FluoroSAM: A Language-aligned Foundation Model for X-ray Image Segmentation

Automated X-ray image segmentation would accelerate research and development in diagnostic and interventional precision medicine. Prior efforts have contributed task-specific models capable of solving specific image analysis problems, but the utility of these models is restricted to their particular task domain, and expanding to broader use requires additional data, labels, and retraining efforts. Recently, foundation models (FMs) -- machine learning models trained on large amounts of highly variable data thus enabling broad applicability -- have emerged as promising tools for automated image analysis. Existing FMs for medical image analysis focus on scenarios and modalities where objects are clearly defined by visually apparent boundaries, such as surgical tool segmentation in endoscopy. X-ray imaging, by contrast, does not generally offer such clearly delineated boundaries or structure priors. During X-ray image formation, complex 3D structures are projected in transmission onto the imaging plane, resulting in overlapping features of varying opacity and shape. To pave the way toward an FM for comprehensive and automated analysis of arbitrary medical X-ray images, we develop FluoroSAM, a language-aligned variant of the Segment-Anything Model, trained from scratch on 1.6M synthetic X-ray images. FluoroSAM is trained on data including masks for 128 organ types and 464 non-anatomical objects, such as tools and implants. In real X-ray images of cadaveric specimens, FluoroSAM is able to segment bony anatomical structures based on text-only prompting with 0.51 and 0.79 DICE with point-based refinement, outperforming competing SAM variants for all structures. FluoroSAM is also capable of zero-shot generalization to segmenting classes beyond the training set thanks to its language alignment, which we demonstrate for full lung segmentation on real chest X-rays.

Bimanual Manipulation of Steady Hand Eye Robots with Adaptive Sclera Force Control: Cooperative vs. Teleoperation Strategies

Performing intricate eye microsurgery, such as retinal vein cannulation (RVC), as a potential treatment for retinal vein occlusion (RVO), without the assistance of a surgical robotic system is very challenging to do safely. The main limitation has to do with the physiological hand tremor of surgeons. Robot-assisted eye surgery technology may resolve the problems of hand tremors and fatigue and improve the safety and precision of RVC. The Steady-Hand Eye Robot (SHER) is an admittance-based robotic system that can filter out hand tremors and enables ophthalmologists to manipulate a surgical instrument inside the eye cooperatively. However, the admittance-based cooperative control mode does not address crucial safety considerations, such as minimizing contact force between the surgical instrument and the sclera surface to prevent tissue damage. An adaptive sclera force control algorithm was proposed to address this limitation using an FBG-based force-sensing tool to measure and minimize the tool-sclera interaction force. Additionally, features like haptic feedback or hand motion scaling, which can improve the safety and precision of surgery, require a teleoperation control framework. We implemented a bimanual adaptive teleoperation (BMAT) control mode using SHER 2.0 and SHER 2.1 and compared its performance with a bimanual adaptive cooperative (BMAC) mode. Both BMAT and BMAC modes were tested in sitting and standing postures during a vessel-following experiment under a surgical microscope. It is shown, for the first time to the best of our knowledge in robot-assisted retinal surgery, that integrating the adaptive sclera force control algorithm with the bimanual teleoperation framework enables surgeons to safely perform bimanual telemanipulation of the eye without over-stretching it, even in the absence of registration between the two robots.

An Endoscopic Chisel: Intraoperative Imaging Carves 3D Anatomical Models

Purpose: Preoperative imaging plays a pivotal role in sinus surgery where CTs offer patient-specific insights of complex anatomy, enabling real-time intraoperative navigation to complement endoscopy imaging. However, surgery elicits anatomical changes not represented in the preoperative model, generating an inaccurate basis for navigation during surgery progression. Methods: We propose a first vision-based approach to update the preoperative 3D anatomical model leveraging intraoperative endoscopic video for navigated sinus surgery where relative camera poses are known. We rely on comparisons of intraoperative monocular depth estimates and preoperative depth renders to identify modified regions. The new depths are integrated in these regions through volumetric fusion in a truncated signed distance function representation to generate an intraoperative 3D model that reflects tissue manipulation. Results: We quantitatively evaluate our approach by sequentially updating models for a five-step surgical progression in an ex vivo specimen. We compute the error between correspondences from the updated model and ground-truth intraoperative CT in the region of anatomical modification. The resulting models show a decrease in error during surgical progression as opposed to increasing when no update is employed. Conclusion: Our findings suggest that preoperative 3D anatomical models can be updated using intraoperative endoscopy video in navigated sinus surgery. Future work will investigate improvements to monocular depth estimation as well as removing the need for external navigation systems. The resulting ability to continuously update the patient model may provide surgeons with a more precise understanding of the current anatomical state and paves the way toward a digital twin paradigm for sinus surgery.

Integrating 3D Slicer with a Dynamic Simulator for Situational Aware Robotic Interventions

Image-guided robotic interventions represent a transformative frontier in surgery, blending advanced imaging and robotics for improved precision and outcomes. This paper addresses the critical need for integrating open-source platforms to enhance situational awareness in image-guided robotic research. We present an open-source toolset that seamlessly combines a physics-based constraint formulation framework, AMBF, with a state-of-the-art imaging platform application, 3D Slicer. Our toolset facilitates the creation of highly customizable interactive digital twins, that incorporates processing and visualization of medical imaging, robot kinematics, and scene dynamics for real-time robot control. Through a feasibility study, we showcase real-time synchronization of a physical robotic interventional environment in both 3D Slicer and AMBF, highlighting low-latency updates and improved visualization.

Haptic-Assisted Collaborative Robot Framework for Improved Situational Awareness in Skull Base Surgery

Skull base surgery is a demanding field in which surgeons operate in and around the skull while avoiding critical anatomical structures including nerves and vasculature. While image-guided surgical navigation is the prevailing standard, limitation still exists requiring personalized planning and recognizing the irreplaceable role of a skilled surgeon. This paper presents a collaboratively controlled robotic system tailored for assisted drilling in skull base surgery. Our central hypothesis posits that this collaborative system, enriched with haptic assistive modes to enforce virtual fixtures, holds the potential to significantly enhance surgical safety, streamline efficiency, and alleviate the physical demands on the surgeon. The paper describes the intricate system development work required to enable these virtual fixtures through haptic assistive modes. To validate our system's performance and effectiveness, we conducted initial feasibility experiments involving a medical student and two experienced surgeons. The experiment focused on drilling around critical structures following cortical mastoidectomy, utilizing dental stone phantom and cadaveric models. Our experimental results demonstrate that our proposed haptic feedback mechanism enhances the safety of drilling around critical structures compared to systems lacking haptic assistance. With the aid of our system, surgeons were able to safely skeletonize the critical structures without breaching any critical structure even under obstructed view of the surgical site.

Enabling Mammography with Co-Robotic Ultrasound

Ultrasound (US) imaging is a vital adjunct to mammography in breast cancer screening and diagnosis, but its reliance on hand-held transducers often lacks repeatability and heavily depends on sonographers' skills. Integrating US systems from different vendors further complicates clinical standards and workflows. This research introduces a co-robotic US platform for repeatable, accurate, and vendor-independent breast US image acquisition. The platform can autonomously perform 3D volume scans or swiftly acquire real-time 2D images of suspicious lesions. Utilizing a Universal Robot UR5 with an RGB camera, a force sensor, and an L7-4 linear array transducer, the system achieves autonomous navigation, motion control, and image acquisition. The calibrations, including camera-mammogram, robot-camera, and robot-US, were rigorously conducted and validated. Governed by a PID force control, the robot-held transducer maintains a constant contact force with the compression plate during the scan for safety and patient comfort. The framework was validated on a lesion-mimicking phantom. Our results indicate that the developed co-robotic US platform promises to enhance the precision and repeatability of breast cancer screening and diagnosis. Additionally, the platform offers straightforward integration into most mammographic devices to ensure vendor-independence.

Cooperative vs. Teleoperation Control of the Steady Hand Eye Robot with Adaptive Sclera Force Control: A Comparative Study

A surgeon's physiological hand tremor can significantly impact the outcome of delicate and precise retinal surgery, such as retinal vein cannulation (RVC) and epiretinal membrane peeling. Robot-assisted eye surgery technology provides ophthalmologists with advanced capabilities such as hand tremor cancellation, hand motion scaling, and safety constraints that enable them to perform these otherwise challenging and high-risk surgeries with high precision and safety. Steady-Hand Eye Robot (SHER) with cooperative control mode can filter out surgeon's hand tremor, yet another important safety feature, that is, minimizing the contact force between the surgical instrument and sclera surface for avoiding tissue damage cannot be met in this control mode. Also, other capabilities, such as hand motion scaling and haptic feedback, require a teleoperation control framework. In this work, for the first time, we implemented a teleoperation control mode incorporated with an adaptive sclera force control algorithm using a PHANTOM Omni haptic device and a force-sensing surgical instrument equipped with Fiber Bragg Grating (FBG) sensors attached to the SHER 2.1 end-effector. This adaptive sclera force control algorithm allows the robot to dynamically minimize the tool-sclera contact force. Moreover, for the first time, we compared the performance of the proposed adaptive teleoperation mode with the cooperative mode by conducting a vessel-following experiment inside an eye phantom under a microscope.

A Quantitative Evaluation of Dense 3D Reconstruction of Sinus Anatomy from Monocular Endoscopic Video

Generating accurate 3D reconstructions from endoscopic video is a promising avenue for longitudinal radiation-free analysis of sinus anatomy and surgical outcomes. Several methods for monocular reconstruction have been proposed, yielding visually pleasant 3D anatomical structures by retrieving relative camera poses with structure-from-motion-type algorithms and fusion of monocular depth estimates. However, due to the complex properties of the underlying algorithms and endoscopic scenes, the reconstruction pipeline may perform poorly or fail unexpectedly. Further, acquiring medical data conveys additional challenges, presenting difficulties in quantitatively benchmarking these models, understanding failure cases, and identifying critical components that contribute to their precision. In this work, we perform a quantitative analysis of a self-supervised approach for sinus reconstruction using endoscopic sequences paired with optical tracking and high-resolution computed tomography acquired from nine ex-vivo specimens. Our results show that the generated reconstructions are in high agreement with the anatomy, yielding an average point-to-mesh error of 0.91 mm between reconstructions and CT segmentations. However, in a point-to-point matching scenario, relevant for endoscope tracking and navigation, we found average target registration errors of 6.58 mm. We identified that pose and depth estimation inaccuracies contribute equally to this error and that locally consistent sequences with shorter trajectories generate more accurate reconstructions. These results suggest that achieving global consistency between relative camera poses and estimated depths with the anatomy is essential. In doing so, we can ensure proper synergy between all components of the pipeline for improved reconstructions that will facilitate clinical application of this innovative technology.

Steady-Hand Eye Robot 3.0: Optimization and Benchtop Evaluation for Subretinal Injection

Subretinal injection methods and other procedures for treating retinal conditions and diseases (many considered incurable) have been limited in scope due to limited human motor control. This study demonstrates the next generation, cooperatively controlled Steady-Hand Eye Robot (SHER 3.0), a precise and intuitive-to-use robotic platform achieving clinical standards for targeting accuracy and resolution for subretinal injections. The system design and basic kinematics are reported and a deflection model for the incorporated delta stage and validation experiments are presented. This model optimizes the delta stage parameters, maximizing the global conditioning index and minimizing torsional compliance. Five tests measuring accuracy, repeatability, and deflection show the optimized stage design achieves a tip accuracy of <30 $\mu$m, tip repeatability of 9.3 $\mu$m and 0.02{\deg}, and deflections between 20-350 $\mu$m/N. Future work will use updated control models to refine tip positioning outcomes and will be tested on in vivo animal models.

Arc-to-line frame registration method for ultrasound and photoacoustic image-guided intraoperative robot-assisted laparoscopic prostatectomy

Purpose: To achieve effective robot-assisted laparoscopic prostatectomy, the integration of transrectal ultrasound (TRUS) imaging system which is the most widely used imaging modelity in prostate imaging is essential. However, manual manipulation of the ultrasound transducer during the procedure will significantly interfere with the surgery. Therefore, we propose an image co-registration algorithm based on a photoacoustic marker method, where the ultrasound / photoacoustic (US/PA) images can be registered to the endoscopic camera images to ultimately enable the TRUS transducer to automatically track the surgical instrument Methods: An optimization-based algorithm is proposed to co-register the images from the two different imaging modalities. The principles of light propagation and an uncertainty in PM detection were assumed in this algorithm to improve the stability and accuracy of the algorithm. The algorithm is validated using the previously developed US/PA image-guided system with a da Vinci surgical robot. Results: The target-registration-error (TRE) is measured to evaluate the proposed algorithm. In both simulation and experimental demonstration, the proposed algorithm achieved a sub-centimeter accuracy which is acceptable in practical clinics. The result is also comparable with our previous approach, and the proposed method can be implemented with a normal white light stereo camera and doesn't require highly accurate localization of the PM. Conclusion: The proposed frame registration algorithm enabled a simple yet efficient integration of commercial US/PA imaging system into laparoscopic surgical setting by leveraging the characteristic properties of acoustic wave propagation and laser excitation, contributing to automated US/PA image-guided surgical intervention applications.