Skin Cancer Detection Using Combined Decision of Deep Learners

Imran, Azhar; Nasir, Arslan; Bilal, Muhammad; Sun, Guangmin; Alzahrani, Abdulkareem; Almuhaimeed, Abdullah

doi:10.1109/access.2022.3220329

Cited by 36 publications

(7 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the ISBI datasets, this model has 89% accuracy, which is superior to individual networks' lower accuracy. Suggested (Imran et al, 2022) a VGGNet, CapsNet, and ResNet ensemble for skin cancer diagnosis utilizing the ISIC public dataset. The suggested model achieves 93.5% accuracy, while VGGNet, CapsNet, and ResNet achieve 79%, 75%, and 69% accuracy, respectively.…”

Section: Literature Reviewmentioning

confidence: 99%

Enhancing skin cancer classification using a fusion of Densenet and Mobilenet models: a deep learning ensemble approach

Imam,

Nahar,

Rahman

et al. 2024

Multidiscip. Sci. J.

View full text Add to dashboard Cite

Skin cancer is a condition that causes the formation of abnormal cells in the skin tissue. Every year, millions of individuals experience skin cancer. Skin cancer identification in its early stages is an expensive and difficult process. Currently, deep learning models have revealed promising results in automated skin cancer classification. The goal of this study is to identify benign or malignant skin lesion using the Internation Skin Imaging Collaboration (ISIC) dataset and a concatenated model that combines two powerful Convolutional Neural Network (CNN) architectures, DenseNet and MobileNet. The ISIC dataset, which consists of a large collection of dermoscopic images, provides a valuable resource for training and evaluating skin cancer classification models. By concatenating the feature maps of DenseNet and MobileNet, the proposed model capitalizes on their individual strengths. The concatenated model is trained using a combination of techniques called transfer learning and fine-tuning, which leverage the pre-trained weights of the individual models and adapt them to the skin cancer classification task. On the test dataset, our proposed model finally achieves 93.75% accuracy, which is 4.69% higher than DenseNet, 3.13% higher than MobileNet, and 3.13% higher than the combination of ResNet50 and InceptionNetV3. The execution time of our proposed ensemble method is 49.48 min, and the execution times of MobileNet and DenseNet are 178.9 and 170.5 min, which are more than our proposed ensemble approach.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Enhancing skin cancer classification using a fusion of Densenet and Mobilenet models: a deep learning ensemble approach

Imam,

Nahar,

Rahman

et al. 2024

Multidiscip. Sci. J.

View full text Add to dashboard Cite

show abstract

“…Imran [22] introduced a convolution-based deep neural network for detecting skin cancer through the ISIC dataset. It integrates an ensemble learning technique such as VGG, ResNet, and CapsNet which exploits learner's diversity to yield a better decision.…”

Section: Literature Reviewmentioning

confidence: 99%

Convolutional Neural Network with Coordinate Attention Module for the Detection of Skin Cancer

2024

IJIES

View full text Add to dashboard Cite

Skin cancer is one of the most common types of cancer globally, by increasing occurrence rates each year. It is a predominant kind of cancer which rises from the uncontrolled growth of abnormal skin cells due to genetic mutations including various factors such as UV radiation, genetics and other factors. The death rate is decreased when skin cancer is detected at early stages. Therefore, this paper proposed a Convolutional Neural Network (CNN) with Coordinate Attention Module (CAM) for early detection of skin cancer. The data augmentation is utilized in this experiment for data pre-processing and fed into the Gray Level Co-occurrence Matrix (GLCM) based feature extraction technique. The Harris Hawk Optimization (HHO) is utilized for selecting features that have faster convergence and strong capability in local optima. The selected features are given as input to CNN with the CAM approach. This model is estimated on ISIC-2019 and ISIC-2020 datasets and attains better results using accuracy, precision, recall, specificity, and F1-score. The obtained result shows that the proposed model achieves better accuracy of 98.77% on the ISIC-2019 dataset and 99.51% on the ISIC-2020 dataset which ensures accurate detection compared to other existing methods like Inception-ResNet and Residual Deep Convolutional Neural Network (RDCNN).

show abstract

“…Tumors of two types, such as benign or malignant, Benign is non-cancerous, which is not more dangerous than malignant. Malignant is more dangerous because it is cancerous and spreads very quickly to all the body parts [3] [4]. The process of converting healthy cells into cancerous cells is known as carcinogenesis.…”

Section: Introductionmentioning

confidence: 99%

A Combined Ensemble Model (CEM) for a Liver Cancer Detection System

Sumellika,

Prasad

2024

IJACSA

View full text Add to dashboard Cite

The liver is one of the most important organs in the human body. The liver's proper function is critical for overall health, and liver diseases or disorders can have serious consequences. Liver cancer is also known as hepatic cancer, which is divided into various types of cells that belong to the cancer. The most common type of liver cancer is hepatocellular carcinoma (HCC). HCC is one of the most common types of liver cancer that can affect up to 85% of people worldwide. Early detection of liver cancer is essential in healthcare because it increases the chances of successful treatment and patient outcomes. Many researchers have developed models that help detect and diagnose liver cancer. The first step in detecting liver cancer is identifying people at a higher risk. Chronic hepatitis B or C infection, cirrhosis, heavy alcohol use, obesity, and exposure to certain chemicals and toxins are all risk factors. This paper is mainly focused on detecting the cancer-affected regions that occur in the liver. In this paper, a combined ensemble model (CEM) for a liver cancer detection system is developed to find and detect liver cancer and liver disorders in their early stages. A pre-trained model, RESNET50 with transfer learning, is used to obtain the features from the pre-trained model-an advanced preprocessing technique involved in filtering the noise from input CT scan images. A hybrid feature extraction (HFE) technique also gets significant elements from the input CT scan images. Finally, the proposed CEM combines an Extreme Gradient Boosting (EGB) algorithm with a Recurrent Neural Network (RNN) that focuses on detecting the abnormal cancer cells present in input CT scan images. The performance of the CEM shows a high accuracy of 98.48% with a 10% high detection rate. Previously, it was 88.12%.

show abstract

Skin Cancer Detection Using Combined Decision of Deep Learners

Cited by 36 publications

References 45 publications

Enhancing skin cancer classification using a fusion of Densenet and Mobilenet models: a deep learning ensemble approach

Enhancing skin cancer classification using a fusion of Densenet and Mobilenet models: a deep learning ensemble approach

Convolutional Neural Network with Coordinate Attention Module for the Detection of Skin Cancer

A Combined Ensemble Model (CEM) for a Liver Cancer Detection System

Contact Info

Product

Resources

About