The growth of developments in machine learning, the image processing methods along with availability of the medical imaging data are taking a big increase in the utilization of machine learning strategies in the medical area. The utilization of neural networks, mainly, in recent days, the convolutional neural networks (CNN), have powerful descriptors for computer added diagnosis systems. Even so, there are several issues when work with medical images in which many of medical images possess a low-quality noise-to-signal (NSR) ratio compared to scenes obtained with a digital camera, that generally qualified a confusingly low spatial resolution and tends to make the contrast between different tissues of body are very low and it difficult to computed and recognized dependably. In this paper, we target to utilized CNN and heatmap to recognized most significant features that the network should focus on it. depending on class activation mapping. The goal of this study is to develop an approach that can determine the most significant features from medical images (such as x-ray, CT, MRI) through gradient the different tissue accurately by made use of heatmap. In our model, we take the gradient with regard to the final convolutional layer and after that weigh it towards the output of this layer. The model is based upon class activation mapping. However, the model is differed from traditional activation mapping based methods, that this model is the dependent on gradients via obtaining the weight of all activation map via make use of it is forward passing score over target class, then the final result is apart from linear combination of activation and weights. The results appears that the model is successfully distortion heat map of tissues in various medical image techniques and obtained better visual accuracy and fairness for interpretation the decision-making procedure.
This work is licensed under a