This paper demonstrates a case of progressive multifocal leukoencephalopathy (PML) in a patient with multiple myeloma (MM) treated with nine different MM therapies. This case report contributes to the already published 16 cases of PML in patients with MM. Additionally, this paper presents an analysis of cases from the United States Food and Drug Administration Adverse Event Report System database (n = 117) with a description of demographics and MM-specific therapies. Patients with MM, that developed PML, were treated with immunomodulatory drugs (97%), alkylating agents (52%), and/or proteasome inhibitors (49%). Prior to PML diagnosis, 72% of patients received two or more MM therapies. These results indicate that PML in MM is underreported and could be related to treatment with multiple immunosuppressive therapies rather than MM as a disease itself. Physicians should be aware of potential PML in the late stage of heavily treated MM patients.

In this case report a 54-year-old woman had an anterior clinoid process meningioma. She was initially diagnosed as having a cerebrovascular disease, however, her stroke-like symptoms were most likely caused by internal carotid artery compression or vasospasm due to meningiomal involvement, but initially overlooked. Meningiomas are rarely reported as a cause of a stroke. A detailed evaluation can provide a high degree of confidence in differentiating stroke and non-stroke medical conditions, known as stroke mimics or chameleons, to be considered when a diagnosis of stroke has not been confirmed.

A common issue with X-ray examinations (XE) is the erroneous quality classification of the XE, implying that the process needs to be repeated, thus delaying the diagnostic assessment of the XE and increasing the amount of radiation the patient receives. The authors propose a system for automatic quality classification of XE based on convolutional neural networks (CNN) that would simplify this process and significantly decrease erroneous quality classification. The data used for CNN training consist of 4000 knee images obtained via radiography procedure (KXE) in total, with 2000 KXE labeled as acceptable and 2000 as unacceptable. Additionally, half of the KXE belonging to each label are right knees and left knees. Due to the sensitivity to image orientation of some CNNs, three approaches are discussed: (1) Left-right-knee (LRK) classifies XE based just on their label, without taking into consideration their orientation; (2) Orientation discriminator (OD) for the left knee (LK) and right knee (RK) analyses images based on their orientation and inserts them into two separate models regarding orientation; (3) Orientation discriminator combined with knee XRs flipped to the left or right (OD-LFK)/OD-RFK trains the models with all images being horizontally flipped to the same orientation and uses the aforementioned OD to determine whether the image needs to be flipped or not. All the approaches are tested with five CNNs (AlexNet, ResNet50, ResNet101, ResNet152, and Xception), with grid search and k-fold cross-validation. The best results are achieved using the OD-RFK hybrid approach with the Xception network architecture as the classifier and ResNet152 as the OD, with an average AUC of 0.97 (±0.01).

To present a 29-year-old immunocompetent patient with neurosyphilitic changes characterized by multiple acute ischemic brain strokes along with significant narrowing of several large intracranial arteries. Ceftriaxone treatment for 14 days followed by benzathine benzylpenicillin weekly for additional 3 weeks, showed improvement in meningovascular changes.

This is a case report about spinal cord ischaemia (SCI) in a 47-year-old woman with no known cerebrovascular risk factors. SCI is a rare entity with debilitating consequences, which typically presents with acute pain corresponding to the involved cord level, followed by flaccid paralysis, decreased sensation and autonomic dysfunction. The most common cause is aortic atheromatosis. Progression of symptoms, normal cerebrospinal fluid analysis and MRI are of key importance for the diagnosis of this entity, yet the latter can initially be normal. Anticoagulant therapy is the initial treatment of choice followed by long-term rehabilitation.

Acute toxic leukoencephalopathy (ATL) and delayed post-hypoxic leukoencephalopathy (DPHL) are two possible adverse entities related to opioid intoxication (OI), each having a distinct clinical course. While ATL shows a monophasic course with gradual neurological deterioration, DPHL has a distinct biphasic course. We report a case of ATL along with a case of DPHL happening in young male patients with OI, including their clinical courses as well as imaging characteristics with comparable time intervals. Initially, both leukoencephalopathies typically show magnetic resonance imaging findings with confluent and symmetric white matter (WM) abnormalities in the periventricular regions on T2 and fluid-attenuated inversion recovery images along with restricted diffusion on diffusion-weighted imaging. The DPHL patient however also presented with WM cystic substance loss in the deterioration phase, several weeks after hospital admission, which was previously described in a case of DPHL. Interestingly, similar WM changes have recently been observed in virus-associated necrotizing disseminated acute leukoencephalopathy in patients with coronavirus disease 2019 which may suggest a common pathophysiological mechanism. Knowing the distinct imaging features of ATL and DPHL along with their typical clinical courses can provide a faster and more reliable differentiation between these two entities.

PurposeTo compare the diagnostic accuracy of convolutional neural networks (CNN) with radiologists as the reference standard in the diagnosis of intracranial hemorrhages (ICH) with non contrast computed tomography of the cerebrum (NCTC).MethodsPubMed, Embase, Scopus, and Web of Science were searched for the period from 1 January 2012 to 20 July 2020; eligible studies included patients with and without ICH as the target condition undergoing NCTC, studies had deep learning algorithms based on CNNs and radiologists reports as the minimum reference standard. Pooled sensitivities, specificities and a summary receiver operating characteristics curve (SROC) were employed for meta-analysis.Results5,119 records were identified through database searching. Title-screening left 47 studies for full-text assessment and 6 studies for meta-analysis. Comparing the CNN performance to reference standards in the retrospective studies found a pooled sensitivity of 96.00% (95% CI: 93.00% to 97.00%), pooled specificity of 97.00% (95% CI: 90.00% to 99.00%) and SROC of 98.00% (95% CI: 97.00% to 99.00%), and combining retrospective and studies with external datasets found a pooled sensitivity of 95.00% (95% CI: 91.00% to 97.00%), pooled specificity of 96.00% (95% CI: 91.00% to 98.00%) and a pooled SROC of 98.00% (95% CI: 97.00% to 99.00%).ConclusionThis review found the diagnostic performance of CNNs to be equivalent to that of radiologists for retrospective studies. Out-of-sample external validation studies pooled with retrospective studies found CNN performance to be slightly worse. There is a critical need for studies with a robust reference standard and external data-set validation.

The fact that Artificial Intelligence (AI) based algorithms exhibit a high performance on image classification tasks has been shown many times. Still, certain issues exist with the application of machine learning (ML) artificial neural network (ANN) algorithms. The best known is the need for a large amount of statistically varied data, which can be addressed with expanded collection or data augmentation. Other issues are also present. Convolutional neural networks (CNNs) show extremely high performance on image-shaped data. Despite their performance, CNNs exhibit a large issue which is the sensitivity to image orientation. Previous research shows that varying the orientation of images may greatly lower the performance of the trained CNN. This is especially problematic in certain applications, such as X-ray radiography, an example of which is presented here. Previous research shows that the performance of CNNs is higher when used on images in a single orientation (left or right), as opposed to the combination of both. This means that the data needs to be differentiated before it enters the classification model. In this paper, the CNN-based model for differentiation between left and right-oriented images is presented. Multiple CNNs are trained and tested, with the highest performing being the VGG16 architecture which achieved an Accuracy of 0.99 (+/- 0.01), and an AUC of 0.98 (+/- 0.01). These results show that CNNs can be used to address the issue of orientation sensitivity by splitting the data in advance of being used in classification models.

BACKGROUND Brain maturation is considered completed around the age of 25, when prefrontal cortex maturation has been achieved. The aim of our study was to investigate the alterations of grey matter (GM) in patients with the onset of schizophrenia before and after the completion of brain maturation. SUBJECTS AND METHODS The study group included 100 schizophrenia patients, while the control group comprised 50 healthy individuals. Brain magnetic resonance imaging was acquired on a 1.5 T scanner. Voxel-based morphometry (VBM) analyses were performed between groups. RESULTS GM of the schizophrenic patients is reduced in many regions (p<0.005 FDR corrected). Most widespread reduction is detected in frontal cortex and cerebellum, the other regions being limbic cortex, insula, cuneus, precuneus, superior temporal gyrus and motor cortex. The decrease of grey matter volume (GMV) increases with the increase in number of psychotic episodes and is more pronounced in the patients with earlier onset of the disease. CONCLUSIONS The age of the onset of the disease is important for both total and relative loss of GMV. Earlier onset of schizophrenia, prior to full brain maturation results in significant reduction of GM in comparison with healthy subjects and patients with later, post full brain maturation onset of the disease.

Introduction Isolated unilateral hypoglossal nerve palsy is an infrequent condition that usually appears in connection to an underlying disease. Rarely, the cause cannot be determined, and there is no symptom remission. Case description We report two cases of male patients who developed persistent idiopathic isolated unilateral hypoglossal nerve palsy. The younger patient complained of involuntary movements of the tongue, while the older patient developed dysarthria. In both cases, the symptoms lasted for several weeks before the initial clinical examination, and after comprehensive clinical, laboratory, and imaging investigations, no underlying cause was detected. Both patients did not show remission of symptoms on the follow-up examinations done after several months. Discussion Idiopathic isolated unilateral hypoglossal nerve palsy is an underreported condition, most likely due to the expected reversible nature of the disease. In the case of persistence of symptoms, extensive medical assessment is needed before postulating a diagnosis of persistent idiopathic isolated unilateral hypoglossal nerve palsy. There are no treatment guidelines for this condition, but oral steroids were reported as a treatment option. Therefore, physicians should use a systematic approach to exclude serious underlying pathology or identify a treatable condition.

BACKGROUND Schizophrenia is a severe illness whose clinical course is characterized by various numbers of psychotic episodes (PE). The neurotoxic hypothesis (NH) of schizophrenia assumes that psychosis is biologically toxic. The aim of the study was to investigate whether schizophrenia patients (SP) with multiple PE have greater grey matter volume (GMV) reduction compared to SP with fewer PE. SUBJECTS AND METHODS We enrolled 106 adult SP and 63 healthy controls. Demographic and clinical data were collected and statistically analysed for all included subjects. Magnetic resonance imaging (MRI) of the brain was acquired on a 1.5 T scanner. SP were grouped according to the number of PE into a group with up to 3 PE (SCHG-1) and with 4 or more PE (SCHG-2). SCHG-1 was further subdivided into two groups regarding to disease duration (DD). Voxel-based morphometry (VBM) analyses were performed between SP groups as well as between SP groups and the healthy controls group (HCG). RESULTS No relevant GMV differences were detected between SP groups. Comparison between HCG and SCHG-1 showed only 3 regions with reduced GMV, while multiple regions with reduced GMV were detected when comparing HCG and SCHG-2. CONCLUSIONS GMV reduction in schizophrenia varies depending on the number of PE when compared to HCG, regardless of disease duration (DD), but PE is not the only contributing factor that leads to neurotoxicity.

To describe carotid plaque composition by computed tomography angiography (CTA) in asymptomatic subjects and to compare this to carotid plaque assessment by ultrasound, coronary plaques by coronary CTA, and inflammatory biomarkers in plasma.

The cyclophosphamide as a predisposing factor for Posterior Reversible Encephalopathy Syndrome (PRES) and therapeutic option for systemic lupus erythematosus (SLE) is still confusing. The first and only case of PRES, probably induced by cyclophosphamide, in Croatia followed by the findings of 36 SLE patients diagnosed with PRES after treatment with cyclophosphamide worldwide are described. An 18-year-old Caucasian female patient with a 1-year history of SLE was admitted to the hospital due to lupus nephritis and acute arthritis. After the second dose of cyclophosphamide was administered, according to the Euro-lupus protocol, the patient presented with a grand mal status epilepticus. The differential diagnosis of neurolupus, cerebrovascular insult, and infection were excluded. The MRI findings showed brain changes in corresponding to PRES. The treatment consisted of antihypertensives, antiepileptics, antiedema therapy, mechanical ventilation, and avoiding further cyclophosphamide use. A Naranjo Adverse Drug Reaction Probability Scale total score of five and a probable reaction related to drug therapy (cyclophosphamide, PRES) was confirmed. In this systematic review, along with cyclophosphamide use, the main predisposing factors involved in PRES occurrence in SLE patients were active SLE and renal involvement. Due to the high number of simultaneously involved predisposing factors (max. six) and their overlapping effect, it is still not possible to clearly establish the role of every factor on PRES onset. The use of cyclophosphamide, as a contributing factor for PRES onset, should be carefully assessed, based on clinicians' experience and knowledge, in the setting of active SLE.

BACKGROUND: Encephalocraniocutaneous lipomatosis is a rare congenital neurocutaneous syndrome resulting from ectomesodermal dysgenesis and characterized by unique hairless scalp lesions in the form of nevus psiloliparus, ipsilateral ocular malformations, and central nervous system anomalies. According to the 2009 diagnostic criteria proposed by Moog et al., ocular abnormalities are supposed to be the most consistent feature of encephalocraniocutaneous lipomatosis. PATIENT DESCRIPTION: We describe an 18-year-old girl with most of the central nervous system manifestations of encephalocraniocutaneous lipomatosis, major skin alterations including nevus psiloliparus, but no ocular involvement. CONCLUSION: Our patient suggests more variability in clinical features and a more complex genetic/embryonic etiology of encephalocraniocutaneous lipomatosis.

Increasing research evidence suggests that basal ganglia are an important part of frontal-subcortical circuit which is involved not only in motor control but also in affective, cognitive and executive functions. In this article, we describe the ability of facial emotion recognition and cognitive functioning in a patient with left basal ganglia and insula damage. The patient's ability to recognise facial emotional expressions was intact in spite of unilateral injury of the left insula and basal ganglia. He showed preserved intellectual function in general, but experienced difficulties on subsets of the executive functions: set-shifting and ability to activate or generate cognitive strategies, commonly found in patients with caudate lesions. This case contributes to evidence that striatal structures are important for executive functions.

Radiological diagnostics in personalized medicine provides indispensable morphological and functional information, unique for every individual. Volumetric imaging enables follow-up of suspicious nodules detected with screening or incidentally obtained on radiological imaging and assessment of tumor response to treatment. Assessment of neovascularity with perfusion-based imaging and restriction of water motion with diffusion-weighted MRI offers better distinction between benign and malignant lesions. Functional MRI of the brain delineates eloquent cortical areas and diffusion tensor imaging allows for in vivo assessment of white matter tracts characteristic for individual patients as prerequisites for guiding invasive procedures. Imaging biomarkers are crucial in personalized diagnostics and therapy. Prognostic biomarkers may prevent aggressive treatment in patients with indolent or slowly progressive disease. Imaging is mandatory for the assessment of therapeutic response and discrimination of responders and non-responders in the early phase of treatment. Identifying biomarkers before clinical manifestation followed by therapeutic intervention prevents the development of a disease. Our ability to detect smaller lesions using sophisticated technology increases the necessity to characterize such findings by extension of diagnostics. Incidental findings of preclinical disorders or indolent lesions without potential to disturb subject's health increase the risk of overdiagnosis. Imaging provides detailed information for the assessment of tumor resectability and is used to guide invasive procedures, including interventional radiology. Different imaging modalities can be used to guide biopsy needle to the specific part of the tumor with higher concentration of biomarkers. These sophisticated procedures are tailored to the individual patient's illness which is essential in personalized diagnostics and treatment.

Background: Internal carotid artery agenesis is a rare anomaly that can be clinically asymptomatic. Klippel-Feil syndrome is a skeletal malformation characterized by vertebral fusion. Presence of postaxial polydactyly is suggestive of an underlying syndrome.Case Report: We report a rare case of a 44-year-old patient with non-specific symptoms and an association between these three rare abnormalities. Vascular anomalies were found using intracranial MR angiography and multi-detector CT angiography of the supraaortic arteries.Conclusions: Presence of a single aforementioned anomaly requires cautious imaging assessment in order to detect possible associated anomalies and avoid diagnostic pitfalls. A possible common genetic background could explain the coexistence of these three anomalies.