Search

Background The traditional coronary calcium score (CCS) is a time-tested tool for the evaluation of coronary atherosclerosis and predictor of future cardiovascular events. Non-traditional tools can also have a value in predicting and detecting subclinical coronary artery disease (CAD). Methods We studied the role of CCS, the traditional CAD risk predictor, and the less-recognized, non-traditional risk factors, i.e. epicardial fat volume (EFV) and thoracic extracoronary calcium (ECC), to assess the degree of subclinical CAD. In this cross-sectional observational study, we included 950 Indian patients (suspected to have CAD). Coronary computed tomography angiography was performed. Estimation of CCS, EFV and thoracic ECC was done. Results A CCS of 0 was seen in 583 patients (61.4%). Of these, 492 patients had normal coronary angiogram but 91 patients had CAD. The median values of EFV were statistically significantly higher in the ‘CAD present and CCS 0’ group compared to the ‘CAD absent and CCS 0’ group (p Conclusion The combined use of traditional CCS along with non-traditional EFV may guide us in better profiling cardiovascular risk and supplement the various traditional cardiovascular risk factors/scores.

A 79-year-old hypertensive man with chronic type B aortic dissection (TBAD) came with acute chest pain. CT revealed partially thrombosed aneurysmal dilatation of false lumen, compressing trachea and oesophagus (chronic complicated TBAD) with the extremely tortuous descending thoracic aorta ([figures

Malaria is a major public health issue that affects people all around the world. The diagnosis of red blood cells contaminated with insects under a microscope by a skilled specialist is a typical way of diagnosing malaria. This method does not function effectively, and the diagnosis is made based on the test taker's experience and expertise. Malaria blood tests have been using automated imaging technologies based on machine learning for early detection. However, thus far, practical performance is insufficient. The convolutional neural network CNN is used in this paper to present an innovative and resilient machine learning model. for automatically distinguishing single cells in tiny blood smears from normal microscope slides, such as infected or non-infected with this virus. Our new CNN model's average accuracy for 16 layers is 97.37 percent based on ten-fold confirmation using 27,578 single-image pictures. In the same photos, the learning transfer model only gets 91.99 percent. All performance indicators, such as sensitivity (96.99 percent vs 89.00 percent), clarity (97.75 percent vs 94.98 percent), accuracy (97.73 percent vs 95.12 percent), F1 school (97.36 percent vs 90.24) percent, and Matthew's correlation coefficient, demonstrate that the CNN model outperforms the transfer learning model (94.75 percent vs 85.25 percent). Index terms: Deep Learning; Convolutional Neural Networks; Malaria; Computer-Aided Diagnostics; Machine Learning

Paraneoplastic Pemphigus (PNP), a rare autoimmune blistering disease, can be accompanied by both benign and malignant neoplasms. The most frequently reported associated malignancies include lymphomatoid and hematologic malignancies, Castleman's disease, carcinoma, thymoma. In a patient suspected of PNP, with no known history of malignancy, an extensive workup is suggested to look for underlying malignancy, which has to be treated to induce PNP remission. In this clinical case report, cross sectional imaging of a young female diagnosed with PNP, unveiled a pericardial mass lesion extending into transverse pericardial sinus. Excisional biopsy was performed. Histopathology revealed pericardial ectopic thymoma.

Fonts are one of the most basic and core design concepts. Numerous use cases can benefit from an in depth understanding of Fonts such as Text Customization which can change text in an image while maintaining the Font attributes like style, color, size. Currently, Text recognition solutions can group recognized text based on line breaks or paragraph breaks, if the Font attributes are known multiple text blocks can be combined based on context in a meaningful manner. In this paper, we propose two engines: Font Detection Engine, which identifies the font style, color and size attributes of text in an image and a Font Prediction Engine, which predicts similar fonts for a query font. Major contributions of this paper are three-fold: First, we developed a novel CNN architecture for identifying font style of text in images. Second, we designed a novel algorithm for predicting similar fonts for a given query font. Third, we have optimized and deployed the entire engine On-Device which ensures privacy and improves latency in real time applications such as instant messaging. We achieve a worst case On-Device inference time of 30ms and a model size of 4.5MB for both the engines., Comment: Accepted for publication in IEEE ICASSP 2021: 46th IEEE International Conference on Acoustics, Speech, & Signal Processing

Diffuse pulmonary arteriovenous malformation is a rare entity, the exact incidence of which is unknown. It can be limited to a single lobe, or it can diffusely involve one or both the lungs. Early diagnosis and treatment is crucial, as it is associated with increased frequency of thoracic and neurologic complications. Different diagnostic modalities offer some advantages over the others. None of the reported cases in the literature have associated stenosis of any major artery. We describe a rare case of diffuse pulmonary arteriovenous malformation limited to a lobe associated with descending pulmonary artery stenosis.

We report a case of 6-week-old boy with a mixed variety of totally anomalous pulmonary venous connection where the common channel had a dual drainage into the coronary sinus and left brachiocephalic vein respectively. The case also highlights the role of preoperative computed tomography angiography in demonstrating the exact pulmonary venous anatomy, course and identifying obstruction, when present.

We present an unusual case of an 18-day-old term neonate with coexistent bilateral bronchopulmonary vascular malformations and right isomerism. This case highlights the importance of computed tomography angiography in depicting such complex anomalies and classifying them according to components involved providing a systematic approach for evaluation of the disease process.

A 9-year-old girl presented with recurrent upper respiratory tract infections since early infancy and was diagnosed with a left to right shunt.CT showed normal visceral and bronchial situs, partial...

We present the case of a 7-year-old child with mycotic aneurysms of bilateral lower lobe pulmonary arteries secondary to pulmonary valve endocarditis. The child underwent pulmonary vegetectomy with ventricular septal defect closure and left lower lobe pulmonary lobectomy via midline sternotomy.

A 1-month-old child with recurrent cyanotic spells underwent echocardiography which revealed tetralogy of Fallot (TOF). Computed tomography angiography (CTA) done for pre-operative evaluation revea...

A 32-year-old male presented with shortness of breath and easy fatiguability for the past six months. There was no history of chest pain, fever, or palpitations. His renal function parameters were ...

Aorto-enteric fistula (AEF) is a catastrophic complication of the abdominal aortic aneurysm with poor prognosis. It can develop after surgery or endovascular repair of the aneurysm (secondary AEF) or without any prior intervention (primary AEF). We present a case of primary AEF in a patient with an abdominal aortic aneurysm who presented with rectal bleed.

We present a rare synchronous occurrence of tetralogy of Fallot, right aortic arch, and isolated left subclavian artery, highlighting potential clinical and therapeutic implications.

Objective: We studied the correlation of quantified epicardial fat with severity of coronary artery disease in patients [suspected cases of coronary artery disease (CAD)] referred for computed tomography (CT) coronary angiography and established cutoffs for epicardial fat volume (EFV) for the presence of CAD and obstructive CAD. Methods: A prospective cum retrospective cross-sectional observational study was carried out on 950 Indian subjects (suspected cases of CAD) who were referred for coronary CT in the year 2013–2016. EFV was quantified using semiautomatic technique on multidetector coronary CT angiography. The presence of atherosclerotic plaques and degree of stenosis was assessed on coronary CT angiography scans. The correlation between quantified EFV and degree of stenosis was assessed. Multivariate analysis was also performed. Results: A higher quantity of epicardial fat is found in patients with increasing severity of coronary artery stenosis. The EFV cutoff for the presence of CAD and obstructive CAD are 49.75 and 67.69 mL with area under the curve, sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of 0.68, 81%, 45.9%,58.24%, 72.2%, and 62.84% and 0.709, 64.9%, 66.4%, 35.84%, 86.55%, and 66%, respectively. EFV correlates with age, weight, and body mass index (BMI). Multivariate analysis revealed EFV to be an independent risk factor for the presence of CAD. Conclusions: Higher quantities of EFV are found in patients with greater degree of coronary artery stenosis. EFV correlates with age, weight, and BMI. EFV is an independent risk factor for CAD. Keywords: Epicardial fat, Epicardial fat volume, Epicardial fat quantification, Regional thoracic fat depots

Takotsubo cardiomyopathy (TC) is a reversible condition in which there is transient left ventricular (LV) dysfunction characterised most commonly by basal hyperkinesis and mid-apical LV ballooning and hypokinesia. It is said to be triggered by stress and mimics, such as acute coronary syndrome (ACS) clinically. Diagnosis is usually suspected on echocardiography due to the characteristic contraction pattern in a patient with symptoms and signs of ACS but normal coronary arteries on catheter angiography. Cardiac magnetic resonance (CMR), with its latest advancements, is the diagnostic modality of choice for diagnosis, prognosis and follow-up of patients. The advances in CMR (including T1, T2, ECV mapping and threshold-based late gadolinium enhancement (LGE) measurements have revolutionised the role of CMR in tissue characterisation and prognostication in patients with TC. In this review, we highlight the current role of CMR in management of TC and enumerate the CMR findings in TC as well the current advances in the field of CMR, which could help in prognosticating these patients.

Pulmonary thromboembolism is a common prevalent problem leading to various kinds of morbidities and can be the potential cause of deaths directly or indirectly in approximately onethird of the cases. Early diagnosis accompanied by early treatment has shown to reduce the morbidity. Due to variable clinical presentation and non-specific symptoms, early diagnosis can be challenging at times. Suspecting this entity on plain radiograph can play important role in early detection and use of subsequent image modalities, i.e. CT angiography and/or echocardiography to establish the diagnosis, leading to improved outcomes. This review highlights the role of chest X ray and CT in diagnosis of pulmonary thromboembolism.

Currently available ultrasound (US) tomography systems suggest utilizing cylindrical transducers that can be used for a specific organ. In this paper, our focus is on an alternative way of creating US tomographic images that could be used for other anatomies and more general applications. This system consists of two conventional US probes facing each other while one or several of the transducers in one probe can act as the transmitter and the rest as the receiver. Aligning the two US probes is a challenging task. To address this issue, we propose a robot assisted US tomography system in which one probe is operated freehanded and another by a robotic arm. In this paper, enabling technologies for this system are described. With the current prototype, a reconstruction precision of 4.12, 1.73, and 2.23 mm for the three calibrations, and an overall alignment repeatability in the range of 5-9 mm were achieved. Copyright © 2016 John WileySons, Ltd.

Ultrasound (US) tomography enables quantitative measurement of acoustic properties. Robot assisted ultrasound tomography system enables alignment of two US probes. The alignment is done automatically by the robotic arm so that tomographic reconstruction of more anatomies becomes possible. In this study, we propose a new system setup for robot assistance in US tomographic imaging. This setup includes two robotic arms holding two US probes. One of the robotic arms is operated by the sonographer to determine the desired location for the tomographic imaging; this probe can also provide the B-mode US image during the search. The other robotic arm can then move automatically to align the two probes. One of the probes will act as transmitter and the other one as receiver to enable tomographic imaging. We provide an overview of the system setup and components together with the calibration procedures. In an attempt to provide a complete framework for the tomography system, we also provide a sample tomographic reconstruction method that can reconstruct speed of sound image using two aligned linear US probes. The reconstruction algorithm is however very prone to alignment inaccuracies. We provide an error propagation analysis to provide an estimation of the overall alignment error and then show the effect of the in-plane translational error in the tomographic reconstruction.

In this study, we are proposing a robot-assisted ultrasound tomography system that can offer soft tissue tomographic imaging and deeper or faster scan of the anatomy. This system consists of a robot-held ultrasound probe that tracks the position of another freehand probe, trying to align with it. One of the major challenges is achieving proper alignment of the two ultrasound probes. To enable proper alignment, two ultrasound calibrations and one hand-eye calibration are required. However, the system functionality and design is such that the ultrasound calibrations have become a challenge. In this paper, after providing an overview of the proposed robotic ultrasound tomography system, we focus on the calibrations problem. The results of the calibrations show a point reconstruction precision of a few millimeters for the current prototype, and the two images have at least 50% overlap visually; confirming the feasibility of such a system relying on accurate probe alignments.

Currently available ultrasound (US) tomography systems suggest utilizing cylindrical transducers that can be used for a specific organ. In this paper, our focus is on an alternative way of creating US tomographic images that could be used for other anatomies and more general applications. This system consists of two conventional US probes facing each other while one or several of the transducers in one probe can act as the transmitter and the rest as the receiver. Aligning the two US probes is a challenging task. To address this issue, we propose a robot assisted US tomography system in which one probe is operated freehanded and another by a robotic arm. In this paper, enabling technologies for this system are described. With the current prototype, a reconstruction precision of 4.12, 1.73, and 2.23 mm for the three calibrations, and an overall alignment repeatability in the range of 5-9 mm were achieved. Copyright © 2016 John Wiley & Sons, Ltd.

Design and implementation of navigation algorithm for intelligent racing car. The paper describes the implementation of intelligent racing car that can recognize the track automatically to run on the specifically designed complex racing track. The objective is to recognize, understand and modify the actual performance of the movements of the car during its pathway by getting information in real time from IR sensors implemented in the system. The travel trajectory consists of continuous black line of about 25 millimeters in width, on a white background in order to have acceptable functioning. Analyzing of the sensor readings was done during the travel, capturing data at the fixed sampling rate and this data was used as inputs to the algorithm to achieve corrections on the decision speed and control movements. A microcontroller assigns the required movement turn and speeds to optimize the performance in order to get a closer behavior as humans could do it without a vision system to catch its environment. The task of this work was to develop an efficient navigation algorithm and it has been successfully implemented in a Motorola S12X 16-bit microcontroller.