Recurrent petit mal seizures in Erdheim-Chester disease mimicking an intra-axial brain tumor: illustrative case.

BACKGROUND: Erdheim-Chester disease (ECD) is a rare non-Langerhans cell histiocytosis characterized histologically by foamy histiocytes and Touton giant cells in a background of fibrosis. Bone pain with long bone osteosclerosis is highly specific for ECD. Central nervous system involvement is rare, although dural, hypothalamic, cerebellar, brainstem, and sellar region involvement has been described. OBSERVATIONS: A 59-year-old man with a history of ureteral obstruction, medically managed petit mal seizures, and a left temporal lesion followed with serial magnetic resonance imaging (MRI) presented with worsening seizure control. Repeat MRI identified bilateral amygdala region lesions. Gradual growth of the left temporal lesion over 1 year with increasing seizure frequency prompted resection. A non-Langerhans cell histiocytosis with a BRAF V600E mutation was identified on pathology. Imaging findings demonstrated retroperitoneal fibrosis and long bone osteosclerosis with increased fluorodeoxyglucose uptake that, together with the neuropathologic findings, were diagnostic of ECD. LESSONS: This case of biopsy-proven ECD is unique in that the singular symptom was seizures well controlled with medical management in the presence of similarly located bilateral anterior mesial temporal lobe lesions. Although ECD is rare intracranially, its variable imaging presentation, including the potential to mimic seizure-associated medial temporal lobe tumors, emphasizes the need for a wide differential diagnosis.

NS-HGlio: A generalizable and repeatable HGG segmentation and volumetric measurement AI algorithm for the longitudinal MRI assessment to inform RANO in trials and clinics.

Background: Accurate and repeatable measurement of high-grade glioma (HGG) enhancing (Enh.) and T2/FLAIR hyperintensity/edema (Ed.) is required for monitoring treatment response. 3D measurements can be used to inform the modified Response Assessment in Neuro-oncology criteria. We aim to develop an HGG volumetric measurement and visualization AI algorithm that is generalizable and repeatable. Methods: A single 3D-Convoluted Neural Network, NS-HGlio, to analyze HGG on MRIs using 5-fold cross validation was developed using retrospective (557 MRIs), multicentre (38 sites) and multivendor (32 scanners) dataset divided into training (70%), validation (20%), and testing (10%). Six neuroradiologists created the ground truth (GT). Additional Internal validation (IV, three institutions) using 70 MRIs, and External validation (EV, single institution) using 40 MRIs through measuring the Dice Similarity Coefficient (DSC) of Enh., Ed. ,and Enh. + Ed. (WholeLesion/WL) tumor tissue and repeatability testing on 14 subjects from the TCIA MGH-QIN-GBM dataset using volume correlations between timepoints were performed. Results: IV Preoperative median DSC Enh. 0.89 (SD 0.11), Ed. 0.88 (0.28), WL 0.88 (0.11). EV Preoperative median DSC Enh. 0.82 (0.09), Ed. 0.83 (0.11), WL 0.86 (0.06). IV Postoperative median DSC Enh. 0.77 (SD 0.20), Ed 0.78. (SD 0.09), WL 0.78 (SD 0.11). EV Postoperative median DSC Enh. 0.75 (0.21), Ed 0.74 (0.12), WL 0.79 (0.07). Repeatability testing; Intraclass Correlation Coefficient of 0.95 Enh. and 0.92 Ed. Conclusion: NS-HGlio is accurate, repeatable, and generalizable. The output can be used for visualization, documentation, treatment response monitoring, radiation planning, intra-operative targeting, and estimation of Residual Tumor Volume among others.

Dual Adversarial Attention Mechanism for Unsupervised Domain Adaptive Medical Image Segmentation.

Domain adaptation techniques have been demonstrated to be effective in addressing label deficiency challenges in medical image segmentation. However, conventional domain adaptation based approaches often concentrate on matching global marginal distributions between different domains in a class-agnostic fashion. In this paper, we present a dual-attention domain-adaptative segmentation network (DADASeg-Net) for cross-modality medical image segmentation. The key contribution of DADASeg-Net is a novel dual adversarial attention mechanism, which regularizes the domain adaptation module with two attention maps respectively from the space and class perspectives. Specifically, the spatial attention map guides the domain adaptation module to focus on regions that are challenging to align in adaptation. The class attention map encourages the domain adaptation module to capture class-specific instead of class-agnostic knowledge for distribution alignment. DADASeg-Net shows superior performance in two challenging medical image segmentation tasks.

Diverse data augmentation for learning image segmentation with cross-modality annotations.

The dearth of annotated data is a major hurdle in building reliable image segmentation models. Manual annotation of medical images is tedious, time-consuming, and significantly variable across imaging modalities. The need for annotation can be ameliorated by leveraging an annotation-rich source modality in learning a segmentation model for an annotation-poor target modality. In this paper, we introduce a diverse data augmentation generative adversarial network (DDA-GAN) to train a segmentation model for an unannotated target image domain by borrowing information from an annotated source image domain. This is achieved by generating diverse augmented data for the target domain by one-to-many source-to-target translation. The DDA-GAN uses unpaired images from the source and target domains and is an end-to-end convolutional neural network that (i) explicitly disentangles domain-invariant structural features related to segmentation from domain-specific appearance features, (ii) combines structural features from the source domain with appearance features randomly sampled from the target domain for data augmentation, and (iii) train the segmentation model with the augmented data in the target domain and the annotations from the source domain. The effectiveness of our method is demonstrated both qualitatively and quantitatively in comparison with the state of the art for segmentation of craniomaxillofacial bony structures via MRI and cardiac substructures via CT.

Anatomy-Regularized Representation Learning for Cross-Modality Medical Image Segmentation.

An increasing number of studies are leveraging unsupervised cross-modality synthesis to mitigate the limited label problem in training medical image segmentation models. They typically transfer ground truth annotations from a label-rich imaging modality to a label-lacking imaging modality, under an assumption that different modalities share the same anatomical structure information. However, since these methods commonly use voxel/pixel-wise cycle-consistency to regularize the mappings between modalities, high-level semantic information is not necessarily preserved. In this paper, we propose a novel anatomy-regularized representation learning approach for segmentation-oriented cross-modality image synthesis. It learns a common feature encoding across different modalities to form a shared latent space, where 1) the input and its synthesis present consistent anatomical structure information, and 2) the transformation between two images in one domain is preserved by their syntheses in another domain. We applied our method to the tasks of cross-modality skull segmentation and cardiac substructure segmentation. Experimental results demonstrate the superiority of our method in comparison with state-of-the-art cross-modality medical image segmentation methods.

Obstructive hydrocephalus due to aqueductal stenosis from developmental venous anomaly draining bilateral medial thalami: a case report.

Hydrocephalus is a pathological buildup of cerebrospinal fluid within the ventricles leading to ventricular enlargement out of proportion to sulci and subarachnoid spaces. Developmental venous anomaly is a common benign and usually asymptomatic congenital cerebrovascular malformation. Hydrocephalus caused by aqueductal developmental venous anomaly is extremely rare. We describe a case of a 47-year-old man who presents with short-term memory impairment who was found to have a developmental venous anomaly draining bilateral medial thalami through a common collector vein that causes aqueductal stenosis and obstructive hydrocephalus.

One-Shot Generative Adversarial Learning for MRI Segmentation of Craniomaxillofacial Bony Structures.

Compared to computed tomography (CT), magnetic resonance imaging (MRI) delineation of craniomaxillofacial (CMF) bony structures can avoid harmful radiation exposure. However, bony boundaries are blurry in MRI, and structural information needs to be borrowed from CT during the training. This is challenging since paired MRI-CT data are typically scarce. In this paper, we propose to make full use of unpaired data, which are typically abundant, along with a single paired MRI-CT data to construct a one-shot generative adversarial model for automated MRI segmentation of CMF bony structures. Our model consists of a cross-modality image synthesis sub-network, which learns the mapping between CT and MRI, and an MRI segmentation sub-network. These two sub-networks are trained jointly in an end-to-end manner. Moreover, in the training phase, a neighbor-based anchoring method is proposed to reduce the ambiguity problem inherent in cross-modality synthesis, and a feature-matching-based semantic consistency constraint is proposed to encourage segmentation-oriented MRI synthesis. Experimental results demonstrate the superiority of our method both qualitatively and quantitatively in comparison with the state-of-the-art MRI segmentation methods.

Sleep-Disordered Breathing and Idiopathic Normal-Pressure Hydrocephalus: Recent Pathophysiological Advances.

PURPOSE OF REVIEW: Idiopathic normal-pressure hydrocephalus (iNPH) is characterized clinically by ventriculomegaly, abnormal gait, falls, incontinence, and cognitive decline. This article reviews recent advances in the pathophysiology of iNPH concerning sleep-disordered breathing (SDB) and glymphatic circulation during deep sleep. RECENT FINDINGS: The authors found iNPH frequently associated with obstructive sleep apnea (OSA). A critical factor in iNPH is intracranial venous hypertension delaying drainage of cerebrospinal fluid (CSF) into the cerebral venous sinuses. CSF-venous blood circulates in the jugular veins and finally drains into the heart. During SDB, repeated reflex attempts to breathe induce strong respiratory efforts against a closed glottis thereby increasing the negative intrathoracic pressure. This causes atrial distortion and decreases venous return to the heart resulting in retrograde intracranial venous hypertension. Additionally, repeated awakenings from OSA impede sleep-associated circulation of interstitial CSF into the glymphatic circulation contributing to hydrocephalus. Sleep has become a critical element in the cognitive changes of aging including iNPH.

Combinatorial Anatomic and Functional Neural Tract Mapping for Stereotactic Radiosurgery Planning.

Introduction Stereotactic radiosurgery (SRS) is effective and safe for the treatment of the vast majority of brain metastases (BMs). SRS is increasingly used for the simultaneous treatment of multiple lesions, retreatment of recurrence, or subsequent treatment of new lesions. Although radiation injury is relatively uncommon, with the increased utilization of SRS, it is imperative to develop approaches to assess and mitigate radiation-induced neurologic toxicity. Multiple factors influence the development of radiation injury, including patient age, genomic variations, prior treatment, dose and volume treated, and anatomic location. Functional neural structure proximity to SRS targets is a critical factor in developing a systematic integrated risk assessment for SRS patients. Methods We developed an approach for risk assessment based on the combinatorial application of i) the anatomic localization of target lesions using a reference neuroanatomical/functional imaging atlas merged with patient-specific imaging and ii) validation with functional MRI (fMRI) and diffusion tensor imaging MRI (DTI-MRI) to identify neural tracts. Results In the case of a thalamic/midbrain junction breast carcinoma metastasis, the reference image analysis revealed proximity to the corticospinal tract (CST), which was validated by functional DTI-MRI. Dose-volume exposure of the CST could be estimated and considered in the development of a final treatment plan. Conclusion Merging pretreatment MR imaging with neuroanatomical/functional reference MRIs and subsequent validation with fMRI or DTI-MRI may prove to be a valuable approach to screen for neural risks in individual SRS patients. Incorporating this approach in larger studies could further our understanding of dose tolerances in a broad range of neural structures.

Craniomaxillofacial Bony Structures Segmentation from MRI with Deep-Supervision Adversarial Learning.

Automatic segmentation of medical images finds abundant applications in clinical studies. Computed Tomography (CT) imaging plays a critical role in diagnostic and surgical planning of craniomaxillofacial (CMF) surgeries as it shows clear bony structures. However, CT imaging poses radiation risks for the subjects being scanned. Alternatively, Magnetic Resonance Imaging (MRI) is considered to be safe and provides good visualization of the soft tissues, but the bony structures appear invisible from MRI. Therefore, the segmentation of bony structures from MRI is quite challenging. In this paper, we propose a cascaded generative adversarial network with deep-supervision discriminator (Deep-supGAN) for automatic bony structures segmentation. The first block in this architecture is used to generate a high-quality CT image from an MRI, and the second block is used to segment bony structures from MRI and the generated CT image. Different from traditional discriminators, the deep-supervision discriminator distinguishes the generated CT from the ground-truth at different levels of feature maps. For segmentation, the loss is not only concentrated on the voxel level but also on the higher abstract perceptual levels. Experimental results show that the proposed method generates CT images with clearer structural details and also segments the bony structures more accurately compared with the state-of-the-art methods.

Idiopathic normal-pressure hydrocephalus and obstructive sleep apnea are frequently associated: A prospective cohort study.

BACKGROUND: Idiopathic normal-pressure hydrocephalus (iNPH) is defined by ventriculomegaly, cognitive decline, urinary incontinence and gait problems. Vascular risk factors (VRF) are associated with iNPH but obstructive sleep apnea (OSA) -a well-known independent VRF- is seldom mentioned. METHODS: We investigated the presence of sleep-disordered breathing in a prospective cohort of 31 consecutive unselected patients with iNPH using sleep questionnaires and nocturnal polysomnography (PSG). RESULTS: We found OSA in 90·3% (28/31) patients with iNPH; all had undiagnosed sleep abnormalities (snoring, awakenings, nocturia) and excessive daytime sleepiness (Epworth scale = 11·4 ±â€¯6·4; normal <8). Nocturnal PSG showed moderate-to-severe OSA in 25 patients (80·6%) with mean apnea-hypopnea index (AHI) 31·6 ±â€¯23·6/h; mean respiratory distress index (RDI) 34·5/h; and, mean SaO2 desaturation at nadir, 82·2 ±â€¯7·5%. The observed OSA prevalence is statistically significant: 90·3%, 95%CI 74·3-97·5; p = 0·000007. Other VRF included overweight body-mass index (BMI >25- < 30 kg/m2) in 59%, hyperhomocysteinemia 57%, hypertension 43%, hyperlipidemia 39%, diabetes 32%, smoking 21%, coronary disease 18%, and previous stroke 10%. CONCLUSION: Abnormal sleep breathing is frequently associated with iNPH. Validation in larger series is required but we suggest including sleep evaluation in patients suspected of iNPH.

Advanced neuroimaging in Balo's concentric sclerosis: MRI, MRS, DTI, and ASL perfusion imaging over 1 year.

Balo concentric sclerosis (BCS) is a rare, atypical demyelinating disease, which may rapidly progress to become severe and fatal. Advanced neuroimaging has proven helpful for early diagnosis, classification, prognostication, and monitoring of progression in multiple sclerosis, but has not been fully explored in BCS. We present the case of a 27-year-old woman with BCS in whom advanced neuroimaging was used to correlate the evolution of disease with clinical findings over the course of 1 year. Magnetic resonance imaging, magnetic resonance spectroscopy (MRS), diffusion tensor imaging (DTI), and arterial spin labeling cerebral perfusion were obtained at presentation (Day 0), and at Day 67 and Day 252. Imaging features include multilayered concentric ring lesion, reduced diffusion along the rim, hypoperfusion with possible mild central hyperperfusion, and MRS findings of increased choline, decreased N-acetylaspartate (NAA), and possible presence of lactate and/or lipid peak. DTI tractography and relative apparent diffusion coefficient analyses correlated with clinical symptoms and may help to determine extent of white matter tract injury and prognosis.

Technical Pitfalls of Signal Truncation in Perfusion MRI of Glioblastoma.

Dynamic susceptibility contrast (DSC) perfusion-weighted imaging (PWI) is widely used in clinical settings for the radiological diagnosis of brain tumor. The signal change in brain tissue in gradient echo-based DSC PWI is much higher than in spin echo-based DSC PWI. Due to its exquisite sensitivity, gradient echo-based sequence is the preferred method for imaging of all tumors except those near the base of the skull. However, high sensitivity also comes with a dynamic range problem. It is not unusual for blood volume to increase in gene-mediated cytotoxic immunotherapy-treated glioblastoma patients. The increase of fractional blood volume sometimes saturates the MRI signal during first-pass contrast bolus arrival and presents signal truncation artifacts of various degrees in the tumor when a significant amount of blood exists in the image pixels. It presents a hidden challenge in PWI, as this signal floor can be either close to noise level or just above and can go no lower. This signal truncation in the signal intensity time course is a significant issue that deserves attention in DSC PWI. In this paper, we demonstrate that relative cerebral blood volume and relative cerebral blood flow (rCBF) are underestimated due to signal truncation in DSC perfusion, in glioblastoma patients. We propose the use of second-pass tissue residue function in rCBF calculation using least-absolute-deviation deconvolution to avoid the underestimation problem.

Paramagnetic Gd(3+) labeled red blood cells for magnetic resonance angiography.

Despite significant advances in contrast enhanced-magnetic resonance angiography, the lack of truly blood-pool agents with long circulating property is limiting the clinical impact of this imaging technique. The terminal half-life for blood elimination of most small molecular weight gadolinium (Gd) based extracellular fluid agents is about 1.5 h when administered intravenously to subjects with normal renal function. The small size of these extracellular fluid agents does not prevent them from extravasating, especially from damaged vessels which are generally hyperpermeable. Therefore, the development of novel, clinically relevant blood pool contrast agents is critically needed to improve outcomes in the prevention, detection, and treatment of vascular diseases. We have demonstrated the fusion strategies in which the Gd-liposome without any stealth property radically fuses with red blood cells (RBCs) forming MR glowing Gd-RBC with the order of magnitude enhancements in circulation half-life (t1/2 = 50 h) and r1 relaxivity (r1 = 19.0 mM(-1) s(-1)) of Gd. The in vivo contrast enhancement of Gd-RBC was studied by using 3T clinical MR scanner for extended period of time, which clearly visualized the abdominal aorta. In summary, the vascular delivery of blood pool agents may benefit from carriage by RBCs because it naturally stays within the vascular lumen.

Transulcal parafascicular minimally invasive approach to deep and subcortical cavernomas: technical note.

Cavernomas comprise 8%-15% of intracranial vascular lesions, usually supratentorial in location and superficial. Cavernomas in the thalamus or subcortical white matter represent a unique challenge for surgeons in trying to identify and then use a safe corridor to access and resect the pathology. Previous authors have described specific open microsurgical corridors based on pathology location, often with technical difficulty and morbidity. This series presents 2 cavernomas that were resected using a minimally invasive approach that is less technically demanding and has a good safety profile. The authors report 2 cases of cavernoma: one in the thalamus and brainstem with multiple hemorrhages and the other in eloquent subcortical white matter. These lesions were resected through a transulcal parafascicular approach with a port-based minimally invasive technique. In this series there was complete resection with no neurological complications. The transulcal parafascicular minimally invasive approach relies on image interpretation and trajectory planning, intraoperative navigation, cortical cannulation and subcortical space access, high-quality optics, and resection as key elements to minimize exposure and retraction and maximize tissue preservation. The authors applied this technique to 2 patients with cavernomas in eloquent locations with excellent outcomes.