An Efficient USE-Net Deep Learning Model for Cancer Detection

Article Chemistry, Analytical

Breast Cancer Classification from Ultrasound Images Using Probability-Based Optimal Deep Learning Feature Fusion

Kiran Jabeen et al.

Summary: This paper proposes a framework for breast cancer classification from ultrasound images using deep learning and feature fusion. The framework achieves high accuracy in early cancer detection, outperforming recent techniques.

SENSORS (2022)

添加到收藏夹

Article Chemistry, Multidisciplinary

Convolutional Neural Networks for Breast Density Classification: Performance and Explanation Insights

Francesca Lizzi et al.

Summary: This study proposes and evaluates a method for the explainability of a breast density deep learning classifier. By building a residual Convolutional Neural Network and studying the model's responses to input changes, the authors find that pre-processing plays a crucial role in both the performance and explainability of the model. The results suggest that the CNN's performance is strongly correlated with dense patterns, and saliency maps can accurately explain the model's decision-making process.

APPLIED SCIENCES-BASEL (2022)

添加到收藏夹

Article Oncology

Influence of the Computer-Aided Decision Support System Design on Ultrasound-Based Breast Cancer Classification

Zuzanna Anna Magnuska et al.

Summary: This study explores different strategies for the computer-aided detection and classification of breast lesions using ultrasound images. By testing various dataset preparations and machine learning algorithms, the researchers identify promising techniques for accurate and effective diagnosis. The findings suggest that deriving radiomics signatures from detection boxes could be a valuable approach in reducing the need for manual segmentation in future CAD systems.

CANCERS (2022)

添加到收藏夹

Review Computer Science, Interdisciplinary Applications

A Characterization Approach for the Review of CAD Systems Designed for Breast Tumor Classification Using B-Mode Ultrasound Images

Kriti et al.

Summary: This paper discusses the various imaging modalities used for screening breast tumors, the challenges in accurate diagnosis of abnormalities in ultrasound images, and the interest in enhancing the diagnostic potential of ultrasound images through machine learning and deep learning approaches in CAD system designs. It highlights the clinically significant sonographic features, achievements, and future challenges in designing CAD systems for breast tumor classification, as well as directions for future research to improve the diagnostic potential of ultrasound imaging modality.

ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING (2022)

添加到收藏夹

Review Radiology, Nuclear Medicine & Medical Imaging

Application of Deep Learning in Breast Cancer Imaging

Luuk Balkenende et al.

Summary: This review provides an overview of the current state of deep learning research in breast cancer imaging. Breast imaging is crucial for early detection, monitoring, and evaluating breast cancer. Digital mammography, digital breast tomosynthesis, ultrasound, and magnetic resonance imaging are commonly used modalities for breast imaging, which can be digitized and applied with deep learning. Studies have shown that deep learning algorithms perform similarly or even better than radiologists in breast cancer imaging.

SEMINARS IN NUCLEAR MEDICINE (2022)

添加到收藏夹

Article Chemistry, Multidisciplinary

TTCNN: A Breast Cancer Detection and Classification towards Computer-Aided Diagnosis Using Digital Mammography in Early Stages

Sarmad Maqsood et al.

Summary: This paper presents a deep learning system for breast cancer screening, using mammogram images to achieve early detection of breast cancer. The proposed approach includes modified contrast enhancement, transferable texture convolutional neural network (TTCNN), and energy layer, as well as deep features and convolutional sparse image decomposition to improve classification accuracy. Experimental results demonstrate that the proposed method outperforms previous methods in classifying mammogram images.

APPLIED SCIENCES-BASEL (2022)

添加到收藏夹

Article Biology

Ensemble Deep-Learning-Enabled Clinical Decision Support System for Breast Cancer Diagnosis and Classification on Ultrasound Images

Mahmoud Ragab et al.

Summary: This study developed an Ensemble Deep-Learning-Enabled Clinical Decision Support System for the diagnosis and classification of breast cancer using ultrasound images. The system utilizes image pre-processing, segmentation techniques, and deep learning models for feature extraction and machine learning classifier for breast cancer detection. The system aims to assist radiologists and healthcare professionals in the breast cancer classification process.

BIOLOGY-BASEL (2022)

添加到收藏夹

Article Computer Science, Software Engineering

An Improved 2D U-Net Model Integrated Squeeze-and-Excitation Layer for Prostate Cancer Segmentation

Bingshuai Liu et al.

Summary: In this paper, an improved 2D U-Net model integrated with a squeeze-and-excitation layer for prostate cancer segmentation was proposed. Experimental results demonstrated that the proposed model could achieve better segmentation performance compared with other traditional methods.

SCIENTIFIC PROGRAMMING (2021)

添加到收藏夹

Article Chemistry, Multidisciplinary

Breast Cancer Detection Using Mammogram Images with Improved Multi-Fractal Dimension Approach and Feature Fusion

Dilovan Asaad Zebari et al.

Summary: This study proposed a new method for breast cancer classification using hybrid thresholding and machine learning techniques to extract the region of interest and process it in blocks with wavelet transform for noise reduction. Multiple features were extracted from each denoised block using an improved fractal dimension method, and an artificial neural network was employed for feature classification, with final decision made through result fusion. The proposed approach outperformed other state-of-the-art models on the Mini-MIAS dataset.

APPLIED SCIENCES-BASEL (2021)

添加到收藏夹

Article Engineering, Multidisciplinary

Deep learning in mammography images segmentation and classification: Automated CNN approach

Wessam M. Salama et al.

Summary: A new framework for breast cancer image segmentation and classification is proposed in this work, utilizing various models to classify mammographic images and segment breast areas. The method aims to assist radiologists in early detection and improve system efficiency.

ALEXANDRIA ENGINEERING JOURNAL (2021)

添加到收藏夹

Article Engineering, Biomedical

Hemorrhagic stroke lesion segmentation using a 3D U-Net with squeeze-and-excitation blocks

Valeriia Abramova et al.

Summary: The deep learning-based approach proposed in this study achieves promising automated segmentation results of hemorrhagic stroke lesions, with significant improvement by incorporating squeeze-and-excitation blocks and restrictive patch sampling.

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS (2021)

添加到收藏夹

Article Computer Science, Information Systems

King Abdulaziz University Breast Cancer Mammogram Dataset (KAU-BCMD)

Asmaa S. Alsolami et al.

Summary: The paper introduces the first dataset in Saudi Arabia for a large number of mammogram scans, called King Abdulaziz University Breast Cancer Mammogram Dataset (KAU-BCMD) version 1. It contains 1416 cases and 5662 images with different cancer grades of breast cancer image modalities.

DATA (2021)

添加到收藏夹

Article Computer Science, Software Engineering

Software reuse analytics using integrated random forest and gradient boosting machine learning algorithm

Amandeep Kaur Sandhu et al.

Summary: Cleaner Production is crucial for achieving sustainable production in companies, and software reuse is pivotal for software enterprises. This paper introduces a new machine learning algorithm (RFGBM) to test the reusability of given software code, outperforming existing algorithms in performance parameters.

SOFTWARE-PRACTICE & EXPERIENCE (2021)

添加到收藏夹

Review Health Care Sciences & Services