ABSTRACT
The progress of incorporating deep learning in the field of medical image interpretation has been greatly hindered due to the tremendous cost and time associated with generating ground truth for supervised machine learning, alongside concerns about the inconsistent quality of images acquired. Active learning offers a potential solution to these problems of expanding dataset ground truth by algorithmically choosing the most informative samples for ground truth labeling. Still, this effort incurs the costs of human labeling, which needs minimization. Furthermore, automatic labeling approaches employing active learning often exhibit overfitting tendencies while selecting samples closely aligned with the training set distribution and excluding out-of-distribution samples, which could potentially improve the model's effectiveness. We propose that the majority of out-of-distribution instances can be attributed to inconsistent cross images. Since the FDA approved the first whole-slide image system for medical diagnosis in 2017, whole-slide images have provided enriched critical information to advance the field of automated histopathology. Here, we exemplify the benefits of a novel deep learning strategy that utilizes high-resolution whole-slide microscopic images. We quantitatively assess and visually highlight the inconsistencies within the whole-slide image dataset employed in this study. Accordingly, we introduce a deep learning-based preprocessing algorithm designed to normalize unknown samples to the training set distribution, effectively mitigating the overfitting issue. Consequently, our approach significantly increases the amount of automatic region-of-interest ground truth labeling on high-resolution whole-slide images using active deep learning. We accept 92% of the automatic labels generated for our unlabeled data cohort, expanding the labeled dataset by 845%. Additionally, we demonstrate expert time savings of 96% relative to manual expert ground-truth labeling.
ABSTRACT
Myocardial ischemia reperfusion injury (IRI) in acute coronary syndromes is a condition in which ischemic/hypoxic injury to cells subtended by the occluded vessel continues despite successful resolution of the thrombotic obstruction. For decades, most efforts to attenuate IRI have focused on interdicting singular molecular targets or pathways, but none have successfully transitioned to clinical use. In this work, we investigate a nanoparticle-based therapeutic strategy for profound but local thrombin inhibition that may simultaneously mitigate both thrombosis and inflammatory signaling pathways to limit myocardial IRI. Perfluorocarbon nanoparticles (PFC NP) were covalently coupled with an irreversible thrombin inhibitor, PPACK (Phe[D]-Pro-Arg-Chloromethylketone), and delivered intravenously to animals in a single dose prior to ischemia reperfusion injury. Fluorescent microscopy of tissue sections and 19F magnetic resonance images of whole hearts ex vivo demonstrated abundant delivery of PFC NP to the area at risk. Echocardiography at 24 h after reperfusion demonstrated preserved ventricular structure and improved function. Treatment reduced thrombin deposition, suppressed endothelial activation, inhibited inflammasome signaling pathways, and limited microvascular injury and vascular pruning in infarct border zones. Accordingly, thrombin inhibition with an extraordinarily potent but locally acting agent suggested a critical role for thrombin and a promising therapeutic strategy in cardiac IRI.
