Automatic skin cancer detection in dermoscopy images by combining convolutional neural networks and texture features

Alizadeh, Seyed Mohammad; Mahloojifar, Ali

doi:10.1002/ima.22490

Cited by 60 publications

(35 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results obtained by Zadeh et al Alizadeh and Mahloojifar (2020) exceed our measurements because the authors validate their model on two classes while we validate our approach on eight classes. The obtained result in the work of Kassem et al Kassem, Khalid Hosny and Fouad (2020) was 94.92% for 10% of the dataset only taken as a test but in our study we have used 20% and we obtain 92.34%.…”

Section: Discussion On Isic 2019 Dataset Experimentscontrasting

confidence: 40%

Multi-features extraction based on deep learning for skin lesion classification

2022

View full text Add to dashboard Cite

For various forms of skin lesion, many different feature extraction methods have been investigated so far. Indeed, feature extraction is a crucial step in machine learning processes. In general, we can distinct handcrafted and deep learning features. In this paper, we investigate the efficiency of using 17 commonly pre-trained convolutional neural networks (CNN) architectures as feature extractors and of 24 machine learning classifiers to evaluate the classification of skin lesions from two different datasets: ISIC 2019 and PH2. In this research, we find out that a DenseNet201 combined with Fine KNN or Cubic SVM achieved the best results in accuracy (92.34% and 91.71% ) for the ISIC 2019 dataset. The results also show that the suggested method outperforms others approaches with an accuracy of 99% on the PH2 dataset.

show abstract

Section: Discussion On Isic 2019 Dataset Experimentscontrasting

confidence: 40%

Multi-features extraction based on deep learning for skin lesion classification

2022

View full text Add to dashboard Cite

show abstract

“…Three layers, namely convolution, pooling, and completely connected layers are the basic blocks of a CNN model. Convolution and pooling layers play a significant role in procuring features, while the completely connected layer usually functions as a classifier 17 . While CNN may independently categorize images, its integration with other classifiers can improve the efficacy of classification.…”

Section: Methodsmentioning

confidence: 99%

Malignancy detection on mammograms by integrating modified convolutional neural network classifier and texture features

Melekoodappattu¹,

Dhas²,

Kumar³

et al. 2021

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Breast cancer is detected by identifying malignancy on breast tissue. Emerging technologies in medical image processing are used to interpret histopathology images. For analyzing medical imaging and pathological data, modified deep neural networks are being used. Automatic detection of malignancy is usually achieved in deep learning by capturing features from a convolutional neural network (CNN) and then categorizing them using a fully connected network. A framework to automatically diagnose malignancy using an ensemble approach, including CNN and extraction of image texture features, is implemented in this research. In the CNN phase, the nine‐layer modified CNN is used to classify images. Texture features are derived and their dimension is minimized using maximum variance unfolding to enhance the efficiency of classification in the extraction‐based phase. The results of each phase were then merged to obtain the final decision. The testing specificity and accuracy of our ensemble method on MIAS repository are 98.9% and 99%, respectively and for the DDSM repository are 98.3% and 98.1%. The ensemble approach increases the measurement metrics compared to each phase separately, as per the experimental findings.

show abstract

“…e majority of them are either based on the low level or high level of features except for [47] that have fused both levels to perform binary classification.…”

Section: Background On Artificial Intelligence In Skinmentioning

confidence: 99%

“…The high-level features extracted from the two MobileNet are combined, and a spiking neural network (SNN) is employed to perform classification reaching a 95.27% accuracy. Conversely, the authors of [ 47 ] extracted low-level radiomics features based on textural analysis such as GLCM and LBP features and then reduced these features using principal component analysis (PCA). Afterward, the reduced features are used to train several individual classifiers to classify malignant and benign skin lesions.…”

Section: Background On Artificial Intelligence In Skin Cancer Diagnosismentioning

confidence: 99%

“…A few of them have classified several subtypes of cancer discussed earlier. The majority of them are either based on the low level or high level of features except for [ 47 ] that have fused both levels to perform binary classification. These shortcomings have motivated us to propose a new intelligent dermatologist tool to classify seven skin cancer categories.…”

Section: Background On Artificial Intelligence In Skin Cancer Diagnosismentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Dermatologist Tool for Classifying Multiple Skin Cancer Subtypes by Incorporating Manifold Radiomics Features Categories

Attallah

Sharkas

2021

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

The rates of skin cancer (SC) are rising every year and becoming a critical health issue worldwide. SC’s early and accurate diagnosis is the key procedure to reduce these rates and improve survivability. However, the manual diagnosis is exhausting, complicated, expensive, prone to diagnostic error, and highly dependent on the dermatologist’s experience and abilities. Thus, there is a vital need to create automated dermatologist tools that are capable of accurately classifying SC subclasses. Recently, artificial intelligence (AI) techniques including machine learning (ML) and deep learning (DL) have verified the success of computer-assisted dermatologist tools in the automatic diagnosis and detection of SC diseases. Previous AI-based dermatologist tools are based on features which are either high-level features based on DL methods or low-level features based on handcrafted operations. Most of them were constructed for binary classification of SC. This study proposes an intelligent dermatologist tool to accurately diagnose multiple skin lesions automatically. This tool incorporates manifold radiomics features categories involving high-level features such as ResNet-50, DenseNet-201, and DarkNet-53 and low-level features including discrete wavelet transform (DWT) and local binary pattern (LBP). The results of the proposed intelligent tool prove that merging manifold features of different categories has a high influence on the classification accuracy. Moreover, these results are superior to those obtained by other related AI-based dermatologist tools. Therefore, the proposed intelligent tool can be used by dermatologists to help them in the accurate diagnosis of the SC subcategory. It can also overcome manual diagnosis limitations, reduce the rates of infection, and enhance survival rates.

show abstract

Automatic skin cancer detection in dermoscopy images by combining convolutional neural networks and texture features

Cited by 60 publications

References 43 publications

Multi-features extraction based on deep learning for skin lesion classification

Multi-features extraction based on deep learning for skin lesion classification

Malignancy detection on mammograms by integrating modified convolutional neural network classifier and texture features

Intelligent Dermatologist Tool for Classifying Multiple Skin Cancer Subtypes by Incorporating Manifold Radiomics Features Categories

Contact Info

Product

Resources

About