Multi-Scale Deep Ensemble Learning for Melanoma Skin Cancer Detection

Guergueb, Takfarines; Akhloufi, Moulay A.

doi:10.1109/iri54793.2022.00063

Cited by 4 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the melanoma detection task, an ensemble learning approach is proposed in [86] to combine the predictive power of three different deep convolutional neural network (DCNN) models known from medical imaging classifications pretrained on the ImageNet dataset: EfficientNetB8, SEResNeXt10, and DenseNet264. Two innovative approaches are used: the multisample dropout approach, whereby, downstream of the pre-trained network architectures, the dropout, fully connected (FC), and softmax layers are duplicated and the loss value (obtained by using a variant of the binary cross-entropy called focal loss to perform dense object detection) is calculated as the average of the loss values of all dropout samples, and, secondly, the multi-penalty approach, whereby each duplicated layer is penalised at a different rate.…”

Section: Deep-learning Methodsmentioning

confidence: 99%

Machine Learning Approaches for Skin Cancer Classification from Dermoscopic Images: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

Skin cancer (SC) is one of the most prevalent cancers worldwide. Clinical evaluation of skin lesions is necessary to assess the characteristics of the disease; however, it is limited by long timelines and variety in interpretation. As early and accurate diagnosis of SC is crucial to increase patient survival rates, machine-learning (ML) and deep-learning (DL) approaches have been developed to overcome these issues and support dermatologists. We present a systematic literature review of recent research on the use of machine learning to classify skin lesions with the aim of providing a solid starting point for researchers beginning to work in this area. A search was conducted in several electronic databases by applying inclusion/exclusion filters and for this review, only those documents that clearly and completely described the procedures performed and reported the results obtained were selected. Sixty-eight articles were selected, of which the majority use DL approaches, in particular convolutional neural networks (CNN), while a smaller portion rely on ML techniques or hybrid ML/DL approaches for skin cancer detection and classification. Many ML and DL methods show high performance as classifiers of skin lesions. The promising results obtained to date bode well for the not-too-distant inclusion of these techniques in clinical practice.

show abstract

Section: Deep-learning Methodsmentioning

confidence: 99%

Machine Learning Approaches for Skin Cancer Classification from Dermoscopic Images: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Specifically, the HR-IQE algorithm was applied to improve image quality, and swarm intelligence and the grasshopper optimization algorithm were used for feature selection. The final classification was performed using a CNN with two convolutional and two max-pooling layers [34].…”

Section: Related Workmentioning

confidence: 99%

Deep learning model enhanced skin cancer detection

Kolachina

Agada²,

Li³

et al. 2023

Biophotonics and Immune Responses XVIII

View full text Add to dashboard Cite

According to the American Academy of Dermatology Association, identifying the types of skin cancer depends on the origin of a cell mutation resulting in the rapid growth of these abnormal cells in the epidermis. These mutations lead the skin cells to multiply rapidly and form malignant tumors. Skin cancer is ranked as the 17th most common form of cancer worldwide according to the World Cancer Research Fund. Skin cancer treatments cost the United States more than $8 billion (about $25 per person in the US) each year, making skin cancer the fifth most costly cancer for Medicare. Furthermore, skin cancer is an under recognized problem for diverse populations, including young women and minorities. Researchers have been exploring different technologies to detect skin care at its early stage to avoid high mortality rate and expensive medical treatment. This paper presents a novel ensembled deep learning model for the early detection of skin cancer. Our research is based on The HAM10000 dataset, a diverse collection of multi-sourced dermatoscopic images of common pigmented skin lesions which consists of 10015 dermatoscopic images. We have compared several deep learning neural network architectures and classifiers such as DNN, RNN, SVM and KNN in terms of accuracy rate and computation complexity and presented an ensembled deep learning model for early skin cancer detection. The main contribution of this paper is the productions of a comparative study of several skin cancer detection techniques using powerful computer vision techniques and deep learning models and a novel ensembled deep learning model for skin cancer detection.

show abstract

“…Malignant and benign cancer cells are the two kinds of cancer cells. To maximize the survival percentage of cancer patients, early, accurate diagnosis is necessary (Guergueb and Akhloufi 2022). Genetic mutations that affect cells' activity, particularly how technique grows and divides, cause the genetic condition that causes it.…”

Section: Introductionmentioning

confidence: 99%

Novel machine learning method in skin cancer diagnosis based on patient's metadata

Ojha,

Awasthi,

Gupta

2023

Multidiscip. Sci. J.

View full text Add to dashboard Cite

The skin's fundamental function in human body as a whole-body covering is crucial. Only if it is discovered while it is in its early stages can skin cancer be cured. Skin function plays a big part in the body's overall system and will be significantly impacted by even the slightest modification. The goal of this work was to develop an effective Machine Learning (ML) based technique for identification of skin cancer using patient information. To diagnose skin cancer with lesions image, this research introduces a novel Augmented May Fly optimized with K-Nearest Neighbors (AMFO-KNN) technique. Here, the AMFO approach is used to improve the classification efficiency of KNN. Utilizing the PAD-UFES-20 and Fitzpatrick17k datasets, the efficiency of suggested method is examined. The noisy data are removed from the raw data samples using Adaptive Median Filter (AMF). The properties are taken out of segmented data using Kernel Principal Component Analysis (KPCA). The performance metrics of research show that recommended methodology performs better than traditional approaches in terms of accuracy, precision, f1-score, and recall measures. The encouraging results demonstrate the effectiveness of suggested strategy and show that including the patient's information with lesions image may improve the performance of skin cancer diagnosis.

show abstract

Multi-Scale Deep Ensemble Learning for Melanoma Skin Cancer Detection

Cited by 4 publications

References 14 publications

Machine Learning Approaches for Skin Cancer Classification from Dermoscopic Images: A Systematic Review

Machine Learning Approaches for Skin Cancer Classification from Dermoscopic Images: A Systematic Review

Deep learning model enhanced skin cancer detection

Novel machine learning method in skin cancer diagnosis based on patient's metadata

Contact Info

Product

Resources

About