Facial recognition software (FRS) has historically been perceived as lacking the capability to identify individuals from cross-sectional medical images. Utilising such data for identification purposes was considered infeasible due to the substantial computational power and specialised technical expertise it would require. However, recent advancements in accessible artificial intelligence-based (AI-based) software and open-source tools have made these applications widely available and easy to use, raising new privacy concerns. This proof-of-concept was designed as a cross-sectional study and included participants with a verified online presence. Standard magnetic resonance imaging (MRI) head scans were performed on these participants, from which three-dimensional rendering (3DR) images were created using free and publicly available software. These images were used for face searches by free and publicly available FRS. Different head orientations and hairstyles were applied to the 3DR images to assess whether non-facial features influenced the FRS results. All results were obtained between the 10th of February 2024 and the 1st of March 2024. Face searches of 3DR images in a database containing over 800 million images from the World Wide Web (WWW) yielded correct matches for 50% of the participants in less than 10 min. The user-friendly software required minimal computational knowledge or resources, making this process broadly accessible. Modifying elements such as hairstyles or the orientation of the 3DR to better resemble actual photographs of the participants improved FRS matches. Current existing FRS can swiftly and accurately identify individuals from MRI head scans. This poses a significant privacy risk for participants in enrolled clinical trials and highlights the urgent need for improved data protection measures and increased sensitivity to ensure participant confidentiality. There was no funding source for this study.

Background: This review evaluates needle navigation technologies in minimally invasive cardiovascular surgery (MICS), identifying their strengths and limitations and the requirements for an ideal needle navigation system that features optimal guidance and easy adoption in clinical practice. Methods: A systematic search of PubMed, Web of Science, and IEEE databases up until June 2024 identified original studies on needle navigation in MICS. Eligible studies were those published within the past decade and that performed MICS requiring needle navigation technologies in adult patients. Animal studies, case reports, clinical trials, or laboratory experiments were excluded to focus on actively deployed techniques in clinical practice. Extracted data included the study year, modalities used, procedures performed, and the reported strengths and limitations, from which the requirements for an optimal needle navigation system were derived. Results: Of 36 eligible articles, 21 used ultrasound (US) for real-time imaging despite depth and needle visibility challenges. Computer tomography (CT)-guided fluoroscopy, cited in 19 articles, enhanced deep structure visualization but involved radiation risks. Magnetic resonance imaging (MRI), though excellent for soft-tissue contrast, was not used due to metallic tool incompatibility. Multimodal techniques, like US–fluoroscopy fusion, improved accuracy but added cost and workflow complexity. No single technology meets all the criteria for an ideal needle navigation system, which should combine real-time imaging, 3D spatial awareness, and tissue integrity feedback while being cost-effective and easily integrated into existing workflows. Conclusions: This review derived the criteria and obstacles an ideal needle navigation system must address before its clinical adoption, along with novel technological approaches that show potential to overcome those challenges. For instance, fusion technologies overlay information from multiple visual approaches within a single interface to overcome individual limitations. Additionally, emerging diagnostic methods like vibroacoustic sensing or optical fiber needles offer information from complementary sensory channels, augmenting visual approaches with insights into tissue integrity and structure, thereby paving the way for enhanced needle navigation systems in MICS.

Purpose: This proof of concept investigates the potential of vibroacoustic signals, originating from a needle tip during puncturing, as a method to differentiate ex vitro materials based on their structural characteristics. The main research question is whether the number and distribution of amplitude events in vibroacoustic waveforms correlates with the material structure, offering a feasible approach for a future real-time tissue differentiation in minimally invasive procedures. Methods: Two types of synthetic foams with different air pocket densities were punctured using a standard Quincke lumbar needle with cutting bevel. Vibroacoustic signals were recorded during the puncture, and the number of amplitude events detected per unit distance was analyzed. The structural differences of the foams were quantified by counting the number of air pockets per unit length. Part of the study was to also consider the impact of puncture / insertion speed on the signal characteristics. Results: A significant correlation was observed between the air pocket density of the foams and the number of detected events per unit distance. The foam with a higher air pocket density produced more detected events compared to the one with a lower density. Insertion speed of the needle did not significantly impact the number of detected events. Conclusion: The findings demonstrate that vibroacoustic signals hold information that allows the differentiation of materials based on their structural properties, laying the foundation for further research into their application in real-time tissue differentiation. Integrating vibroacoustic sensing into minimally invasive procedures could provide valuable additional information about tissue composition and integrity, potentially improving surgical precision in procedures such as tumor biopsies. Further research is needed to validate these findings with biological tissues and refine the technology for clinical use.

Robotic-assisted needle insertions lack haptic feedback, a key sensory cue for detecting tissue transitions and regulating puncture force. Modeling this feedback requires an understanding of soft-tissue biomechanics during insertion. Vibroacoustic signals generated by needle-tissue interactions may provide an additional sensing modality, but their interpretation requires validation against anatomical ground truth. Methods: A multimodal framework was developed to correlate vibroacoustic signals with high-resolution post-puncture microCT imaging in Manduca sexta, an insect model containing interconnected soft-tissue layers. A custom clip-on prototype recorded vibroacoustic signals during manual needle insertions. Three trajectory-marking strategies were evaluated to determine 3D coordinates of soft-tissue layer crossings and to assess correlations between acoustic events and anatomical transitions. Distances between layer crossings and needle displacement were used for spatiotemporal alignment of vibroacoustic and microCT data. Results: A microCT-compatible nylon string preserved puncture trajectories without artifacts and enabled high-resolution 3D reconstruction of anatomy and needle paths. Fusion of vibroacoustic and imaging data allowed identification of acoustic events associated with tissue entry, exit, and transitions. Conclusion: By integrating high-resolution microCT imaging with vibroacoustic sensing, this study establishes a biologically grounded framework for validating the relationship between vibroacoustic signals and anatomical tissue transitions during needle insertion, providing a basis for future quantitative analyses. Significance: This work provides initial evidence for correlating vibroacoustic signals recorded during needle insertion with corresponding microCT-identified tissue barriers. Because vibroacoustics offers substantially higher temporal and spatial resolution than most imaging modalities, it has the potential to improve tissue sensing and procedural accuracy in future needle-based interventions.

Clinical needle placement requires accurate information about tissue boundaries and transitions, which are often not reliably resolved by standard imaging modalities due to limited spatial resolution. Vibroacoustic signals can encode such information and could complement existing modalities with real-time feedback, but their signal composition and the influence of insertion depth remain unclear. By applying physical concepts from established force-based needle insertion models we assess whether tip-related excitations contribute characteristics relevant for tissue classification and whether shaft-interactions alter these components with insertion depth. A ResNet-18 model was trained on tip-dominated interactions and tested on the same tissue at the bottom of a stacked phantom, to assess the shaft contributions and depth-dependent effects. The model failed to classify similar tissues beneath an overlying layer. However, augmentation with shaft-dominated recordings elevated classification performance over 90%, indicating that tissue-discriminative information remained present. As augmented signals did not reproduce spectral characteristics of depth-affected signals, shaft interactions alone were insufficient to explain observed transformations, suggesting additional modification by depth-dependent propagation effects including attenuation and damping. This study proposes a conceptual model in which vibroacoustic needle signals are interpreted as a depth-dependent superposition of tip- and shaft-related excitations, which are modified during propagation along the shaft.