4.7 Article

Deep emb e ddings and logistic regression for rapid active learning in histopathological images

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Review Biology

The impact of pre- and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis

Massimo Salvi et al.

Summary: Deep learning frameworks have become the main methodology for analyzing medical images, especially in digital pathology. These frameworks can handle various image analysis tasks, such as classification, detection, and segmentation. Recent studies have shown that integrating traditional image processing methods for pre- and post-processing within a deep learning pipeline can improve model performance significantly.

COMPUTERS IN BIOLOGY AND MEDICINE (2021)

Article Engineering, Biomedical

Saak Transform-Based Machine Learning for Light-Sheet Imaging of Cardiac Trabeculation

Yichen Ding et al.

Summary: The combination of Saak transform, machine learning, and edge detection allows for efficient and accurate quantification of cardiac ultra-structure, improving segmentation efficiency and ensuring the accuracy and robustness of the images. This new methodology enhances segmentation efficiency by 20-fold compared to manual processing.

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING (2021)

Article Computer Science, Interdisciplinary Applications

Deep learning-based tumor microenvironment analysis in colon adenocarcinoma histopathological whole-slide images

Yiping Jiao et al.

Summary: This study aimed to automatically evaluate the tumor microenvironment in colon cancer whole-slide images, quantifying TME descriptors through a neural network and identifying stroma as an independent predictor of progression-free interval. Validation on cases from The Cancer Genome Atlas project showed high necrosis and lymphocyte components tend to be correlated with poor PFI.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2021)

Article Computer Science, Information Systems

Measuring Domain Shift for Deep Learning in Histopathology

Karin Stacke et al.

Summary: This research focuses on exploring the potential of deep learning in histopathology and the internal representation of domain shift learned by convolutional neural networks. A novel measure, representation shift, is proposed to quantify the degree of model-specific domain shift. By studying different datasets, models, and data preparation techniques to reduce domain shift, the proposed measure shows high correlation with performance drop across various domain shifts and improves upon existing methods for measuring data shift and uncertainty. This measure can help reveal a model's sensitivity to domain variations and detect new data that may pose challenges for generalization. Techniques for measuring, understanding, and overcoming domain shift are seen as crucial for the future reliable use of deep learning in clinical pathology applications.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2021)

Article Computer Science, Artificial Intelligence

A survey on active learning and human-in-the-loop deep learning for medical image analysis

Samuel Budd et al.

Summary: Fully automatic deep learning is advanced in tasks such as medical image analysis, but retaining a human end user in deep learning systems remains beneficial, making Human-in-the-Loop computing increasingly important in future research. Key areas of focus include active learning, interaction with model outputs, practical considerations, and future perspectives and unanswered questions, to ensure effective utilization of deep learning in clinical practice.

MEDICAL IMAGE ANALYSIS (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Deep Active Learning for Joint Classification & Segmentation with Weak Annotator

Soufiane Belharbi et al.

Summary: A proposed active learning framework gradually integrates pixel-level annotations to improve CNN visualization and interpretation methods in processing challenging images. Experimental results show that the method achieves significant improvements in image classification and segmentation tasks.

2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021 (2021)

Article Computer Science, Artificial Intelligence

Batch Mode Active Learning on the Riemannian Manifold for Automated Scoring of Nuclear Pleomorphism in Breast Cancer

Asha Das et al.

ARTIFICIAL INTELLIGENCE IN MEDICINE (2020)

Article Computer Science, Artificial Intelligence

O-MedAL: Online active deep learning for medical image analysis

Asim Smailagic et al.

WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY (2020)

Article Multidisciplinary Sciences

Deep learning-based cross-classifications reveal conserved spatial behaviors within tumor histological images

Javad Noorbakhsh et al.

NATURE COMMUNICATIONS (2020)

Article Computer Science, Artificial Intelligence

High-accuracy prostate cancer pathology using deep learning

Yuri Tolkach et al.

NATURE MACHINE INTELLIGENCE (2020)

Article Computer Science, Information Systems

Classifying non-small cell lung cancer types and transcriptomic subtypes using convolutional neural networks

Kun-Hsing Yu et al.

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION (2020)

Article Biochemical Research Methods

Structured crowdsourcing enables convolutional segmentation of histology images

Mohamed Amgad et al.

BIOINFORMATICS (2019)

Article Biochemistry & Molecular Biology

Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer

Jakob Nikolas Kather et al.

NATURE MEDICINE (2019)

Article Biochemistry & Molecular Biology

Clinical-grade computational pathology using weakly supervised deep learning on whole slide images

Gabriele Campanella et al.

NATURE MEDICINE (2019)

Article Computer Science, Information Systems

Label-Efficient Breast Cancer Histopathological Image Classification

Qi Qi et al.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2019)

Article Biochemistry & Molecular Biology

Deep learning-based classification of mesothelioma improves prediction of patient outcome

Pierre Courtiol et al.

NATURE MEDICINE (2019)

Article Medicine, General & Internal

Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer

Babak Ehteshami Bejnordi et al.

JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION (2017)

Article Multidisciplinary Sciences

Interactive phenotyping of large-scale histology imaging data with HistomicsML

Michael Nalisnik et al.

SCIENTIFIC REPORTS (2017)

Article Computer Science, Interdisciplinary Applications

On Combining Multiple-Instance Learning and Active Learning for Computer-Aided Detection of Tuberculosis

Jaime Melendez et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2016)

Article Engineering, Biomedical

A Nonlinear Mapping Approach to Stain Normalization in Digital Histopathology Images Using Image-Specific Color Deconvolution

Adnan Mujahid Khan et al.

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING (2014)