Glaucoma is a major cause of blindness and is frequently associated with elevated intraocular pressure. The trabecular meshwork (TM), the tissue that primarily regulates intraocular pressure, is known to have reduced cellularity in glaucoma. Thus, stem cells, if properly delivered to the TM, may offer a novel therapeutic option for intraocular pressure control in glaucoma patients. For this purpose, targeted delivery of stem cells to the TM is desired. Here, we used magnetic nanoparticles (Prussian blue nanocubes [PBNCs]) to label mesenchymal stem cells and to magnetically steer them to the TM following injection into the eye’s anterior chamber. PBNC-labeled stem cells showed increased delivery to the TM vs. unlabeled cells after only 15-minute exposure to a magnetic field. Further, PBNC-labeled mesenchymal stem cells could be delivered to the entire circumference of the TM, which was not possible without magnetic steering. PBNCs did not affect mesenchymal stem cell viability or multipotency. We conclude that this labeling approach allows for targeted, relatively high-efficiency delivery of stem cells to the TM in clinically translatable time-scales, which are necessary steps towards regenerative medicine therapies for control of ocular hypertension in glaucoma patients.

Ultrasound imaging is essential for non-invasively diagnosing injuries where advanced diagnostics may not be possible. However, image interpretation remains a challenge as proper expertise may not be available. In response, artificial intelligence algorithms are being investigated to automate image analysis and diagnosis. Here, we highlight an image classification convolutional neural network for detecting shrapnel in ultrasound images. As an initial application, different shrapnel types and sizes were embedded first in a tissue mimicking phantom and then in swine thigh tissue. The algorithm architecture was optimized stepwise by minimizing validation loss and maximizing F1 score. The final algorithm design trained on tissue phantom image sets had an F1 score of 0.95 and an area under the ROC curve of 0.95. It maintained higher than a 90% accuracy for each of 8 shrapnel types. When trained only on swine image sets, the optimized algorithm format had even higher metrics: F1 and area under the ROC curve of 0.99. Overall, the algorithm developed resulted in strong classification accuracy for both the tissue phantom and animal tissue. This framework can be applied to other trauma relevant imaging applications such as internal bleeding to further simplify trauma medicine when resources and image interpretation are scarce.

Glaucoma, a leading cause of blindness, is characterized by an increase in intraocular pressure, which is largely determined by resistance to aqueous humour outflow through the trabecular meshwork (TM). In glaucoma, the cellularity of the TM is decreased, and, as a result, stem cell therapies for the TM represent a potential therapeutic option for restoring TM function and treating glaucoma patients. We here focus on adipose derived mesenchymal stem cells (MSCs) as a potential autologous cell source for TM regenerative medicine applications and describe characterization techniques at the messenger (reverse transcription-quantitative polymerase chain reaction), protein (western blotting, flow cytometry), and functional (contractility, phagocytosis) levels to distinguish MSCs from TM cells. We present a panel of 12 transcripts to allow: (a) suitable normalization of reverse transcription-quantitative polymerase chain reaction results across cell types and after exposure to potential differentiation stimuli; (b) distinguishing MSCs from TM cells; (c) distinguishing subtypes of TM cells; and (d) distinguishing TM cells from those in neighbouring tissue. At the protein level, dexamethasone induction of myocilin was a robust discriminating factor between MSCs and TM cells and was complemented by other protein markers. Finally, we show that contractility and phagocytosis differ between MSCs and TM cells. These methods are recommended for use in future differentiation studies to fully define if a functional TM-like phenotype is being achieved.

Ultrasound (US) imaging is a critical tool in emergency and military medicine because of its portability and immediate nature. However, proper image interpretation requires skill, limiting its utility in remote applications for conditions such as pneumothorax (PTX) which requires rapid intervention. Artificial intelligence has the potential to automate ultrasound image analysis for various pathophysiological conditions. Training models require large data sets and a means of troubleshooting in real-time for ultrasound integration deployment, and they also require large animal models or clinical testing. Here, we detail the development of a dynamic synthetic tissue phantom model for PTX and its use in training image classification algorithms. The model comprises a synthetic gelatin phantom cast in a custom 3D-printed rib mold and a lung mimicking phantom. When compared to PTX images acquired in swine, images from the phantom were similar in both PTX negative and positive mimicking scenarios. We then used a deep learning image classification algorithm, which we previously developed for shrapnel detection, to accurately predict the presence of PTX in swine images by only training on phantom image sets, highlighting the utility for a tissue phantom for AI applications.

Physiological Closed-Loop Controlled systems continue to take a growing part in clinical practice, offering possibilities of providing more accurate, goal-directed care while reducing clinicians’ cognitive and task load. These systems also provide a standardized approach for the clinical management of the patient, leading to a reduction in care variability across multiple dimensions. For fluid management and administration, the advantages of closed-loop technology are clear, especially in conditions that require precise care to improve outcomes, such as peri-operative care, trauma, and acute burn care. Controller design varies from simplistic to complex designs, based on detailed physiological models and adaptive properties that account for inter-patient and intra-patient variability; their maturity level ranges from theoretical models tested in silico to commercially available, FDA-approved products. This comprehensive scoping review was conducted in order to assess the current technological landscape of this field, describe the systems currently available or under development, and suggest further advancements that may unfold in the coming years. Ten distinct systems were identified and discussed.

Deep learning predictive models have the potential to simplify and automate medical imaging diagnostics by lowering the skill threshold for image interpretation. However, this requires predictive models that are generalized to handle subject variability as seen clinically. Here, we highlight methods to improve test accuracy of an image classifier model for shrapnel identification using tissue phantom image sets. Using a previously developed image classifier neural network—termed ShrapML—blind test accuracy was less than 70% and was variable depending on the training/test data setup, as determined by a leave one subject out (LOSO) holdout methodology. Introduction of affine transformations for image augmentation or MixUp methodologies to generate additional training sets improved model performance and overall accuracy improved to 75%. Further improvements were made by aggregating predictions across five LOSO holdouts. This was done by bagging confidences or predictions from all LOSOs or the top-3 LOSO confidence models for each image prediction. Top-3 LOSO confidence bagging performed best, with test accuracy improved to greater than 85% accuracy for two different blind tissue phantoms. This was confirmed by gradient-weighted class activation mapping to highlight that the image classifier was tracking shrapnel in the image sets. Overall, data augmentation and ensemble prediction approaches were suitable for creating more generalized predictive models for ultrasound image analysis, a critical step for real-time diagnostic deployment.