Convolutional neural networks for the automatic diagnosis of melanoma: An extensive experimental study

Pérez, Eduardo; Reyes, Óscar; Ventura, Sebastián

doi:10.1016/j.media.2020.101858

Cited by 51 publications

(34 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study set is composed of 1095 dermoscopic and non-dermoscopic images for skin lesions (i.e., melanoma, dysplastic nevus and regular nevus) collected from four databases (denoted B1 to B4); their properties are specified in Table 1 . The selection of these databases was driven according to the analysis performed by Pérez et al [ 38 ]. They show that a high variability in skin lesion images exists, which underlays the intricacy of the skin cancer diagnosis problem when using these public databases.…”

Section: Methodsmentioning

confidence: 99%

Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks

et al. 2021

View full text Add to dashboard Cite

In the automatic detection framework, there have been many attempts to develop models for real-time melanoma detection. To effectively discriminate benign and malign skin lesions, this work investigates sixty different architectures of the Feedforward Back Propagation Network (FFBPN), based on shape asymmetry for an optimal structural design that includes both the hidden neuron number and the input data selection. The reason for the choice of shape asymmetry was based on the 5–10% disagreement between dermatologists regarding the efficacy of asymmetry in the diagnosis of malignant melanoma. Asymmetry is quantified based on lesion shape (contour), moment of inertia of the lesion shape and histograms. The FFBPN has a high architecture flexibility, which indicates it as a favorable tool to avoid the over-parameterization of the ANN and, equally, to discard those redundant input datasets that usually result in poor test performance. The FFBPN was tested on four public image datasets containing melanoma, dysplastic nevus and nevus images. Experimental results on multiple benchmark data sets demonstrate that asymmetry A2 is a meaningful feature for skin lesion classification, and FFBPN with 16 neurons in the hidden layer can model the data without compromising prediction accuracy.

show abstract

Section: Methodsmentioning

confidence: 99%

Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Furthermore, melanoma is the third most common source of brain metastases after lung and breast cancer, with more than 60% of patients with metastatic melanoma having or developing brain metastases during their onset [9]. The early detection of melanoma is a key factor for melanoma therapy [10,11]. Although an earlier diagnosis has been documented with better outcomes, one-fifth of deaths counterintuitively occur in patients who are initially presenting with early disease [12].…”

Section: Introductionmentioning

confidence: 99%

Nanocarrier-Based Drug Delivery for Melanoma Therapeutics

Song

Liu

Chen

et al. 2021

IJMS

View full text Add to dashboard Cite

Melanoma, as a tumor cell derived from melanocyte transformation, has the characteristics of malignant proliferation, high metastasis, rapid recurrence, and a low survival rate. Traditional therapy has many shortcomings, including drug side effects and poor patient compliance, and so on. Therefore, the development of an effective treatment is necessary. Currently, nanotechnologies are a promising oncology treatment strategy because of their ability to effectively deliver drugs and other bioactive molecules to targeted tissues with low toxicity, thereby improving the clinical efficacy of cancer therapy. In this review, the application of nanotechnology in the treatment of melanoma is reviewed and discussed. First, the pathogenesis and molecular targets of melanoma are elucidated, and the current clinical treatment strategies and deficiencies of melanoma are then introduced. Following this, we discuss the main features of developing efficient nanosystems and introduce the latest reports in the literature on nanoparticles for the treatment of melanoma. Subsequently, we review and discuss the application of nanoparticles in chemotherapeutic agents, immunotherapy, mRNA vaccines, and photothermal therapy, as well as the potential of nanotechnology in the early diagnosis of melanoma.

show abstract

“…The new methods have significantly advanced the state of the art in skin lesion analysis. The CNN can automatically extract and learn high-level features, increasing the robustness of melanoma images' inter-and intra-class variability [19,20]. With the rapid increase in the number of automatic recognition of melanoma from dermoscopy images using CNNs, comparing results among pieces of works and evaluation has become an awkward task.…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Evaluation and Benchmarking of Convolutional Neural Networks for Melanoma Diagnosis

Alzahrani

Al-Bander

Al-Nuaimy

2021

Cancers

View full text Add to dashboard Cite

Melanoma is the most invasive skin cancer with the highest risk of death. While it is a serious skin cancer, it is highly curable if detected early. Melanoma diagnosis is difficult, even for experienced dermatologists, due to the wide range of morphologies in skin lesions. Given the rapid development of deep learning algorithms for melanoma diagnosis, it is crucial to validate and benchmark these models, which is the main challenge of this work. This research presents a new benchmarking and selection approach based on the multi-criteria analysis method (MCDM), which integrates entropy and the preference ranking organization method for enrichment of evaluations (PROMETHEE) methods. The experimental study is carried out in four phases. Firstly, 19 convolution neural networks (CNNs) are trained and evaluated on a public dataset of 991 dermoscopic images. Secondly, to obtain the decision matrix, 10 criteria, including accuracy, classification error, precision, sensitivity, specificity, F1-score, false-positive rate, false-negative rate, Matthews correlation coefficient (MCC), and the number of parameters are established. Third, entropy and PROMETHEE methods are integrated to determine the weights of criteria and rank the models. Fourth, the proposed benchmarking framework is validated using the VIKOR method. The obtained results reveal that the ResNet101 model is selected as the optimal diagnosis model for melanoma in our case study data. Thus, the presented benchmarking framework is proven to be useful at exposing the optimal melanoma diagnosis model targeting to ease the selection process of the proper convolutional neural network architecture.

show abstract

Convolutional neural networks for the automatic diagnosis of melanoma: An extensive experimental study

Cited by 51 publications

References 45 publications

Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks

Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks

Nanocarrier-Based Drug Delivery for Melanoma Therapeutics

A Comprehensive Evaluation and Benchmarking of Convolutional Neural Networks for Melanoma Diagnosis

Contact Info

Product

Resources

About