Image level detection of large vessel occlusion on 4D-CTA perfusion data using deep learning in acute stroke

OBJECTIVES

Automated image-level detection of large vessel occlusions (LVO) could expedite patient triage for mechanical thrombectomy. A few studies have previously attempted LVO detection using artificial intelligence (AI) on CT angiography (CTA) images. To our knowledge this is the first study to detect LVO existence and location on raw 4D-CTA/ CT perfusion (CTP) images using neural network (NN) models.

MATERIALS AND METHODS

Retrospective study using data from a level-I stroke center was performed. A total of 306 (187 with LVO, and 119 without) patients were evaluated. Image pre-processing included co-registration, normalization and skull stripping. Five consecutive time-points for each patient were selected to provide variable contrast density in data. Additional data augmentation included rotation and horizonal image flipping. Our model architecture consisted of two neural networks, first for classification (based on hemispheric asymmetry), followed by second model for exact site of LVO detection. Only cases deemed positive by the classification model were routed to the detection model, thereby reducing false positives and improving specificity. The results were compared with expert annotated LVO detection.

RESULTS

Using a 80:20 split for training and validation, the combination of both classification and detection model achieved a sensitivity of 86.5%, a specificity of 89.5%, and an accuracy of 87.5%. A 5-fold cross-validation using the entire data achieved a mean sensitivity of 82.7%, a specificity of 89.8%, and an accuracy of 85.5% and a mean AUC of 0.89 (95% CI: 0.85-0.93).

CONCLUSION

Our findings suggest that accurate image-level LVO detection is feasible on CTP raw images.

CT Perfusion Maps Improve Detection of M2-MCA Occlusions in Acute Ischemic Stroke

OBJECTIVES

Middle cerebral artery occlusions, particularly M2 branch occlusions are challenging to identify on CTA. We hypothesized that additional review of the CTP maps will increase large vessel occlusion (LVO) detection accuracy on CTA and reduce interpretation time.

MATERIALS AND METHODS

Two readers (R1 and R2) retrospectively reviewed the CT studies in 99 patients (27 normal, 26 M1-MCA, 46 M2-MCA occlusions) who presented with suspected acute ischemic stroke (AIS). The time of interpretation and final diagnosis were recorded for the CTA images (derived from CTP data), both without and with the CTP maps. The time for analysis for all vascular occlusions was compared using McNemar tests. ROC curve analysis and McNemar tests were performed to assess changes in diagnostic performance with the addition of CTP maps.

RESULTS

With the addition of the CTP maps, both readers showed increased sensitivity (p = 0.01 for R1 and p = 0.04 for R2), and accuracy (p = 0.02 for R1 and p = 0.004 for R2) for M2-MCA occlusions. There was a significant improvement in diagnostic performance for both readers for detection of M2-MCA occlusions (AUC R1 = 0.86 to 0.95, R2 = 0.84 to 0.95; p < 0.05). Both readers showed reduced interpretation time for all cases combined, as well as for normal studies (p < 0.001) when CTP images were reviewed along with CTA. Both readers also showed reduced interpretation time for M2-MCA occlusions, which was significant for one of the readers (p < 0.02).

CONCLUSION

The addition of CTP maps improves accuracy and reduces interpretation time for detecting LVO and M2-MCA occlusions in AIS. Incorporation of CTP in acute stroke imaging protocols may improve detection of more distal occlusions.

Segmental testicular infarct with an associated testicular artery aneurysm: Case report of a rare clinical entity

Segmental testicular infarct is a rare clinical entity and can be a diagnostic challenge. Although cases are often idiopathic, underlying etiologies can include testicular torsion, epididymo-orchitis, trauma, vasculitis, and hypercoagulable states. Once suspected, an underlying testicular neoplasm should be excluded. We present a case of a 43-year-old male who developed acute onset left sided scrotal pain. A diagnostic scrotal ultrasound showed a focal, heterogeneous region in left testicle with absent focal Doppler signal, concerning for a segmental testicular infarction. There was no history of trauma, urinary symptoms, sexually transmitted diseases, or constitutional symptoms. Work up for associated underlying etiologies was negative. A computed tomography angiogram scan of the abdomen and pelvis revealed an incidental left testicular artery aneurysm. The patient's consulting multidisciplinary care teams included urology and vascular surgery. Urology deemed surgical intervention inappropriate for the segmental testicular infarct, and vascular surgery elected not to intervene on the testicular artery aneurysm due to risk of completing testicular infarct and damaging blood supply to the testis. The patient was discharged after achieving adequate pain control, and completion of inpatient work up. No underlying malignancy was diagnosed on follow up, and pain symptoms resolved. To the authors’ knowledge, no literature exists describing the concurrent incidence of a segmental testicular infarct and an ipsilateral testicular artery aneurysm. In this report, we aim to further describe both diagnoses, and explore the association between the 2 entities.

Factors influencing the acquisition of COVID infection among high-risk contacts of COVID-19 patients in Madurai district-A case control study

Introduction

COVID is a new disease; understanding the transmission dynamics and epidemiological characteristics may help in developing the effective control measures. The study is done 1. To determine the various factors influencing the acquisition of COVID-19 infection among high-risk contacts 2. To estimate the secondary attack rate among high-risk contacts 3. To determine the factors in COVID index cases influencing their secondary attack rate.

Methodology

Unmatched case control study was conducted from March to August 2020 among 139 COVID index cases in Madurai district from March-May (Reference period) and their 50 COVID positive (cases), 551 COVID negative (controls) high-risk contacts. Case investigation form* and contact tracing Proforma*were used to collect data. Chi-square test and independent sample t test were used to find out the association. Univariate* and Multivariate logistic regression* were used to predict the risk of various factors in acquisition of COVID infection with the help of adjusted and unadjusted odds ratio. P value < 0.05 was considered statistically significant.

Results

Male contacts (P = 0.005, OR = 2.520), overcrowding (P = 0.007, OR = 3.810), and duration of exposure to index case (for 4-7 days P = 0.014, OR = 2.902, for >7 days P = 0.001, OR = 6.748 and for > 12 hours/day P = 0.000, OR = 5.543) were significant factors predicted to be associated with acquisition of COVID infection among high-risk contacts. Reproductive number (R0)* estimated was 1.3. Secondary attack rate (SAR)* estimated among high-risk contacts was 8.32%. Index cases whose outcome was death (P = 0.026); symptomatic index cases (P = 0.000), cases with fever (P = 0.001); sorethroat (P = 0.019); breathlessness (P = 0.010); cough (P = 0.006) and running nose (P = 0.002) had significantly higher mean SAR than their counterparts.

Conclusion

Contacts with above said risk factors who were found to be more prone to infection could be given special focus to prevent the transmission in them.

Dual Energy CT Physics-A Primer for the Emergency Radiologist

Dual energy CT (DECT) refers to the acquisition of CT images at two energy spectra and can provide information about tissue composition beyond that obtainable by conventional CT. The attenuation of a photon beam varies depends on the atomic number and density of the attenuating material and the energy of the incoming photon beam. This differential attenuation of the beam at varying energy levels forms the basis of DECT imaging and enables separation of materials with different atomic numbers but similar CT attenuation. DECT can be used to detect and quantify materials like iodine, calcium, or uric acid. Several post-processing techniques are available to generate virtual non-contrast images, iodine maps, virtual mono-chromatic images, Mixed or weighted images and material specific images. Although initially the concept of dual energy CT was introduced in 1970, it is only over the past two decades that it has been extensively used in clinical practice owing to advances in CT hardware and post-processing capabilities. There are numerous applications of DECT in Emergency radiology including stroke imaging to differentiate intracranial hemorrhage and contrast staining, diagnosis of pulmonary embolism, characterization of incidentally detected renal and adrenal lesions, to reduce beam and metal hardening artifacts, in identification of uric acid renal stones and in the diagnosis of gout. This review article aims to provide the emergency radiologist with an overview of the physics and basic principles of dual energy CT. In addition, we discuss the types of DECT acquisition and post processing techniques including newer advances such as photon-counting CT followed by a brief discussion on the applications of DECT in Emergency radiology.

Assessment of retinal manifestations of Parkinson's disease using spectral domain optical coherence tomography: A study in Indian eyes

Purpose:

To assess the retinal manifestations of Parkinson’s disease using optical coherence tomography.

Methods:

A prospective case-control study comparing 30 eyes from 15 patients with Parkinson’s disease and 22 eyes from 11 healthy age-matched controls. Total macular subfield thickness and the thickness of the ganglion cell layer, nerve fiber layer, and peripapillary retinal nerve fiber layer were measured with spectral-domain optical coherence tomography (SD-OCT).

Results:

The mean age of PD patients was 68.4 years ± 10.64 (range: 46–82) and in the control group was 66.36 ± 5.22 (range: 64–68). The average disease duration in patients with PD was 6.7 ± 2.8 years (range: 2–10 years). The mean best-corrected visual acuity in PD was 20/26 and 20/20 in controls, with P = 0.0059, which was significant. Significant difference was also found in the contrast sensitivity between both groups. Structural differences in the central macular thickness (P = 0.0001), subfield thicknesses in the superior (P = 0.003), inferior (P = 0.001), nasal (P = 0.004), and temporal subfields (P = 0.017) was seen. Severe thinning of the ganglion cell layer was seen in PD patients (P = 0.000) as well as of the nerve fiber layer (P = 0.004). Peripapillary retinal nerve fiber thickness measured showed significant thinning in superotemporal (P = 0.000), superonasal (P = 0.04), inferonasal (P = 0.000), inferotemporal (P = 0.000), nasal (P = 0.000), and temporal quadrants (P = 0.000).

Conclusion:

Visual dysfunction was observed in patients with PD along with structural alterations on OCT, which included macular volumes, ganglion cell layer, and peripapillary retinal nerve fiber layer.

A cross sectional study on psychological impact of covid19 on post graduate doctors and Compulsory Rotatory Residential interns in COVID isolation ward of a tertiary care centre, Madurai

Background

COVID-19 pandemic causes major impact on economic, physical, mental well-being of people all over the world. Doctors are working in stressful, unprepared, limited resource setting, and they are under the continuous threat of getting infection. Managing mental health of these warriors is great importance. Hence the present study to estimate the psychological impact of COVID-19* and factors associated with it among doctors in tertiary care hospital, Madurai.

Methods

A Cross-sectional study was conducted during October–November 2020 using a pre-designed semi structured questionnaire and DASS-21 scale which were sent through Google form to doctors who were in their quarantine period after the COVID duty. Totally 292 responses were received. Descriptive statistics done to find frequencies and percentages. Correlation for continuous variables; Univariate and multivariate regression for categorical variables were used to predict the factors influencing the psychological impact.

Results

In our study, 42.1% doctors were depressed, 43.8% were stressed and 50.7% had anxiety. Depression*, anxiety*, stress* scores were positively correlated with number of COVID duties(r² 0.163,0.138,0.133), number of elderly persons(r² 0.188,0.169,0.188) in their family and negatively correlated with sleep duration(r ²–0.219,-0.281,-0.239), attitude of study participants(r²-0.319,-0.274,-0.291). Multiple logistic regression showed that disturbed sleep(odd'sratio = 3.931,2.734,3.420) and poor quality of sleep which affect the next day function(odd'sratio = 3.470,2.968,3.122) were significant predictors for all three psychological impacts.

Conclusion

High prevalence of psychological impact estimated, ensures the requirement of early screening with timely psychological intervention and establishment of guideline policies to support mental health of healthcare workers* for maintaining the functionality of healthcare system.

Formulation and Evaluation of Gabapentin Sustained Release Matrix Tablet Using Hibiscus rosa sinensis Leaves Mucilage as Release Retardant

The major goal of this study was to develop and evaluate Sustained release matrix tablets of Gabapentin with Hibiscus rosa - sinensis leaves mucilage prepared by using wet granulation technique with microcrystalline cellulose as a diluents and magnesium stearate as a lubricant. Pre-compression and post-compression evaluation of physicochemical parameters were carried out and to be within acceptable limits. Drug and polymer compatibility were validated by FTIR measurements. Further, tablets were evaluated for in vitro release study. To get the sustained release of Gabapentin, the concentration of Hibiscus rosa- sinensis mucilage was tuned with a gas-generating agent. The % drug release of all formulation from F1 to F5 showed 91.24%, 80.24%, 70.53%, 62.12% and 49.83% respectively. All the dosage form release kinetics was computed using zero order, first order, Higuchi, and Korsmeyer–Peppas methods. From the above results, it is concluded that the n value of formulation F5 showed 0.78 suggesting anomalous (non-fickian) behavior of the drug. Mucilage from the leaves of Hibiscus rosa-sinensis has a great retarding effect in drug release from sustained release tablets.

Demographic profile of COVID-19 positive mothers & their outcome in government Rajaji hospital, Madurai, Tamilnadu - A cross sectional Study

Background

COVID-19 is a new pandemic disease. This disease course and its effect on pregnancy is little known due to limited available data. The objective of this study was to describe the demographic profile of COVID-19 positive mothers admitted in Government Rajaji hospital, Madurai in terms of time, place and person and to assess the general and pregnancy outcome of study population.

Methods

This cross-sectional study was done among 381 COVID-19 positive mothers* admitted during March 22 – August 31, 2020 in dedicated COVID-19 hospital, Madurai. Data was collected using Case Investigation Form (CIF) as a part of Rapid Response Team*(RRT) by Community Medicine* Department and analysed using SPSS version 21. Descriptive statistics done; Chi-square test & Fischer exact test was done to find out association between patient profile and outcomes.

Results

Out of 381, 154 (40.4%) belonged to 21–25 years, 192 (50.4%) to rural area, 318 (83.5%) to 3rd trimester,189 (49.6%) Primi gravida. 125 (32.8%) were symptomatic and 153 (80.8%) had at least one comorbidity. Death as general outcome was 3 (0.8%), all of them were referred cases and had comorbidity like GDM/PIH. 10 (2.62%) had abortion or perinatal death, 14 (3.77%) had preterm delivery, 99 (25.98%) babies were born small for gestational age. Increased maternal age had more death but was not statistically significant; All symptomatic mothers (p = 0.000),1st & 2nd trimester (p = 0.000) mothers had statistically significant poor pregnancy outcome*.

Conclusion

COVID positive mothers with increased age, symptomatic, 1st & 2nd trimester were significantly associated with poor outcome, requires special attention. Early referral must be emphasized to mitigate maternal death.

A Rare Case of Emphysematous Osteomyelitis of Femur in an Intravenous Drug User

Emphysematous osteomyelitis (EO) is a rare condition characterized by the appearance of gas locules within the bone on imaging, usually as a result of anaerobic bacterial infection. We present the case of a 46-year-old known intravenous (IV) drug user who was admitted to the emergency department with intractable pain in the right groin. He was febrile with elevated white cell count and C-reactive protein. He underwent an X-ray and CT of the pelvis which demonstrated intraosseous gas in the proximal right femur. A diagnosis of EO was made radiologically, allowing for prompt antibiotic treatment and a plan for surgical debridement. There are only a handful of published cases of EO in the literature, only one of which has described IV drug use as the underlying factor.

SVEP1 IS IMPORTANT FOR MORPHOGENESIS OF LYMPHATIC SYSTEM: POSSIBLE IMPLICATIONS IN LYMPHEDEMA

SVEP1, also known as Polydom, is a large extracellular mosaic protein with functions in protein interactions and adhesion. Since Svep1 knockout animals show severe edema and lymphatic system malformations, the aim of this study is to evaluate the presence of SVEP1 variants in patients with lymphedema. We analyzed DNA from 246 lymphedema patients for variants in known lymphedema genes, 235 of whom tested negative and underwent a second testing for new candidate genes, including SVEP1, as reported here. We found three samples with rare heterozygous missense single-nucleotide variants in the SVEP1 gene. In one family, healthy members were found to carry the same variants and reported some subclinical edema. Based on our findings and a review of the literature, we propose SVEP1 as a candidate gene that should be sequenced in patients with lymphatic malformations, with or without lymphedema, in order to investigate and add evidence on its possible involvement in the development of lymphedema.

Multimodality imaging in a case of multiple pulmonary hyalinizing granulomas - A decade follow-up

A 44-year-old male was referred to our clinic (2015) to evaluate multiple lung nodules with increasing fatigue, dyspnea, and weight loss. He was being assessed to an outside hospital for the same since 2010. The X-ray and computed-tomography (CT)-chest showed numerous pulmonary nodules and bilateral hilar adenopathy. Imaging workup at our institute (2015) redemonstrated extensive calcified pulmonary nodules. 18fluoro-2-deoxy-d-glucose positron emission tomographyCT showed widespread pulmonary nodules with low-grade uptake. Video-assisted thoracic surgery lung biopsy revealed pulmonary hyalinizing granuloma (PHG). Recently because of increasing symptoms, he is being evaluated for a lung transplant. This case represents a rare diagnosis of PHG with a decade follow-up.

Vascular Involvement in Neurosarcoidosis: Early Experiences From Intracranial Vessel Wall Imaging

BACKGROUND AND OBJECTIVES

Cerebrovascular manifestations in neurosarcoidosis (NS) were previously considered rare but are being increasingly recognized. We report our preliminary experience in patients with NS who underwent high-resolution vessel wall imaging (VWI).

METHODS

A total of 13 consecutive patients with NS underwent VWI. Images were analyzed by 2 neuroradiologists in consensus. The assessment included segment-wise evaluation of larger- and medium-sized vessels (internal carotid artery, M1-M3 middle cerebral artery; A1-A3 anterior cerebral artery; V4 segments of vertebral arteries; basilar artery; and P1-P3 posterior cerebral artery), lenticulostriate perforator vessels, and medullary and deep cerebral veins. Cortical veins were not assessed due to flow-related artifacts. Brain biopsy findings were available in 6 cases and were also reviewed.

RESULTS

Mean patient age was 54.9 years (33-71 years) with an M:F of 8:5. Mean duration between initial diagnosis and VWI study was 18 months. Overall, 9/13 (69%) patients had vascular abnormalities. Circumferential large vessel enhancement was seen in 3/13 (23%) patients, whereas perforator vessel involvement was seen in 6/13 (46%) patients. Medullary and deep vein involvement was also seen in 6/13 patients. In addition, 7/13 (54%) patients had microhemorrhages in susceptibility-weighted imaging, and 4/13 (31%) had chronic infarcts. On biopsy, 5/6 cases showed perivascular granulomas with vessel wall involvement in all 5 cases.

DISCUSSION

Our preliminary findings suggest that involvement of intracranial vascular structures may be a common finding in patients with NS and should be routinely looked for. These findings appear concordant with previously reported autopsy literature and need to be validated on a larger scale.

Deep learning framework for handling concept drift and class imbalanced complex decision-making on streaming data

In present times, data science become popular to support and improve decision-making process. Due to the accessibility of a wide application perspective of data streaming, class imbalance and concept drifting become crucial learning problems. The advent of deep learning (DL) models finds useful for the classification of concept drift in data streaming applications. This paper presents an effective class imbalance with concept drift detection (CIDD) using Adadelta optimizer-based deep neural networks (ADODNN), named CIDD-ADODNN model for the classification of highly imbalanced streaming data. The presented model involves four processes namely preprocessing, class imbalance handling, concept drift detection, and classification. The proposed model uses adaptive synthetic (ADASYN) technique for handling class imbalance data, which utilizes a weighted distribution for diverse minority class examples based on the level of difficulty in learning. Next, a drift detection technique called adaptive sliding window (ADWIN) is employed to detect the existence of the concept drift. Besides, ADODNN model is utilized for the classification processes. For increasing the classifier performance of the DNN model, ADO-based hyperparameter tuning process takes place to determine the optimal parameters of the DNN model. The performance of the presented model is evaluated using three streaming datasets namely intrusion detection (NSL KDDCup) dataset, Spam dataset, and Chess dataset. A detailed comparative results analysis takes place and the simulation results verified the superior performance of the presented model by obtaining a maximum accuracy of 0.9592, 0.9320, and 0.7646 on the applied KDDCup, Spam, and Chess dataset, respectively.

A cross-sectional study on COVID19 mortality among people below 30 years of age in Tamilnadu-2020

Introduction

The COVID19 pandemic has turned out to be one of the public health* burdens in 2020. The fear of deaths due to COVID19 has surmounted even in developed countries and hasn't spared young age. This study aims in assessing the mortality due to COVID19 among patients below 30years of age in TamilNadu.

Methods

The data was collected from a publicly available secondary data source(www.stopcorona.tn.gov.in)which is an official COVID19 state dashboard. Details of the young COVID19 deaths* under 30yrs of age, their gender, symptoms, Co-morbidities, date of symptoms, date of admission, and death were collected till October 2020. A total of 158 deaths were included in the analysis. Fischer exact test and Mann Whitney U test* were used and p-value <0.05 was considered significant.

Results

Among the 158 COVID19 deaths under 30 years of age, the median age affected was 25 years(IQR-7) and 70.3% (n-111) had at least one co-morbidity*. The median time interval between symptom onset and hospital admission was 3 days (IQR-3) and between admission and death was 4 days(IQR-7).There was a significant association of myocarditis, refractory seizures, Central nervous system involvement as the cause of death in the age group 0–15years, compared with 16–30years(p < 0.05). The majority of deaths occurred with a late presentation, also patients with higher age were admitted after 2 days of symptoms and the results were statistically significant(p < 0.05).

Conclusion

Understanding the age-dependent risk gradient and their trend of this new virus at young age* is essential for public health planning and prevent future deaths, future research gateways.

Role of FDG PET/CT for detection of primary tumor in patients with extracervical metastases from carcinoma of unknown primary

AIM

To explore the diagnostic performance of ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) to detect the primary tumor site in patients with extracervical metastases from carcinoma of unknown primary (CUP). We evaluated patient outcomes as overall survival (OS).

MATERIALS AND METHODS

In a single-center, retrospective study (2005-2019), patients with extracervical metastases from CUP underwent FDG PET/CT to detect primary tumor sites. The final diagnosis was based on histopathology/or clinical follow-up of at least 12 months.

RESULTS

A total of 83 patients [Male 41 (49%), mean age 59 ± 14 years, range: 32-83 years] fulfilled the inclusion/exclusion criteria and were enrolled for analysis. The primary tumor was detected in 36 out of 83 (43%) patients based on histopathology/or clinical follow-up. PET/CT suggested the primary tumor site in 39 (47%) patients with diagnostic accuracy of 87%, sensitivity 89%, specificity 85%, PPV 82%, NPV 91% and detection rate 39%. Patients with oligometastases (<3) (2.16 years, 1.04-2.54) and primary unidentified (1 year, 0.34-2.14) had longer median survival time compared to the patients with multiple metastases (0.67 years, 0.17-1.58, p = 0.009) and primary identified (0.67 years,0.16-1.33, p = 0.002). The SUVmax of the primary or metastatic lesions with maximum uptake was not significantly related to survival.

CONCLUSIONS

PET/CT could reveal the primary tumor site in 39% of the patients. It demonstrated the metastatic disease burden and distribution in patients with 'primary obscured', which directs management. Patients with multiple metastases and primary identified had a poorer prognosis. In patients with primary unidentified after PET/CT, a further search was futile.