Artificial intelligence can accurately distinguish IgA nephropathy from diabetic nephropathy under Masson staining and becomes an important assistant for renal pathologists

Article Multidisciplinary Sciences

Abstracts written by ChatGPT fool scientists

Holly Else

NATURE (2023)

Add to Collection

Editorial Material Multidisciplinary Sciences

ChatGPT is fun, but not an author

H. Holden Thorp

SCIENCE (2023)

Add to Collection

Article Urology & Nephrology

Explainable Biomarkers for Automated Glomerular and Patient-Level Disease Classification

Matthew Nicholas Basso et al.

Summary: A study demonstrates that explainable biomarkers through machine learning can distinguish between different glomerular disorders at the light-microscopy level. Morphologic and microstructural texture features extracted using image analysis techniques are the best performing biomarkers. This computational approach has potential value in diagnosis and understanding disease pathogenesis.

KIDNEY360 (2022)

Add to Collection

Article Medical Informatics

Deep learning-based classification of kidney transplant pathology: a retrospective, multicentre, proof-of-concept study

Jesper Kers et al.

Summary: This study demonstrated that deep learning-based classification of transplant biopsies could aid in the pathological diagnosis of kidney allograft rejection.

LANCET DIGITAL HEALTH (2022)

Add to Collection

Review Urology & Nephrology

AI applications in renal pathology

Yuankai Huo et al.

Summary: The explosive growth of AI technologies, particularly in deep learning, has led to revolutionary applications in AI-assisted healthcare, including in renal pathology. However, successful integration of AI in renal pathology requires close interdisciplinary collaborations between computer scientists and renal pathologists. Understanding the high-level principles of AI technologies and optimizing AI techniques for renal pathology are crucial for future applications in this field.

KIDNEY INTERNATIONAL (2021)

Add to Collection

Article Microscopy

Deep learning for the classification of medical kidney disease: a pilot study for electron microscopy

Sean Hacking et al.

Summary: Artificial intelligence and cloud computing are playing a significant role in the field of medicine, particularly in histopathology. This study demonstrates the feasibility of using deep learning for identification of kidney diseases, showing good overall classification results.

ULTRASTRUCTURAL PATHOLOGY (2021)

Add to Collection

Article Engineering, Biomedical

Automated assessment of glomerulosclerosis and tubular atrophy using deep learning

Massimo Salvi et al.

Summary: This study introduces an automated algorithm, RENTAG, for segmenting and classifying glomerular and tubular structures in histopathological images, which shows excellent performance and has the potential to assist pathologists in diagnostic activities during kidney transplantation.

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS (2021)

Add to Collection

Review Biotechnology & Applied Microbiology

Diabetic Nephropathy: Challenges in Pathogenesis, Diagnosis, and Treatment

Nur Samsu

Summary: Diabetic nephropathy is the leading cause of end-stage renal disease worldwide and diagnosis and treatment pose challenges, requiring additional therapeutic interventions. In addition to standard therapy, vitamin D receptor activators, incretin-related drugs, and therapies targeting inflammation may also be promising for preventing the progression of DN.

BIOMED RESEARCH INTERNATIONAL (2021)

Add to Collection

Article Engineering, Biomedical

Deep-learning models for the detection and incidence prediction of chronic kidney disease and type 2 diabetes from retinal fundus images

Kang Zhang et al.

Summary: Deep-learning models trained on retinal fundus images can accurately identify chronic kidney disease and type 2 diabetes, as well as predict disease progression risk. These models demonstrate high accuracy in training and validation, providing reliable predictions for blood glucose and glomerular filtration rate.

NATURE BIOMEDICAL ENGINEERING (2021)

Add to Collection

Article Urology & Nephrology

Deep Learning-Based Segmentation and Quantification in Experimental Kidney Histopathology

Nassim Bouteldja et al.

Summary: This study utilized a convolutional neural network for accurate segmentation of kidney tissue in various species and disease models, showing high performance and providing a new high-throughput tool for pathology analysis.

JOURNAL OF THE AMERICAN SOCIETY OF NEPHROLOGY (2021)

Add to Collection

Review Endocrinology & Metabolism