Digital pathology in cardiac transplant diagnostics: from biopsies to algorithms

Article Cardiac & Cardiovascular Systems

Endomyocardial biopsy in the clinical context: current indications and challenging scenarios

Aldostefano Porcari et al.

Summary: Endomyocardial biopsy (EMB) is a method for diagnosing various cardiac diseases, and recent advances in imaging techniques provide better non-invasive diagnostic methods, which may require redefining the role of EMB.

HEART FAILURE REVIEWS (2023)

添加到收藏夹

Review Immunology

The Molecular Microscope Diagnostic System: Assessment of Rejection and Injury in Heart Transplant Biopsies

Philip F. Halloran et al.

Summary: This review discusses the Molecular Microscope Diagnostic System (MMDx) for heart transplant endomyocardial biopsies. MMDx utilizes microarrays and machine learning algorithms to assess rejection and injury in biopsies. It classifies biopsies into different categories based on transcript-based algorithms and can also evaluate the degree of parenchymal injury and atrophy-fibrosis.

TRANSPLANTATION (2023)

添加到收藏夹

Review Cardiac & Cardiovascular Systems

The End of Endomyocardial Biopsy? A Practical Guide for Noninvasive Heart Transplant Rejection Surveillance

Luise Holzhauser et al.

Summary: Noninvasive heart transplant rejection surveillance using gene expression profiling (GEP) and donor-derived cell-free DNA (dd-cfDNA) assays is becoming more common. This review provides practical guidance for clinicians transitioning to a less invasive monitoring protocol after heart transplantation, addressing 10 common questions about GEP and dd-cfDNA assays. The review also discusses evidence supporting these tests and provides guidance on test interpretation and future directions.

JACC-HEART FAILURE (2023)

添加到收藏夹

Review Cardiac & Cardiovascular Systems

The Role of Machine Learning in Cardiovascular Pathology

Carolyn Glass et al.

Summary: Machine learning has been slowly adopted in diagnostic pathology, showing potential to standardize and improve histopathologic diagnoses. However, there are challenges in image quality standardization, consensus diagnosis, and the availability of large datasets. Despite these challenges, the power of histopathology-based machine learning technologies is tremendous and could greatly benefit clinical practice.

CANADIAN JOURNAL OF CARDIOLOGY (2022)

添加到收藏夹

Review Cardiac & Cardiovascular Systems

Innovations in Heart Transplantation: A Review

Amanda C. Coniglio et al.

Summary: Advanced heart failure is a serious condition with high morbidity and mortality. Cardiac transplantation is the optimal treatment strategy, but donor availability has been a limitation. Recent advances in organ allocation, donor-recipient matching, organ preservation, and expansion of the donor pool have overcome these challenges and improved outcomes for heart transplant candidates.

JOURNAL OF CARDIAC FAILURE (2022)

添加到收藏夹

Review Pathology

Digital pathology and artificial intelligence in translational medicine and clinical practice

Vipul Baxi et al.

Summary: Recent technological advancements have enabled the development of digital pathology and AI-based solutions for quantitative pathologic assessments, revolutionizing disease diagnosis and drug development. These innovations provide valuable opportunities in immuno-oncology for deciphering complex pathophysiology and discovering novel biomarkers, while also supporting practitioners in selecting the most appropriate treatment based on patient profiles. The integration of AI-powered analysis tools enhances the traditional role of pathologists in delivering accurate diagnoses and assessing biomarkers, with potential applications in translational medicine and clinical settings.

MODERN PATHOLOGY (2022)

添加到收藏夹

Review Cardiac & Cardiovascular Systems

Current status and outcomes in heart transplantation: a narrative review

Morcos A. Awad et al.

Summary: This article reviews the recent advances and short-term and long-term outcomes of heart transplantation. It is one of the most effective treatments for patients with end-stage heart failure, but still faces challenges such as limited availability of donors, rejection, and non-cardiac complications.

REVIEWS IN CARDIOVASCULAR MEDICINE (2022)

添加到收藏夹

Article Cardiac & Cardiovascular Systems

Computational Analysis of Routine Biopsies Improves Diagnosis and Prediction of Cardiac Allograft Vasculopathy

Eliot G. Peyster et al.

Summary: This study developed a precision medicine tool for predicting the development of cardiac allograft vasculopathy (CAV) in heart transplant recipients using computational analysis of digital pathology images. The incorporation of computationally extracted histological features greatly improved the prediction of future CAV development, enhancing the precision and personalization of treatment plans.

CIRCULATION (2022)

添加到收藏夹

Review Cell Biology

A guide to machine learning for biologists

Joe G. Greener et al.

Summary: This passage discusses the application of machine learning in the analysis of biological data and provides guidance for experimentalists. The increasing scale and complexity of biological data have led to a growing use of machine learning in biology.

NATURE REVIEWS MOLECULAR CELL BIOLOGY (2022)

添加到收藏夹

Article Biochemistry & Molecular Biology

Deep learning-enabled assessment of cardiac allograft rejection from endomyocardial biopsies

Jana Lipkova et al.

Summary: A deep learning-based AI system has been developed for automated assessment of gigapixel whole-slide images obtained from endomyocardial biopsy, addressing the detection, subtyping and grading of allograft rejection. The system showed non-inferior performance to conventional assessment, reducing interobserver variability and assessment time.

NATURE MEDICINE (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A manifesto on explainability for artificial intelligence in medicine

Carlo Combi et al.

Summary: This paper focuses on the importance of explainable artificial intelligence (XAI) in the field of biomedicine. By bringing together researchers with different roles and perspectives, it explores XAI in depth and presents a series of requirements for achieving explainability in AI.

ARTIFICIAL INTELLIGENCE IN MEDICINE (2022)

添加到收藏夹

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)

添加到收藏夹

Review Medicine, Research & Experimental

Artificial intelligence and computational pathology

Miao Cui et al.

Summary: Computational pathology, driven by data processing and clinical informatics, offers innovative solutions for patient care. However, challenges such as data integration, hardware limitations, and talent development need to be addressed for the field to advance further.

LABORATORY INVESTIGATION (2021)

添加到收藏夹

Article Cardiac & Cardiovascular Systems

The International Thoracic Organ Transplant Registry of the International Society for Heart and Lung Transplantation: Thirty-eighth adult heart transplantation report-2021; Focus on recipient characteristics

Kiran K. Khush et al.

JOURNAL OF HEART AND LUNG TRANSPLANTATION (2021)

添加到收藏夹

Review Biochemistry & Molecular Biology

A Changing Paradigm in Heart Transplantation: An Integrative Approach for Invasive and Non-Invasive Allograft Rejection Monitoring

Alessia Giarraputo et al.

Summary: Diagnosing cardiac allograft rejection post-heart transplantation is challenging, with tissue biopsies being the current gold standard. Non-invasive methods like liquid biopsy show promise for improving rejection diagnosis. Future advancements may involve molecular techniques and omics science to enhance monitoring accuracy for heart transplant patients.

BIOMOLECULES (2021)

添加到收藏夹

Article Cardiac & Cardiovascular Systems

Epidemiology of Heart Failure A Contemporary Perspective

Veronique L. Roger

Summary: This review summarizes recent studies on the epidemiology of heart failure (HF) over the past decade, indicating that while the incidence of HF is mostly flat or declining, the burden of mortality and hospitalization remains significant, especially with major disparities among younger Black men and women. Emerging risk factors and holistic management approaches may help improve the treatment and management of HF.

CIRCULATION RESEARCH (2021)

添加到收藏夹

Article Cardiac & Cardiovascular Systems

An automated computational image analysis pipeline for histological grading of cardiac allograft rejection

Eliot G. Peyster et al.

Summary: The study aimed to demonstrate that cellular rejection grades generated via computational histological analysis are comparable to those provided by expert pathologists, showing that the computational method can provide expert-quality rejection grading within the range of inter-grader variability seen among human pathologists.

EUROPEAN HEART JOURNAL (2021)

添加到收藏夹

Article Urology & Nephrology

Image Analysis Pipeline for Renal Allograft Evaluation and Fibrosis Quantification

Alton Brad Farris et al.

Summary: Digital pathology technology allows for automatic detection of glomeruli and selection of cortical regions of interest in kidney allograft biopsy specimens. The automatic fibrosis quantification was moderately correlated with pathologists' assessment, but not significantly associated with eGFR or allograft survival. This pipeline provides a promising method for developing and applying image analysis algorithms in kidney pathology.

KIDNEY INTERNATIONAL REPORTS (2021)

添加到收藏夹

Review Gastroenterology & Hepatology

Advances in Digital Pathology: From Artificial Intelligence to Label-Free Imaging

Frederik Grosserueschkamp et al.

Summary: In digital pathology, computer technology is utilized for tissue image analysis to draw conclusions about diseases. Future digital pathology will be significantly impacted by new innovative technologies (such as label-free infrared imaging), bringing major changes to the field.

VISCERAL MEDICINE (2021)

添加到收藏夹

Review Medicine, Research & Experimental

Developing image analysis pipelines of whole-slide images: Pre- and post-processing

Byron Smith et al.

Summary: Deep learning is pushing the boundaries of digital pathology by going beyond simple digitization and telemedicine, potentially becoming a disruptive technology that can reduce processing time and improve anomaly detection. However, integrating deep learning into standard laboratory workflow requires more steps than just training and testing a model.

JOURNAL OF CLINICAL AND TRANSLATIONAL SCIENCE (2021)

添加到收藏夹

Article Cardiac & Cardiovascular Systems

An automated computational image analysis pipeline for histological grading of cardiac allograft rejection

Eliot G. Peyster et al.

Summary: The study demonstrates that a computational histological analysis tool, CACHE-Grader, can provide expert-quality rejection grading that is on par with human pathologists, showing nearly identical performance in both internal and external validation sets. The tool has the ability to accurately reproduce the clinical standard for cellular rejection diagnosis and has superior sensitivity for high-grade rejection.

EUROPEAN HEART JOURNAL (2021)

添加到收藏夹

Review Anesthesiology