Search

The carotid artery is a clinically important site in the human circulatory system as the consequences of its disease results in adverse outcomes like ischemic strokes, or death for too prolonged ischemia. Understanding the hemodynamics of this artery and its bifurcation are important. A method of treating the stenosis of this artery is Carotid Angioplasty and Stenting (CAS). This procedure results in a heavily modified hemodynamics or state of flow. To understand and predict this flow field modification Computational Fluid Dynamics (CFD) is an important computational tool. Further, the presence of a stent would affect hemodynamics. The aim of this work is to study these effects in patient-specific cases. The reconstructed patient-specific models will form the basis of the construction of the post-stenting carotid bifurcation models. A transient analysis was carried out to estimate the time-varying parameters in the fluid domains over a cardiac cycle as well as to gauge time average values over a cardiac cycle. Results are obtained for hemodynamic parameters, like wall shear stress, velocity, pressure, vorticity, and helicity, in both the prepared stenosed and stented geometries. It is seen that the stenting procedure leads to the renewal of the CCA to ICA flow path. But simultaneously the region in which the stent is present becomes a region of low TAWSS and contains areas of high OSI. These areas of low TAWSS and high OSI within the stented portions of the carotid bifurcations are indications for regions of possible restenosis. Therefore, the investigation demonstrates the likely region for future plaque growth. Further, the effects of widening of the lumen are also noted in comparison to the pre-stent cases

Content-based image retrieval (CBIR) systems are designed to retrieve images that are relevant, based on detailed analysis of latent image characteristics, thus eliminating the dependency of natural language tags, text descriptions, or keywords associated with the images. A CBIR system maintains high-level image visuals in the form of feature vectors, which the retrieval engine leverages for similarity-based matching and ranking for a given query image. In this paper, a CBIR system is proposed for the retrieval of medical images (CBMIR) for enabling the early detection and classification of lung diseases based on lung X-ray images. The proposed CBMIR system is built on the predictive power of deep neural models for the identification and classification of disease-specific features using transfer learning based models trained on standard COVID-19 Chest X-ray image datasets. Experimental evaluation on the standard dataset revealed that the proposed approach achieved an improvement of 49.71% in terms of precision, averaging across various distance metrics. Also, an improvement of 26.55% was observed in the area under precision-recall curve (AUPRC) values across all subclasses.

Malaria is a severe worldwide health issue that requires rapid and accurate diagnosis in order to control the disease. Malaria is easy to treat if discovered early and followed up with correct medical therapy. Computer-aided diagnosis is becoming more prominent since it can be used as a basic screening test in the absence of an expert microbiologist. To automate malaria diagnosis, an image processing algorithm necessary. In order to construct picture characteristics based on colour, texture, and the geometry of the cells and parasites. It incorporates many representations of the data for imaging, image processing, segmentation, and classification of test images.

Accurate risk stratification using patient data is a vital task in channeling prioritized care. Most state-of-the-art models are predominantly reliant on digitized data in the form of structured Electronic Health Records (EHRs). Those models overlook the valuable patient-specific information embedded in unstructured clinical notes, which is the prevalent medium employed by caregivers to record patients’ disease timeline. The availability of such patient-specific data presents an unprecedented opportunity to build intelligent systems that provide exclusive insights into patients’ disease physiology. Moreover, very few works have attempted to benchmark the performance of deep neural architectures against the state-of-the-art models on publicly available datasets. This article presents significant observations from our benchmarking experiments on the applicability of deep learning models for the clinical task of ICD-9 code group prediction. We present FarSight , a long-term aggregation mechanism intended to recognize the onset of the disease with the earliest detected symptoms. Vector space and topic modeling approaches are utilized to capture the semantic information in the patient representations. Experiments on MIMIC-III database underscored the superior performance of the proposed models built on unstructured data when compared to structured EHR based state-of-the-art model, achieving an improvement of 19.34 percent in AUPRC and 5.41 percent in AUROC.