Skin Cancer Classification using Deep Learning and Transfer Learning

Hosny, Khalid M.; Kassem, Mohamed A.; Foaud, Mohamed M.

doi:10.1109/cibec.2018.8641762

Cited by 167 publications

(82 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These nodes represent the classes of the segmentation methods and predict the most effective skin lesion detection and segmentation technique in any image data. A pre-trained deep learning network and transfer learning were proposed in Khalid et al [31]. The transfer learning was applied to AlexNet to identify skin lesions in addition to fine-tuning and data increase.…”

Section: A) Pre-trained Modelsmentioning

confidence: 99%

“…Efficiency is the key factor for the model reliability. For this purpose, Khalid et al [31]uses AlexNet for transfer learning and classify three different lesions. The proposed system was trained and tested on the PH2 dataset only, the achieve accuracy rates were high, but the credibility of the method was low due to the use of only one dataset.…”

Section: A) Efficiency Calculation On Single Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Malignant Melanoma Classification Using Deep Learning: Datasets, Performance Measurements, Challenges and Opportunities

et al. 2020

View full text Add to dashboard Cite

Melanoma remains the most harmful form of skin cancer. Convolutional neural network (CNN) based classifiers have become the best choice for melanoma detection in the recent era. The research has indicated that classifiers based on CNN classify skin cancer images equivalent to dermatologists, which has allowed a quick and life-saving diagnosis. This study provides a systematic literature review of the latest research on melanoma classification using CNN. We restrict our study to the binary classification of melanoma. In particular, this research discusses the CNN classifiers and compares the accuracies of these classifiers when tested on non-published datasets. We conducted a systematic review of existing literature, identifying the literature through a systematic search of the IEEE, Medline, ACM, Springer, Elsevier, and Wiley databases. A total of 5112 studies were identified out of which 55 well-reputed studies were selected. The main objective of this study is to collect state of the art research which identify the recent research trends, challenges and opportunities for melanoma diagnosis and investigate the existing solutions for the diagnosis of melanoma detection using deep learning. Moreover, proposed taxonomy for melanoma detection has been presented that summarizes the broad variety of existing melanoma detection solutions. Lastly, proposed model, challenges and opportunities have been presented which helps the researchers in the domain of melanoma detection.

show abstract

Section: A) Pre-trained Modelsmentioning

confidence: 99%

Section: A) Efficiency Calculation On Single Datasetsmentioning

confidence: 99%

Malignant Melanoma Classification Using Deep Learning: Datasets, Performance Measurements, Challenges and Opportunities

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Some neural network layers comprise a deep convolutional neural network [7]. Deeper layers can extract more semantic and global features, but these signs do not prove that the last layer is the ultimate representation for any task [12].…”

Section: A Skip Connectionmentioning

confidence: 99%

“…In recent years, convolutional neural networks (CNNs) have achieved great success in image classification tasks through supervised learning. CNNs are effective for learning better feature representations in the field of computer vision [1]- [7]. We have witnessed a tremendous improvement in image classification tasks due to the use of supervised learning combined with the powerful model of CNNs [8].…”

Section: Introductionmentioning

confidence: 99%

Improving the Performance of VGG Through Different Granularity Feature Combinations

Zhou

Chang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Convolutional neural networks have achieved amazing success in many areas in recent years, and VGG is a widely used convolutional neural network model. However, it has some limitations, such as a large number of parameters, which take up significant memory and thus restrict its application in resourceconstrained scenarios such as mobile devices and embedded systems. In convolutional neural network models, the different number of convolutional layers can extract different granularity features, which represent the different levels of importance in the image recognition process. Here, we propose a new VGG architecture with different granularity feature combinations that combine different granularity features from block1, block2, block3, block4, and block5 in VGG. Each block is followed by a local fully connected layer to reduce the dimensionality of the coarse and fine features, and five different granularity features are combined as the input of the first global fully connected layer. By combining the features of different blocks, it can increase information flow from a lower layer directly to a fully connected layer and increase feature reuse without adding too many connections. The addition of five local fully connected layers means an increase in parameters, so we reduce the neuron number in two global fully connected layers to reduce the number of parameters. The well-known datasets CIFAR-10 and MNIST were used to evaluate the network's classification performance. The experimental results show that the proposed model achieves better training and testing performance than traditional VGGs and reduces the number of parameters.

show abstract

“…The softmax layer is used for classification. Skin cancer classification system using deep learning is described in [4]. The alexnet layer in the CNN perfoms the convolution in each layer and classification is made by softmax layer.…”

Section: Introductionmentioning

confidence: 99%

Skin Cancer Diagnostic using Machine Learning Techniques - Shearlet Transform and Naïve Bayes Classifier

Kumar¹,

Kumar²,

Gopalakrishnan³

2019

IJEAT

View full text Add to dashboard Cite

Development of abnormal cells in the skin is known as skin cancer or melanoma, which can spread other parts of the body. Melanoma rarely occurs in eye, mouth and intestines. In this study, the classification of melanoma using shearlet transform coefficients and naïve Bayes classifier is discussed. The melanoma images are decomposed by the shearlet transform. Then, from the shearlet coefficients, predefined number of (50, 75 and 100) coefficients are selected from the decomposed subbands. The selected subband coefficients are directly applied to the naïve Bayes classifier. Performance of skin cancer classification system is measured in terms of accuracy. Results show that a better classification accuracy of 90.5 % is achieved at 3rd level with 100 coefficients of shearlet transform and naïve Bayes classifier for skin image classification system.

show abstract

Skin Cancer Classification using Deep Learning and Transfer Learning

Cited by 167 publications

References 19 publications

Malignant Melanoma Classification Using Deep Learning: Datasets, Performance Measurements, Challenges and Opportunities

Malignant Melanoma Classification Using Deep Learning: Datasets, Performance Measurements, Challenges and Opportunities

Improving the Performance of VGG Through Different Granularity Feature Combinations

Skin Cancer Diagnostic using Machine Learning Techniques - Shearlet Transform and Naïve Bayes Classifier

Contact Info

Product

Resources

About