ContourTL-Net: Contour-Based Transfer Learning Algorithm for Early-Stage Brain Tumor Detection

Table 5

Experimental result (%) evaluation of the proposed methodology with the state-of-the-art methods for BR253 dataset.

Methods	Sensitivity (recall)	Specificity (TN)	Accuracy
Improved model [50]	94.70	100	97.01
ResNet-50 model [53]	—	—	95.0
VGG-SCNet model [27]	99.10	—	—
UNet-VGG-16 model [26]	—	—	96.10
BrainMRNet model [39]	96.0	96.08	96.05
OS-DNN model [17]	97.94	98.08	98.02
Proposed model	99.63	99.33	99.51

Significant performances are denoted in bold.