Table 2 Performance of the proposed model is evaluated in comparison to other existing models.
Classifier | Dataset | AUC-ROC | Recall | Dice Co-efficient | F1-Score | IOU | P Precision | O ACC (%) |
|---|---|---|---|---|---|---|---|---|
CNN design10 | BRATS2013 | 76.85 | 76.85% | 60.12% | 79.8 | |||
VGG + ConvNets11 | BRATS2013 | 91.56 | 91.56 | 78.21 | 91.56% | 78.21% | 94.0 | 94 |
Support Vector Machine (SVM) classifier12 | Harvard, RIDER | 89.17 | 89.17 | 76.58 | 89.17% | 76.58% | 91.0 | 93.1 |
NNU-Net13 | BraTS 2020 | 89.76 | 89.76 | 74.56 | 89.76% | 74.56% | 90.0 | 88.9 |
SVM + CNN14 | BRATS 2015 | 96.38 | 96.38 | 83.64 | 96.38% | 83.64% | 97.0 | 96.4 |
RGA-Unet15 | TCIA | 95.14 | 95.14 | 84.21 | 95.14% | 84.21% | 96.0 | 95.04 |
InceptionResNetV216 | BraTS 2020 | 96.32 | 96.32 | 82.35 | 96.32% | 82.35% | 95.0 | 96 |
VGG-1617 | BraTS 2020 | 87.25 | 87.25 | 73.32 | 87.25% | 73.32% | 89.0 | 88.9 |
U-Net++18 | Diverse set of ultrasound images | 88.25 | 88.25 | 76.58 | 88.25% | 76.58% | 90.0 | 89.25 |
3D U-Net19 | BraTS 2020 | 84.97 | 84.97 | 71.25 | 84.97% | 71.25% | 86.0 | 86 |
Segmentation network U-Net20 | TCIA | 93.67 | 93.67 | 81.25 | 93.67% | 81.25% | 95.0 | 94.57 |
ResNet50-Unet21 | CVC Clinic-DB | 90.25 | 90.25 | 78.23 | 90.25% | 78.23% | 92.0 | 91.2 |
CNN-Based Inception-V322 | TCIA | 92.65 | 92.65 | 78.89 | 92.65% | 78.89% | 94.0 | 95 |
Hyperparameter-Tuned CNN23 | MRI datasets | 91.45 | 91.45 | 77.85 | 91.45% | 77.85% | 93.0 | 94 |
RCS-YOLO24 | Br35H dataset | 93.56 | 93.56 | 79.65 | 93.56% | 79.65% | 95.0 | 94.6 |
AlexNet-SVM and AlexNet-KNN25 | Br35H dataset | 90.31 | 90.31 | 76.89 | 90.31% | 76.89% | 92.0 | 91.5 |
MSDLM Model | CBIS-DDSM | 91.26 | 91.26 | 85.61 | 91.26% | 85.61% | 98.0 | 97.6 |
