Table 2 DL frameworks for analyzing and recognizing brain tumors and covid-related behaviors, as well as identifying, classifying, and detecting different sorts of Covid and Brain tumors cases.
Previous Work | Methods | Objective | Dataset | Performance Measures |
|---|---|---|---|---|
I. D. Apostolopoulos et al. [63] | VGG-19, Mobile Net, Inception, Xception, and Inception_ResNet_V2 | Detecting Covid-19 from X-ray images | 1427 X-ray Images | Accuracy = 98.75% |
A. Shelke et al. [64] | DenseNet-161 | Diagnosis of COVID-19 from CXR images | 2271 CXR Images | Accuracy= 98.9% |
A. Narin et al. [25] | ResNet50, Inception_V3, and Inception ResNet_V2 | Detection Coronavirus Infection in CXR images | 5064 CXR Images | Accuracy= 98% |
L. Duran-Lopez et al. [26] | Inception-v3 | Covid-19 Patients Classification using CXR images | 2589 CXR Images | Accuracy = 98.8% |
N. N. Das et al. [27] | Alex Net, DenseNet121, Inception_V3, ResNet18, and Google Net | Covid-19 Patients Classification using CXR images | 5232 CXR Images | Accuracy= 96.4% |
M. Wo´zniak et al. [65] | CLM+CNN | Brain tumor detection from CT Brain Scan images | 3064, CT Brain Scan Images | Accuracy = 97.5%, Sensitivity = 95.6% and Specificity =96.21% |
M.R. Obeidavi et al. [66] | Residual Network | Brain Tumor detection from MRI images | BRATS 2015 Dataset, 2000 MR Images | Accuracy = 97.05% and BF Score = 57.02% |
Anantharajan S et al. [67] | END-SVM | Detection of Brain Tumor from MRI Images | MRI images | Accuracy= 97.93%, Sensitivity = 92% and Specificity =98% |
Hao R et al. [68] | AlexNet | Classifying MRI images | 2019 BRATS | AUC= 82% |
Rahman T et al. [69] | PDCNN | Brain tumor detection and classification using MRI images | MRI Images | Accuracy = 97.33% and Cohen’s Kapp = 0.944 |
Proposed FL ensemble Work | ¬ Non-priority-Vote: HincV3XGBoost, LT-ViT, BM-Net, VGG-SCNet, MEEDNets, ResGANet ¬ Priority Vote: ResGANet and CE-EEN-B0 | Classifying into Covid-19, TB, PNA, and healthy individuals using CXR images as well as Glioma, Meningioma, Pituitary and no tumor using MRI images. | 7000 CXR, 6420 MRI Images | Accuracy = 99.24%, Error Rate = 0.0076, Cohen’s Kapp = 0.9967 and Average F1 Score = 0.995 for CXR Dataset. For MRI dataset, Accuracy = 99%, Error Rate = 0.01, Cohen’s Kapp = 0.97 and Average F1 Score = 0.995 |
