Skip to main content
. 2019 Aug 23;11(9):1235. doi: 10.3390/cancers11091235
ABCD Asymmetry, Border, Color Variation and Diameter
ABCDE Asymmetry, Border, Color Variation, Diameter and Expansion
AD Adenocarcinoma
ANN Artificial neural networks
AI-ANN Artificial intelligence-artificial neural networks
AK Actinic Keratosis
AUC Area under the characteristic curve
BoF Bag-of-features
BCC Basal cell carcinoma
BK Benign Keratosis
CAD Computer aided diagnosis
CAE Convolutional autoencoders
CNNs Convolutional neural networks
cCCNs Combined convolutional networks
CT Computed tomography
DANs Deep auto encoders
DF Dermatofibroma
FCNs Fully convolutional networks
FCRN Fully convolutional Residual networks
FCM Fuzzy-c Mean
FPS Fourier power spectrum
FP False positives
FN False negatives
GVF Gradient Vector Flow
GAN Generative adversarial models
GPU Graphics processing units
GLCM Grey level co-occurrence matrix
GM Generalization mean
histo.path Histopathology
IC Intraepithelial carcinoma
ILSVRC ImageNet large scale visual recognition competition
K-NN K-Nearest neighbor
LBPS Local binary patterns
LABS Laboratory retrospective study
LTSM Long short-term memory
M-CNN Multi-scale convolutional neural network
MIL-CNN Multiinstance convolutional neural network
MRI Magnetic resonance image
mAP multi class accuracy and mean average prediction
Neg.F Negative features
OBS Observational study
PACS Picture archiving and communication society
Pos.F Positive features
PCA Principal component analysis
RBF Radial basis function
RBM Restricted Boltzmann’s machine
ReLU Rectified linear unit
ROC Receiver operating characteristic curve
ROI Region of interest
Rsurf Rotated speeded-up robust features
RNN Recurrent neural networks
SAE Stacked autoencoders
SA-SVM Self-advised support vector machine
SCC Squamous cell carcinoma
SNR Signal too noise ratio
SVM Support Vector Machine
TP True positives
TN True negatives
WPT Wavepacket transform