Melanoma Skin Cancer Classification based on CNN Deep Learning Algorithms

Waheed, Safa Riyadh; Saadi, Saadi Mohammed; Rahim, Mohd Shafry Mohd; Suaib, Norhaida Mohd; Najjar, Fallah H.; Adnan, Myasar Mundher; Salim, A.A.

doi:10.11113/mjfas.v19n3.2900

Cited by 15 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By 2023, Ref. [32] proposed a CNN strategy for early melanoma detection involving five convolution layers, five pooling layers, a fully connected layer, an input layer, and an output layer. Employing 10,000 and 1000 images for training and testing, respectively, the system achieved an accuracy of 91% [33].…”

Section: Related Workmentioning

confidence: 99%

Performance Improvement of Melanoma Detection Using a Multi-Network System Based on Decision Fusion

El-khatib,

Ștefan,

Popescu

2023

Applied Sciences

View full text Add to dashboard Cite

The incidence of melanoma cases continues to rise, underscoring the critical need for early detection and treatment. Recent studies highlight the significance of deep learning in melanoma detection, leading to improved accuracy. The field of computer-assisted detection is extensively explored along all lines, especially in the medical industry, as the benefit in this field is to save hu-man lives. In this domain, this direction must be maximally exploited and introduced into routine controls to improve patient prognosis, disease prevention, reduce treatment costs, improve population management, and improve patient empowerment. All these new aspects were taken into consideration to implement an EHR system with an automated melanoma detection system. The first step, as presented in this paper, is to build a system based on the fusion of decisions from multiple neural networks, such as DarkNet-53, DenseNet-201, GoogLeNet, Inception-V3, InceptionResNet-V2, ResNet-50, ResNet-101, and compare this classifier with four other applications: Google Teachable Machine, Microsoft Azure Machine Learning, Google Vertex AI, and SalesForce Einstein Vision based on the F1 score for further integration into an EHR platform. We trained all models on two databases, ISIC 2020 and DermIS, to also test their adaptability to a wide range of images. Comparisons with state-of-the-art research and existing applications confirm the promising performance of the proposed system.

show abstract

Section: Related Workmentioning

confidence: 99%

Performance Improvement of Melanoma Detection Using a Multi-Network System Based on Decision Fusion

El-khatib,

Ștefan,

Popescu

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…We had 5,819 photos in the normal category and 10,622 in the abnormal category. That brings the total number of photos in this collection to 16,441 [30][31][32][33].…”

Section: A Databasesmentioning

confidence: 99%

New Proposed Mixed Transforms: CAW and FAW and Their Application in Medical Image Classification

Mousa Al-Khuzaay,

Mahmoud Al-Jawher

2023

Int J Innov Comp

View full text Add to dashboard Cite

The transformation model plays a vital role in medical image processing. This paper proposed new two Mixed Transforms models that are the hybrid combination of linear and nonlinear Transformations techniques. The first mixed transform is computed in three steps: calculate 2D discrete cosine transform (DCT) of the image, and applying Arnold Transform (AT) on the DCT coefficients, and applying the discrete Wavelet Transform (DWT) on the result to get which was abbreviated as (CAW). The second mixed transform consists of firstly computing the discrete Fourier transform (DFT), net applying the Arnold Transform (AT), and finally, the computation of discrete Wavelet Transform (DWT) which was abbreviated as (FAW). These transforms have superior directional representations as compared to other multiresolution representations such as DWT or DCT and work as non-adaptive mixed transformations for multi-scale object analysis. Due to their relationship to the wavelet idea, they are finding increasing use in areas like image processing and scientific computing. These transforms are tested in medical image classification task and their performances are compared with that of the traditional transforms. CAW and FAW transforms are used in the feature extraction stage of a classification VGG16 deep learning (DNN) task of Tumor MRI medical image. The numerical findings favor CAW and FAW over the wavelet transform for estimating and classifying pictures. From the results obtained it was shown that the CAW and FAW transform gave e much higher classification rate than that achieved with the traditional transforms, namely DCT, DFT and DWT. Furthermore, this combination leads to a family of directional and multi-transformation bases for image processing.

show abstract

“…In 2021 [21][22][23][24][25][26] developed a foreground extraction method for investigating the multi-frame, multi-scale, and generative adversarial network concepts (mFS-GANs). Additionally, a hybrid optimization technique known as HGWOSA that combines Simulated Annealing (SA) and Grey Wolf Optimizer (GWO) is suggested to guarantee a worldwide optimum outcome with minimal computational cost.…”

Section: Video Summarizationmentioning

confidence: 99%

Digital Video Summarization: A Survey

H. Hendi,

Q. Hussein,

B. Taher

2023

Int J Innov Comp

View full text Add to dashboard Cite

Video summarization has arisen as a method that can help with efficient storage, rapid browsing, indexing, fast retrieval, and quick sharing of the material. The amount of video data created has grown exponentially over time. Huge amounts of video are produced continuously by a large number of cameras. Processing these massive amounts of video requires a lot of time, labor, and hardware storage. In this situation, a video summary is crucial. The architecture of video summarization demonstrates how a lengthy film may be broken down into shorter, story-like segments. Numerous sorts of studies have been conducted in the past and continue now. As a result, several approaches and methods—from traditional computer vision to more modern deep learning approaches—have been offered by academics. However, several issues make video summarization difficult, including computational hardware, complexity, and a lack of datasets. Many researchers have recently concentrated their research efforts on developing efficient methods for extracting relevant information from videos. Given that data is gathered constantly, seven days a week, this study area is crucial for the advancement of video surveillance systems that need a lot of storage capacity and intricate data processing. To make data analysis easier, make it easier to store information, and make it easier to access the video at any time, a summary of video data is necessary for these systems. In this paper, methods for creating static or dynamic summaries from videos are presented. The authors provide many approaches for each literary form. The authors have spoken about some features that are utilized to create video summaries.

show abstract

Melanoma Skin Cancer Classification based on CNN Deep Learning Algorithms

Cited by 15 publications

References 29 publications

Performance Improvement of Melanoma Detection Using a Multi-Network System Based on Decision Fusion

Performance Improvement of Melanoma Detection Using a Multi-Network System Based on Decision Fusion

New Proposed Mixed Transforms: CAW and FAW and Their Application in Medical Image Classification

Digital Video Summarization: A Survey

Contact Info

Product

Resources

About