Classification of chest X-ray images using a hybrid deep learning method

Abstract

This work presents a technique for classifying X-ray images of the chest (CXR) by applying deep learning-based techniques. The CXR will be classified into three different types, i.e. (i) normal, (ii) COVID-19, and (iii) pneumonia. The classification challenge is raised when the X-ray images of COVID-19 and pneumonia are subtle. The CXR images of the chest are first proceeded to be standardized and to improve the visual contrast of the images. Then, the classification is performed by applying a deep learningbased technique that binds two deep learning network architectures, i.e., convolution neural network (CNN) and long short-term memory (LSTM), to generate a hybrid model for the classification problem. The deep features of the images are extracted by CNN before the final classification is performed using LSTM. In addition to the hybrid models, this work explores the validity of image pre-processing methods that improve the quality of the images before the classification is performed. The experiments were conducted on a public image dataset. The experimental results demonstrate that the proposed technique provides promising results and is superior to the baseline techniques.

Classification of lower limb rehabilitation exercises with multiple and individual inertial measurement units

“…Leg raise data was collected at 250 Hz frequency. Proper physical monitoring of physiotherapists helps the patients to get into the comfort position (both physically and psychologically) during the whole measurement cycles and trials [19]. For the detection of characteristic frequencies of the signal, a Fourier transform was used and it was found to be less than 50 Hertz.…”

Identification of medicinal plant using hybrid transfer learning technique

“…There are many algorithms that can be used to extract leaf features, including GIST, relative subimage coefficient (RSC) [20], inner distance shape context (IDSC) [21], curvelet transform (CT) [22], leaf skeleton (LS) [23], fuzzy inference neural network [24], [25], and more are utilized for extraction of leaf features [26]. CNN models can perform better if extracted features are provided to them as it requires less computational power [27]- [30] with less number of features [31]- [33]. These studies have led to a few questions: i) which is the best feature extraction method to extract features from plant leaves with minimum loss?…”

Detecting COVID-19 in chest X-ray images

“…The dataset was preprocessed using a histogram equalizer before training. In contrast, the k-nearest neighbors method (KNN) was proposed in [10] In 2022, the hybrid approach was proposed [11]. The model was composed of CNN as the feature extraction and long short-term memory (LSTM) for classifying chest x-ray images into three classes: normal, COVID-19, and pneumonia.…”