Classification of Skin Cancer Dermoscopy Images using Transfer Learning

Younis, Haseeb; Bhatti, Muhammad Hamza; Azeem, Muhammad

doi:10.1109/icet48972.2019.8994508

Cited by 53 publications

(19 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This dataset consists of seven highly imbalanced classes. Initially, the HAM10000 dataset includes more than 10,000 images of seven skin classes such as 6705 images of melanocytic nevi, 1113 images in melanomas, 1099 images in benign keratoses, 514 images in basal cell carcinomas, 327 images of actinic keratoses, 142 images in vascular lesions, and 115 images in dermatofibromas [ 39 ]. From this information, it is noted that few classes are highly imbalanced; therefore, it is essential to balance this dataset.…”

Section: Proposed Methodologymentioning

confidence: 99%

A Computer‐Aided Diagnosis System Using Deep Learning for Multiclass Skin Lesion Classification

Arshad

Khan

Tariq

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In the USA, each year, almost 5.4 million people are diagnosed with skin cancer. Melanoma is one of the most dangerous types of skin cancer, and its survival rate is 5%. The development of skin cancer has risen over the last couple of years. Early identification of skin cancer can help reduce the human mortality rate. Dermoscopy is a technology used for the acquisition of skin images. However, the manual inspection process consumes more time and required much cost. The recent development in the area of deep learning showed significant performance for classification tasks. In this research work, a new automated framework is proposed for multiclass skin lesion classification. The proposed framework consists of a series of steps. In the first step, augmentation is performed. For the augmentation process, three operations are performed: rotate 90, right-left flip, and up and down flip. In the second step, deep models are fine-tuned. Two models are opted, such as ResNet-50 and ResNet-101, and updated their layers. In the third step, transfer learning is applied to train both fine-tuned deep models on augmented datasets. In the succeeding stage, features are extracted and performed fusion using a modified serial-based approach. Finally, the fused vector is further enhanced by selecting the best features using the skewness-controlled SVR approach. The final selected features are classified using several machine learning algorithms and selected based on the accuracy value. In the experimental process, the augmented HAM10000 dataset is used and achieved an accuracy of 91.7%. Moreover, the performance of the augmented dataset is better as compared to the original imbalanced dataset. In addition, the proposed method is compared with some recent studies and shows improved performance.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

A Computer‐Aided Diagnosis System Using Deep Learning for Multiclass Skin Lesion Classification

Arshad

Khan

Tariq

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…To expand the number of input photographs, data argumentation techniques such as horizontal and vertical ipping were used. Transfer learning [14] is a technique based on machine learning in which a model that was trained for one task is repurposed for another. When the dataset is limited, another important use of transfer learning is to obtain excellent performance by using a pre-trained model on comparable photos.…”

Section: Preprocessingmentioning

confidence: 99%

A new method for detection and classification of melanoma skin cancer using deep learning based transfer learning architecture models

Subramanian

Muthusamy

Thangaraj³

et al. 2022

Preprint

View full text Add to dashboard Cite

Melanoma is a kind of skin cancer that develops in melanocyte cells. It is one of the most serious kind of skin cancer, yet it is not as frequent as other types of skin cancer.It is very hard to detect, even under expert supervision. A Deep Convolutional Neural Network (D-CNN) Visual Geometry Group (VGG16) model, is proposed to improve the classification performance of skin lesions.The main disadvantage of using the deep learning methods is that more time is needed for training. Thus, with the help of transfer learning technique, the training time is reduced. The datasets utilized in the proposed strategy to train the model were obtained from International Skin Imaging Collaboration (ISIC).Metrics like Accuracy (ACC), Positive Predictive Value (PPV), Negative Predictive Value (NPV), Specificity (SPC), and Sensitivity (SE) were measured for the evaluation of the classification.The performance of the classification process done by the classifier model on a test data is represented using a confusion matrix. The proposed method of using transfer learning technique in Deep Convolutional Neural Network improved the accuracy of classification to 85% compared to 81% obtained from Convolutional Neural Network.

show abstract

“…Morphological analyses have recently been performed by the combination of segmentation and pre-processing steps to obtain gray-level skin lesion images with a pre-trained Levenberg-Marquardt neural network for clustering and classification of images from the PH2 database [25]. Transfer learning has also been employed to achieve high-accuracy predictions on skin cancer images from the HAM10000 database using the MobileNet CNN [26]. Recent work on the use of CNN for skin cancer prediction has also pointed to outstanding challenges in the inclusion of the full range of patient population and all types of melanoma subtypes [27].…”

Section: Introductionmentioning

confidence: 99%

“…Here, we assess the accuracy of various ML and DL approaches for the development of diagnostic tools on the sole basis of dermoscopic images. More specifically, the aim of this work is to design a diagnostic tool that classifies skin lesion images between two classes (benign and malignant), rather than based on multi-class segmentation and classification tasks [26,30]. Given the impact of the training/testing dataset on the results [27], we systematically test a wide range of ML and DL models on the same dataset, the publicly available Kaggle database, to obtain a consistent set of metrics for their performance.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning and Deep Learning Algorithms for Skin Cancer Classification from Dermoscopic Images

Bechelli

Delhommelle

2022

Bioengineering

View full text Add to dashboard Cite

We carry out a critical assessment of machine learning and deep learning models for the classification of skin tumors. Machine learning (ML) algorithms tested in this work include logistic regression, linear discriminant analysis, k-nearest neighbors classifier, decision tree classifier and Gaussian naive Bayes, while deep learning (DL) models employed are either based on a custom Convolutional Neural Network model, or leverage transfer learning via the use of pre-trained models (VGG16, Xception and ResNet50). We find that DL models, with accuracies up to 0.88, all outperform ML models. ML models exhibit accuracies below 0.72, which can be increased to up to 0.75 with ensemble learning. To further assess the performance of DL models, we test them on a larger and more imbalanced dataset. Metrics, such as the F-score and accuracy, indicate that, after fine-tuning, pre-trained models perform extremely well for skin tumor classification. This is most notably the case for VGG16, which exhibits an F-score of 0.88 and an accuracy of 0.88 on the smaller database, and metrics of 0.70 and 0.88, respectively, on the larger database.

show abstract

Classification of Skin Cancer Dermoscopy Images using Transfer Learning

Cited by 53 publications

References 11 publications

A Computer‐Aided Diagnosis System Using Deep Learning for Multiclass Skin Lesion Classification

A Computer‐Aided Diagnosis System Using Deep Learning for Multiclass Skin Lesion Classification

A new method for detection and classification of melanoma skin cancer using deep learning based transfer learning architecture models

Machine Learning and Deep Learning Algorithms for Skin Cancer Classification from Dermoscopic Images

Contact Info

Product

Resources

About