Aid In Diagnosis Research Articles

Bilateral and Symmetrical Basal Ganglia Calcifications May Aid in Mitochondrial Disease Diagnosis in Resource-Limited Settings.

Bilateral and Symmetrical Basal Ganglia Calcifications May Aid in Mitochondrial Disease Diagnosis in Resource-Limited Settings.

Augmented Reality Visualization and Interaction for COVID-19 CT-Scan NN Automated Segmentation: A Validation Study

Although medical imaging technology has persisted in evolving over the last decades, the techniques and technologies used for analytical and visualisation purposes have remained constant. Manual or semi-automatic segmentation is, in many cases, complicated. It requires the intervention of a specialist and is time-consuming, especially during the Coronavirus disease (COVID-19) pandemic, which has had devastating medical and economic consequences. Processing and visualising medical images with advanced techniques represent medical professionals’ breakthroughs. This paper studies how augmented reality (AR) and artificial intelligence (AI) can transform medical practice during COVID-19 and post-COVID-19 pandemic. Here we report an augmented reality visualisation and interaction platform; it covers the whole process from uploading chest Ct-scan images to automatic segmentation-based deep learning, 3D reconstruction, 3D visualisation, and manipulation. AR provides a more realistic 3D visualisation system, allowing doctors to effectively interact with the generated 3D model of segmented lungs and COVID-19 lesions. We use the U-Net Neural Network (NN) for automated segmentation. The statistical measures obtained using the Dice score, pixel accuracy, sensitivity, G-mean, and specificity are 0.749, 0.949, 0.956, 0.955, and 0.954, respectively. The user-friendliness and usability are objectified by a formal user study that compared our augmented reality-assisted design to the standard diagnosis setup. One hundred and six doctors and medical students, including eight senior medical lecturers, volunteered to assess our platform. The platform could be used as an aid diagnosis tool to identify and analyse the COVID-19 infectious or as a training tool for residents and medical students. The prototype can be extended to other pulmonary pathologies.

Undiagnosed uterine anomalies revealed by breech on ultrasound prior to external cephalic version – A chance to take a closer look

ObjectiveUterine anomalies (UA) occur in up to 6.7% of women. Breech is eight times more likely to occur with UA which may not be diagnosed prior to pregnancy and may only be found in the third trimester with breech. The objective of the study is to assess the prevalence of both already known and newly sonographically diagnosed UA in breech from 36 weeks of gestation and its impact on external cephalic version (ECV), delivery options and perinatal outcomes. Study DesignWe recruited 469 women with breech at 36 weeks of gestation over a 2-year period at the Charité University Hospital, Berlin. Ultrasound examination was performed to rule out UA. Patients with known and newly ‘de novo’ diagnosed anomalies were identified and delivery options and perinatal outcomes analyzed. ResultsThe ‘de novo’ diagnosis of UA at 36–37 weeks of pregnancy with breech was found to be significantly higher compared to the diagnosis prior to pregnancy with 4.5% vs 1.5% (p < 0.001 and odds ratio 4 with 95% confidence interval 2.12–7.69). Anomalies found included 53.6% bicornis unicollis, 39.3% subseptus, 3.6% unicornis and 3.6% didelphys. A trial of vaginal breech delivery was successful in 55.5% of cases when attempted. There were no successful ECVs. ConclusionBreech is a marker for uterine malformation. Diagnosis of UA with breech can be up to four times improved with focused ultrasound screening in pregnancy even from 36 weeks of gestation prior to ECV to identify missed anomalies. Timely diagnosis aids antenatal care and delivery planning. Importantly, definitive diagnosis and treatment can be planned postpartum to improve outcomes in future pregnancies. ECV plays a limited role in selected cases.

0574 Artificial Intelligence to Aid in Diagnosis of Type I Narcolepsy

Abstract Introduction Accurate diagnosis of Type 1 narcolepsy (T1N) is cumbersome – involving clinical, biological, and electrophysiological components. Multiple sleep latency tests (MSLT) are central to diagnosis; however, current medications, sleep schedule, drug use, and testing environment can all compromise the interpretation of an MSLT. Incorrect MSLT results have devastating consequences for patients, including prolonged suffering from untreated T1N or adverse effects from unnecessary testing and therapies. Simple, accessible, accurate and cost-effective diagnostic solutions are needed. We evaluate automated methods to expand the diagnosis of T1N based on single night polysomnography (PSG). Methods The dataset included N=225 T1N patients and N=455 negative controls from 6 different cohorts. We evaluated two separate machine learning (ML) models for T1N detection: a supervised PSG-EEG based deep learning (PSG-DL) model focused on sleep microarchitecture, and a random forest (Sleep-RF) model based on traditional PSG report data. To measure performance, we calculated the area under the receiver operating characteristic curve (AUC-ROC) for each model and performed a feature importance analysis for the Sleep-RF model. Results AUC-ROC values were 0.960 and 0.878 for the PSG-DL and Sleep-RF models, respectively. Furthermore, the PSG-DL model produced a sensitivity and specificity of 84% and 94%, while the Sleep-RF model resulted in 75% and 83%. The feature importance analysis for the Sleep-RF model revealed these most important features: REM latency, sleep latency, total N3 time, and ratio of arousals in REM vs. non-REM. Conclusion ML methods automatically detected T1N in PSG-EEG with promising degrees of accuracy. These methods overcome common barriers to accurate diagnosis that can compromise the interpretability of an MSLT. Broad implementation of this method has potential to supplement the MSLT, increasing diagnostic detection rates and accuracy for T1N. Access to care can be broadened if T1N diagnosis were to occur anywhere a sleep EEG can be obtained, including the home setting, rather than being limited to in-center testing. This work has potential to further the developments of T1N detectors and assist in their widespread clinical adoption. Additional research is underway to help improve accuracy and ensure these methods are generalizable across platforms and clinical datasets. Support (if any)

Cryptococcosis in Africa: What the data tell us.

Cryptococcosis is a neglected tropical disease and the main cause of fungal-related deaths in HIV-positive persons in Africa. It is an AIDS-defining illness that has almost surpassed tuberculosis (TB) in mortality despite wide coverage with antiretroviral therapy. What is known about the cryptococcosis burden in Africa is from estimations based on data from a few studies on the infection burden and associated complications. Consequently, the projected implications of cryptococcosis in Africa have been based on these estimations. This systematic review is aimed at providing unique and up-to-date data on the burden of cryptococcosis in Africa using published hospital-based research data on cryptococcosis in HIV infected and uninfected persons. The review also focused on providing temporal data on the availability of diagnostic and therapeutic options for cryptococcosis in Africa. From our results, about 40 948 cases of cryptococcosis were reported in Africa from 1969 to 2021, and the highest prevalence of cryptococcosis was from southern Africa. The most isolated species was Cryptococcus neoformans 42.4% (17 710/41 801) and only 1.3% (549/41 801) isolates were C. gattii. C. neoformans (serotype A) VN I 64.5% (918/1522) was the most prevalent serotype in Africa, while C. gattii (serotype C) VG IV was thought to pose a huge danger. However, C. neoformans (serotype A) VN I continued to be the major threat in Africa. Due to the limited availability of molecular typing methods and the widespread use of culture, direct microscopy, and serological techniques for diagnosis, 23 542 isolates were uncharacterised. Amphotericin B and flucytosine combination therapy is highly recommended for treatment of cryptococcal meningitis. However, these drugs are expensive and remain largely unavailable in most African countries. Amphotericin B requires laboratory facilities to monitor for toxicity. Although fluconazole monotherapy is the readily available treatment option for cryptococcosis, drug resistance, and high mortality have been recorded in majority of cases in Africa. The lack of awareness and paucity of published data on cryptococcosis are likely to have contributed to the underestimation of cases in Africa and led to underprioritisation of this important disease.

Rare non-epithelial tumors of the gastrointestinal tract: features of endoscopic and morphological diagnosis

Non-epithelial tumors (NO) of the gastrointestinal tract (GIT) are a large heterogeneous group of neoplasms. OIs are characterized by the absence of a pathognomonic clinical picture, as well as by the fact that they cause difficulties both at the stage of endoscopic diagnosis and morphological examination. Often, the final diagnosis can be established only after a complete morphological diagnosis of the removed tumor. In most cases, an immunohistochemical study is required to make the diagnosis. Understanding the endoscopic manifestations provides an essential aid in the differential diagnosis. The article presents a review of the literature on the choice of method for endoscopic and endoscopic diagnosis of rare non-epithelial tumors of the gastrointestinal tract.

Hereditary Persistence Of Alpha-fetoprotein: A Rare Entity From A Primary Care Center In Bangladesh

Hereditary persistence of alpha- fetoprotein (HFAFP) is a rare benign autosomal dominant disorder.Here we report a case of 15 years old boy who was found to have elevated alpha-fetoprotein during her routine evaluation for gynaecomastia. All other common possibilities for raised alpha-fetoprotein were excluded.Subsequently, 2 of his family members were found to have raised alpha-fetoprotein.One is his father and another one is his brother.Raised alpha-fetoprotein has a wide differential diagnosis including, pregnancy, germ cell tumors, hepatocellular carcinoma and others.But after exclusion of other possibilities, persisting elevated alphafetoprotein raises the suspicion for HPAFP.Testing other family members for AFP and specific genetic study aid in diagnosis. Bangladesh J Medicine 2023; Vol. 34, No. 2(1) Supplement: 216-217

Nationwide genetic analysis of more than 600 families with inherited eye diseases in Argentina

This study corresponds to the first large-scale genetic analysis of inherited eye diseases (IED) in Argentina and describes the comprehensive genetic profile of a large cohort of patients. Medical records of 22 ophthalmology and genetics services throughout 13 Argentinian provinces were analyzed retrospectively. Patients with a clinical diagnosis of an ophthalmic genetic disease and a history of genetic testing were included. Medical, ophthalmological and family history was collected. A total of 773 patients from 637 families were included, with 98% having inherited retinal disease. The most common phenotype was retinitis pigmentosa (RP, 62%). Causative variants were detected in 379 (59%) patients. USH2A, RPGR, and ABCA4 were the most common disease-associated genes. USH2A was the most frequent gene associated with RP, RDH12 early-onset severe retinal dystrophy, ABCA4 Stargardt disease, PROM1 cone-rod dystrophy, and BEST1 macular dystrophy. The most frequent variants were RPGR c.1345 C > T, p.(Arg449*) and USH2A c.15089 C > A, p.(Ser5030*). The study revealed 156/448 (35%) previously unreported pathogenic/likely pathogenic variants and 8 possible founder mutations. We present the genetic landscape of IED in Argentina and the largest cohort in South America. This data will serve as a reference for future genetic studies, aid diagnosis, inform counseling, and assist in addressing the largely unmet need for clinical trials to be conducted in the region.

Bony and Soft Tissue Hand Tumors

Background: The hand is a common site of tumors and tumor-like pathology. This study aimed to evaluate hand tumors and their distribution regarding age, gender, and histopathological characteristics to promote better understanding and aid in diagnosis. Material and Methods: A total of 261 incisional or excisional biopsies for hand tumors were reviewed retrospectively from January 2017 to December 2022 at Princess Iman Research Center. The tumor was assessed according to the tumor origin, and histopathological diagnosis was analyzed regarding age and gender to find the correlation. Biopsies with more than one possible diagnosis and excised hand tumors that were not sent to a pathologist were not included. Results: Soft tissue tumors represented 93.5% and bone tumors 6.5% of all hand tumors. Malignant tumors were reported in 6.1%. Tendon sheath (19.2%) and synovial (17.6%) origin tumors were the most common types, followed by skin (13%) and vascular (12.6%) tumors. Giant cell tumor was the most common hand tumor type (18.8%), followed by Ganglion cyst (16.5%). Enchondroma was the most common bone tumor (3.1%), and squamous cell carcinoma was the most common malignant tumor in hand. There was no difference in the distribution of tumors between different gender and ages. Conclusions: Although ganglion is the most common hand tumor in all reports, in our study, it was the second most common after the Giant cell tumor of tendon sheath because many surgeons depended on the clinical picture alone. Multicenter studies and other study designs, such as clinical and radiological evaluation, are required for a better understanding of the distribution of hand tumors.

COVID-19 in people with HIV in the Netherlands.

We investigated occurrence of and risk factors for severe COVID-19 outcomes in people with HIV (PWH) in the Netherlands. An ongoing prospective nationwide HIV cohort study. COVID-19 diagnoses and outcomes with other relevant medical information were prospectively collected from electronic medical records in all HIV treatment centers in the Netherlands, from the start of the COVID-19 epidemic until December 31, 2021. Risk factors for COVID-19 related hospitalization and death were investigated using multivariable logistic regression, including demographics, HIV-related factors, and comorbidities. The cohort comprises 21 289 adult PWH, median age 51.2 years, 82% male, 70% were of Western origin, 12.0% were of sub-Saharan African and 12.6% Latin American/Caribbean origin, 96.8% had HIV-RNA less than 200 copies/ml, median CD4 + cell count 690 (IQR 510-908) cells/μl. Primary SARS-CoV-2 infections were registered in 2301 individuals, of whom 157 (6.8%) required hospitalization and 27 (1.2%) ICU admission. Mortality rates were 13 and 0.4% among hospitalized and nonhospitalized individuals, respectively. Independent risk factors for severe outcomes (COVID-19-related hospitalization and death) were higher age, having multiple comorbidities, a CD4 + cell count less than 200 cells/μl, uncontrolled HIV replication, and prior AIDS diagnosis. Migrants from sub-Saharan Africa, Latin America, and the Caribbean were at an increased risk of severe outcomes independently of other risk factors. In our national cohort of PWH, risk of severe COVID-19 outcomes was increased in individuals with uncontrolled HIV replication, low CD4 + cell count, and prior AIDS diagnosis, independently of general risk factors such as higher age, comorbidity burden and migrants originating from non-Western countries.

Addressing HIV/AIDS and syphilis in Venezuelan migrant women from the perspective of health managers in the North of BrazilManejo de la infección por el VIH/sida y la sífilis en mujeres migrantes venezolanas desde la perspectiva de los gestores de salud en el norte de Brasil

To identify the perception of health managers regarding the actions taken and the challenges encountered in addressing HIV and syphilis in Venezuelan migrant women in Brazil. This descriptive-exploratory study using a qualitative approach was conducted from January to March 2021 in the municipalities of Boa Vista (state of Roraima) and Manaus (state of Amazonas). Audio interviews with the participants were transcribed in full and examined using thematic content analysis. Ten managers were interviewed (five in Boa Vista and five in Manaus). Content analysis identified the following domains and themes: available infrastructure for diagnosis and treatment of AIDS and syphilis - access, availability of medical appointments /waiting list, training of health teams, and psychosocial support; challenges faced by Venezuelan women - language, documentation issues, and frequent address changes; and strategies and actions adopted and expectations for addressing HIV/AIDS and syphilis in the context of migration. Despite the care provided to Venezuelan women in Brazil - guaranteed by the universal nature of the Brazilian health system - language and lack of documentation remain as barriers. Given the absence of action plans and future planning for the care of migrant women with HIV or syphilis in municipalities, it is important to develop public policies aimed at minimizing the difficulties faced by this population.

THE ROLE OF NASAL ENDOSCOPY IN PATIENTS OF MUCORMYCOSIS

Objective: The Rhino-orbital- cerebral infection is the most typical presentation of mucormycosis where there is an invasion of the fungal infection from paranasal sinuses to orbit and brain (6,11).Extension of the disease leads to vascular thrombosis, including the cavernous sinus and other cerebral vessels due to fibrin reaction and Mucor thrombus formation. Nasal Endoscopy aids in the early detection and management of the disease (8). This study aims to study the signs and symptoms of patients with mucormycosis and the role of nasal endoscopy in early diagnosis. Subjects And Methods: A Prospective study was conducted on 150 patients of age 20-90 years attending ENT OPD and admitted under the Department of otorhinolaryngology at a tertiary care center in Central India. Subjects with or without Covid 19 infection, comorbidities like diabetes and hypertension and patients on steroids were selected for nasal endoscopy. Patients with benign or malignant lesions of nasal cavity and post operative cases of FESS for mucor were excluded. Results: In out study, majority patients were from the 5th decade followed by the 6th. In the classification system designed on the basis of endoscopy findings, majority were in Group B(42%) followed by Group C (28.7%). Maxillary sinus was found to be the most common sinuses involved as seen in the MRI of 110 patients. Out of 150 patients, debridement was done in 74 patients. In our study, we have concluded that diagnostic nasal endosco Conclusion: py aids in early diagnosis and management of mucormycosis. The grading system makes the management of the large number of patients easier. Appropriate time, treatment and resources can be given to the required patients. All patients after this management protocol stood well and were successfully discharged with only 8% mortality rate.

Imaging Recommendations for Image-Guided Biopsy in Oncology

AbstractThe percutaneous needle biopsy (PNB) is the initial step for obtaining the diagnosis and it helps in treatment. It aids in primary diagnosis, tumor staging, or ruling out infective etiology. It is a safe and successful minimally invasive method compared to open biopsies. PNB is defined as the placement and insertion of a needle into a suspected lesion or organ with the intent of retrieving tissue or cells for diagnosis. It can fine needle aspiration cytology or core needle biopsy. The patient needs to be counseled regarding the procedure and detailed history, including anticoagulant history needs to be taken. The SIR consensus guidelines have divided biopsies into low-risk procedures with a bleeding risk of &lt; 1.5% and high-risk procedures &gt; 1.5%. There are advancements in needle design (e.g., echogenic tip while performing ultrasound-guided needle biopsy) and image-guidance technology (ultrasound quality, multi-slice CT scan) that improved these procedures safety and efficacy. There are different types of needles available such as coaxial, aspiration needles, Murphy's bone biopsy needle, which depends on the tissue which needs to be sampled or the organ to be biopsied. Various different types of biopsy guns, such as semi-automatic, automatic, or manual are available. The newer technology such as fusion and navigation biopsies helps in better characterizing and localization of the lesion, improving the yield of the biopsy. Open and excisional biopsies have a higher mortality and morbidity rate than percutaneous biopsies, they are reserved for cases where the image-guided method has failed to provide the diagnostic yield. Sample collection must be done under a sterile container in formaline or microbiological examination. Regular analysis and rad-path correlation are key to success and improving diagnostic yield. This abstract provides an overview of the existing biopsy literature.

Assessment of Functional Impotence in a Young Person Revealing Kienböck's Disease: Radio-Clinical Case and Review of the Literature

Kienbock's disease is a rare form of avascular necrosis affecting the lunate bone. The underlying mechanism is poorly understood. Clinical examination is not specific, and diagnosis is typically made through imaging. Plain radiography, CT, and MRI can all aid in diagnosis, staging, and guiding treatment decisions.

Any correlation between severity of symptoms and the adenoid nasopharyngeal ratio?

Objective: Adenoid Hypertrophy is a common childhood condition that presents with mouth breathing, nasal discharge, snoring and sleep apnea. Lateral Nasopharyngeal X-ray aids diagnosis and assessment of patency of the Nasopharyngeal air column through Adenoid Nasopharyngeal Ratio (ANR). This study aims to correlate ANR with symptoms and signs of Adenoid Hypertrophy. Material and Methods: A retrospective study conducted in the Ear, Nose and Throat/Head and Neck Surgery (ENT/HNS) Department of University of Abuja Teaching Hospital, Gwagwalada from January 2019 to December 2021. The case notes and Lateral Nasopharyngeal X-rays of 66 Children aged between 2months to 11 years, with suspected Adenoid Hypertrophy were retrieved and relevant retrieved data analyzed. Results: A total of 66 patients were enrolled into this study with 50 (75.76%) males and 16 (24.24%) females. The age range was between 2 months to 11 years, with a mean of 3.65±2.76 years. ANR ranged from 0.03 to 0.94 with mean 0.71±0.15. Out of the 66 participants, 30 (46.15%) had ANR of 0.7, while 35 (53.85%) had ANR of &gt; 0.7. Linear regression analysis showed association between age and ANR (P &lt; 0.05). Snoring was the most common symptom (92.42%), followed by Mouth breathing (89.39%) and Nasal Discharge (77.27%). Majority of patients (88.6%) had a Mild Symptom Score. There was no statistically significant relationship between any of the clinical features and ANR. Conclusion: There is no significant correlation between the clinical features and adenoid nasopharyngeal ratio.

"Dye another day!" - dyes in ophthalmology.

Dyes are substances that are an integral part of ocular procedures and surgeries. In Clinical practice, dyes help in better visualization and aid in diagnoses of ocular surface disorders. In Surgical practice, dyes help in better resolution of the structures that are otherwise naked to the surgeon's eyes. To educate ophthalmologists about the importance and uses of dyes. Dyes have become an important part of an ophthalmologists' clinical as well as surgical practice. This video aims at educating the different characteristics, uses, advantages and disadvantages of each dye. Dyes help in identifying the obscure and highlighting the invisible. The indications and contraindications as well as the side effects of each dye are discussed which would help ophthalmologists in the correct usage of these wonder substances. This video will also help the new eye doctors understand and utilize these dyes judiciously which would aid in their learning process and provide better patient care. This video highlights the uses, indications, contraindications and side effects of all the dyes used in ophthalmology. https://youtu.be/shdV4a6oc20.

A rare case report on neonatal complications from Nepal: solitary neonatal hepatic abscess.

We present the case of a patient who presented with one day of sudden abdominal distension and two episodes of projectile nonbilious vomiting. A solitary liver abscess was diagnosed using ultrasonography and contrast-enhanced computed tomography findings, and the patient was treated conservatively with parenteral broad-spectrum antibiotics. Following the completion of the antibiotic dose, an ultrasound of the abdomen reveals that the size of the liver abscess has decreased. Neonatal liver abscess is a rare clinical condition that causes significant morbidity and mortality in premature and term babies. In a neonate with potential risk factors, a high index of suspicion is required to make the diagnosis. Baseline tests, as well as computed tomography with or without contrast, aid in the definitive diagnosis of a hepatic abscess. For management, a multidisciplinary approach should be considered, including correction of the predisposing factor as well as appropriate medical and/or surgical intervention. Neonatal liver abscess is frequently overlooked due to its rarity. Thus, whenever a neonate exhibits the aforementioned clinical spectrum, it should be considered in the differential diagnosis, and a diagnostic workup and treatment should be initiated as soon as possible to avoid debilitating complications.

X-Ray image-based COVID-19 detection using deep learning.

COVID-19 is a type of respiratory infection that primarily affects the lungs. Obtaining a chest X-ray is one of the most important steps in detecting and treating COVID-19 occurrences. Our study's goal is to detect COVID-19 fromchest X-ray images using a Convolutional Neural Network (CNN). This study presentsan effective method for categorizing chest X-ray images as Normal or COVID-19 infected. We used CNN, activation functions dropout, batch normalization, and Keras parameters to build this model. The classification method was implemented usingopen source tools "Python" and "OpenCV," both of which are freely available. The acquired images are transmitted through a series of convolutional and max pooling layers activated with the Rectified Linear Unit (ReLU) activation function, and then fed into the neurons of the dense layers, and finally activated with the sigmoidal function. Thereafter, SVM was used for classification using the knowledge from the learning model to classify the images into a predefined class (COVID-19 or Normal). As the model learns, its accuracy improves while its loss decreases. The findingsof the study indicate thatall models produced promising results, with augmentation, image segmentation, and image cropping producing the most efficient results, with a training accuracy of 99.8% and a test accuracy of 99.1%. As a result, the findings show that deep features provided consistent and reliable features for COVID-19 detection. Therefore,the proposed method aids in faster diagnosis of COVID-19 and thescreening of COVID-19 patientsby radiologists.

Intracranial Pachymeningitis: A Case-Series Describing Clinical Features, Imaging, Serological and Cerebrospinal Fluid Markers, Biopsy Findings and Management (P9-5.018)

<h3>Objective:</h3> We present a case-series of patients with intracranial pachymeningitis and outline their management for successful outcomes. <h3>Background:</h3> Hypertrophic pachymeningitis is characterized by focal/diffuse thickening of intracranial and/or intraspinal dura. <h3>Design/Methods:</h3> <h3>Case-1:</h3> 48-year-old-woman with Crohn’s disease, relapsing polychondritis, presented with persistent left-sided headaches. MRI brain revealed left-sided contrast-enhancing pachymeningeal thickening; CSF showed lymphocytic pleocytosis. Glucocorticoids, adalimumab, and methotrexate resulted in clinical and neuroimaging improvement. <h3>Case-2:</h3> 78-year-old-woman presented with intractable headache, bilateral sensorineural-hearing-loss and vision-impairment. MRI brain showed nodular, multifocal dural-thickening at clivus, parasellar region, cavernous-sinuses extension encasing major vessels at skull-base. CSF showed lymphocytic pleocytosis, protein and serology demonstrated IgG4-subclasses, attributing etiology to IgG4-related-disease. Steroids, methotrexate, and later IV-rituximab resulted in equivocal response. Intrathecal rituximab, resulted in clinical and imaging stabilization, from better CNS penetration. <h3>Case-3:</h3> 60-year-old woman, with sarcoidosis presented with severe headaches. MRI demonstrated contrast-enhancing dural thickening in left posterior-temporo-occipital regions. Brain-biopsy showed non-necrotizing granulomas involving dura, parenchyma consistent with sarcoidosis. Steroids and infliximab, lead to clinical and radiological improvement. <h3>Case-4:</h3> 76-year-old man with prior metastatic melanoma, post-chemotherapy (nivolumab+ipilimumab), presented with headaches. MRI showed diffuse intracranial contrast-enhancing pachymeningeal thickening. Chest CT-scan showed circumferential thickening, contrast-enhancing thoracic aorta indicating systemic vasculitis. Serologically, ANA 1:320, +SSA/SSB, ESR/CRP both &gt;100 and ANCA was negative. Meningeal biopsy demonstrated granulomatosis with polyangiitis; etiology considered paraneoplastic. Steroids and methotrexate demonstrated clinical and radiological response. <h3>Case-5:</h3> 56-year-old woman presented with headaches and CN-VII palsy. MRI brain revealed hypertrophic pachymeningitis causing mass-effect on right lateral ventricle. ANCA serological positivity and biopsy demonstrated AFB-stain-negative caseating granulomas, consistent with ANCA-vasculitis. Rituximab led to complete resolution of both pachymeningeal and CN-VII enhancement. <h3>Results:</h3> Clinical resolution and radiological stability was achieved for all 5 patients. <h3>Conclusions:</h3> Intracranial pachymeningitis presents in setting of systemic autoimmune disorders and sarcoidosis. Brain imaging, CSF-analysis, serological immune-markers, and biopsy aid in diagnosis. Immunosuppressive therapies provide for clinical and radiologic stabilization. <b>Disclosure:</b> Dr. Varma-Doyle has nothing to disclose. Dr. Manzano has nothing to disclose. Dr. Venna has nothing to disclose.

A meta-learning based method for segmentation of few-shot magnetic resonance images

When applying deep learning algorithms to magnetic resonance (MR) image segmentation, a large number of annotated images are required as data support. However, the specificity of MR images makes it difficult and costly to acquire large amounts of annotated image data. To reduce the dependence of MR image segmentation on a large amount of annotated data, this paper proposes a meta-learning U-shaped network (Meta-UNet) for few-shot MR image segmentation. Meta-UNet can use a small amount of annotated image data to complete the task of MR image segmentation and obtain good segmentation results. Meta-UNet improves U-Net by introducing dilated convolution, which can increase the receptive field of the model to improve the sensitivity to targets of different scales. We introduce the attention mechanism to improve the adaptability of the model to different scales. We introduce the meta-learning mechanism, and employ a composite loss function for well-supervised and effective bootstrapping of model training. We use the proposed Meta-UNet model to train on different segmentation tasks, and then use the trained model to evaluate on a new segmentation task, where the Meta-UNet model achieves high-precision segmentation of target images. Meta-UNet has a certain improvement in mean Dice similarity coefficient (DSC) compared with voxel morph network (VoxelMorph), data augmentation using learned transformations (DataAug) and label transfer network (LT-Net). Experiments show that the proposed method can effectively perform MR image segmentation using a small number of samples. It provides a reliable aid for clinical diagnosis and treatment.