Show abstract - PDF - Reviews

We propose a novel diagnostic method for clonal hematopoiesis of indeterminate potential (CHIP), a condition characterized by the presence of somatic mutations in hematopoietic stem cells without detectable hematologic malignancy, using deep-learning techniques. We developed a convolutional neural network (CNN) to predict CHIP status using 4 different views from standard delayed gadolinium-enhanced cardiac MRI. We used 5-fold cross validation on 82 patients to assess the performance of our model. Different algorithms were compared to find the optimal patient-level prediction method using the image-level CNN predictions. We found that the best model had an AUC of 0.85 and an accuracy of 82%. We conclude that a deep learning-based diagnostic approach for CHIP is promising.
Hide abstract