A Mask-guided Attention Deep Learning Model for COVID-19 Diagnosis based on an Integrated CT Scan Images Database

<p>The global extent of COVID-19 mutations and the consequent depletion of hospital resources highlighted the necessity of effective computer-assisted medical diagnosis. COVID-19 detection mediated by deep learning models can help diagnose this highly contagious disease and lower infectivity and mortality rates. Computed tomography (CT) is the preferred imaging modality for building automatic COVID-19 screening and diagnosis models. It is well-known that the training set size significantly impacts the performance and generalization of deep learning models. However, accessing a large dataset of CT scan images from an emerging disease like COVID-19 is challenging. Therefore, data efficiency becomes a significant factor in choosing a learning model. To this end, we present a multi-task learning approach, namely, a mask-guided attention (MGA) classifier, to improve the generalization and data efficiency of COVID-19 classification on lung CT scan images.</p><p>The novelty of this method is compensating for the scarcity of data by employing more supervision with lesion masks, increasing the sensitivity of the model to COVID-19 manifestations, and helping both generalization and classification performance. Our proposed model achieves better overall performance than the single-task baseline and state-of-the-art models, as measured by various popular metrics. In our experiment with different percentages of data from our curated dataset, the classification performance gain from this multi-task learning approach is more significant for the smaller training sizes. Furthermore, experimental results demonstrate that our method enhances the focus on the lesions, as witnessed by both</p><p>attention and attribution maps, resulting in a more interpretable model.</p>

A Mask-guided Attention Deep Learning Model for COVID-19 Diagnosis based on an Integrated CT Scan Images Database

<p>The global extent of COVID-19 mutations and the consequent depletion of hospital resources highlighted the necessity of effective computer-assisted medical diagnosis. COVID-19 detection mediated by deep learning models can help diagnose this highly contagious disease and lower infectivity and mortality rates. Computed tomography (CT) is the preferred imaging modality for building automatic COVID-19 screening and diagnosis models. It is well-known that the training set size significantly impacts the performance and generalization of deep learning models. However, accessing a large dataset of CT scan images from an emerging disease like COVID-19 is challenging. Therefore, data efficiency becomes a significant factor in choosing a learning model. To this end, we present a multi-task learning approach, namely, a mask-guided attention (MGA) classifier, to improve the generalization and data efficiency of COVID-19 classification on lung CT scan images.</p><p>The novelty of this method is compensating for the scarcity of data by employing more supervision with lesion masks, increasing the sensitivity of the model to COVID-19 manifestations, and helping both generalization and classification performance. Our proposed model achieves better overall performance than the single-task baseline and state-of-the-art models, as measured by various popular metrics. In our experiment with different percentages of data from our curated dataset, the classification performance gain from this multi-task learning approach is more significant for the smaller training sizes. Furthermore, experimental results demonstrate that our method enhances the focus on the lesions, as witnessed by both</p><p>attention and attribution maps, resulting in a more interpretable model.</p>

Camel-Hump T-Wave, Tee-Pee Sign, and Wavy Triple Sign (Yasser’s Sign) with Hypocalcemia and Hyperkalemia in Covid-19 Pneumonia with Lacunar Infarction

Rationale: A novel COVID-19 is a multi-systemic critical worldwide pandemic infection. Certainly, associated multiple electrolytes imbalance in COVID-19 pneumonia is a remarkable decisive event. Camel-hump T-wave, Tee-Pee sign, and Wavy triple sign (Yasser’s sign)are novel highly significant descriptive electrocardiographic signs that are seen in calcium and potassium disturbance. There is an established and strong relationship between and electrocardiographic abnormalities and electrolytes imbalance. COVID-19 pneumonia and cerebrovascular stroke are commonly seen in a patient with Coronavirus infection. Patient concerns: A 69-year-old married worker Egyptian male patient was presented to the emergency department with COVID-19 pneumonia and cerebrovascular stroke. Diagnosis: COVID-19 pneumonia with lacunar infarction, hypocalcemia, and hyperkalemia. Interventions: Chest CT scan, brain CT scan, electrocardiography, oxygenation, and echocardiography. Outcomes: Initial bad and deterioration outcome but, the dramatic outcome had happened after later management. Lessons: The understanding of electrocardiographic signs regarding metabolic disorders such as electrolytes imbalance and other associated systemic diseases is very important. Elderly male sex, heavy smoker, COVID-19 pneumonia, cerebrovascular stroke, chronic renal impairment, ischemic heart disease, hypokalemia, hypocalcemia, and hypernatremia represent bad prognostic points and is indicating a high-risk condition.

Approach to an adult with an episode of seizure

A patient with known epilepsy who has had a single, habitual seizure and whose mental status has returned to baseline need not be transported to the emergency department (ED) unless other injuries require so, whereas a patient with no history of epilepsy who has returned to baseline following a seizure should be evaluated. The evaluation should include basic biochemical parameters, toxicology screening and a brain imaging. One should investigate circumstances that may have precipitated a seizure, such as alcohol withdrawal, stimulant use, or head injury. Risk of recurrence of seizures is more likely in those with a history of significant brain injury or infection. If the patient has a normal magnetic resonance imaging (MRI) and electroencephalograph (EEG), the likelihood of a second seizure is approximately 1 in 3; if either test result is abnormal, the chances are approximately 1 in 2; if both are abnormal, the probability rises to 2 in 3. Computed tomography (CT) scan head is very useful in the evaluation of first seizure in infants less than six months of age. The clinical characteristics predictive of an abnormal CT scan for patients presenting with seizures were age less than 6 months or age greater than 65 years, history of cysticercosis, altered mentation, closed head injury, recent cerebrospinal fluid (CSF) shunt revision, malignancy, neurocutaneous disorder and seizures with focal onset or duration longer than 15 minutes. MRI has been shown to be superior to CT for the detection of cerebral lesions associated with epilepsy.

Effectiveness of Functional Endoscopic Sinus Surgery in Surgical Management of Ethmoid Polyps

Background: Aim: To assess efficacy of functional endoscopic sinus surgery in surgical management of ethmoid polyps.Methods:One hundred twelve adult patients age ranged 18- 38 years of either gender with ethmoid polyps underwent FESS under general anesthesia. The extent of surgery was decided based on the findings in pre-operative CT scan of paranasal sinuses. Anterior ethmoidectomy, posterior ethmoidectomy, middle meatus antrostomy and clearance of frontal recess were performed in all the patients. Five functional criteria were evaluated as nasalobstruction , anosmia, rhinorrhea, post nasal drip, head ache and facial pain.Results:Pre- operative nasal obstruction percentage was 3.42 and post- operative ercentage was 2.10, Anosmia percentage was 2.14 and 1.15, Rhinorrhea percentage was 3.56 and 2.08 and ocular problem in 1 and synechia in 4 cases.Conclusions:Functional endoscopic sinus surgery found to be effective in management of ethmoid polyps and hence can be the treatment of choice.

Study of Epilepsy and its Correlation with Neuroimaging and Drug Therapy

Background: Thousands of people in the world suffer from epilepsy. Inspite of modern advances, it can be controlled in only 80% of treated once. Diagnosis and treatment of epilepsy is still challenged. The present study is attempted to highlight the importance of clinical findings and role of EEG and CT scan and MRI in diagnosis of epilepsy2.Aim:To study the incidence and epidemiological profile, various types of epilepsy and correlation with MRI, CT SCAN, EEG and the effectiveness of various Anti epilepticdrugs in different types of epilepsy. Settings and Design: This is a prospective study carried out at Civil Hospital, Ahmedabad.Methods:All the patients having 2 and/or more unprovoked seizures and already enrolled patients in epilepsy clinic in 1 year duration from January 1,2020 to December 31,2020 were included.Results &Conclusions:Out of 6930 total admissions, 163 patients with epilepsy were enrolled in this study from age group of 1 month to 12 years. Out of 163 patients, 97 were male and 66 were female. Most common age group affected is of 1-5 years. 128 patients (78.62%) were of generalized epilepsy and 35 patients were of partial epilepsy. Most common precipitating factor in epilepsy is inadequate drug dosages (45%). 45 patients (22.7%) have developmental delay. Abnormal EEG findings were present in 123 patients (75.46%). Abnormal MRI findings were present in 37 patients (22.7%). CT scan was done in 56 patients, 20 were abnormal. 107 patients were on monotherapy and 56 patients were on polytherapy. Valproate is most commonly used drug (76.6%).

Therapeutic effect of cycloserine combined with anti-tuberculosis drugs in the treatment of multidrug-resistant tuberculosis

Purpose: The present study analyzes the comprehensive therapeutic effect of cycloserine, in combination with anti-tuberculosis drugs using chest X-ray and chest CT (computed tomography) scan techniques. Methods: A total of 90 patients, diagnosed with multidrug resistant tuberculosis (MDR TB) were subjected to chest x-ray and CT scan before and after treatment in the two groups. Different views such as sagittal, coronal, lung window and multiplanar imaging of mediastinal window were taken. Some parameters such as case detection rate (CDR) in chest X-ray and CT scan and comprehensive curative effect were observed in two groups. Further, the changes in chest CT signs in addition to absorption of focus, cavity closure and changes in CT extra pulmonary signs were also observed. Results: The clinical profile of the patients and the course of disease were statistically insignificant (p > 0.05). Total effectiveness rate and case detection rate (CDR) values exhibited a significant difference between the groups (p < 0.05). Lung consolidation, nodules and cavities significantly improved in both groups before and after the treatment (p < 0.05). Both groups showed significant improvements in extrapulmonary signs in CT scan (p < 0.05) after the treatment. Conclusion: Based on the study outcomes, the CT scan method has good potentials for diagnosing and treating MDR TB at the early stages. Further, it can clarify the signs and outcomes of the disease at early stages, thus providing the medical fraternity a great opportunity to cure the disease.