used for presurgical evaluation in epilepsy surgery. Neuroimaging for epilepsy includes structural and functional neuroimaging. Lesions detected by structural neuroimaging are crucial to determine the indication of epilepsy surgery, as well as to predict seizure outcomes, as patients with MRI-visible lesions are likely to have better seizure outcomes. However, MRI lesions sometimes show very faint findings; therefore, the diagnosis of structural neuroimaging requires sophisticated skills. Moreover, the epilepsy focus should not only involve the MRI-visible lesion, but also the surrounding tissue with abnormal neuronal function. The MRI-lesion, which is almost the same as that epileptogenic lesion, is a part of the epileptogenic zone. Surgical strategy should be conducted by comprehensive evaluation including neuroimaging in addition to other modalities.

Application of Machine Learning Techniques for Characterization of Ischemic Stroke with MRI Images: A Review.

Magnetic resonance imaging (MRI) is a standard tool for the diagnosis of stroke, but its manual interpretation by experts is arduous and time-consuming. Thus, there is a need for computer-aided-diagnosis (CAD) models for the automatic segmentation and classification of stroke on brain MRI. The heterogeneity of stroke pathogenesis, morphology, image acquisition modalities, sequences, and intralesional tissue signal intensity, as well as lesion-to-normal tissue contrast, pose significant challenges to the development of such systems. Machine learning (ML) is increasingly being used in predictive neuroimaging diagnosis and prognostication. This paper reviews image processing and machine learning techniques that have been applied to detect ischemic stroke on brain MRI, including details on image acquisition, pre-processing, techniques to segment, extraction of features, and classification into stroke types. The main objective of this work is to find the state-of-art machine learning techniques used to predict the ischemic stroke and their application in clinical set-up. The article selection is performed according to PRISMA guideline. The state-of-the-art on automated MRI stroke diagnosis, with a focus on machine learning, is discussed, along with its advantages and limitations. We found that the various machine learning models discussed in this article are able to detect the infarcts with an acceptable accuracy of 70–90%. However, no one has highlighted the time complexity to predict the stroke in the model developed, which is an important factor. The work concludes with proposals for future recommendations for building efficient and robust deep learning (DL) models for quantitative brain MRI analysis. In recent work, with the application of DL approaches, using large datasets to train the models has improved the detection accuracy and reduced computational complexity. We suggest that the design of a decision support system based on artificial intelligence (AI) and clinical data presenting symptoms is essential to support clinicians to accelerate diagnosis and timeous therapy in the emergency management of stroke.

Spectrum of Surgically Resected Lesions of the Cavernous Sinus: A Neuropathologic Audit.

Background The cavernous sinus is a complex space composed of extradural venous plexus within dural folds. Several important structures like the carotid artery, cranial nerves, and sympathetic nerve fibers traverse through this space. Radiological diagnosis may not be definitive and in the context of discordance between clinical and neuroimaging diagnosis, histopathological evaluation becomes essential for diagnosis and management. Literature on the pathological spectrum of lesions is scarce as, with a shift in the treatment paradigm, most small lesions of cavernous sinus are treated with radiosurgery. However, surgical management still plays a role for larger lesions and in radiologically ambiguous cases for planning the definitive management. Materials and Methods We retrospectively reviewed all surgically resected lesions of the cavernous sinus over the last two decades (1998–2019). The clinical presentation, neuroimaging features, and histopathological findings were reviewed. Lesions extending from sella and other adjacent areas were excluded. Results Thirty-eight cases of isolated cavernous sinus mass lesions were diagnosed over the last two decades (1998–2019). Cavernous hemangiomas (19 cases, 50%) constituted the most frequent pathology, followed by aspergilloma, meningioma, schwannoma, metastatic adenocarcinoma, chondrosarcoma, and chordoma. Overall, 29.4% (10/34) could not be accurately diagnosed on neuroimaging. Of these, four cases of cavernous hemangiomas were mistaken for either meningioma (three cases) or schwannoma (one case). Neither chordoma nor chondrosarcoma was suspected. Conclusion This is the first study in literature, enumerating the pathological and imaging spectrum of surgically resected cavernous sinus lesions. Cavernous hemangiomas, metastases and chordomas, and chondrosarcoma posed the greatest difficulty in diagnosis on neuroimaging and the reasons for the same are analyzed. In the context of clinical and neuroimaging discordance in diagnosis, pathological characterization becomes essential for appropriate and timely management.

Lacunar infarction aggravates the cognitive deficit in the elderly with white matter lesion.

Cerebral white matter lesion (WML) and lacunar infarction (LI) were primary causes of cognitive deficit. Our study aimed to investigate the correlation between LI and cognitive deficit in the elderly with WML. A total of 118 participants (96 WML patients and 22 controls) were consecutively enrolled according to neuroimaging diagnosis of magnetic resonance imaging for this retrospective study. Neuroimaging evaluation and cognitive function assessment were analyzed. Compared with the controls, moderate and severe WML groups had significantly lower scores of Mini-mental State Examination (MMSE) and Montreal Cognitive Assessment (MOCA). Most cognitive domains of MOCA scores decreased, corresponding to the severity of WMLs. While there was no significant difference in score of MMSE between deep WML (DWML) and periventricular WML (PVL) groups, the scores of visuospatial/executive and naming function domains of MOCA appeared to be low in the DWML group. The scores of MMSE and MOCA were higher in only WMLs (WML−) group than WMLs combined with LIs (WML+) group, except for the naming cognitive domain. Moreover, LIs were independently correlated with the cognitive deficit in the elderly with WMLs. In the elderly with WMLs, the presence of LIs is associated with further aggravation of cognitive deficit.

Two case reports of chorea-acanthocytosis and review of literature

BackgroundChorea-acanthocytosis (ChAc), as the most common subtype of neuroacanthocytosis syndrome, is characterized by the presence of acanthocytes and neurological symptoms. It is thought to be caused by the VPS13A (vacuolar protein sorting-associated protein 13A) mutations. This article reports two confirmed cases of ChAc and summarizes some suggestive features, which provide direction for the diagnosis and treatment of acanthocytosis in the future.Case presentationHere, we present two cases of ChAc diagnosed based on typical clinical symptoms, neuroimaging features, genetic findings of VPS13A, and response to the symptomatic treatment.ConclusionsChorea-acanthocytosis is a rare neurodegenerative disease with various early clinical manifestations. The final diagnosis of the ChAc can be established by either genetic analysis or protein expression by Western blotting. Supportive treatments and nursing are helpful to improve the quality of the patient’s life. Nevertheless, it is imperative to investigate the impact of neuroimaging and neuropathological diagnosis in a larger group of ChAc in future studies.

Role of Neuroimaging in Diagnosis of Alzheimer's Disease

Role of Neuroimaging in Diagnosis of Alzheimer's Disease

Клинические синдромы инсультов таламуса заднелатеральной сосудистой территории: результаты проспективного клинического когортного исследования

Актуальность. В статье проанализированы и описаны патофизиологические особенности и закономерности возникновения неврологических, нейропсихологических и клинических сосудистых синдромов таламических инсультов заднелатеральной сосудистой территории. Освещаются особенности неврологической клиники, топической, клинической и нейровизуализационной диагностики таламических инсультов заднелатеральной сосудистой территории по результатам проспективного клинического когортного исследования. Цель исследования: описать и проанализировать клинико-нейровизуализационные особенности сосудистых синдромов таламических инсультов заднелатеральной сосудистой территории в проспективном клиническом когортном исследовании. Материалы и методы. Мы провели проспективное клиническое когортное исследование 319 пациентов с острым инсультом, поступивших в неврологический центр Александровской клинической больницы г. Киева, Украина, в течение первых 24 часов с момента развития инсульта. Все пациенты прошли комплексное клинико-неврологическое, лабораторное, ультразвуковое и нейровизуализационное обследования. Результаты. Среди 319 обследованных больных с острым инсультом нейровизуализационно подтвержденный таламический инсульт диагностирован у 34 (10,6 %) пациентов. Из них у 22 пациентов (средний возраст 61,9 ± 10,2 года) диагностирован острый изолированный инфаркт таламуса, а у 12 пациентов (средний возраст 59,0 ± 9,6 года) — острое таламическое кровоизлияние. Проанализированы, сравнены и описаны специфические неврологические особенности клинических сосудистых синдромов острых таламических инсультов заднелатеральной сосудистой территории.

Long-Term Trends in Stroke Management and Burden Among Low-Income Women in a Rural Area From China (1992-2019): A Prospective Population-Based Study.

Although an increasing number of studies are considering sex-related differences in stroke burden, the trends in stroke burden and management among women in China, especially among low-income women, remain unclear. This study evaluated the long-term trends in stroke management and burden among low-income Chinese women during the period between 1992 and 2019. Stroke burden was assessed using the age-adjusted incidence of first-ever stroke, whereas stroke management was assessed using the rates of neuroimaging diagnoses, hospitalizations, case fatalities, and stroke recurrence. Stroke burden and management were analyzed during four study periods: 1992–1998, 1999–2004, 2005–2012, and 2013–2019. During the 193,385 person-years of surveillance in this study, 597 female stroke patients were identified. The stroke incidences per 100,000 person-years were 88.1 cases during 1992–1998, 145.4 cases during 1999–2004, 264.3 cases during 2005–2012, and 309.8 cases during 2013–2019 (P < 0.001). Between 1992 and 2019, the incidence of stroke significantly increased (6.4% annually) as did the incidence of ischemic stroke (7.8% annually; both, P < 0.001). The rates of neuroimaging diagnoses and hospitalizations significantly increased during the four periods, while the case fatality rates and 1-year recurrence rates decreased significantly for both overall strokes and ischemic strokes, especially among patients ≥45 years old (all, P < 0.001). Among low-income women in China, stroke management is gradually improving, despite the increasing stroke burden. Thus, improved healthcare coverage is needed to further reduce the stroke burden among low-income Chinese women.