MSeg-Net: A Melanoma Mole Segmentation Network Using CornerNet and Fuzzy -Means Clustering

Table 6

Performance analysis of the proposed work with the new methods over the ISIC-2018 dataset.

Reference	Sensitivity	Specificity	Accuracy (%)	Jaccard index (%)	Dice (%)
[72]	0.9100	0.9699	95.78	82.02	89.00
[74]	0.9554	0.9840	97.39	—	93.00
[73]	0.9910	0.9878	98.86	95.66	97.78
[79]	0.8620	0.9860	96.70	80.00	88.90
[75]	0.8600	—	—	—	—
[80]	0.8691	0.9809	97.20	97.57	—
[76]	0.9049	—	96.19	83.45	89.99
[81]	0.7890	0.9800	—	94.00	—
Proposed	0.9939	0.9948	99.63	97.83	98.86