Assessment of intraocular foreign body using high resolution 3D ultrasound imaging.

Ocular trauma often involves intraocular foreign bodies (IOFBs) that pose challenges in accurate diagnosis due to their size, shape, and material composition. In this study, we proposed a novel whole-eye 3D ophthalmic ultrasound B-scan (3D-UBS) system for automating image acquisition and improved 3D visualization, thereby improving sensitivity for detecting IOFBs. 3D-UBS utilizes 14 MHz Clarius L20 probe, a motorized translation stage, and a surgical microscope for precise placement and movement. The system's 3D point spread function (PSF) is 0.377 × 0.550 × 0.894 mm3 characterized by the full-width at half-maximum intensity values in the axial, lateral and elevation directions. Digital phantom and ex vivo ocular models were prepared using four types of IOFBs (i.e., plastic, wood, metal, and glass). Ex vivo models were imaged with both 3D-UBS and clinical computed tomography (CT). Image preprocessing was performed on 3D-UBS images to remove uneven illumination and speckle noise. Multiplanar reformatting in 3D-UBS provides optimal plane selection after acquisition, reducing the need for a trained ultrasonographer. 3D-UBS outperforms CT in contrast for wood and plastic, with mean contrast improvement of 2.43 and 1.84 times, respectively. 3D-UBS was able to identify wood and plastic IOFBs larger than 250 µm and 300 in diameter, respectively. CT, with its wider PSF, was only able to detect wood and plastic IOFBs larger than 600 and 550 µm, respectively. Although contrast was higher in CT for metal and glass IOFBs, 3D-UBS provided sufficient contrast to identify those. 3D-UBS provides an easy-to-use, non-expert imaging approach for identifying small IOFBs of different materials and related ocular injuries at the point of care.

Enhancing cardiovascular risk prediction through AI-enabled calcium-omics.

Whole-heart coronary calcium Agatston score is a well-established predictor of major adverse cardiovascular events (MACE), but it does not account for individual calcification features related to the pathophysiology of the disease (e.g., multiple-vessel disease, spread of the disease along the vessel, stable calcifications, numbers of lesions, and density). We used novel, hand-crafted calcification features (calcium-omics); Cox time-to-event modeling; elastic net; and up and down synthetic sampling methods for imbalanced data, to assess MACE risk. We used 2457 CT calcium score (CTCS) images enriched for MACE events from our large no-cost CLARIFY program (ClinicalTrials.gov Identifier: NCT04075162). Among calcium-omics features, numbers of calcifications, LAD mass, and diffusivity (a measure of spatial distribution) were especially important determinants of increased risk, with dense calcification (> 1000HU, stable calcifications) associated with reduced risk Our calcium-omics model with (training/testing, 80/20) gave C-index (80.5%/71.6%) and 2-year AUC (82.4%/74.8%). Although the C-index is notoriously impervious to model improvements, calcium-omics compared favorably to Agatston and gave a significant difference (P < 0.001). The calcium-omics model identified 73.5% of MACE cases in the high-risk group, a 13.2% improvement as compared to Agatston, suggesting that calcium-omics could be used to better identity candidates for intensive follow-up and therapies. The categorical net-reclassification index was NRI = 0.153. Our findings from this exploratory study suggest the utility of calcium-omics in improved risk prediction. These promising results will pave the way for more extensive, multi-institutional studies of calcium-omics.

AI prediction of cardiovascular events using opportunistic epicardial adipose tissue assessments from CT calcium score.

Background: Recent studies have used basic epicardial adipose tissue (EAT) assessments (e.g., volume and mean HU) to predict risk of atherosclerosis-related, major adverse cardiovascular events (MACE). Objectives: Create novel, hand-crafted EAT features, "fat-omics", to capture the pathophysiology of EAT and improve MACE prediction. Methods: We segmented EAT using a previously-validated deep learning method with optional manual correction. We extracted 148 radiomic features (morphological, spatial, and intensity) and used Cox elastic-net for feature reduction and prediction of MACE. Results: Traditional fat features gave marginal prediction (EAT-volume/EAT-mean-HU/BMI gave C-index 0.53/0.55/0.57, respectively). Significant improvement was obtained with 15 fat-omics features (C-index=0.69, test set). High-risk features included volume-of-voxels-having-elevated-HU-[-50, -30-HU] and HU-negative-skewness, both of which assess high HU, which as been implicated in fat inflammation. Other high-risk features include kurtosis-of-EAT-thickness, reflecting the heterogeneity of thicknesses, and EAT-volume-in-the-top-25%-of-the-heart, emphasizing adipose near the proximal coronary arteries. Kaplan-Meyer plots of Cox-identified, high- and low-risk patients were well separated with the median of the fat-omics risk, while high-risk group having HR 2.4 times that of the low-risk group (P<0.001). Conclusion: Preliminary findings indicate an opportunity to use more finely tuned, explainable assessments on EAT for improved cardiovascular risk prediction.

Deep learning segmentation of fibrous cap in intravascular optical coherence tomography images.

Thin-cap fibroatheroma (TCFA) is a prominent risk factor for plaque rupture. Intravascular optical coherence tomography (IVOCT) enables identification of fibrous cap (FC), measurement of FC thicknesses, and assessment of plaque vulnerability. We developed a fully-automated deep learning method for FC segmentation. This study included 32,531 images across 227 pullbacks from two registries (TRANSFORM-OCT and UHCMC). Images were semi-automatically labeled using our OCTOPUS with expert editing using established guidelines. We employed preprocessing including guidewire shadow detection, lumen segmentation, pixel-shifting, and Gaussian filtering on raw IVOCT (r,θ) images. Data were augmented in a natural way by changing θ in spiral acquisitions and by changing intensity and noise values. We used a modified SegResNet and comparison networks to segment FCs. We employed transfer learning from our existing much larger, fully-labeled calcification IVOCT dataset to reduce deep-learning training. Postprocessing with a morphological operation enhanced segmentation performance. Overall, our method consistently delivered better FC segmentation results (Dice: 0.837 ± 0.012) than other deep-learning methods. Transfer learning reduced training time by 84% and reduced the need for more training samples. Our method showed a high level of generalizability, evidenced by highly-consistent segmentations across five-fold cross-validation (sensitivity: 85.0 ± 0.3%, Dice: 0.846 ± 0.011) and the held-out test (sensitivity: 84.9%, Dice: 0.816) sets. In addition, we found excellent agreement of FC thickness with ground truth (2.95 ± 20.73 µm), giving clinically insignificant bias. There was excellent reproducibility in pre- and post-stenting pullbacks (average FC angle: 200.9 ± 128.0°/202.0 ± 121.1°). Our fully automated, deep-learning FC segmentation method demonstrated excellent performance, generalizability, and reproducibility on multi-center datasets. It will be useful for multiple research purposes and potentially for planning stent deployments that avoid placing a stent edge over an FC.

Deep learning segmentation of endothelial cell images using an active learning paradigm with guided label corrections.

Purpose: To create Guided Correction Software for informed manual editing of automatically generated corneal endothelial cell (EC) segmentations and apply it to an active learning paradigm to analyze a diverse set of post-keratoplasty EC images. Approach: An original U-Net model trained on 130 manually labeled post-Descemet stripping automated endothelial keratoplasty (EK) images was applied to 841 post-Descemet membrane EK images generating "uncorrected" cell border segmentations. Segmentations were then manually edited using the Guided Correction Software to create corrected labels. This dataset was split into 741 training and 100 testing EC images. U-Net and DeepLabV3+ were trained on the EC images and the corresponding uncorrected and corrected labels. Model performance was evaluated in a cell-by-cell analysis. Evaluation metrics included the number of over-segmentations, under-segmentations, correctly identified new cells, and endothelial cell density (ECD). Results: Utilizing corrected segmentations for training U-Net and DeepLabV3+ improved their performance. The average number of over- and under-segmentations per image was reduced from 23 to 11 with the corrected training set. Predicted ECD values generated by networks trained on the corrected labels were not significantly different than the ground truth counterparts (p=0.02, paired t-test). These models also correctly segmented a larger percentage of newly identified cells. The proposed Guided Correction Software and semi-automated approach reduced the time to accurately segment EC images from 15 to 30 to 5 min, an ∼80% decrease compared to manual editing. Conclusions: Guided Correction Software can efficiently label new training data for improved deep learning performance and generalization between EC datasets.

SLIC-Occ: functional segmentation of occupancy images improves precision of EC50 images.

BACKGROUND: Drug occupancy studies with positron emission tomography imaging are used routinely in early phase drug development trials. Recently, our group introduced the Lassen Plot Filter, an extended version of the standard Lassen plot to estimate voxel-level occupancy images. Occupancy images can be used to create an EC50 image by applying an Emax model at each voxel. Our goal was to apply functional clustering of occupancy images via a clustering algorithm and produce a more precise EC50 image while maintaining accuracy. METHOD: A digital brain phantom was used to create 10 occupancy images (corresponding to 10 different plasma concentrations of drug) that correspond to a ground truth EC50 image containing two bilateral local "hot spots" of high EC50 (region-1: 25; region-2: 50; background: 6-10 ng/mL). Maximum occupancy was specified as 0.85. An established noise model was applied to the simulated occupancy images and the images were smoothed. Simple Linear Iterative Clustering, an existing k-means clustering algorithm, was modified to segment a series of occupancy images into K clusters (which we call "SLIC-Occ"). EC50 images were estimated by nonlinear estimation at each cluster (post SLIC-Occ) and voxel (no clustering). Coefficient of variation images were estimated at each cluster and voxel, respectively. The same process was also applied to human occupancy data produced for a previously published study. RESULTS: Variability in EC50 estimates was reduced by more than 80% in the phantom data after application of SLIC-Occ to occupancy images with only minimal loss of accuracy. A similar, but more modest improvement was achieved in variability when SLIC-Occ was applied to human occupancy images. CONCLUSIONS: Our results suggest that functional segmentation of occupancy images via SLIC-Occ could produce more precise EC50 images and improve our ability to identify local "hot spots" of high effective affinity of a drug for its target(s).

Image harmonization and deep learning automated classification of plus disease in retinopathy of prematurity.

Purpose: Retinopathy of prematurity (ROP) is a retinal vascular disease affecting premature infants that can culminate in blindness within days if not monitored and treated. A disease stage for scrutiny and administration of treatment within ROP is "plus disease" characterized by increased tortuosity and dilation of posterior retinal blood vessels. The monitoring of ROP occurs via routine imaging, typically using expensive instruments ($50 to $140 K) that are unavailable in low-resource settings at the point of care. Approach: As part of the smartphone-ROP program to enable referrals to expert physicians, fundus images are acquired using smartphone cameras and inexpensive lenses. We developed methods for artificial intelligence determination of plus disease, consisting of a preprocessing pipeline to enhance vessels and harmonize images followed by deep learning classification. A deep learning binary classifier (plus disease versus no plus disease) was developed using GoogLeNet. Results: Vessel contrast was enhanced by 90% after preprocessing as assessed by the contrast improvement index. In an image quality evaluation, preprocessed and original images were evaluated by pediatric ophthalmologists from the US and South America with years of experience diagnosing ROP and plus disease. All participating ophthalmologists agreed or strongly agreed that vessel visibility was improved with preprocessing. Using images from various smartphones, harmonized via preprocessing (e.g., vessel enhancement and size normalization) and augmented in physically reasonable ways (e.g., image rotation), we achieved an area under the ROC curve of 0.9754 for plus disease on a limited dataset. Conclusions: Promising results indicate the potential for developing algorithms and software to facilitate the usage of cell phone images for staging of plus disease.

Load-sharing characteristics of stenting and post-dilation in heavily calcified coronary artery.

In this work, stenting in non-calcified and heavily calcified coronary arteries was quantified in terms of diameter-pressure relationships and load transfer from the balloon to the artery. The efficacy of post-dilation in non-calcified and heavily calcified coronary arteries was also characterized in terms of load sharing and the changes in tissue mechanics. Our results have shown that stent expansion exhibits a cylindrical shape in non-calcified lesions, while it exhibits a dog bone shape in heavily calcified lesions. Load-sharing analysis has shown that only a small portion of the pressure load (1.4 N, 0.8% of total pressure load) was transferred to the non-calcified lesion, while a large amount of the pressure load (19 N, 12%) was transferred to the heavily calcified lesion. In addition, the increasing inflation pressure (from 10 to 20 atm) can effectively increase the minimal lumen diameter (from 1.48 to 2.82 mm) of the heavily calcified lesion, the stress (from 1.5 to 8.4 MPa) and the strain energy in the calcification (1.77 mJ to 26.5 mJ), which are associated with the potential of calcification fracture. Results indicated that increasing inflation pressure can be an effective way to improve the stent expansion if a dog bone shape of the stenting profile is observed. Considering the risk of a balloon burst, our results support the design and application of the high-pressure balloon for post-dilation. This work also sheds some light on the stent design and choice of stent materials for improving the stent expansion at the dog bone region and mitigating stresses on arterial tissues.

Prediction of stent under-expansion in calcified coronary arteries using machine learning on intravascular optical coherence tomography images.

It can be difficult/impossible to fully expand a coronary artery stent in a heavily calcified coronary artery lesion. Under-expanded stents are linked to later complications. Here we used machine/deep learning to analyze calcifications in pre-stent intravascular optical coherence tomography (IVOCT) images and predicted the success of vessel expansion. Pre- and post-stent IVOCT image data were obtained from 110 coronary lesions. Lumen and calcifications in pre-stent images were segmented using deep learning, and lesion features were extracted. We analyzed stent expansion along the lesion, enabling frame, segmental, and whole-lesion analyses. We trained regression models to predict the post-stent lumen area and then computed the stent expansion index (SEI). Best performance (root-mean-square-error = 0.04 ± 0.02 mm2, r = 0.94 ± 0.04, p < 0.0001) was achieved when we used features from both lumen and calcification to train a Gaussian regression model for segmental analysis of 31 frames in length. Stents with minimum SEI > 80% were classified as "well-expanded;" others were "under-expanded." Under-expansion classification results (e.g., AUC = 0.85 ± 0.02) were significantly improved over a previous, simple calculation, as well as other machine learning solutions. Promising results suggest that such methods can identify lesions at risk of under-expansion that would be candidates for intervention lesion preparation (e.g., atherectomy).

Enhancing cardiovascular risk prediction through AI-enabled calcium-omics.

Background: Coronary artery calcium (CAC) is a powerful predictor of major adverse cardiovascular events (MACE). Traditional Agatston score simply sums the calcium, albeit in a non-linear way, leaving room for improved calcification assessments that will more fully capture the extent of disease. Objective: To determine if AI methods using detailed calcification features (i.e., calcium-omics) can improve MACE prediction. Methods: We investigated additional features of calcification including assessment of mass, volume, density, spatial distribution, territory, etc. We used a Cox model with elastic-net regularization on 2457 CT calcium score (CTCS) enriched for MACE events obtained from a large no-cost CLARIFY program (ClinicalTrials.gov Identifier: NCT04075162). We employed sampling techniques to enhance model training. We also investigated Cox models with selected features to identify explainable high-risk characteristics. Results: Our proposed calcium-omics model with modified synthetic down sampling and up sampling gave C-index (80.5%/71.6%) and two-year AUC (82.4%/74.8%) for (80:20, training/testing), respectively (sampling was applied to the training set only). Results compared favorably to Agatston which gave C-index (71.3%/70.3%) and AUC (71.8%/68.8%), respectively. Among calcium-omics features, numbers of calcifications, LAD mass, and diffusivity (a measure of spatial distribution) were important determinants of increased risk, with dense calcification (>1000HU) associated with lower risk. The calcium-omics model reclassified 63% of MACE patients to the high risk group in a held-out test. The categorical net-reclassification index was NRI=0.153. Conclusions: AI analysis of coronary calcification can lead to improved results as compared to Agatston scoring. Our findings suggest the utility of calcium-omics in improved prediction of risk.

Transport pathways and kinetics of cerebrospinal fluid tracers in mouse brain observed by dynamic contrast-enhanced MRI.

Recent studies have suggested the glymphatic system as a key mechanism of waste removal in the brain. Dynamic contrast-enhanced MRI (DCE-MRI) using intracisternally administered contrast agents is a promising tool for assessing glymphatic function in the whole brain. In this study, we evaluated the transport kinetics and distribution of three MRI contrast agents with vastly different molecular sizes in mice. Our results demonstrate that oxygen-17 enriched water (H217O), which has direct access to parenchymal tissues via aquaporin-4 water channels, exhibited significantly faster and more extensive transport compared to the two gadolinium-based contrast agents (Gd-DTPA and GadoSpin). Time-lagged correlation and clustering analyses also revealed different transport pathways for Gd-DTPA and H217O. Furthermore, there were significant differences in transport kinetics of the three contrast agents to the lateral ventricles, reflecting the differences in forces that drive solute transport in the brain. These findings suggest the size-dependent transport pathways and kinetics of intracisternally administered contrast agents and the potential of DCE-MRI for assessing multiple aspects of solute transport in the glymphatic system.

Load-sharing characteristics of stenting and post-dilation in heavily calcified coronary artery.

In this work, stenting in non-calcified and heavily calcified coronary arteries was quantified in terms of diameter-pressure relationships and load transfer from the balloon to the artery. The efficacy of post-dilation in non-calcified and heavily calcified coronary arteries was also characterized in terms of load sharing and the changes in tissue mechanics. Our results have shown that stent expansion exhibits a cylindrical shape in non-calcified lesions, while it exhibits a dog bone shape in heavily calcified lesions. Load-sharing analysis has shown that only a small portion of the pressure load (1.4 N, 0.8% of total pressure load) was transferred to the non-calcified lesion, while a large amount of the pressure load (19 N, 12%) was transferred to the heavily calcified lesion. In addition, the increasing inflation pressure (from 10 to 20 atm) can effectively increase the minimal lumen diameter (from 1.48 mm to 2.82 mm) of the heavily calcified lesion, the stress (from 1.5 MPa to 8.4 MPa) the strain energy in the calcification (1.77 mJ to 26.5 mJ), which associated with the potential of calcification fracture. Results indicated that increasing inflation pressure can be an effective way to improve the stent expansion if a dog bone shape of the stenting profile is observed. Considering the risk of a balloon burst, our results support the design and application of the high-pressure balloon for post-dilation.

Optimal slice thickness for improved accuracy of quantitative analysis of fluorescent cell and microsphere distribution in cryo-images.

Cryo-imaging has been effectively used to study the biodistribution of fluorescent cells or microspheres in animal models. Sequential slice-by-slice fluorescent imaging enables detection of fluorescent cells or microspheres for corresponding quantification of their distribution in tissue. However, if slices are too thin, there will be data overload and excessive scan times. If slices are too thick, then cells can be missed. In this study, we developed a model for detection of fluorescent cells or microspheres to aid optimal slice thickness determination. Key factors include: section thickness (X), fluorescent cell intensity (Ifluo), effective tissue attenuation coefficient (µT), and a detection threshold (T). The model suggests an optimal slice thickness value that provides near-ideal sensitivity while minimizing scan time. The model also suggests a correction method to compensate for missed cells in the case that image data were acquired with overly large slice thickness. This approach allows cryo-imaging operators to use larger slice thickness to expedite the scan time without significant loss of cell count. We validated the model using real data from two independent studies: fluorescent microspheres in a pig heart and fluorescently labeled stem cells in a mouse model. Results show that slice thickness and detection sensitivity relationships from simulations and real data were well-matched with 99% correlation and 2% root-mean-square (RMS) error. We also discussed the detection characteristics in situations where key assumptions of the model were not met such as fluorescence intensity variation and spatial distribution. Finally, we show that with proper settings, cryo-imaging can provide accurate quantification of the fluorescent cell biodistribution with remarkably high recovery ratios (number of detections/delivery). As cryo-imaging technology has been used in many biological applications, our optimal slice thickness determination and data correction methods can play a crucial role in further advancing its usability and reliability.

Deep-learning segmentation of fascicles from microCT of the human vagus nerve.

Introduction: MicroCT of the three-dimensional fascicular organization of the human vagus nerve provides essential data to inform basic anatomy as well as the development and optimization of neuromodulation therapies. To process the images into usable formats for subsequent analysis and computational modeling, the fascicles must be segmented. Prior segmentations were completed manually due to the complex nature of the images, including variable contrast between tissue types and staining artifacts. Methods: Here, we developed a U-Net convolutional neural network (CNN) to automate segmentation of fascicles in microCT of human vagus nerve. Results: The U-Net segmentation of ~500 images spanning one cervical vagus nerve was completed in 24 s, versus ~40 h for manual segmentation, i.e., nearly four orders of magnitude faster. The automated segmentations had a Dice coefficient of 0.87, a measure of pixel-wise accuracy, thus suggesting a rapid and accurate segmentation. While Dice coefficients are a commonly used metric to assess segmentation performance, we also adapted a metric to assess fascicle-wise detection accuracy, which showed that our network accurately detects the majority of fascicles, but may under-detect smaller fascicles. Discussion: This network and the associated performance metrics set a benchmark, using a standard U-Net CNN, for the application of deep-learning algorithms to segment fascicles from microCT images. The process may be further optimized by refining tissue staining methods, modifying network architecture, and expanding the ground-truth training data. The resulting three-dimensional segmentations of the human vagus nerve will provide unprecedented accuracy to define nerve morphology in computational models for the analysis and design of neuromodulation therapies.

Digital labeling for 3D histology: segmenting blood vessels without a vascular contrast agent using deep learning.

Recent advances in optical tissue clearing and three-dimensional (3D) fluorescence microscopy have enabled high resolution in situ imaging of intact tissues. Using simply prepared samples, we demonstrate here "digital labeling," a method to segment blood vessels in 3D volumes solely based on the autofluorescence signal and a nuclei stain (DAPI). We trained a deep-learning neural network based on the U-net architecture using a regression loss instead of a commonly used segmentation loss to achieve better detection of small vessels. We achieved high vessel detection accuracy and obtained accurate vascular morphometrics such as vessel length density and orientation. In the future, such digital labeling approach could easily be transferred to other biological structures.

Pericoronary Adipose Tissue Radiomics from Coronary Computed Tomography Angiography Identifies Vulnerable Plaques.

Pericoronary adipose tissue (PCAT) features on Computed Tomography (CT) have been shown to reflect local inflammation and increased cardiovascular risk. Our goal was to determine whether PCAT radiomics extracted from coronary CT angiography (CCTA) images are associated with intravascular optical coherence tomography (IVOCT)-identified vulnerable-plaque characteristics (e.g., microchannels (MC) and thin-cap fibroatheroma (TCFA)). The CCTA and IVOCT images of 30 lesions from 25 patients were registered. The vessels with vulnerable plaques were identified from the registered IVOCT images. The PCAT-radiomics features were extracted from the CCTA images for the lesion region of interest (PCAT-LOI) and the entire vessel (PCAT-Vessel). We extracted 1356 radiomic features, including intensity (first-order), shape, and texture features. The features were reduced using standard approaches (e.g., high feature correlation). Using stratified three-fold cross-validation with 1000 repeats, we determined the ability of PCAT-radiomics features from CCTA to predict IVOCT vulnerable-plaque characteristics. In the identification of TCFA lesions, the PCAT-LOI and PCAT-Vessel radiomics models performed comparably (Area Under the Curve (AUC) ± standard deviation 0.78 ± 0.13, 0.77 ± 0.14). For the identification of MC lesions, the PCAT-Vessel radiomics model (0.89 ± 0.09) was moderately better associated than the PCAT-LOI model (0.83 ± 0.12). In addition, both the PCAT-LOI and the PCAT-Vessel radiomics model identified coronary vessels thought to be highly vulnerable to a similar standard (i.e., both TCFA and MC; 0.88 ± 0.10, 0.91 ± 0.09). The most favorable radiomic features tended to be those describing the texture and size of the PCAT. The application of PCAT radiomics can identify coronary vessels with TCFA or MC, consistent with IVOCT. Furthermore, the use of CCTA radiomics may improve risk stratification by noninvasively detecting vulnerable-plaque characteristics that are only visible with IVOCT.

Transport Pathways and Kinetics of Cerebrospinal Fluid Tracers in Mouse Brain Observed by Dynamic Contrast-Enhanced MRI.

Background: Recent studies have suggested the glymphatic system as a solute transport pathway and waste removal mechanism in the brain. Imaging intracisternally administered tracers provides the opportunity of assessing various aspects of the glymphatic function. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) allows the evaluation of both the kinetics and spatial distribution of tracer transport in the whole brain. However, assessing mouse glymphatic function by DCE-MRI has been challenged by the small size of a mouse brain and the limited volume of fluids that can be delivered intracisternally without significantly altering the intracranial pressure. Further, previous studies in rats suggest that assessment of glymphatic function by DCE-MRI is dependent on the molecular size of the contrast agents. Methods: We established and validated an intracisternal infusion protocol in mice that allowed the measurements of the entire time course of contrast agent transport for 2 hours. The transport kinetics and distribution of three MRI contrast agents with drastically different molecular weights (MWs): Gd-DTPA (MW=661.8 Da, n=7), GadoSpin-P (MW=200 kDa, n=6), and oxygen-17 enriched water (H 2 17 O, MW=19 Da, n=7), were investigated. Results: The transport of H 2 17 O was significantly faster and more extensive than the two gadolinium-based contrast agents. Time-lagged correlation analysis and clustering analysis comparing the kinetics of Gd-DTPA and H 2 17 O transport also showed different cluster patterns and lag time between different regions of the brain, suggesting different transport pathways for H 2 17 O because of its direct access to parenchymal tissues via the aquaporin-4 water channels. Further, there were also significant differences in the transport kinetics of the three tracers to the lateral ventricles, which reflects the differences in forces that drive tracer transport in the brain. Conclusions: Comparison of the transport kinetics and distribution of three MRI contrast agents with different molecular sizes showed drastically different transport profiles and clustering patterns, suggesting that the transport pathways and kinetics in the glymphatic system are size-dependent.

Machine Learning Analysis of Postkeratoplasty Endothelial Cell Images for the Prediction of Future Graft Rejection.

Purpose: This study developed machine learning (ML) classifiers of postoperative corneal endothelial cell images to identify postkeratoplasty patients at risk for allograft rejection within 1 to 24 months of treatment. Methods: Central corneal endothelium specular microscopic images were obtained from 44 patients after Descemet membrane endothelial keratoplasty (DMEK), half of whom had experienced graft rejection. After deep learning segmentation of images from all patients' last and second-to-last imaging, time points prior to rejection were analyzed (175 and 168, respectively), and 432 quantitative features were extracted assessing cellular spatial arrangements and cell intensity values. Random forest (RF) and logistic regression (LR) models were trained on novel-to-this-application features from single time points, delta-radiomics, and traditional morphometrics (endothelial cell density, coefficient of variation, hexagonality) via 10 iterations of threefold cross-validation. Final assessments were evaluated on a held-out test set. Results: ML classifiers trained on novel-to-this-application features outperformed those trained on traditional morphometrics for predicting future graft rejection. RF and LR models predicted post-DMEK patients' allograft rejection in the held-out test set with >0.80 accuracy. RF models trained on novel features from second-to-last time points and delta-radiomics predicted post-DMEK patients' rejection with >0.70 accuracy. Cell-graph spatial arrangement, intensity, and shape features were most indicative of graft rejection. Conclusions: ML classifiers successfully predicted future graft rejections 1 to 24 months prior to clinically apparent rejection. This technology could aid clinicians to identify patients at risk for graft rejection and guide treatment plans accordingly. Translational Relevance: Our software applies ML techniques to clinical images and enhances patient care by detecting preclinical keratoplasty rejection.

OCTOPUS - Optical coherence tomography plaque and stent analysis software.

Background and objective: Compared with other imaging modalities, intravascular optical coherence tomography (IVOCT) has significant advantages for guiding percutaneous coronary interventions, assessing their outcomes, and characterizing plaque components. To aid IVOCT research studies, we developed the Optical Coherence TOmography PlaqUe and Stent (OCTOPUS) analysis software, which provides highly automated, comprehensive analysis of coronary plaques and stents in IVOCT images. Methods: User specifications for OCTOPUS were obtained from detailed, iterative discussions with IVOCT analysts in the Cardiovascular Imaging Core Laboratory at University Hospitals Cleveland Medical Center, a leading laboratory for IVOCT image analysis. To automate image analysis results, the software includes several important algorithmic steps: pre-processing, deep learning plaque segmentation, machine learning identification of stent struts, and registration of pullbacks for sequential comparisons. Intuitive, interactive visualization and manual editing of segmentations were included in the software. Quantifications include stent deployment characteristics (e.g., stent area and stent strut malapposition), strut level analysis, calcium angle, and calcium thickness measurements. Interactive visualizations include (x,y) anatomical, en face, and longitudinal views with optional overlays (e.g., segmented calcifications). To compare images over time, linked visualizations were enabled to display up to four registered vessel segments at a time. Results: OCTOPUS has been deployed for nearly 1 year and is currently being used in multiple IVOCT studies. Underlying plaque segmentation algorithm yielded excellent pixel-wise results (86.2% sensitivity and 0.781 F1 score). Using OCTOPUS on 34 new pullbacks, we determined that following automated segmentation, only 13% and 23% of frames needed any manual touch up for detailed lumen and calcification labeling, respectively. Only up to 3.8% of plaque pixels were modified, leading to an average editing time of only 7.5 s/frame, an approximately 80% reduction compared to manual analysis. Regarding stent analysis, sensitivity and precision were both greater than 90%, and each strut was successfully classified as either covered or uncovered with high sensitivity (94%) and specificity (90%). We demonstrated use cases for sequential analysis. To analyze plaque progression, we loaded multiple pullbacks acquired at different points (e.g., pre-stent, 3-month follow-up, and 18-month follow-up) and evaluated frame-level development of in-stent neo-atherosclerosis. In ex vivo cadaver experiments, the OCTOPUS software enabled visualization and quantitative evaluation of irregular stent deployment in the presence of calcifications identified in pre-stent images. Conclusions: We introduced and evaluated the clinical application of a highly automated software package, OCTOPUS, for quantitative plaque and stent analysis in IVOCT images. The software is currently used as an offline tool for research purposes; however, the software's embedded algorithms may also be useful for real-time treatment planning.