Respiratory motion in living organisms is known to result in image blurring and loss of resolution, chiefly due to the lengthy acquisition times of the corresponding image acquisition methods. Optoacoustic tomography can effectively eliminate in vivo motion artifacts due to its inherent capacity for collecting image data from the entire imaged region following a single nanoseconds-duration laser pulse. However, multi-frame image analysis is often essential in applications relying on spectroscopic data acquisition or for scanning-based systems. Thereby, efficient methods to correct for image distortions due to motion are imperative. Herein, we demonstrate that efficient motion rejection in optoacoustic tomography can readily be accomplished by frame clustering during image acquisition, thus averting excessive data acquisition and post-processing. The algorithm’s efficiency for two- and three-dimensional imaging was validated with experimental whole-body mouse data acquired by spiral volumetric optoacoustic tomography (SVOT) and full-ring cross-sectional imaging scanners.
Images rendered with common optoacoustic system implementations are often afflicted with distortions and poor visibility of structures, hindering reliable image interpretation and quantification of bio-chrome distribution. Among the practical limitations contributing to artifactual reconstructions are insufficient tomographic detection coverage and suboptimal illumination geometry, as well as inability to accurately account for acoustic reflections and speed of sound heterogeneities in the imaged tissues. Here we developed a convolutional neural network (CNN) approach for enhancement of optoacoustic image quality which combines training on both time-resolved signals and tomographic reconstructions. Reference human finger data for training the CNN were recorded using a full-ring array system that provides optimal tomographic coverage around the imaged object. The reconstructions were further refined with a dedicated algorithm that minimizes acoustic reflection artifacts induced by acoustically mismatch structures, such as bones. The combined methodology is shown to outperform other learning-based methods solely operating on image-domain data.
Computer-aided drug discovery is an essential component of modern drug development. Therein, deep learning has become an important tool for rapid screening of billions of molecules in silico for potential hits containing desired chemical features. Despite its importance, substantial challenges persist in training these models, such as severe class imbalance, high decision thresholds, and lack of ground truth labels in some datasets. In this work we argue in favor of directly optimizing the receiver operating characteristic (ROC) in such cases, due to its robustness to class imbalance, its ability to compromise over different decision thresholds, certain freedom to influence the relative weights in this compromise, fidelity to typical benchmarking measures, and equivalence to positive/unlabeled learning. We also propose new training schemes (coherent mini-batch arrangement, and usage of out-of-batch samples) for cost functions based on the ROC, as well as a cost function based on the logAUC metric that facilitates early enrichment (i.e. improves performance at high decision thresholds, as often desired when synthesizing predicted hit compounds). We demonstrate that these approaches outperform standard deep learning approaches on a series of PubChem high-throughput screening datasets that represent realistic and diverse drug discovery campaigns on major drug target families.
Holistic deciphering of spatially-resolved delivery and biokinetics of nanoparticles (NPs) in the lung, along with the mobility of tissue-resident macrophages (TRMs) and their role in regulating NP cellular fate, remains unclear. Multimodal imaging and deep learning were applied to elucidate the longitudinal inter- and intra-acinar deposition features and regional dosimetry of NPs. The initial NP distribution patterns depended significantly on the pulmonary delivery routes and were most uniform for aerosol inhalation. Artificial intelligence-driven 3D airway segmentation enabled direct determination of bronchial and acinar NP dose. Longitudinal imaging uncovered an intra-acinar NP kinetics profile independent of delivery route. Contrary to the traditional notion of passive diffusion, this study reveals that long-term NP lung retention is facilitated by intra-acinar NP transport mediated by phagocytosis and patrolling of TRMs. Overall, this study elucidates the complexities of NP-lung delivery features and TRM immunity on the fate of biopersistent NPs.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.