Melanoma classification using EfficientNets and Ensemble of models with different input resolution
TL;DR: In this paper, a method to classify melanoma cases using deep learning on dermoscopic images was proposed, which demonstrates that heavy augmentation during training and testing produces promising results and warrants further research.
Abstract: Early and accurate detection of melanoma with data analytics can make treatment more effective. This paper proposes a method to classify melanoma cases using deep learning on dermoscopic images. The method demonstrates that heavy augmentation during training and testing produces promising results and warrants further research. The proposed method has been evaluated on the SIIM-ISIC Melanoma Classification 2020 dataset and the best ensemble model achieved 0.9411 area under the ROC curve on hold out test data.
Citations
More filters
01 Jan 2022
TL;DR: A systematic review of recent advances in an area of increased interest for cancer prediction, with a focus on a comparative perspective of melanoma detection using artificial intelligence, especially neural network-based systems.
Abstract: Due to its increasing incidence, skin cancer, and especially melanoma, is a serious health disease today. The high mortality rate associated with melanoma makes it necessary to detect the early stages to be treated urgently and properly. This is the reason why many researchers in this domain wanted to obtain accurate computer-aided diagnosis systems to assist in the early detection and diagnosis of such diseases. The paper presents a systematic review of recent advances in an area of increased interest for cancer prediction, with a focus on a comparative perspective of melanoma detection using artificial intelligence, especially neural network-based systems. Such structures can be considered intelligent support systems for dermatologists. Theoretical and applied contributions were investigated in the new development trends of multiple neural network architecture, based on decision fusion. The most representative articles covering the area of melanoma detection based on neural networks, published in journals and impact conferences, were investigated between 2015 and 2021, focusing on the interval 2018–2021 as new trends. Additionally presented are the main databases and trends in their use in teaching neural networks to detect melanomas. Finally, a research agenda was highlighted to advance the field towards the new trends.
26 citations
TL;DR: In this article, the authors proposed an automated skin cancer diagnosis and triaging model and explored the impact of integrating clinical features in the diagnosis and enhance the outcomes achieved by the literature study.
Abstract: Due to the successful application of machine learning techniques in several fields, automated diagnosis system in healthcare has been increasing at a high rate. The aim of the study is to propose an automated skin cancer diagnosis and triaging model and to explore the impact of integrating the clinical features in the diagnosis and enhance the outcomes achieved by the literature study. We used an ensemble-learning framework, consisting of the EfficientNetB3 deep learning model for skin lesion analysis and Extreme Gradient Boosting (XGB) for clinical data. The study used PAD-UFES-20 data set consisting of six unbalanced categories of skin cancer. To overcome the data imbalance, we used data augmentation. Experiments were conducted using skin lesion merely and the combination of skin lesion and clinical data. We found that integration of clinical data with skin lesions enhances automated diagnosis accuracy. Moreover, the proposed model outperformed the results achieved by the previous study for the PAD-UFES-20 data set with an accuracy of 0.78, precision of 0.89, recall of 0.86, and F1 of 0.88. In conclusion, the study provides an improved automated diagnosis system to aid the healthcare professional and patients for skin cancer diagnosis and remote triaging.
22 citations
TL;DR: A comprehensive literature review of the methodologies, techniques, and approaches applied for the examination of skin lesions to date can be found in this article , which includes preprocessing, segmentation, feature extraction, selection, and classification approaches for skin cancer recognition.
Abstract: The skin is the human body’s largest organ and its cancer is considered among the most dangerous kinds of cancer. Various pathological variations in the human body can cause abnormal cell growth due to genetic disorders. These changes in human skin cells are very dangerous. Skin cancer slowly develops over further parts of the body and because of the high mortality rate of skin cancer, early diagnosis is essential. The visual checkup and the manual examination of the skin lesions are very tricky for the determination of skin cancer. Considering these concerns, numerous early recognition approaches have been proposed for skin cancer. With the fast progression in computer-aided diagnosis systems, a variety of deep learning, machine learning, and computer vision approaches were merged for the determination of medical samples and uncommon skin lesion samples. This research provides an extensive literature review of the methodologies, techniques, and approaches applied for the examination of skin lesions to date. This survey includes preprocessing, segmentation, feature extraction, selection, and classification approaches for skin cancer recognition. The results of these approaches are very impressive but still, some challenges occur in the analysis of skin lesions because of complex and rare features. Hence, the main objective is to examine the existing techniques utilized in the discovery of skin cancer by finding the obstacle that helps researchers contribute to future research.
4 citations
TL;DR: In this article , the authors proposed a method to solve the problem of the problem: this article ] of "uniformity" of the distribution of data points in the data set.
Abstract: Abstract
1 citations
01 Jan 2022
TL;DR: In this paper , a very efficient deep-convolutional neural network was used to analyze and predict skin lesions as accurately as possible, which achieved an average accuracy of 97.156%.
Abstract: Skin infection is one of the most frequent diseases all over the world, and persons under the age of 40–60 have a lot of skin problems. This paper shows how to use a very efficient deep-convolution neural network to analyze and predict skin lesions as accurately as possible. The dataset was acquired from the public domain and contains over 22,900 photos that include different categories of skin lesions and of which 2726 images related to squamous cell carcinoma, malignant melanoma, and basal cell carcinoma are extracted, and the remaining images are ignored. Some of the obtained photos may contain noise; filters are used to reduce the noise in the photographs. The suggested deep-convolution neural network technique encompasses six convolution layers, to reduce the size max-pooling layer applied wherever possible, and the model was used to categorize and forecast skin cancer once the data were cleaned. The model was able to distinguish skin lesions such as squamous cell carcinoma, malignant melanoma, and basal cell carcinoma generated an average accuracy of 97.156%. The paper’s major goal is to predict skin cancer in its early stages and give the best accuracy with the least amount of error possible.
1 citations
References
More filters
TL;DR: A methodological approach to the classification of pigmented skin lesions in dermoscopy images is presented and the issue of class imbalance is addressed using various sampling strategies and the classifier generalization error is estimated using Monte Carlo cross validation.
583 citations
TL;DR: Wang et al. as discussed by the authors proposed two deep learning methods to address three main tasks emerging in the area of skin lesion image processing, i.e., lesion segmentation, dermoscopic feature extraction, and lesion classification.
Abstract: Skin lesions are a severe disease globally. Early detection of melanoma in dermoscopy images significantly increases the survival rate. However, the accurate recognition of melanoma is extremely challenging due to the following reasons: low contrast between lesions and skin, visual similarity between melanoma and non-melanoma lesions, etc. Hence, reliable automatic detection of skin tumors is very useful to increase the accuracy and efficiency of pathologists. In this paper, we proposed two deep learning methods to address three main tasks emerging in the area of skin lesion image processing, i.e., lesion segmentation (task 1), lesion dermoscopic feature extraction (task 2) and lesion classification (task 3). A deep learning framework consisting of two fully convolutional residual networks (FCRN) is proposed to simultaneously produce the segmentation result and the coarse classification result. A lesion index calculation unit (LICU) is developed to refine the coarse classification results by calculating the distance heat-map. A straight-forward CNN is proposed for the dermoscopic feature extraction task. The proposed deep learning frameworks were evaluated on the ISIC 2017 dataset. Experimental results show the promising accuracies of our frameworks, i.e., 0.753 for task 1, 0.848 for task 2 and 0.912 for task 3 were achieved.
411 citations
TL;DR: It is concluded that color features outperform texture features when used alone and that both methods achieve very good results, i.e., Sensitivity = 96% and Specificity = 75% for local methods.
Abstract: Melanoma is one of the deadliest forms of cancer; hence, great effort has been put into the development of diagnosis methods for this disease. This paper addresses two different systems for the detection of melanomas in dermoscopy images. The first system uses global methods to classify skin lesions, whereas the second system uses local features and the bag-of-features classifier. This paper aims at determining the best system for skin lesion classification. The other objective is to compare the role of color and texture features in lesion classification and determine which set of features is more discriminative. It is concluded that color features outperform texture features when used alone and that both methods achieve very good results, i.e., Sensitivity = 96% and Specificity = 80% for global methods against Sensitivity = 100% and Specificity = 75% for local methods. The classification results were obtained on a data set of 176 dermoscopy images from Hospital Pedro Hispano, Matosinhos.
356 citations
TL;DR: An Internet-based melanoma screening system that separates the tumor area from the surrounding skin using highly accurate dermatologist-like tumor area extraction algorithm, and classifies the tumor as melanoma or nevus using a neural network classifier, and presents the diagnosis.
247 citations
TL;DR: In this article, the discriminatory power of k-nearest neighbors, logistic regression, artificial neural networks (ANNs), decision trees, and support vector machines (SVMs) on the task of classifying pigmented skin lesions as common nevi, dysplastic nevi or melanoma was analyzed.
240 citations