[HTML][HTML] Artificial intelligence for the classification of focal liver lesions in ultrasound–a systematic review

M Vetter, MJ Waldner, S Zundler, D Klett… - Ultraschall in der …, 2023 - thieme-connect.com
Focal liver lesions are detected in about 15% of abdominal ultrasound examinations. The
diagnosis of frequent benign lesions can be determined reliably based on the characteristic …

Classification of breast lesions in ultrasound images using deep convolutional neural networks: transfer learning versus automatic architecture design

A AlZoubi, F Lu, Y Zhu, T Ying, M Ahmed… - Medical & Biological …, 2024 - Springer
Deep convolutional neural networks (DCNNs) have demonstrated promising performance in
classifying breast lesions in 2D ultrasound (US) images. Exiting approaches typically use …

3d us-based evaluation and optimization of tumor coverage for us-guided percutaneous liver thermal ablation

S Xing, JC Romero, DW Cool… - … on Medical Imaging, 2022 - ieeexplore.ieee.org
Complete tumor coverage by the thermal ablation zone and with a safety margin (5 or 10
mm) is required to achieve the entire tumor eradication in liver tumor ablation procedures …

ENAS-B: Combining ENAS with Bayesian Optimization for Automatic Design of Optimal CNN Architectures for Breast Lesion Classification from Ultrasound Images

M Ahmed, H Du, A AlZoubi - Ultrasonic Imaging, 2024 - journals.sagepub.com
Efficient Neural Architecture Search (ENAS) is a recent development in searching for optimal
cell structures for Convolutional Neural Network (CNN) design. It has been successfully …

Ultrasound image augmentation by tumor margin appending for robust deep learning based breast lesion classification

T Hassan, A Al Zoubi, H Du… - … Image Exploitation and …, 2022 - spiedigitallibrary.org
The difficulty of obtaining sufficient number of appropriately labelled samples is a major
obstacle to learning class discriminating features by Machine Learning (ML) algorithms for …

Image Data Preparation For CNN-based Breast Ultrasound Lesion Diagnostic with Reduced Overfitting

TM Hassan - 2023 - bear.buckingham.ac.uk
This thesis aims to contribute to efforts of leveraging deep learning (DL) techniques,
specifically convolutional neural networks (CNNs), for improved diagnostics of breast …

[PDF][PDF] Enhancing generalization of CNN models for breast lesion classification from ultrasound images

T Hassan, H Du, S Jassim - 27th Conference on Medical Image …, 2019 - research.ed.ac.uk
This proof-of-concept study is concerned with the frequently occurring problem: CNN models
trained and tested on breast ultrasound (BUS) images from one clinical centre, fail to …