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

Table 1

Relative investigation of existing approaches for recognizing melanoma moles.

Author	Year	Approach	Task	Database	Accuracy
ML techniques
Alquran et al. [20]	2017	Pattern features + SVM	Categorization	Custom database	92.10%
Codella et al. [22]	2017	U-Net + SVM	Categorization	ISIC-2016	76%
Daghrir et al. [23]	2020	SIFT + SVM and KNN	Categorization	ISIC-2017	88.40%
Bama et al. [24]	2021	GMM model	Segmentation	PH2	86.83%
Hu et al. [25]	2019	SIFT + SVM	Categorization	PH2	82%
Durgarao et al. [44]	2021	LVP, and LBP + -means	Segmentation	PH2	79.44%
DL techniques
Ameri et al. [26]	2020	AlexNet	Categorization	HAM10000	84%
Acosta et al. [27]	2021	ResNet-152	Categorization	ISIC-2017	90.40%
Zhang et al. [28]	2019	VGG-16	Categorization	ISIC-2017	92.72%
Shan et al. [29]	2020	FC-DPN	Segmentation	ISIC-2017	95.14%
Bi et al. [30]	2019	Res-FCN	Segmentation	ISIC-2016	95.78%
Adegun et al. [31]	2019	Encoder-decoder	Categorization	ISIC-2017	95%
Nawaz et al. [32]	2021	Faster-RCNN + FKM	Segmentation	PH2	95.6%
Nawaz et al. [35]	2021	Faster-RCNN + SVM	Categorization	ISIC-2016	89.10%
Banerjee et al. [36]	2020	YOLO + L-type fuzzy clustering	Segmentation	ISIC-2017	97.33%
Iqbal et al. [37]	2021	CNN	Categorization	ISIC-2019	88.75%
Khan et al. [38]	2021	Mask-RCNN, DenseNet201 + SVM	Segmentation	ISIC-2016	93.6%
Mohakud et al. [39]	2022	Encoder-decoder	Segmentation	ISIC-2016	98.32%
Abdar et al. [40]	2021	Bayesian model	Categorization	Kaggle skin cancer dataset	88.95%
Pacheco et al. [41]	2021	Metadata and block-based method	Categorization	ISIC-2019	74.90%
Wang et al. [42]	2022	U-Net	Segmentation	ISIC-2017	94.67%
Zhao et al. [43]	2022	U-Net++	Segmentation	ISIC-2018	95.30%
Ali et al. [46]	2021	DCNN	Categorization	HAM10000	91.93%