Related Experiment Video
Updated: Dec 25, 2025
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
Automated detection algorithm for C4d immunostaining showed comparable diagnostic performance to pathologists in
Gyuheon Choi1, Young-Gon Kim2, Haeyon Cho1
1Department of Pathology, University of Ulsan College of Medicine, Asan Medical Center, 88 Olympic-ro 43-gil, Songpa-gu, Seoul, 05505, South Korea.
Insights
A new deep learning algorithm for C4d immunostaining in renal allografts shows diagnostic performance comparable to pathologists. This AI tool accurately predicts C4d scores, aiding in transplant diagnostics.
Area of Science:
- Nephrology
- Pathology
- Artificial Intelligence in Medicine
Background:
- Deep learning-based image analysis offers potential for enhanced diagnostic accuracy and efficiency in pathology.
- C4d immunostaining in renal allografts is crucial for diagnosing antibody-mediated rejection.
- Variability in human interpretation necessitates objective and reproducible diagnostic tools.
Purpose of the Study:
- To assess the diagnostic performance of a proposed deep learning-based C4d detection algorithm in renal allografts.
- To compare the algorithm's diagnostic accuracy against experienced pathologists.
- To analyze the association of the algorithm's results with clinical data and patient outcomes.
Main Methods:
- A deep learning algorithm was developed for C4d detection in renal allograft immunostaining slides.
- Slides from two institutions were evaluated independently by three pathologists and the algorithm using Banff 2017 criteria.
- Algorithm performance was compared to individual pathologists and a consensus diagnosis; clinicopathological associations were analyzed.
Main Results:
- Pathologist reproducibility was fair to moderate (kappa 0.36-0.54), similar to algorithm-pathologist agreement (kappa 0.34-0.51).
- The algorithm achieved substantial concordance with the consensus diagnosis (kappa = 0.61).
- Algorithm-predicted C4d scores significantly correlated with microvascular inflammation, donor-specific antibody detection, and shorter graft survival.
Conclusions:
- The deep learning-based C4d detection algorithm demonstrates diagnostic performance comparable to human pathologists.
- The algorithm shows significant associations with key indicators of renal allograft dysfunction and poor outcomes.
- This AI tool holds promise for improving the objectivity and efficiency of C4d assessment in renal transplantation.
Abstract:
A deep learning-based image analysis could improve diagnostic accuracy and efficiency in pathology work. Recently, we proposed a deep learning-based detection algorithm for C4d immunostaining in renal allografts. The objective of this study is to assess the diagnostic performance of the algorithm by comparing pathologists' diagnoses and analyzing the associations of the algorithm with clinical data. C4d immunostaining slides of renal allografts were obtained from two different institutions (100 slides from the Asan Medical Center and 86 slides from the Seoul National University Hospital) and scanned using two different slide scanners. Three pathologists and the algorithm independently evaluated each slide according to the Banff 2017 criteria. Subsequently, they jointly reviewed the results for consensus scoring. The result of the algorithm was compared with that of each pathologist and the consensus diagnosis. Clinicopathological associations of the results of the algorithm with allograft survival, histologic evidence of microvascular inflammation, and serologic results for donor-specific antibodies were also analyzed. As a result, the reproducibility between the pathologists was fair to moderate (kappa 0.36-0.54), which is comparable to that between the algorithm and each pathologist (kappa 0.34-0.51). The C4d scores predicted by the algorithm achieved substantial concordance with the consensus diagnosis (kappa = 0.61), and they were significantly associated with remarkable microvascular inflammation (P = 0.001), higher detection rate of donor-specific antibody (P = 0.003), and shorter graft survival (P < 0.001). In conclusion, the deep learning-based C4d detection algorithm showed a diagnostic performance similar to that of the pathologists.
