Preliminary data on artificial intelligence tool in magnetic resonance imaging assessment of degenerative pathologies of lumbar spine.

PURPOSE: To evaluate the ability of an artificial intelligence (AI) tool in magnetic resonance imaging (MRI) assessment of degenerative pathologies of lumbar spine using radiologist evaluation as a gold standard. METHODS: Patients with degenerative pathologies of lumbar spine, evaluated with MRI study, were enrolled in a retrospective study approved by local ethical committee. A comprehensive software solution (CoLumbo; SmartSoft Ltd., Varna, Bulgaria) designed to label the segments of the lumbar spine and to detect a broad spectrum of degenerative pathologies based on a convolutional neural network (CNN) was employed, utilizing an automatic segmentation. The AI tool efficacy was compared to data obtained by a senior neuroradiologist that employed a semiquantitative score. Chi-square test was used to assess the differences among groups, and Spearman's rank correlation coefficient was calculated between the grading assigned by radiologist and the grading obtained by software. Moreover, agreement was assessed between the value assigned by radiologist and software. RESULTS: Ninety patients (58 men; 32 women) affected with degenerative pathologies of lumbar spine and aged from 60 to 81 years (mean 66 years) were analyzed. Significant correlations were observed between grading assigned by radiologist and the grading obtained by software for each localization. However, only when the localization was L2-L3, there was a good correlation with a coefficient value of 0.72. The best agreements were obtained in case of L1-L2 and L2-L3 localizations and were, respectively, of 81.1% and 72.2%. The lowest agreement of 51.1% was detected in case of L4-L5 locations. With regard canal stenosis and compression, the highest agreement was obtained for identification of in L5-S1 localization. CONCLUSIONS: AI solution represents an efficacy and useful toll degenerative pathologies of lumbar spine to improve radiologist workflow.

Artificial intelligence and radiation effects on brain tissue in glioblastoma patient: preliminary data using a quantitative tool.

PURPOSE: The quantification of radiotherapy (RT)-induced functional and morphological brain alterations is fundamental to guide therapeutic decisions in patients with brain tumors. The magnetic resonance imaging (MRI) allows to define structural RT-brain changes, but it is unable to evaluate early injuries and to objectively quantify the volume tissue loss. Artificial intelligence (AI) tools extract accurate measurements that permit an objective brain different region quantification. In this study, we assessed the consistency between an AI software (Quibim Precision® 2.9) and qualitative neruroradiologist evaluation, and its ability to quantify the brain tissue changes during RT treatment in patients with glioblastoma multiforme (GBM). METHODS: GBM patients treated with RT and subjected to MRI assessment were enrolled. Each patient, pre- and post-RT, undergoes to a qualitative evaluation with global cerebral atrophy (GCA) and medial temporal lobe atrophy (MTA) and a quantitative assessment with Quibim Brain screening and hippocampal atrophy and asymmetry modules on 19 extracted brain structures features. RESULTS: A statistically significant strong negative association between the percentage value of the left temporal lobe and the GCA score and the left temporal lobe and the MTA score was found, while a moderate negative association between the percentage value of the right hippocampus and the GCA score and the right hippocampus and the MTA score was assessed. A statistically significant strong positive association between the CSF percentage value and the GCA score and a moderate positive association between the CSF percentage value and the MTA score was found. Finally, quantitative feature values showed that the percentage value of the cerebro-spinal fluid (CSF) statistically differences between pre- and post-RT. CONCLUSIONS: AI tools can support a correct evaluation of RT-induced brain injuries, allowing an objective and earlier assessment of the brain tissue modifications.

Can Craniometry Play a Role in Cluster Headache Diagnosis? A Pilot Exploratory TC-3D Based Study.

BACKGROUND: Since the pioneering reports of the so-called leonine face in cluster headache (CH) patients, cranial and facial features of these patients have been poorly investigated with conflicting results. We aimed to investigate whether abnormalities in craniometric measurements could characterize male CH patients and represent reliable and reproducible diagnostic biomarkers able to identify CH patients. METHODS: Brain CT images were recorded between 2018 and 2020 in 24 male patients with CH and in 24 matched healthy controls (HC). Then, craniometric measurements were obtained, and logistic regression and receiver operating characteristic curves analyses were used to identify the craniometric abnormalities able to distinguish CH patients from HC. RESULTS: Logistic regression analyses showed that frontal bone height and facial width were able to discriminate, one independently from the other, CH patients from HC with an overall accuracy of 77%. The optimal cutoff score in detecting the probable presence of CH was 11.50 cm for frontal bone height and 13.30 cm for facial width. DISCUSSION: In the present study we found, for the first time by means of brain 3D computed tomography approach, abnormal craniometric measurements in CH patients when compared with HC. The absence of differences in smoke and alcohol intake suggests that the observed craniometric abnormalities may represent a specific feature of CH patients. CONCLUSION: The craniometric evaluation by means of brain 3D computed tomography could represent a widespread, noninvasive, and accurate tool to support CH diagnosis to avoid frequent misdiagnosis or delay in the diagnostic process.

ODLURO syndrome: personal experience and review of the literature.

INTRODUCTION: The O'Donnell-Luria-Rodan (ODLURO) syndrome, caused by heterozygous mutation in the lysine N-methyltransferase2E (KMT2E) gene in chromosome 7q22, has been recently described. Mutation of KMT2E produces a protein-truncating variant gene that may be responsible for both developmental delay and intellectual disability disorders commonly defined by an Intelligence Quotient < 70 and usually unspecific pathologic brain features demonstrated by brain Magnetic Resonance imaging. The symptoms of ODLURO syndrome include variably developmental and speech delay, autism, seizures, hypotonia, and dysmorphic features. The aim of the study is to search for correlation between this specific gene mutation and clinical/radiological features, trying to provide new insights in this recently described pathological condition. METHODS: We reviewed the 38 cases collected by O'Donnel-Luria et al., adding three cases of a familial heterozygosis novel mutation in KMT2E gene; different degrees of neurological disorder, subtle dysmorphic features, intellectual disability, epilepsy, and various brain Magnetic Resonance features are described. RESULTS: Magnetic Resonance data were integrated by genetic analysis and clinical features. Brain Magnetic Resonance study of our patients confirmed peculiar pathologic features previously reported in ODLURO syndrome; cerebellar dysplasia was identified in one of them. All 3 patients had epilepsy, intellectual disability, and mild dysmorphisms. CONCLUSIONS: Our study adds 3 new patients genetically, clinically, and radiologically evaluated to the ODLURO syndrome case series. While CC hypoplasia and widening of subarachnoid spaces are already reported in literature, we document for the first time the presence of cerebellar dysplasia in ODLURO syndrome. We also highlight the extremely low IQ value and the presence of epilepsy in all 3 patients.

Increased interictal visual network connectivity in patients with migraine with aura.

OBJECTIVE: To evaluate the resting-state visual network functional connectivity in patients with migraine with aura and migraine without aura during the interictal period. POPULATION AND METHODS: Using resting-state functional magnetic resonance imaging, the resting-state visual network integrity was investigated in 20 patients with migraine with aura, 20 age- and sex-matched patients with migraine without aura and 20 healthy controls. Voxel-based morphometry and diffusion tensor imaging were used to assess whether between-groups differences in functional connectivity were dependent on structural or microstructural changes. RESULTS: Resting-state functional magnetic resonance imaging data showed that patients with migraine with aura, compared to both patients with migraine without aura and healthy controls, had a significant increased functional connectivity in the right lingual gyrus within the resting-state visual network (p < 0.05, cluster-level corrected). This abnormal resting-state visual network functional connectivity was observed in the absence of structural or microstructural abnormalities and was not related to migraine severity. CONCLUSIONS: Our imaging data revealed that patients with migraine with aura exhibit an altered resting-state visual network connectivity. These results support the hypothesis of an extrastriate cortex involvement, centred in the lingual gyrus, a brain region related to mechanisms underlying the initiation and propagation of the migraine aura. This resting-state functional magnetic resonance imaging finding may represent a functional biomarker that could differentiate patients experiencing the aura phenomenon from patients with migraine without aura, even between migraine attacks.

Dilated perivascular spaces and fatigue: is there a link? Magnetic resonance retrospective 3Tesla study.

INTRODUCTION: Fatigue (F) is a common, inexplicable, and disabling symptom in multiple sclerosis (MS) patients. The purpose of this study was to evaluate a possible correlation between fatigue and morpho-volumetric features and site of dilated perivascular spaces (dPS), visible on 3T magnetic resonance (MR) in fatigued multiple sclerosis patients (FMS). METHODS: We studied 82 relapsing remitting (RR) FMS patients and 43 HC, matched for age, sex, and education. F was assessed by the Fatigue Severity Scale (FSS). To evaluate a possible correlation between degree of F and characteristics of dPS, patients were divided in two groups: more (mFMS) (FSS ≥ 5; n = 30) and less fatigued (lFMS) (FSS ≥ 4; n = 52), compared to a matched healthy control (HC) subject group. The MR study was performed with 3T scanner by SpinEcho T1, Fast-SpinEcho DP-T2, FLAIR, and 3D FSPGR T1 sequences. dPS volumes were measured with Medical Image Processing Analysis and Visualization (MIPAV); Global Cerebral Atrophy (GCA), expressed as Brain Parenchymal Fraction (BPF), was assessed by FSL SIENAX. RESULTS: The t test showed significantly increased dPS number (p = 0.021) in FMS patients (mFMS p = 0.0024 and lFMS p = 0.033) compared to HC. Pearson correlation revealed a significant correlation between dPS number and FSS (r = 0.208 p = 0.051). Furthermore, the chi-squared test confirms the intragroup (HC, mFMS, lFMS) differences about dPS location (p = 0.01) and size (p = 0.0001). CONCLUSION: Our study confirms that PS in MS patients presents with different volumetric and site characteristics as compared to HC; moreover, F severity significantly correlates with dPS number, site, and size.

Dilated Virchow-Robin spaces and multiple sclerosis: 3 T magnetic resonance study.

PURPOSE: The aim of this study was to assess differences in the presence, size, number and site of dilated cerebral Virchow-Robin spaces (VRSd) between patients with multiple sclerosis (MS) in the inactive phase and healthy controls, and between MS patients with disabling (MSd) or nondisabling (MSnd) disease. MATERIALS AND METHODS: The study was performed by retrospectively analysing the 3 T magnetic resonance studies of 40 MS patients and 30 healthy subjects (matched for age, education and gender). The data were analysed with MIPAV (Medical Image Processing, Analysis and Visualisation) software to assess for VRSd and with FSL SIENA-X to measure global cerebral atrophy (GCA) expressed as brain parenchyma fraction. RESULTS: The MS patients had significantly higher VRSd number (p < 0.011), area (p < 0.0073) and volume (p < 0.0071) than controls, with a marked increase for atypical sites (p < 0.0069) without significant intragroup differences between the disease forms (MSd vs MSnd). The number and size of VRSd did not correlate with GCA. CONCLUSIONS: Our results confirm previous reports regarding the increase in VRSd in nonactive phases of MS and support the immunological role of the VRS within the central nervous system. The lack of correlation between VRSd and the degree of GCA and their prevailing localisation in atypical sites in MS patients make VRSd a potential marker of inflammatory-demyelinating disease.

Recurrent glioblastoma multiforme versus radiation injury: a multiparametric 3-T MR approach.

OBJECTIVE: The discrimination between recurrent glioma and radiation injury is often a challenge on conventional magnetic resonance imaging (MRI). We verified whether adding and combining proton MR spectroscopic imaging ((1)H-MRSI), diffusion-weighted imaging (DWI) and perfusion-weighted imaging (PWI) information at 3 Tesla facilitate such discrimination. MATERIALS AND METHODS: Twenty-nine patients with histologically verified high-grade gliomas, who had undergone surgical resection and radiotherapy, and had developed new contrast-enhancing lesions close to the treated tumour, underwent MRI, (1)H-MRSI, DWI and PWI at regular time intervals. The metabolite ratios choline (Cho)/normal( n )Cho n , N-acetylaspartate (NAA)/NAA n , creatine (Cr)/Cr n , lactate/lipids (LL)/LL n , Cho/Cr n , NAA/Cr n , Cho/NAA, NAA/Cr and Cho/Cr were derived from (1)H-MRSI; the apparent diffusion coefficient (ADC) from DWI; and the relative cerebral blood volume (rCBV) from PWI. RESULTS: In serial MRI, recurrent gliomas showed a progressive enlargement, and radiation injuries showed regression or no modification. Discriminant analysis showed that discrimination accuracy was 79.3 % when considering only the metabolite ratios (predictor, Cho/Cr n ), 86.2 % when considering ratios and ADC (predictors, Cho/Cr n and ADC), 89.7 % when considering ratios and rCBV (predictors, Cho/Cr n , Cho/Cr and rCBV), and 96.6 % when considering ratios, ADC and rCBV (predictors, Cho/Cho n , ADC and rCBV). CONCLUSIONS: The multiparametric 3-T MR assessment based on (1)H-MRSI, DWI and PWI in addition to MRI is a useful tool to discriminate tumour recurrence/progression from radiation effects.

[From anatomy to image: the cranial nerves at MRI]. / Dall'anatomia all'immagine: la visualizzazione dei nervi cranici in RM.

In this article, we review the expected course of each of the 12 cranial nerves. Traditional magnetic resonance imaging depicts only the larger cranial nerves but SSFP sequences of magnetic resonance imaging are capable of depicting the cisternal segments of 12 cranial nerves and also provide submillimetric spatial resolution.

[Acustic neurinoma: correlation between clinic and MRI]. / Neurinoma dell'acustico: correlazione tra clinica e RM.

The purpose of this paper is to study acoustic neuroma diagnostic process, describe tumor's molecular basis and its magnetic resonance imaging characterization, which is considered to be the gold standard diagnostic tool to study this disease.

[New development in neuroradiological diagnosis of migraine]. / Emicrania: recenti progressi in diagnostica neuroradiologica.

Migraine is one of the most common forms of primary headache. In recent years there have been important discoveries thanks to a greater understanding of conventional radiologic studies and the advent of the advanced exams. This has led to a revolution of the knowledge of its pathophysiological mechanisms and opens the way for future therapeutic developments.

[Chordoma: diagnostic considerations and review of the literature]. / Cordoma: considerazioni diagnostiche e revisione della letteratura.

Chordoma is a rare malignant tumor of the bone; it arises from embryonic remnants of the primitive notochord and occurs along the midline from the skull base to the sacrum. In this article, we reviewed the origin, location, clinical, histopatological and imaging features, treatment, and differential diagnosis of chordoma.

[The value of the MRI in defining the morfology of cerebral aging]. / Il ruolo della RM nella definizione morfologica dell'invecchiamento cerebrale.

White matter changes are one of the several aging brain alterations. Actually, magnetic resonance imaging is the best diagnostic tool in investigation and monitoring these lesions that determine some common clinical manifestations in the elderly population.

[MR imaging of the Tornwaldt's cyst: retrospective study of 1300 patients]. / Imaging di RM della cisti di Tornwaldt: uno studio retrospettivo di 1300 pazienti.

Tornwaldt's cyst is a benign developmental lesion of the nasopharynx, most of all midline located, originating from an outpouching of the pharyngeal mucosa caused by notocord retraction. Usually, the cyst represents an incidental finding of magnetic resonance study. The purpose of this study is to investigate the differential diagnostic aspects of Tornwaldt's cysts, making a comparison with other diseases of nasopharynx on the basis of morphological characteristics and signal, contributing to the previous statistical works.

[Cerebral pseudovasculitic lesion associated with von Recklinghausen's neurofibromatosis: a case report]. / Lesione pseudovasculitica cerebrale associata a neurofibromatosi di von Recklinghausen.

A child with neurofibromatosis type 1 (NF1) with headache was submitted to magnetic resonanace imaging and a pseudovasculitic lesion was found. Vascular lesions are uncommon in patients with NF1 and our case highlights an even more rare feature of this form of vascular disease.

[Diagnostic tools in neurodegenerative disorders of adult-elderly]. / Strumenti diagnostici dei disordini neurodegenerativi nell'adulto-anziano.

Neurodegenerative disorders are an inhomogeneous group of neurological diseases that affect a large part of the population because of the rise in life expectancy. Although clinical manifestations are important to make the correct diagnosis, the new advanced imaging technique represent a very useful tool for the diagnostic work-up.

[The cerebral perivascular spaces: review of the literature on diffuse or focal expansion]. / Gli spazi perivascolari encefalici: revisione della letteratura sulle dilatazioni focali o diffuse.

Virchow-Robin spaces (VRS) are pial-lined, interstitial fluid-filled structures that do not directly communicate with the subarachnoid space, accompany penetrating arteries and veins and can be visualized on magnetic resonance imaging. This article reviews the imageology characteristics, the functions, the causes and the relation with neurological disorders of VRS.

[Enlargment of Virchow-Robin spaces in cranial trauma: literature review]. / La dilatazione degli spazi di Virchow-Robin nel trauma cranico. Aspetti caratteristici in RM e revisione della letteratura.

In this review it is discussed the role of mild traumatic brain injury as a cause of Virchow-Robin spaces (VRS) pathological enlargement. Anatomy and physiology of normal VRS, and their immunological role are described. Special attention is given to magnetic resonance imaging findings of both normal and enlarged perivascular spaces.

Giant Tumefactive Perivascular Space: Advanced Fusion MR Imaging and Tractography Study-A Case Report and a Systematic Review.

Perivascular spaces (PVSs) are small extensions of the subpial cerebrospinal space, pial-lined and interstitial fluid-filled. They surround small penetrating arteries, and veins, crossing the subarachnoid space to the brain tissue. Magnetic Resonance Imaging (MRI) shows a PVS as a round-shape or linear structure, isointense to the cerebrospinal fluid, and, if larger than 1.5 cm, they are known as giant/tumefactive PVSs (GTPVS) that may compress neighboring parenchymal/liquoral compartment. We report a rare asymptomatic case of GTPVS type 1 in a diabetic middle-aged patient, occasionally discovered. Our MRI study focuses on diffusion/tractography and fusion imaging: three-dimensional (3D) constructive interference in steady state (CISS) and time of fly (TOF) sequences. The advanced and fusion MR techniques help us to track brain fiber to assess brain tissue compression consequences and some PVS anatomic features as the perforating arteries inside them.