|
Citation/year of publishing | Reference | Approach | Objective | Challenges of the approach |
|
[1]/2021 | FIN | CDLLC-CNN, VGG19, VGG16 | To develop brain tumor classification technique by using CDLLC on CNN. | Dataset contained 3064 brain tumor images. It implemented binary classification and yielded an accuracy of 96.39%. |
[2]/2021 | JAIHC | SVM-CNN, VGG16, VGG19 | To distinguish brain tumor from healthy individuals using SVM with CNN. | Dataset contained 1426 brain tumor images. It implemented binary classification and yielded an accuracy of 95.82%. |
[3]/2021 | MMTA | RNGAP-CNN, DenseNet201, VGG16 | To predict brain tumor from normal individual by RNGAP model on CNN. | Dataset contained 3064 brain tumor images. It implemented binary classification and yielded an accuracy of 97.08%. |
[4]/2021 | MRT | 3DCNN, DenseNet201, VGG 16 | To detect brain tumor on CT scans using 3DCNN technique. | Dataset contained 1074 brain tumor images. It implemented binary classification and yielded an accuracy of 92.67%. |
[5]/2021 | NCA | MSMCNN, DenseNet121, VGG19 | To automatically classify CT images into brain tumor and normal individuals by using MSMCNN. | Dataset contained 374 brain tumor images. It implemented binary classification and yielded an accuracy of 96.36%. |
[6]/2019 | BS | HSANN, VGG19, DenseNet201 | To classify BT by using HSANN architecture. | Dataset contained 3064 brain tumor images. It implemented binary classification and yielded an accuracy of 97.33%. |
[7]/2017 | SIVP | ELM-CNN, DenseNet201, VGG16 | To develop an ELM system to early diagnose BT individuals. | Dataset contained 1074 brain tumor images. It implemented binary classification and yielded an accuracy of 97.8%. |
[8]/2020 | JDI | 3DCNN, DenseNet201 | To classify BT analysis by using 3DCNN | Dataset contained 1074 brain tumor images. It implemented binary classification and yielded an accuracy of 96.49%. |
[9]/2021 | JCS | Deep-CNN, DenseNet121, DenseNet201 | To develop Deep-CNN system that can determine BT by using CT scans. | Dataset contained 121 brain tumor images. It implemented binary classification and yielded an accuracy of 94.58%. |
[10]/2021 | WMPBE | CNN, VGG16, VGG19, DenseNet201 | To diagnose BT by using an ensemble system of CNN. | Dataset contained 3064 brain tumor images. It implemented binary classification and yielded an accuracy of 84.19%. |
|