Identification Of Abnormal Tissue Research Articles

Brainchop: Providing an Edge Ecosystem for Deployment of Neuroimaging Artificial Intelligence Models.

Deep learning has proven highly effective in various medical imaging scenarios, yet the lack of an efficient distribution platform hinders developers from sharing models with end-users. Here, we describe brainchop, a fully functional web application that allows users to apply deep learning models developed with Python to local neuroimaging data from within their browser. While training artificial intelligence models is computationally expensive, applying existing models to neuroimaging data can be very fast; brainchop harnesses the end user's graphics card such that brain extraction, tissue segmentation, and regional parcellation require only seconds and avoids privacy issues that impact cloud-based solutions. The integrated visualization allows users to validate the inferences, and includes tools to annotate and edit the resulting segmentations. Our pure JavaScript implementation includes optimized helper functions for conforming volumes and filtering connected components with minimal dependencies. Brainchop provides a simple mechanism for distributing models for additional image processing tasks, including registration and identification of abnormal tissue, including tumors, lesions and hyperintensities. We discuss considerations for other AI model developers to leverage this open-source resource.

Intracranial tumour haemorrhage following intravenous thrombolysis

Intravenous administration of thrombolytic agents is considered to be contraindicated in patients with intracranial neoplasms. However, only a single case of thrombolysis-related intracranial tumour haemorrhage has been reported to our knowledge and several studies have suggested that systemic thrombolysis can be safely carried out in these patients. Here we report a patient who developed haemorrhage into a previously unknown intracranial tumour following intravenous thrombolysis for acute myocardial ST-elevation infarction. Identification of abnormal tissue during surgical haematoma evacuation initiated histopathological examination which revealed meningioma World Health Organization Grade I. Intracranial tumours may represent the causative pathology in cases of thrombolysis-related intracranial haemorrhage and this should be considered in the treatment of these patients.

Two-dimensional echocardiographic image texture analysis: reduction of regional variability using polar coordinates.

Factors inherent to the ultrasound imaging system can influence quantitative ultrasound image texture and may produce changes that mask or mimic those due to alterations in tissue structure. In this study, we assessed the effect of the method of image data acquisition and analysis on the variations in quantitative texture measures that occurred solely due to the position of a region of interest (ROI) within the field of view. When ROI's, which varied in range and azimuth within the image of a tissue equivalent phantom (of uniform composition), were assessed by conventional analysis of scan-converted (rectangular coordinate) data, over 50 percent of all texture measures showed significant differences. Pseudo polar analysis reduced the number of texture measures showing regional variation by 80 percent (p less than 0.01) and true polar coordinate data analysis reduced the number by 74 percent (p less than 0.01). True polar analysis completely abolished differences in texture measures between ROI's separated in azimuth. Acquisition and analysis of tissue texture data using polar coordinates should allow a more definitive identification of abnormal tissue.