4.5 Article

Deep-learning based breast cancer detection for cross-staining histopathology images

Related references

Note: Only part of the references are listed.
Article Biochemical Research Methods

CellSeg: a robust, pre-trained nucleus segmentation and pixel quantification software for highly multiplexed fluorescence images

Michael Y. Lee et al.

Summary: CellSeg is a powerful cell segmentation software for analyzing highly multiplexed tissue images that is accessible to biology researchers of any programming skill level.

BMC BIOINFORMATICS (2022)

Article Oncology

The utility of color normalization for AI-based diagnosis of hematoxylin and eosin-stained pathology images

Jeffrey Boschman et al.

Summary: This study compared eight color normalization algorithms for AI-based classification of H&E-stained histopathology slides, finding that while color normalization does not consistently improve classification on single-center data, it significantly enhances accuracy on multi-center datasets. Introducing a novel augmentation strategy by mixing color-normalized images using three algorithms consistently improves diagnosis of test images from external centers, showing the potential for reliable color normalization in AI-based digital pathology diagnosis of cancers from multiple centers.

JOURNAL OF PATHOLOGY (2022)

Article Medicine, Research & Experimental

Computer-assisted three-dimensional quantitation of programmed death-ligand 1 in non-small cell lung cancer using tissue clearing technology

Yen-Yu Lin et al.

Summary: Immune checkpoint blockade therapy has revolutionized non-small cell lung cancer treatment, but not all patients respond to it. Assessing the expression of immune checkpoint molecules, such as PD-L1, in tumors is the current standard for predicting treatment response, but the correlation is not perfect. Researchers have developed a new method that can make formalin-fixed, paraffin-embedded tissue translucent for 3D imaging and developed a computer-assisted PD-L1 quantitation method to analyze these images, improving the accuracy of tumor PD-L1 expression assessment.

JOURNAL OF TRANSLATIONAL MEDICINE (2022)

Review Pharmacology & Pharmacy

Leveraging advances in immunopathology and artificial intelligence to analyze in vitro tumor models in composition and space

Tze Ker Matthew Leong et al.

Summary: Cancer is the leading cause of death globally, with efforts to understand the complex and heterogeneous tumor microenvironment (TME) being crucial for research into this disease. Utilizing in vitro tumor models and artificial intelligence to study the TME holds great potential, but faces limitations such as inadequate data and ethical concerns. Overcoming these limitations is essential for future research to improve clinical outcomes.

ADVANCED DRUG DELIVERY REVIEWS (2021)

Review Oncology

The journey of tumor-infiltrating lymphocytes as a biomarker in breast cancer: clinical utility in an era of checkpoint inhibition

S. Loi et al.

Summary: The method described in 2014 allows quantification of tumor-infiltrating lymphocytes in breast cancer samples, showing strong prognostic value and potential for use in chemotherapy de-escalation studies. The inclusion of TIL biomarker in international guidelines and its association with better prognoses in TNBC and HER2+ BC have been confirmed. The recent focus has shifted to investigating the clinical utility of TIL in the setting of immune checkpoint-targeted agents, with TIL quantity potentially helping to identify patients who benefit most from PD-1/PD-L1 inhibition.

ANNALS OF ONCOLOGY (2021)

Article Biochemical Research Methods

Cellpose: a generalist algorithm for cellular segmentation

Carsen Stringer et al.

Summary: Cellpose is a generalist, deep learning-based segmentation method that can precisely segment cells from various types of images without requiring retraining or parameter adjustments. It was trained on a highly diverse image dataset and supports a three-dimensional extension. Software has been developed to support community contributions to the training data.

NATURE METHODS (2021)

Article Computer Science, Artificial Intelligence

A new complete color normalization method for H&E stained histopatholgical images

Surbhi Vijh et al.

Summary: The popularity of digital histopathology is increasing rapidly, but the challenge lies in the color variations in digital pathological image analysis. The proposed new complete color normalization method addresses the issues of color and stain variability through three phases, showing efficient performance and promising results in experimental validations.

APPLIED INTELLIGENCE (2021)

Article Multidisciplinary Sciences

A fast and effective detection framework for whole-slide histopathology image analysis

Jun Ruan et al.

Summary: With the rapid development of whole-slide digital scanners for histopathology, computer-assisted digital pathology image analysis has gained clinical attention, impacting the working style of pathologists. This paper presents a novel lightweight detection framework for automatic tumor detection in whole-slide histopathology images, achieving excellent performance in pixel-level detection with improved methods and models.

PLOS ONE (2021)

Article Anatomy & Morphology

Deep Learning-Based Classification of GAD67-Positive Neurons Without the Immunosignal

Kotaro Yamashiro et al.

Summary: Excitatory neurons and GABAergic interneurons are essential components of neural circuits, with fewer interneurons than excitatory neurons in certain brain areas. Researchers quantified interneurons and identified cell types using immunohistochemistry and deep learning algorithms, achieving successful binary classification of neurons without needing specific markers. The deep learning method outperformed classic machine-learning approaches in cell-type classification, providing a new platform for unbiased criteria.

FRONTIERS IN NEUROANATOMY (2021)

Article Oncology

Automated Quantification of sTIL Density with H&E-Based Digital Image Analysis Has Prognostic Potential in Triple-Negative Breast Cancers

Jeppe Thagaard et al.

Summary: Triple-negative breast cancer (TNBC) is a difficult-to-treat cancer type with lower survival rates, with stromal tumor-infiltrating lymphocytes (sTIL) emerging as a strong prognostic biomarker for overall survival. Automated image analysis can quantify sTIL density effectively, showing high concordance with manual scoring and potential for clinical use.

CANCERS (2021)

Article Multidisciplinary Sciences

An annotated fluorescence image dataset for training nuclear segmentation methods

Florian Kromp et al.

SCIENTIFIC DATA (2020)

Review Urology & Nephrology

Digital pathology and computational image analysis in nephropathology

Laura Barisoni et al.

NATURE REVIEWS NEPHROLOGY (2020)

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 Biochemistry & Molecular Biology

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

Pierre Courtiol et al.

NATURE MEDICINE (2019)

Article Medicine, Research & Experimental

Nondestructive, multiplex three-dimensional mapping of immune infiltrates in core needle biopsy

Steve Seung-Young Lee et al.

LABORATORY INVESTIGATION (2019)

Article Multidisciplinary Sciences

An alternative reference space for H&E color normalization

Mark D. Zarella et al.

PLOS ONE (2017)

Review Oncology

Clinical relevance of host immunity in breast cancer: from TILs to the clinic

Peter Savas et al.

NATURE REVIEWS CLINICAL ONCOLOGY (2016)

Review Oncology

Clinical significance of tumor-infiltrating lymphocytes in breast cancer

Sasha E. Stanton et al.

JOURNAL FOR IMMUNOTHERAPY OF CANCER (2016)

Review Pharmacology & Pharmacy

Applications of immunohistochemistry

Jeyapradha Duraiyan et al.

JOURNAL OF PHARMACY AND BIOALLIED SCIENCES (2012)

Review Engineering, Biomedical

Computational pathology: Challenges and promises for tissue analysis

Thomas J. Fuchs et al.

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS (2011)

Article Cell Biology

Systematic Analysis of Breast Cancer Morphology Uncovers Stromal Features Associated with Survival

Andrew H. Beck et al.

SCIENCE TRANSLATIONAL MEDICINE (2011)

Article Engineering, Electrical & Electronic

Nuclei segmentation using marker-controlled watershed, tracking using mean-shift, and Kalman filter in time-lapse microscopy

Xiaodong Yang et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS (2006)

Review Pathology

Technical aspects of immunohistochemistry

JA Ramos-Vara

VETERINARY PATHOLOGY (2005)