Detection of various lung diseases including COVID-19 using extreme learning machine algorithm based on the features extracted from a lightweight CNN architecture

Nahiduzzaman, Md.; Goni, Md. Omaer Faruq; Islam, Md. Robiul; Sayeed, Abu; Anower, Md. Shamim; Ahsan, Mominul; Haider, Julfikar; Kowalski, Marcin

doi:10.1016/j.bbe.2023.06.003

Cited by 12 publications

(3 citation statements)

References 73 publications

(82 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, CNN-based models might differ in terms of convolution layer kind and number, size of kernel, pooling operation, and fully linked layers [32]. The features can be extracted from different models of pre-trained CNN models like VGG, SqueezeNet, EfficientNet, Inception, ResNet, and DenseNet and using the deep features in classification medical images to diagnose some diseases such as lung diseases and brain tumors [33][34][35][36][37][38].…”

Section: Denesnet-201 Modelmentioning

confidence: 99%

Medical Image-Based Diagnosis Using a Hybrid Adaptive Neuro-Fuzzy Inferences System (ANFIS) Optimized by GA with a Deep Network Model for Features Extraction

Rashed,

Popescu

2024

Mathematics

View full text Add to dashboard Cite

Predicting diseases in the early stages is extremely important. By taking advantage of advances in deep learning and fuzzy logic techniques, a new model is proposed in this paper for disease evaluation depending on the adaptive neuro-fuzzy inference system (ANFIS) with a genetic algorithm (GA) for classification, and the pre-trained DenseNet-201 model for feature extraction, in addition to the whale optimization algorithm (WOA) for feature selection. Two medical databases (chest X-ray and MRI brain tumor) for the diagnosis of two disease types were used as input in the suggested model. The optimization of ANFIS parameters was performed by GA to achieve the optimum prediction capability. DenseNet-201 for feature extraction was employed to obtain better classification accuracy. Having more features sometimes leads to lower accuracy, and this issue can be rectified using a feature selection strategy WOA which gave good results. The proposed model was evaluated utilizing statistical metrics root mean square error (RMSE), mean square error (MSE), standard deviation (STD), and coefficient of determination (R2), and it was compared with the conventional ANFIS model, with the proposed model (ANFIS-GA) showing a superior prediction capability over the ANFIS model. As a result, it can be concluded that the proposed ANFIS-GA model is efficient and has the potential for a robust diseases evaluation with good accuracy. Also, we conclude from this work that integrating optimization algorithms with ANFIS boosts its performance, resulting in a more accurate and reliable model.

show abstract

Section: Denesnet-201 Modelmentioning

confidence: 99%

Medical Image-Based Diagnosis Using a Hybrid Adaptive Neuro-Fuzzy Inferences System (ANFIS) Optimized by GA with a Deep Network Model for Features Extraction

Rashed,

Popescu

2024

Mathematics

View full text Add to dashboard Cite

show abstract

“…Nahiduzzaman et al [13] developed a method for detecting COVID-19 cases among various lung diseases. A three-class classification approach specifically designed to identify COVID-19 cases from pneumonia and normal cases.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Nahiduzzaman et al [13] employed a lightweight CNN-ELM method with only three layers in which they applied a three-class classification approach that achieved 97.42% accuracy. Yaman et al [14] introduced the ACL model, combining attention, LSTM, and CNN for classifying healthy, COVID-19, and pneumonia cases in chest X-ray (CXR) images.…”

Section: Comparative Analysis Of Multi-scale Cnn With Other Research ...mentioning

confidence: 99%

Multi-Scale CNN: An Explainable AI-Integrated Unique Deep Learning Framework for Lung-Affected Disease Classification

Sarkar,

Islam,

Syfullah

et al. 2023

Technologies

Self Cite

View full text Add to dashboard Cite

Lung-related diseases continue to be a leading cause of global mortality. Timely and precise diagnosis is crucial to save lives, but the availability of testing equipment remains a challenge, often coupled with issues of reliability. Recent research has highlighted the potential of Chest X-ray (CXR) images in identifying various lung diseases, including COVID-19, fibrosis, pneumonia, and more. In this comprehensive study, four publicly accessible datasets have been combined to create a robust dataset comprising 6650 CXR images, categorized into seven distinct disease groups. To effectively distinguish between normal and six different lung-related diseases (namely, bacterial pneumonia, COVID-19, fibrosis, lung opacity, tuberculosis, and viral pneumonia), a Deep Learning (DL) architecture called a Multi-Scale Convolutional Neural Network (MS-CNN) is introduced. The model is adapted to classify multiple numbers of lung disease classes, which is considered to be a persistent challenge in the field. While prior studies have demonstrated high accuracy in binary and limited-class scenarios, the proposed framework maintains this accuracy across a diverse range of lung conditions. The innovative model harnesses the power of combining predictions from multiple feature maps at different resolution scales, significantly enhancing disease classification accuracy. The approach aims to shorten testing duration compared to the state-of-the-art models, offering a potential solution toward expediting medical interventions for patients with lung-related diseases and integrating explainable AI (XAI) for enhancing prediction capability. The results demonstrated an impressive accuracy of 96.05%, with average values for precision, recall, F1-score, and AUC at 0.97, 0.95, 0.95, and 0.94, respectively, for the seven-class classification. The model exhibited exceptional performance across multi-class classifications, achieving accuracy rates of 100%, 99.65%, 99.21%, 98.67%, and 97.47% for two, three, four, five, and six-class scenarios, respectively. The novel approach not only surpasses many pre-existing state-of-the-art (SOTA) methodologies but also sets a new standard for the diagnosis of lung-affected diseases using multi-class CXR data. Furthermore, the integration of XAI techniques such as SHAP and Grad-CAM enhanced the transparency and interpretability of the model’s predictions. The findings hold immense promise for accelerating and improving the accuracy and confidence of diagnostic decisions in the field of lung disease identification.

show abstract

Interpretable Deep Learning Model for Tuberculosis Detection Using X-Ray Images

Ahamed,

Nahiduzzaman,

Islam

et al. 2024

Surveillance, Prevention, and Control of Infectious Diseases

View full text Add to dashboard Cite

Detection of various lung diseases including COVID-19 using extreme learning machine algorithm based on the features extracted from a lightweight CNN architecture

Cited by 12 publications

References 73 publications

Medical Image-Based Diagnosis Using a Hybrid Adaptive Neuro-Fuzzy Inferences System (ANFIS) Optimized by GA with a Deep Network Model for Features Extraction

Medical Image-Based Diagnosis Using a Hybrid Adaptive Neuro-Fuzzy Inferences System (ANFIS) Optimized by GA with a Deep Network Model for Features Extraction

Multi-Scale CNN: An Explainable AI-Integrated Unique Deep Learning Framework for Lung-Affected Disease Classification

Interpretable Deep Learning Model for Tuberculosis Detection Using X-Ray Images

Contact Info

Product

Resources

About