Paper Title
Ensemble Learning Based Ischemic Stroke Etiology Classification Using Whole Slide Histopathological Images

Abstract
Abstract - Ischemic stroke is one of the most common causes of disability and death worldwide. Early and accurate pathological analysis of Ischemic Stroke can significantly increase patients’ chances of survival. This research proposed an Ensemble Learn- ing based framework to classify the Ischemic Stroke etiology Using Whole Slide Histopathological images. Two well-known pre-trained VGG16 and ViT state-of-the-art models are used to implement the proposed framework. The proposed Ensemble Learning Framework used a simple concatenation ensemble approach to combine the effects of features extracted by each pre-trained model. Our study shows that the proposed Ensemble Learning based framework outperforms the individual state-of- the-art models in terms of generalization accuracy. Keywords - Ensemble Learning, Whole Slide Histopatholog- ical images, VGG16, ViT.

Author - Mahendra Kumar Gurve, Yamuna Prasad, Nitin Nitin

Published : Volume-10,Issue-1  ( Jan, 2023 )

	|		PDF	|	Viewed - 39	|	Published on 2023-04-03