Foot fractures diagnosis using a deep convolutional neural network optimized by extreme learning machine and enhanced snow ablation optimizer

Abstract

The current investigation proposes a novel hybrid methodology for the diagnosis of the foot fractures. The method uses a combination of deep learning methods and a metaheuristic to provide an efficient model for the diagnosis of the foot fractures problem. the method has been first based on applying some preprocessing steps before using the model for the features extraction and classification of the problem. the main model is based on a pre-trained ZFNet. The final layers of the network have been substituted using an extreme learning machine (ELM) in its entirety. The ELM part also optimized based on a new developed metaheuristic, called enhanced snow ablation optimizer (ESAO), to achieve better results. for validating the effectiveness of the proposed ZFNet/ELM/ESAO-based model, it has been applied to a standard benchmark from Institutional Review Board (IRB) and the findings have been compared to some different high-tech methods, including Decision Tree / K-Nearest Neighbour (DT/KNN), Linear discriminant analysis (LDA), Inception-ResNet Faster R-CNN architecture (FRCNN), Transfer learning‑based ensemble convolutional neural network (TL-ECNN), and combined model containing a convolutional neural network and long short-term memory (DCNN/LSTM). Final results show that using the proposed ZFNet/ELM/ESAO-based can be utilized as an efficient model for the diagnosis of the foot fractures.

Keywords: Deep learning; Enhanced snow ablation optimizer; Extreme learning machine; Foot fractures; Metaheuristic; ZFNet.