Micropatterning is often used to engineer the surface properties of objects because it allows the enhancement or modification of specific functionalities without modification of the bulk material properties. Microneedle arrays have been explored in the past for drug delivery and enhancement of tissue anchoring; however, conventional methods are primarily limited to thick, planar substrates. Here, we demonstrate a method for the fabrication of microneedle arrays on thin flexible polyurethane substrates. These thin-film microneedle arrays can be used to fabricate balloons and other inflatable objects. In addition, these thin-filmed microneedles can be transferred, using thermal forming processes, to more complex 3D objects on which it would otherwise be difficult to directly pattern microneedles. This function is especially useful for medical devices, which require effective tissue anchorage but are a challenging target for micropatterning due to their 3D nonplanar shape, large size, and the complexity of the required micropatterns. Ultrathin flexible thermoplastic polyurethane microneedle arrays were fabricated from a polydimethylsiloxane (PDMS) mold. The technique was applied onto the nonplanar surface of rapidly prototyped soft robotic implantable polyurethane devices. We found that a microneedle-patterned surface can increase the anchorage of the device to a tissue by more than twofold. In summary, our soft lithographic patterning method can rapidly and inexpensively generate thin-film microneedle surfaces that can be used to produce balloons or enhance the properties of other 3D objects and devices.

With a growing geriatric population estimated to triple by 2050, minimally invasive procedures that are image-guided are becoming both more popular and necessary for treating a variety of diseases. To lower the learning curve for new procedures, it is necessary to develop better guidance systems and methods to analyze procedure performance. Since fluoroscopy remains the primary mode of visualizations, the ability to perform catheter tracking from fluoroscopic images is an important part of this endeavor. This paper explores the use of deep learning to perform the landmark detection of a catheter from fluoroscopic images in 3D-printed heart models. We show that a two-stage deep-convolutional-neural-network-based model architecture can provide improved performance by initially locating a region of interest before determining the coordinates of the catheter tip within the image. This model has an average error of less than 2% of the image resolution and can be performed within 4 milliseconds, allowing for its potential use for real-time intraprocedural tracking. Coordinate regression models have the advantage of directly outputting values that can be used for quantitative tracking in future applications and are easier to create ground truth values (~50× faster), as compared to semantic segmentation models that require entire masks to be made. Therefore, we believe this work has better long-term potential to be used for a broader class of cardiac devices, catheters, and guidewires.

Catheterization is a procedure used to diagnose and treat various cardiovascular diseases. Intracardiac echocardiography (ICE) is an emerging imaging modality that has gained popularity in these procedures due to its ability to provide high-resolution images of the heart and its surrounding structures in a minimally invasive manner. However, given its limited field of view, its orientation within the heart is difficult to judge simply from observing the acquired images. Therefore, ICE catheter tracking, which requires six degrees of freedom, would be useful to better guide interventionalists during a procedure. This work demonstrates a machine learning-based approach that has been trained to predict the roll angle of an ICE catheter using landmark scalar values extracted from bi-plane fluoroscopy images. The model consists of two fully connected deep neural networks that were trained on a dataset of bi-plane fluoroscopy images acquired from a 3D printed heart phantom. The results showed high accuracy in roll angle prediction, suggesting the ability to achieve 6 degrees of freedom tracking using bi-plane fluoroscopy that can be integrated into future navigation systems embedded into the c-arm, integrated within an AR/MR headset, or in other commercial navigation systems.

Uterine fibroids represent the highest prevalence of benign tumors in women, with reports ranging from 4.5% to 68.6%, with a significant bias towards African American women. For uterine fibroids, a significant decision is determining whether fibroids can be successfully removed using minimally invasive (MI) techniques or their removal requires open surgery. Currently, the standard-of-care for intra-procedural visualization for myomectomies is ultrasound, which has low image quality and requires a specially trained assistant. Currently, the state-of-the-art is to obtain a pre-procedural MRI scan of the patient, which can be used for diagnosis and pre-procedural planning. Although proven incredibly useful pre-procedurally, MRI scans are not often used intra-procedurally due to the inconvenient visualization as 2D slices, which are seen on 2D monitors that do not intuitively convey the depth or orientation of the fibroids, as needed to effectively perform myomectomies. To address this limitation, herein, we present the use of a mixed reality headset (i.e., Microsoft HoloLens 2), as a tool for intra-procedural image-guidance during a mock myomectomy of an ex vivo animal uterus. In this work, we created a patient-specific holographic rendering by performing image segmentation of an MRI scan of a custom-made uterine fibroid animal model. A physician qualitatively assessed the usefulness of the renderings for fibroid localization, as compared to the same visualization on a 2D monitor. In conclusion, the use of mixed reality as an intra-procedural image guidance tool for myomectomies was perceived as a better visualization technique that could lead to improvements in MI approaches and make them accessible to patients from lower socioeconomic populations.

Uterine fibroids are one of the leading health concerns for women worldwide, affecting up to 80% of women by the age of 50. While recent advancements have improved the diagnosis and treatment of fibroids, the current standard of care still faces important limitations due to the need for a personalized approach to treatment. Uterine fibroid embolization (UFE) has emerged as a promising minimally invasive alternative to traditional surgery, offering advantages such as shorter recovery times, fewer complications, and the preservation of the uterus. However, despite their highly reported effectiveness, only about 1% of eligible patients are offered UFE. This drastic underutilization is partially due to limited physician confidence in predicting patient-specific outcomes. To address this challenge, in this study, we aim to present an objective analysis of the factors influencing UFE success and introduce a scalable and interpretable machine learning (ML) system designed to support clinical decision-making. We have curated a dataset that includes 74 patients, with a total of 311 fibroids for our analysis. We have also developed two sets of ML models for predicting UFE procedure success based on a pre-operative MRI scan as the input. The first model predicts overall procedure success and the likelihood of relieving specific symptoms, achieving an accuracy of 75% (AUC = 0.74) for procedure outcome and 81–88% (AUC = 0.81–0.87) for different symptoms, respectively. The second set of models predicts the success of each individual fibroid responding to the treatment, achieving a 76% accuracy and 75% F-1 score. The AI models in this study can potentially provide patient-specific prediction of procedure effectiveness on both patient-level and fibroid-level, enhancing procedure referral accuracy.

The authors present in this study the development of a novel method for creating stretchable electronics from dual-layer flex printed circuit boards (flex-PCBs) as a platform for soft robotic sensor arrays (SRSAs) for cardiac voltage mapping applications. There is a crucial need for devices that utilize multiple sensors and provide high performance signal acquisition for cardiac mapping. Previously, our group demonstrated how single-layer flex-PCB can be postprocessed to create a stretchable electronic sensing array. In this work, a detailed fabrication process for creating a dual-layer multielectrode flex-PCB SRSA is presented, along with relevant parameters to achieve optimal postprocessing with a laser cutter. The dual-layer flex-PCB SRSA’s ability to acquire electrical signals is demonstrated both in vitro as well as in vivo on a Leporine cardiac surface. These SRSAs could be extended into full-chamber cardiac mapping catheter applications. Our results show a significant contribution towards the scalable use of dual-layer flex-PCB for stretchable electronics.