A Hybrid Dependable Deep Feature Extraction and Ensemble-Based Machine Learning Approach for Breast Cancer Detection

Sharmin, S.; Ahammad, Tanvir; Talukder, Md. Alamin; Ghose, Partho

doi:10.1109/access.2023.3304628

Cited by 41 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The convolutional networks are inherently translation invariant, meaning they can recognize patterns regardless of their location in the input. This property is crucial for tasks like image classification [ 23 , 24 ], where the position of objects may vary. The outputs of the first convolution layer are a kind of time series containing information from the three channels.…”

Section: Methodsmentioning

confidence: 99%

Ultrasound tomography enhancement by signal feature extraction with modular machine learning method

Baran,

Majerek,

Szyszka

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Robust and reliable diagnostic methods are desired in various types of industries. This article presents a novel approach to object detection in industrial or general ultrasound tomography. The key idea is to analyze the time-dependent ultrasonic signal recorded by three independent transducers of an experimental system. It focuses on finding common or related characteristics of these signals using custom-designed deep neural network models. In principle, models use convolution layers to extract common features of signals, which are passed to dense layers responsible for predicting the number of objects or their locations and sizes. Predicting the number and properties of objects are characterized by a high value of the coefficient of determination R2 = 99.8% and R2 = 98.4%, respectively. The proposed solution can result in a reliable and low-cost method of object detection for various industry sectors.

show abstract

Section: Methodsmentioning

confidence: 99%

Ultrasound tomography enhancement by signal feature extraction with modular machine learning method

Baran,

Majerek,

Szyszka

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…The researchers utilized DeeplapV3 + ResNet-50 and VGG-16 + ResNet-50 V2 + U-Net++; these methods were highly accurate in the diagnosis of liver tumors. Sharmin et al [ 27 ] In this study, a novel hybrid model is proposed for the reliable detection of breast cancer that integrates deep learning (DL) and machine learning (ML) techniques. This model utilizes the capabilities of the deep learning-based pre-trained ResNet50V2 transfer learning model to extract intricate patterns and representations from invasive ductal carcinoma (IDC) pictures effectively.…”

Section: Related Workmentioning

confidence: 99%

Using hybrid pre-trained models for breast cancer detection

Zarif,

Abdulkader,

Elaraby

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Breast cancer is a prevalent and life-threatening disease that affects women globally. Early detection and access to top-notch treatment are crucial in preventing fatalities from this condition. However, manual breast histopathology image analysis is time-consuming and prone to errors. This study proposed a hybrid deep learning model (CNN+EfficientNetV2B3). The proposed approach utilizes convolutional neural networks (CNNs) for the identification of positive invasive ductal carcinoma (IDC) and negative (non-IDC) tissue using whole slide images (WSIs), which use pre-trained models to classify breast cancer in images, supporting pathologists in making more accurate diagnoses. The proposed model demonstrates outstanding performance with an accuracy of 96.3%, precision of 93.4%, recall of 86.4%, F1-score of 89.7%, Matthew’s correlation coefficient (MCC) of 87.6%, the Area Under the Curve (AUC) of a Receiver Operating Characteristic (ROC) curve of 97.5%, and the Area Under the Curve of the Precision-Recall Curve (AUPRC) of 96.8%, which outperforms the accuracy achieved by other models. The proposed model was also tested against MobileNet+DenseNet121, MobileNetV2+EfficientNetV2B0, and other deep learning models, proving more powerful than contemporary machine learning and deep learning approaches.

show abstract

“…In parallel, the clinical sciences generate an abundance of data, including clinical reports and a myriad of patient symptoms. Leveraging data mining and machine learning techniques, we can address critical prediction-related challenges within the realm of clinical fields, particularly those associated with cardiovascular health [15].…”

Section: Introductionmentioning

confidence: 99%

Advancements in Cardiovascular Disease Detection: Leveraging Data Mining and Machine Learning

Hossain,

Talukder,

Mahmud

2024

Preprint

Self Cite

View full text Add to dashboard Cite

Cardiovascular disease (CVD) is a significant global health concern, requiring early detection and accurate prediction for effective intervention. Machine learning (ML) offers a data-driven approach to analyzing patient data, identifying complex patterns and predicting CVD risk factors like blood pressure (BP), cholesterol levels, and genetic predispositions. Our research aims to predict CVD presence using ML algorithms, leveraging the Heart Disease UCI dataset with 14 attributes and 303 instances. Extensive feature engineering enhanced model performance. We developed five models using Logistic Regression, K-Nearest Neighbors (KNN), Decision Tree Classifier, Support Vector Machine (SVM), and Random Forest Classifier, refining them with hyperparameter tuning. Results show substantial accuracy improvements post-tuning and feature engineering. 'Logistic Regression' achieved the highest accuracy at 93.44%, closely followed by 'Support Vector Machine' at 91.80%. Our findings emphasize the potential of ML in early CVD prediction, underlining its value in healthcare and proactive risk management. ML's utilization for CVD risk assessment promises personalized healthcare, benefiting both patients and healthcare providers. This research showcases the practicality and effectiveness of ML-based CVD risk assessment, enabling early intervention, improving patient outcomes, and optimizing healthcare resource allocation.

show abstract

A Hybrid Dependable Deep Feature Extraction and Ensemble-Based Machine Learning Approach for Breast Cancer Detection

Cited by 41 publications

References 33 publications

Ultrasound tomography enhancement by signal feature extraction with modular machine learning method

Ultrasound tomography enhancement by signal feature extraction with modular machine learning method

Using hybrid pre-trained models for breast cancer detection

Advancements in Cardiovascular Disease Detection: Leveraging Data Mining and Machine Learning

Contact Info

Product

Resources

About