Self-attention based BiLSTM-CNN classifier for the prediction of ischemic and non-ischemic cardiomyopathy
This work addresses the need for more accurate diagnosis of heart failure causes, potentially reducing reliance on variable endomyocardial biopsies, but it appears incremental as it combines existing methods like CNN and BiLSTM with self-attention.
The paper tackled the problem of classifying ischemic or non-ischemic cardiomyopathy from histopathological images, proposing a self-attention based BiLSTM-CNN model that improved classification performance, though no concrete numbers were provided.
Heart Failure is a major component of healthcare expenditure and a leading cause of mortality worldwide. Despite higher inter-rater variability, endomyocardial biopsy (EMB) is still regarded as the standard technique, used to identify the cause (e.g. ischemic or non-ischemic cardiomyopathy, coronary artery disease, myocardial infarction etc.) of unexplained heart failure. In this paper, we focus on identifying cardiomyopathy as ischemic or non-ischemic. For this, we propose and implement a new unified architecture comprising CNN (inception-V3 model) and bidirectional LSTM (BiLSTM) with self-attention mechanism to predict the ischemic or non-ischemic to classify cardiomyopathy using histopathological images. The proposed model is based on self-attention that implicitly focuses on the information outputted from the hidden layers of BiLSTM. Through our results we demonstrate that this framework carries a high learning capacity and is able to improve the classification performance.