COVID-19 diagnosis: A comprehensive review of pre-trained deep learning models based on feature extraction algorithm

Poola, Rahul Gowtham; Pl, Lahari; Y, Siva Sankar

doi:10.1016/j.rineng.2023.101020

Cited by 17 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inception-V3 is selected as a preliminary feature extraction method since it has the capability to extract high-level features with a variety of filter modifications (277), as well as an efficient grouping of several forms of convolution process ( 35 ). In this technique, a gain of 28% can be achieved utilizing two (

) convolutions.…”

Section: Proposed Methodsmentioning

confidence: 99%

Histopathology-based breast cancer prediction using deep learning methods for healthcare applications

Ramamoorthy,

Ramakantha Reddy,

Askar

et al. 2024

Front. Oncol.

View full text Add to dashboard Cite

Breast cancer (BC) is the leading cause of female cancer mortality and is a type of cancer that is a major threat to women's health. Deep learning methods have been used extensively in many medical domains recently, especially in detection and classification applications. Studying histological images for the automatic diagnosis of BC is important for patients and their prognosis. Owing to the complication and variety of histology images, manual examination can be difficult and susceptible to errors and thus needs the services of experienced pathologists. Therefore, publicly accessible datasets called BreakHis and invasive ductal carcinoma (IDC) are used in this study to analyze histopathological images of BC. Next, using super-resolution generative adversarial networks (SRGANs), which create high-resolution images from low-quality images, the gathered images from BreakHis and IDC are pre-processed to provide useful results in the prediction stage. The components of conventional generative adversarial network (GAN) loss functions and effective sub-pixel nets were combined to create the concept of SRGAN. Next, the high-quality images are sent to the data augmentation stage, where new data points are created by making small adjustments to the dataset using rotation, random cropping, mirroring, and color-shifting. Next, patch-based feature extraction using Inception V3 and Resnet-50 (PFE-INC-RES) is employed to extract the features from the augmentation. After the features have been extracted, the next step involves processing them and applying transductive long short-term memory (TLSTM) to improve classification accuracy by decreasing the number of false positives. The results of suggested PFE-INC-RES is evaluated using existing methods on the BreakHis dataset, with respect to accuracy (99.84%), specificity (99.71%), sensitivity (99.78%), and F1-score (99.80%), while the suggested PFE-INC-RES performed better in the IDC dataset based on F1-score (99.08%), accuracy (99.79%), specificity (98.97%), and sensitivity (99.17%).

show abstract

) convolutions.…”

Section: Proposed Methodsmentioning

confidence: 99%

Histopathology-based breast cancer prediction using deep learning methods for healthcare applications

Ramamoorthy,

Ramakantha Reddy,

Askar

et al. 2024

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…To predict and categorize COVID-19 and lung-related diseases from radiography images, many artificial intelligence (AI) frameworks were developed through advanced machine learning (ML) techniques such as deep learning (DL). Compared to simple DL methods, the pre-trained models [16,17] outperformed based on the architecture of convolutional neural networks.…”

Section: Methodological Background and Related Studiesmentioning

confidence: 99%

“…The models with a moderate architecture that consists of a Fifth Convolutional layer with pooling applied between the layers, along with a Flattened, Dropout, and Single Fully Connected Layer, won the ImageNet competition. A computer-aided diagnosis system based on deep learning has been suggested by the authors in references [15][16][17].…”

Section: Vgg-19mentioning

confidence: 99%

Optimized Xception Learning Model and XgBoost Classifier for Detection of Multiclass Chest Disease from X-ray Images

et al. 2023

View full text Add to dashboard Cite

Computed tomography (CT) scans, or radiographic images, were used to aid in the early diagnosis of patients and detect normal and abnormal lung function in the human chest. However, the diagnosis of lungs infected with coronavirus disease 2019 (COVID-19) was made more accurately from CT scan data than from a swab test. This study uses human chest radiography pictures to identify and categorize normal lungs, lung opacities, COVID-19-infected lungs, and viral pneumonia (often called pneumonia). In the past, several CAD systems using image processing, ML/DL, and other forms of machine learning have been developed. However, those CAD systems did not provide a general solution, required huge hyper-parameters, and were computationally inefficient to process huge datasets. Moreover, the DL models required high computational complexity, which requires a huge memory cost, and the complexity of the experimental materials’ backgrounds, which makes it difficult to train an efficient model. To address these issues, we developed the Inception module, which was improved to recognize and detect four classes of Chest X-ray in this research by substituting the original convolutions with an architecture based on modified-Xception (m-Xception). In addition, the model incorporates depth-separable convolution layers within the convolution layer, interlinked by linear residuals. The model’s training utilized a two-stage transfer learning process to produce an effective model. Finally, we used the XgBoost classifier to recognize multiple classes of chest X-rays. To evaluate the m-Xception model, the 1095 dataset was converted using a data augmentation technique into 48,000 X-ray images, including 12,000 normal, 12,000 pneumonia, 12,000 COVID-19 images, and 12,000 lung opacity images. To balance these classes, we used a data augmentation technique. Using public datasets with three distinct train-test divisions (80–20%, 70–30%, and 60–40%) to evaluate our work, we attained an average of 96.5% accuracy, 96% F1 score, 96% recall, and 96% precision. A comparative analysis demonstrates that the m-Xception method outperforms comparable existing methods. The results of the experiments indicate that the proposed approach is intended to assist radiologists in better diagnosing different lung diseases.

show abstract

“…An artificial neural network model provided by the Statistics and Machine Learning Toolbox (MathWorks Inc., Natick, MA, USA) was used as the classification method. The function “fitcnet” has been used in previous clinical studies [ 22 , 23 ], and we set up a single intermediate layer with 64 nodes.…”

Section: Methodsmentioning

confidence: 99%

Artificial Intelligence-Based Diagnostic Support System for Functional Dyspepsia Based on Brain Activity and Food Preference

Katsumata,

Hosokawa,

Kamada

2023

Cureus

View full text Add to dashboard Cite

Background and aim Disorders of gut-brain interaction (DGBI) are disorders where no organic clinical abnormalities are detected such as functional dyspepsia (FD) and irritable bowel syndrome (IBS). The brain activity of individuals with FD and IBS differs from that of healthy controls. Artificial intelligence can distinguish healthy controls from individuals with DGBI using several biomarkers. This study aimed to establish an artificial intelligence-based diagnostic support system using food preferences and brain activity in patients with DGBI. Methods ROME IV criteria were used to diagnose patients with FD and IBS. Their food preference was scored using a visual analog scale, and brain activity in the prefrontal cortex was investigated using functional near-infrared spectroscopy (fNIRS). The diagnostic model was developed based on the brain activity and visual analog scale scores for food using an artificial neural network model. Results Forty-one participants, including 25 patients with DGBI were enrolled in the study. The accuracy of the artificial intelligence-based diagnostic model using an artificial neural network in differentiating between healthy controls and patients with DGBI and between healthy controls and those with FD were 72.3% and 77.1%, respectively. Conclusions The artificial intelligence-based diagnostic model using brain activity and preference to food images showed sufficiently high accuracy in distinguishing patients with DGBI from healthy controls, and those with FD from healthy controls. Therefore, the fNIRS system provides objective evidence for diagnosing DGBI.

show abstract

COVID-19 diagnosis: A comprehensive review of pre-trained deep learning models based on feature extraction algorithm

Cited by 17 publications

References 35 publications

Histopathology-based breast cancer prediction using deep learning methods for healthcare applications

Histopathology-based breast cancer prediction using deep learning methods for healthcare applications

Optimized Xception Learning Model and XgBoost Classifier for Detection of Multiclass Chest Disease from X-ray Images

Artificial Intelligence-Based Diagnostic Support System for Functional Dyspepsia Based on Brain Activity and Food Preference

Contact Info

Product

Resources

About