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

Abstract

Aim Allograft rejection is a serious concern in heart transplant medicine. Though endomyocardial biopsy with histological grading is the diagnostic standard for rejection, poor inter-pathologist agreement creates significant clinical uncertainty. The aim of this investigation is to demonstrate that cellular rejection grades generated via computational histological analysis are on-par with those provided by expert pathologists Methods and results The study cohort consisted of 2472 endomyocardial biopsy slides originating from three major US transplant centres. The ‘Computer-Assisted Cardiac Histologic Evaluation (CACHE)-Grader’ pipeline was trained using an interpretable, biologically inspired, ‘hand-crafted’ feature extraction approach. From a menu of 154 quantitative histological features relating the density and orientation of lymphocytes, myocytes, and stroma, a model was developed to reproduce the 4-grade clinical standard for cellular rejection diagnosis. CACHE-grader interpretations were compared with independent pathologists and the ‘grade of record’, testing for non-inferiority (δ = 6%). Study pathologists achieved a 60.7% agreement [95% confidence interval (CI): 55.2–66.0%] with the grade of record, and pair-wise agreement among all human graders was 61.5% (95% CI: 57.0–65.8%). The CACHE-Grader met the threshold for non-inferiority, achieving a 65.9% agreement (95% CI: 63.4–68.3%) with the grade of record and a 62.6% agreement (95% CI: 60.3–64.8%) with all human graders. The CACHE-Grader demonstrated nearly identical performance in internal and external validation sets (66.1% vs. 65.8%), resilience to inter-centre variations in tissue processing/digitization, and superior sensitivity for high-grade rejection (74.4% vs. 39.5%, P < 0.001). Conclusion These results show that the CACHE-grader pipeline, derived using intuitive morphological features, can provide expert-quality rejection grading, performing within the range of inter-grader variability seen among human pathologists.

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

“…Specifically within cardiac transplant, several studies have used quantitative analyses to examine transplant EMBs in recent years. However, these works largely focused on acute rejection grading, either trying to develop automated systems to complete this task more reliably, 29,53 or piloting more expensive and complex in situ analyses to aid in discerning more benign versus more serious immune processes. 30 This work differs from these previous efforts, focusing on using clinical EMBs to predict a distant future outcome.…”

“…To date, no study has attempted to pursue a rigorous analysis of the histological data contained within routine EMB tissues as a means of generating better, more personalized CAV risk assessments. This can be considered an unmet need 26 and an emerging opportunity, 27 given the promise computational digital pathology analysis has shown for providing clinically valuable predictions in heart transplant medicine [28][29][30] and beyond. [31][32][33][34][35] In this proof-of-concept study, we perform computational image analysis of digitized EMB histology slides using an interpretable, handcrafted method to discover and measure novel histological biomarkers associated with the development of CAV.…”

“…Digitized slides underwent quality control assessments using HistoQC, an open-source, automated digital pathology tool for identifying artifacts and measuring slide quality that we have successfully applied to previous investigations in cardiac histology. 29,38…”

Deep Neural Network-Aided Histopathological Analysis of Myocardial Injury

“…DNN has been proved as a generalizable tool in assisting cardiovascular disease diagnosis, for example, evaluating cardiac allograft rejection by analyzing histopathological or multiplex immunofluorescence images ( 4 , 34 ). DNN has also led to breakthroughs in other imaging modalities for cardiovascular diagnosis or research, such as echocardiography, coronary artery calcium scoring, coronary computed tomography angiography, light-sheet microscopy, light-field imaging, etc.…”

“…EMB is a useful but invasive modality for making a definite diagnosis in diseases that are often difficult to diagnose by imaging modality alone. However, current grading methods in assessing histological patterns of myocardial injury are labor-intensive, error-prone, and suffer from a high inter-rater variability ( 4 ). Thus, a robust and reproducible method for the quantitative analysis of EMB is urgently needed.…”