Prediction of Malignancy in Breast Histopathology Images with Deep Learning Model Using Resource Limited Embedded Devices and Edge Computing

Abstract

newlineComputer assisted diagnosis of diseases provides more accurate and newlineprecise diagnostic reports towards better information regarding the medical newlinecondition of patients. A clinician can minimize the error by applying his newlineexperience acquired by practice, cognitive intuition or scientific research newlinebacked by laboratory reports and computer assisted medical image analysis. newlineThe findings by the experts based on the analysis of such data is crucial as newlinethe suggested treatment is dependent on evaluation at this stage. Machine newlinelearning techniques while applied in the medical field performs decision newlinemaking by mimicking the steps performed by a medical expert in diagnosing newlinethe disease, but using algorithms rather intuitive. It brings out accurate newlinemedical data through analysis of images performed by computing devices newlinethat can reveal valuable information regarding the disease prognosis. newlineComputer aided disease diagnosis with state-of-the-art machine newlinelearning and deep learning offers seamless assistance in medical care with newlinenear human accuracy. Technology integrated medical support systems newlinecombined with sophisticated algorithms can reduce the number of false newlinepositive incidents as well as false negative cases. Convolutional neural newlinenetwork (CNN) models can be trained using handcrafted features to newlinederive conclusive inferences for binary class as well as multi-class newlineclassification. Artificial Intelligence (AI) supported techniques in disease newlinediagnosis provide assistance to medical experts in decision making by newlinevirtue of cloud based data analytics tools for storage and computing.