Pneumonia binary classification using multi-scale feature classification network on chest x-ray images

Abstract

<span lang="EN-US">According to the world health organization, pneumonia was the cause for 14% of all deaths of children under 5 years old. A computer-aided diagnosis (CADx) system can help the radiologist in the detection of pneumonia in chest radiographs by serving as a second opinion. The typical CADx is based on transfer learning which is done by transferring the learning of feature extraction from one task with plenty of available data to a related task with a scarcity of data. This approach has two limitations which are first, blocking the transferred model from extracting the features that are singular to the new dataset as well as the inability to reduce the complexity of the original model. To address these drawbacks, we proposed a convolutional neural network (CNN) model with low complexity and three paths for feature extraction. The proposed model extracts three different types of features and concatenates them into one feature that provides a good representation for the classes. The proposed model was evaluated on a publicly available dataset. The results showed outperformance by the proposed model compared to the transfer learning models with recall 0.912±0.039, precision 0.942±0.029, F-beta score 0.93, and Cohen’s kappa score 0.740±0.008. </span>

Classification of Chest X-ray Images using CNN for Medical Decision Support System

“…Dividing each element by the sum of all exponential values normalizes these values. [18] The SoftMax function outputs a vector of probabilities with This augmentation technique helps the model learn to be invariant to changes in orientation. Additionally, we applied zooming transformations to the images by defining a zoom range.…”

The diagnostic performance of impacted third molars in the mandible: A review of deep learning on panoramic radiographs

“…These systems enable direct data analysis without the need of expert ( Yasa et al, 2021 ). Recently, deep learning has been investigated to provide a second opinion for the diagnosis of pneumonia based on X-ray images ( Mandeel et al, 2022 ) and improve the diagnostic performance for skin lesion classification using dermoscopy images ( Pratiwi et al, 2021 ). Convolutional neural networks (CNNs) are subsets of deep learning which emulate human intelligence in learning and problem solving, allowing dentists and radiologists to interpret radiographs more efficiently and accurately for caries detection and classification ( Vinayahalingam et al, 2021b , Vinayahalingam et al, 2021a ), perform teeth detection and numbering ( Estai et al, 2022 ), predict third molar eruption ( Vranckx et al, 2020 ), predict time to extraction of third molar ( Kwon et al, 2022 ), detect apical lesion ( Ekert et al, 2019 ), execute segmentation on panoramic radiograph for periodontitis ( Widyaningrum et al, 2022 ) and detect the periodontal disease ( Lee et al, 2018 ), as well as classify maxillary sinus ( Murata et al, 2019 ).…”

Image classification-based transfer learning framework for image detection of IoT devices

“…Multiple studies in [8]- [17], [18]- [26], [27]- [29] have examined the implementation of TL in diverse applications. The works in [8]- [11] proposes TL frameworks using pre-trained convolutional neural networks (CNN) models for medical images classifications including melanoma detection, anthracnose and red-rust leaf disease detection, diabetic retinopathy identification, and pneumonia classification. Meanwhile, some CNNbased TL approaches for brain and breast tumor detection using magnetic resonance images have been investigated in [12]- [14].…”