Improving accuracy of CADx system by hybrid PCA and backpropagation

Harba, Hind S.; Harba, Eman S.; Hussein, Samera Shams; Farttoos, Mohammed

doi:10.1109/cata.2018.8398681

Cited by 3 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conventional CADx systems utilize computer algorithms to aid healthcare professionals in diagnosing diseases. ,, These systems operate by furnishing clinicians with information regarding potential disease presence and by scrutinizing data derived from medical imaging modalities such as X-rays, magnetic resonance imaging (MRI), and computed tomography (CT) scans. Recognized as valuable tools, conventional CADx systems enhance the accuracy and efficiency of medical diagnoses. , They follow a series of steps to analyze medical images, encompassing preprocessing, segmentation, feature extraction, feature selection, and classification as illustrated in Figure .…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Approaches for Skin Neoplasm Diagnosis

Asaduzzaman,

Thompson,

Uddin

2024

ACS Omega

View full text Add to dashboard Cite

Approaches for skin neoplasm diagnosis include physical exam, skin biopsy, lab tests of biopsy samples, and image analyses. These approaches often involve error-prone and time-consuming processes. Recent studies show that machine learning shows promise in effectively classifying skin images into different categories such as melanoma and melanocytic nevi. In this work, we investigate machine learning approaches to enhance the performance of computer-aided diagnosis (CADx) systems to diagnose skin diseases. In the proposed CADx system, generative adversarial network (GAN) discriminator is used to identify (and remove) fake images. Exploratory data analysis (EDA) is applied to normalize the original data set for preventing model overfitting. Synthetic minority oversampling technique (SMOTE) is employed to rectify class imbalances in the original data set. To accurately classify skin images, the following machine learning models are utilized: linear discriminant analysis (LDA), support vector machine (SVM), convolutional neural network (CNN), and an ensemble CNN−SVM. Experimental results using the HAM10000 data set demonstrate the ability of the machine learning models to improve CADx performance in treating skin neoplasm. Initially, the LDA, SVM, CNN, and ensemble CNN−SVM show 49%, 72%, 77%, and 79% accuracy, respectively. After applying GAN (discriminator) and SMOTE, the LDA, SVM, CNN, and ensemble CNN−SVM show 76%, 83%, 87%, and 94% accuracy, respectively. We plan to explore other machine learning models and data sets in our next endeavor.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Recognized as valuable tools, conventional CADx systems enhance the accuracy and efficiency of medical diagnoses. 22 , 23 They follow a series of steps to analyze medical images, encompassing preprocessing, segmentation, feature extraction, feature selection, and classification as illustrated in Figure 1 .…”

Section: Related Workmentioning

confidence: 99%

Machine Learning Approaches for Skin Neoplasm Diagnosis

Asaduzzaman,

Thompson,

Uddin

2024

ACS Omega

View full text Add to dashboard Cite

show abstract

“…The technical definition of a sensor is "a device that converts physical parameters or events into signals that can be measured and analyzed" [15]. Keeping tabs on environmental and physical factors is the main goal of employing WSN [16], [17].. Information is received by the Cluster Head (CH) from the sensor nodes that make up its cluster. To the CH, all cluster members transmit their data [18] .The CH then sends the aggregated data to the sink node, central node, or Base Station (BS), may be linked to the network or the Internet via a gateway, granting access to the gathered data to users located far [19], [20].…”

Section: Introductionmentioning

confidence: 99%

New Technology for Advanced Results for Security Wireless Sensor Networks

Al-Khafaji

2024

wjps

View full text Add to dashboard Cite

Designing wireless sensor networks (WSNs), which are new technologies with the potential to perceive, analyze, communicate, and send data, is difficult since it impacts the network's performance and longevity. The goals of this study are to enhance network longevity, mitigate power usage, and safeguard transmitted data. An energy-saving procedure was suggested as a means to accomplish this objective. Every node in the network uses the same amount of electricity according to this protocol. The restricted resources of the nodes are also taken into account while recommending an algorithm. Additionally, in order to provide optimal outcomes for assessing the system's effectiveness. The suggested model and the network's performance were evaluated using the Quality of Service (Q o S) metrics of Packet Loss Ratio (PLR), Network Energy Consumption (NEC), and Network Throughput Ratio (NTR). , this method ensures that the data remains intact. Additionally, we came up with a method to save electricity. This protocol ensures that all nodes in the network use an equal amount of electricity

show abstract

Machine Learning Approaches for Skin Neoplasm Diagnosis

Asaduzzaman,

Thompson,

Uddin

2024

Preprint

View full text Add to dashboard Cite

Approaches for skin neoplasm diagnosis include physical exam, skin biopsy, lab tests of biopsy samples, and image analyses. These approaches often involve error-prone and time-consuming processes. Recent studies show that machine learning has promises to effectively classify skin images into different classes such as melanoma and melanocytic nevi. In this work, we investigate machine learning approaches to enhance the performance of computer-aided diagnosis (CADx) systems to diagnose skin diseases. In the proposed CADx system, generative adversarial network (GAN) is used to identify (and remove) fake images. Exploratory data analysis (EDA) is applied to normalize the original dataset for preventing model overfitting. Synthetic minority over-sampling technique (SMOTE) is employed to rectify class imbalances in the original dataset. To accurately classify skin images, the following four machine learning models are utilized: linear discriminant analysis (LDA), support vector machine (SVM), convolutional neural network (CNN), and an ensemble CNN-SVM. Experimental results using the HAM10000 dataset demonstrate the ability of the machine learning models to improve CADx performance in treating skin neoplasm. Initially, the LDA, SVM, CNN, and ensemble CNN-SVM show 49%, 72%, 77%, and 79% accuracy, respectively. After applying GAN, EDA, and SMOTE, the LDA, SVM, CNN, and ensemble CNN-SVM show 76%, 83%, 87%, and 94% accuracy, respectively. We plan to explore other machine learning models and datasets in our next endeavor.

show abstract

Improving accuracy of CADx system by hybrid PCA and backpropagation

Cited by 3 publications

References 6 publications

Machine Learning Approaches for Skin Neoplasm Diagnosis

Machine Learning Approaches for Skin Neoplasm Diagnosis

New Technology for Advanced Results for Security Wireless Sensor Networks

Machine Learning Approaches for Skin Neoplasm Diagnosis

Contact Info

Product

Resources

About