Related references
Note: Only part of the references are listed.
Article
Computer Science, Information Systems
Vivek Patel et al.
Summary: Breast cancer is a fatal disease faced by women globally, due to lack of awareness and convenient diagnostic systems. This paper proposes a graph-based adaptive regularized learning of deep network (GARL-Net) for more accurate breast cancer classification. The proposed method outperforms existing state-of-the-art methods with high precision, recall, F-1 score, and accuracy.
Article
Computer Science, Interdisciplinary Applications
Meiyan Liang et al.
Summary: In this study, we propose an interpretable classification model named ABMIL-GCN, which hierarchically aggregates context-aware features using graph convolutional networks to predict the labels of WSI and locate the region of lymph node metastasis. The results demonstrate the superiority of this method on the Camelyon16 dataset, with improved accuracy and AUC scores compared to existing algorithms.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Pei Liu et al.
Summary: This paper proposes a new method, called dual-stream network with cross-attention (DSCA), to efficiently exploit WSI pyramids for cancer prognosis. The method addresses the problems of high computational cost and unnoticed semantical gap in multi-resolution feature fusion. Experimental results show that the proposed DSCA outperforms existing state-of-the-art methods in cancer prognosis.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Review
Health Care Sciences & Services
R. Rashmi et al.
Summary: Breast cancer is the second most common cancer worldwide, and early detection is crucial. Both traditional non-invasive techniques and recent computer tools are used for the analysis of breast cancer histopathological images. This review paper summarizes traditional and deep learning methods and discusses the importance and challenges of region of interest selection and technology choices.
JOURNAL OF MEDICAL SYSTEMS
(2022)
Article
Oncology
K. Shankar et al.
Summary: This study introduces a novel chaotic sparrow search algorithm with a deep transfer learning-enabled breast cancer classification (CSSADTL-BCC) model on histopathological images. The proposed model utilizes Gaussian filtering for noise elimination, MixNet-based feature extraction model, and stacked gated recurrent unit (SGRU) classification approach. The performance of the CSSADTL-BCC model outperforms recent state-of-the-art approaches in benchmark dataset.
Article
Engineering, Biomedical
R. Karthik et al.
Summary: Manual delineation of tumours in breast histopathology images is time-consuming and laborious, and computer-aided detection systems can improve efficiency. This study proposes an ensemble of two CNN architectures integrated with Channel and Spatial attention, achieving high accuracy in breast cancer classification.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2022)
Review
Engineering, Biomedical
Linhao Qu et al.
Summary: Histopathological images are crucial for disease diagnosis, patient prognosis, and treatment outcome prediction. The development of computer-automated analysis techniques for these images is in high demand in clinical practice. Traditional supervised algorithms based on large-scale annotated data face challenges, which has led to recent studies focusing on weakly supervised learning, semi-supervised learning, and self-supervised learning paradigms. These new methods have ushered in a new wave of automatic pathological image diagnosis and analysis aimed at improving annotation efficiency.
PHYSICS IN MEDICINE AND BIOLOGY
(2022)
Article
Oncology
Melina Arnold et al.
Summary: Breast cancer is the most commonly diagnosed cancer worldwide, with over 2.3 million new cases and 685,000 deaths in 2020. There is significant geographic variation in incidence rates, with lower rates in some Asian and African countries and higher rates in countries like Australia, New Zealand, Northern America, and parts of Europe. Mortality rates show less variation, but transitioning countries still bear a disproportionate burden of breast cancer deaths. By 2040, the burden of breast cancer is predicted to increase further due to population growth and ageing. Global efforts are needed to address this growing burden, especially in transitioning countries where incidence rates are rising rapidly and mortality rates remain high.
Proceedings Paper
Computer Science, Artificial Intelligence
Yonghang Guan et al.
Summary: The paper proposes a hierarchical global-to-local clustering strategy to build a Node-Aligned GCN (NAGCN) for representing WSIs with rich local structural information and global distribution. By deploying a global clustering operation for instance features to establish correspondence across different WSIs, and using a local clustering-based sampling strategy to select typical instances for each cluster within WSIs, followed by graph convolution for representation, the method ensures alignment among WSIs and achieves better performance in cancer subtype classification compared to state-of-the-art methods.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Hongrun Zhang et al.
Summary: This paper investigates the multiple instance learning problem in the classification of histopathology whole slide images, and proposes a double-tier MIL framework for small sample cohorts. It also introduces the concept of pseudo-bags and utilizes attention-based MIL framework to calculate instance probability. The proposed method outperforms other approaches on multiple datasets.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Mathematical & Computational Biology
Nadia Brancati et al.
Summary: Breast cancer is a common and deadly disease for women, and the use of Artificial Intelligence (AI) and digital workflows can improve diagnosis and patient care. This paper presents a large breast cancer subtyping dataset, consisting of annotated whole-slide images and regions of interest, which can be used to advance AI algorithms.
DATABASE-THE JOURNAL OF BIOLOGICAL DATABASES AND CURATION
(2022)
Article
Computer Science, Artificial Intelligence
Chetan L. Srinidhi et al.
Summary: This paper presents a comprehensive review of state-of-the-art deep learning approaches used in histopathological image analysis. Through a survey of over 130 papers, the progress in the field based on different machine learning strategies is reviewed. Additionally, the paper discusses the application of deep learning in survival models and highlights the challenges and limitations of current deep learning methods, as well as potential directions for future research.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Engineering, Biomedical
Ming Y. Lu et al.
Summary: The CLAM method utilizes attention-based learning to identify subregions with high diagnostic value for accurate classification of whole-slide images. It can localize well-known morphological features without the need for spatial labels, outperforming standard weakly supervised classification algorithms, and adapt to independent test cohorts, smartphone microscopy, and varying tissue content.
NATURE BIOMEDICAL ENGINEERING
(2021)
Proceedings Paper
Acoustics
Hang Li et al.
Summary: The article introduces a novel embedded-space MIL model, based on deformable transformer (DT) architecture and convolutional layers, termed DT-MIL, which outperforms other MIL models by generating the bag representation in a fully trainable way, representing the bag with a high-level and nonlinear combination of all instances, and encoding the position relationship and context information during bag embedding phase.
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT VIII
(2021)
Review
Health Care Sciences & Services
Andre Esteva et al.
Summary: The past decade has seen unprecedented progress in artificial intelligence, particularly in the field of medicine. Modern computer vision techniques powered by deep learning are revolutionizing medical applications, including imaging and video analysis. However, there are challenges to overcome for the real-world clinical deployment of these technologies.
NPJ DIGITAL MEDICINE
(2021)
Article
Oncology
Domenico Bellomo et al.
JCO PRECISION ONCOLOGY
(2020)
Article
Radiology, Nuclear Medicine & Medical Imaging
Chunling Liu et al.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2019)
Article
Biochemistry & Molecular Biology
Gabriele Campanella et al.
Article
Computer Science, Artificial Intelligence
Xinggang Wang et al.
PATTERN RECOGNITION
(2018)
Article
Medicine, General & Internal
Babak Ehteshami Bejnordi et al.
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION
(2017)
Article
Multidisciplinary Sciences
Andre Esteva et al.
