Multi‐scaled feature fusion enabled convolutional neural network for predicting fibrous dysplasia bone disorder

Abstract

AbstractBackgroundConvolutional Neural Network (CNN) has exciting advantages in the processing of medical images. It produces the denoised and segmented results of images. When an image has orientation and scaling issues over the bundle that is not correctly recognized by the classifier.MethodsTo overcome these issues, we propose Extreme Deep Learning on Feature Fusion Convolutional Neural Network (EDL‐FFCNN) for classification. Feature fusion workflow enhances the ability to learn the feature from the inconsistent behaviour. And, to learn the texture, colour, and intensities of an image. The initial step of the FFCNN framework is to reconstruct the images using filtered back projection. It reduces the noise in edges and cross‐sectional areas. Contrast Limited Adaptive Histogram Equalization and Local Binary Pattern is applied to an image to adjust and extract the intensity and textural features of an image. The proposed FFCNN is a decision‐based approach that consists of two persistent classifiers. One, the convolutional features are combined with manually extracted multi‐scaled features. Subsequently, the normalization techniques are built‐in every layer to adjust the input dimensions. It also helps to reduce the training time. As an outcome of Image abnormalities is considered as knowledge transfer to the CNN.ResultsThe fused features on the CNN classifier produce the abnormality prediction results. Second, the Inception V2 CNN classifier framework classifies the bone images with extracted features. With these two comparative‐classification results, the major counting has been taken as the decision for final abnormality prediction. The proposed model gives improved accuracy of 95% for the elbow, 93% for the forearm, 92% for the shoulder, 92% for the wrist, 93% for the finger, 92% for humerus images.