Key result
Automatic computational analysis of digitalized histological images using machine learning techniques may help in the diagnosis of cardiac allograft rejection.
This editorial discusses the challenges of diagnosing cardiac allograft vasculopathy and rejection in heart transplant recipients, highlighting the potential of machine learning in analyzing endomyocardial biopsy images.
This editorial refers to ‘Prognostic value of comprehensive intracoronary physiology assessment early after heart transplantation’, by J.-M. Ahn et al., https://doi.org/10.1093/eurheartj/ehab568. In heart transplant (HTx) recipients, acute rejection represents the main early clinical concern, whereas cardiac allograft vasculopathy (CAV) remains a major cause of morbidity and mortality beyond the first year.1 , 2 Endomyocardial biopsy (EMB) constitutes the gold standard for the diagnosis of HTx rejection.1 , 2 However, this is an invasive procedure that needs to be performed serially and it is not free of complications.2 In addition, the grading of pathological findings may be challenging, despite the use of accepted international criteria and the advent of immunostaining for complement fixation and cell characterization.2 EMB is associated with significant interobserver variability.2 , 3 Recent data suggest that automatic computational analysis of digitalized histological images, using biologically inspired machine learning techniques for grading, including intuitive cellular morphological features (namely density and orientation of lymphocytes, myocytes, and stroma), may help in the diagnosis of cardiac allograft rejection.3
No takes yet. Share an insight, caveat, or question.
Alfonso et al. (2021) conducted an editorial in Heart transplantation. Automatic computational analysis of digitalized histological images using machine learning techniques may help in the diagnosis of cardiac allograft rejection.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: