Russell Taylor

Yuxin Chen, Anna Goodridge, Manish Sahu et al.

Purpose: Robotic assistance in otologic surgery can reduce the task load of operating surgeons during the removal of bone around the critical structures in the lateral skull base. However, safe deployment into the anatomical passageways necessitates the development of advanced sensing capabilities to actively limit the interaction forces between the surgical tools and critical anatomy. Methods: We introduce a surgical drill equipped with a force sensor that is capable of measuring accurate tool-tissue interaction forces to enable force control and feedback to surgeons. The design, calibration and validation of the force-sensing surgical drill mounted on a cooperatively controlled surgical robot are described in this work. Results: The force measurements on the tip of the surgical drill are validated with raw-egg drilling experiments, where a force sensor mounted below the egg serves as ground truth. The average root mean square error (RMSE) for points and path drilling experiments are 41.7 (pm 12.2) mN and 48.3 (pm 13.7) mN respectively. Conclusions: The force-sensing prototype measures forces with sub-millinewton resolution and the results demonstrate that the calibrated force-sensing drill generates accurate force measurements with minimal error compared to the measured drill forces. The development of such sensing capabilities is crucial for the safe use of robotic systems in a clinical context.

Russell Taylor, Benjamin Herbert, Michael Sana

Translating wordplay across languages presents unique challenges that have long confounded both professional human translators and machine translation systems. This research proposes a novel approach for translating puns from English to French by combining state-of-the-art large language models with specialized techniques for wordplay generation. Our methodology employs a three-stage approach. First, we establish a baseline using multiple frontier large language models with feedback based on a new contrastive learning dataset. Second, we implement a guided chain-of-thought pipeline with combined phonetic-semantic embeddings. Third, we implement a multi-agent generator-discriminator framework for evaluating and regenerating puns with feedback. Moving beyond the limitations of literal translation, our methodology's primary objective is to capture the linguistic creativity and humor of the source text wordplay, rather than simply duplicating its vocabulary. Our best runs earned first and second place in the CLEF JOKER 2025 Task 2 competition where they were evaluated manually by expert native French speakers. This research addresses a gap between translation studies and computational linguistics by implementing linguistically-informed techniques for wordplay translation, advancing our understanding of how language models can be leveraged to handle the complex interplay between semantic ambiguity, phonetic similarity, and the implicit cultural and linguistic awareness needed for successful humor.

Gregory Hager, Vijay Kumar, Robin Murphy et al.

The recent coronavirus pandemic has highlighted the many challenges faced by the healthcare, public safety, and economic systems when confronted with a surge in patients that require intensive treatment and a population that must be quarantined or shelter in place. The most obvious and pressing challenge is taking care of acutely ill patients while managing spread of infection within the care facility, but this is just the tip of the iceberg if we consider what could be done to prepare in advance for future pandemics. Beyond the obvious need for strengthening medical knowledge and preparedness, there is a complementary need to anticipate and address the engineering challenges associated with infectious disease emergencies. Robotic technologies are inherently programmable, and robotic systems have been adapted and deployed, to some extent, in the current crisis for such purposes as transport, logistics, and disinfection. As technical capabilities advance and as the installed base of robotic systems increases in the future, they could play a much more significant role in future crises. This report is the outcome of a virtual workshop co-hosted by the National Academy of Engineering (NAE) and the Computing Community Consortium (CCC) held on July 9-10, 2020. The workshop consisted of over forty participants including representatives from the engineering/robotics community, clinicians, critical care workers, public health and safety experts, and emergency responders. It identifies key challenges faced by healthcare responders and the general population and then identifies robotic/technological responses to these challenges. Then it identifies the key research/knowledge barriers that need to be addressed in developing effective, scalable solutions. Finally, the report ends with the following recommendations on how to implement this strategy.

Mareike Thies, Jan-Nico Zäch, Cong Gao et al.

During spinal fusion surgery, screws are placed close to critical nerves suggesting the need for highly accurate screw placement. Verifying screw placement on high-quality tomographic imaging is essential. C-arm Cone-beam CT (CBCT) provides intraoperative 3D tomographic imaging which would allow for immediate verification and, if needed, revision. However, the reconstruction quality attainable with commercial CBCT devices is insufficient, predominantly due to severe metal artifacts in the presence of pedicle screws. These artifacts arise from a mismatch between the true physics of image formation and an idealized model thereof assumed during reconstruction. Prospectively acquiring views onto anatomy that are least affected by this mismatch can, therefore, improve reconstruction quality. We propose to adjust the C-arm CBCT source trajectory during the scan to optimize reconstruction quality with respect to a certain task, i.e. verification of screw placement. Adjustments are performed on-the-fly using a convolutional neural network that regresses a quality index for possible next views given the current x-ray image. Adjusting the CBCT trajectory to acquire the recommended views results in non-circular source orbits that avoid poor images, and thus, data inconsistencies. We demonstrate that convolutional neural networks trained on realistically simulated data are capable of predicting quality metrics that enable scene-specific adjustments of the CBCT source trajectory. Using both realistically simulated data and real CBCT acquisitions of a semi-anthropomorphic phantom, we show that tomographic reconstructions of the resulting scene-specific CBCT acquisitions exhibit improved image quality particularly in terms of metal artifacts. Since the optimization objective is implicitly encoded in a neural network, the proposed approach overcomes the need for 3D information at run-time.

Cong Gao, Xingtong Liu, Wenhao Gu et al.

Differentiable rendering is a technique to connect 3D scenes with corresponding 2D images. Since it is differentiable, processes during image formation can be learned. Previous approaches to differentiable rendering focus on mesh-based representations of 3D scenes, which is inappropriate for medical applications where volumetric, voxelized models are used to represent anatomy. We propose a novel Projective Spatial Transformer module that generalizes spatial transformers to projective geometry, thus enabling differentiable volume rendering. We demonstrate the usefulness of this architecture on the example of 2D/3D registration between radiographs and CT scans. Specifically, we show that our transformer enables end-to-end learning of an image processing and projection model that approximates an image similarity function that is convex with respect to the pose parameters, and can thus be optimized effectively using conventional gradient descent. To the best of our knowledge, this is the first time that spatial transformers have been described for projective geometry. The source code will be made public upon publication of this manuscript and we hope that our developments will benefit related 3D research applications.

Robert Grupp, Mathias Unberath, Cong Gao et al.

Fluoroscopy is the standard imaging modality used to guide hip surgery and is therefore a natural sensor for computer-assisted navigation. In order to efficiently solve the complex registration problems presented during navigation, human-assisted annotations of the intraoperative image are typically required. This manual initialization interferes with the surgical workflow and diminishes any advantages gained from navigation. We propose a method for fully automatic registration using annotations produced by a neural network. Neural networks are trained to simultaneously segment anatomy and identify landmarks in fluoroscopy. Training data is obtained using an intraoperatively incompatible 2D/3D registration of hip anatomy. Ground truth 2D labels are established using projected 3D annotations. Intraoperative registration couples an intensity-based strategy with annotations inferred by the network and requires no human assistance. Ground truth labels were obtained in 366 fluoroscopic images across 6 cadaveric specimens. In a leave-one-subject-out experiment, networks obtained mean dice coefficients for left and right hemipelves, left and right femurs of 0.86, 0.87, 0.90, and 0.84. The mean 2D landmark error was 5.0 mm. The pelvis was registered within 1 degree for 86% of the images when using the proposed intraoperative approach with an average runtime of 7 seconds. In comparison, an intensity-only approach without manual initialization, registered the pelvis to 1 degree in 18% of images. We have created the first accurately annotated, non-synthetic, dataset of hip fluoroscopy. By using these annotations as training data for neural networks, state of the art performance in fluoroscopic segmentation and landmark localization was achieved. Integrating these annotations allows for a robust, fully automatic, and efficient intraoperative registration during fluoroscopic navigation of the hip.

Robert Grupp, Ryan Murphy, Rachel Hegeman et al.

Accurate and consistent mental interpretation of fluoroscopy to determine the position and orientation of acetabular bone fragments in 3D space is difficult. We propose a computer assisted approach that uses a single fluoroscopic view and quickly reports the pose of an acetabular fragment without any user input or initialization. Intraoperatively, but prior to any osteotomies, two constellations of metallic ball-bearings (BBs) are injected into the wing of a patient's ilium and lateral superior pubic ramus. One constellation is located on the expected acetabular fragment, and the other is located on the remaining, larger, pelvis fragment. The 3D locations of each BB are reconstructed using three fluoroscopic views and 2D/3D registrations to a preoperative CT scan of the pelvis. The relative pose of the fragment is established by estimating the movement of the two BB constellations using a single fluoroscopic view taken after osteotomy and fragment relocation. BB detection and inter-view correspondences are automatically computed throughout the processing pipeline. The proposed method was evaluated on a multitude of fluoroscopic images collected from six cadaveric surgeries performed bilaterally on three specimens. Mean fragment rotation error was 2.4 +/- 1.0 degrees, mean translation error was 2.1 +/- 0.6 mm, and mean 3D lateral center edge angle error was 1.0 +/- 0.5 degrees. The average runtime of the single-view pose estimation was 0.7 +/- 0.2 seconds. The proposed method demonstrates accuracy similar to other state of the art systems which require optical tracking systems or multiple-view 2D/3D registrations with manual input. The errors reported on fragment poses and lateral center edge angles are within the margins required for accurate intraoperative evaluation of femoral head coverage.

Robert Grupp, Yoshito Otake, Ryan Murphy et al.

Computer-aided surgical systems commonly use preoperative CT scans when performing pelvic osteotomies for intraoperative navigation. These systems have the potential to improve the safety and accuracy of pelvic osteotomies, however, exposing the patient to radiation is a significant drawback. In order to reduce radiation exposure, we propose a new smooth extrapolation method leveraging a partial pelvis CT and a statistical shape model (SSM) of the full pelvis in order to estimate a patient's complete pelvis. A SSM of normal, complete, female pelvis anatomy was created and evaluated from 42 subjects. A leave-one-out test was performed to characterise the inherent generalisation capability of the SSM. An additional leave-one-out test was conducted to measure performance of the smooth extrapolation method and an existing "cut-and-paste" extrapolation method. Unknown anatomy was simulated by keeping the axial slices of the patient's acetabulum intact and varying the amount of the superior iliac crest retained; from 0% to 15% of the total pelvis extent. The smooth technique showed an average improvement over the cut-and-paste method of 1.31 mm and 3.61 mm, in RMS and maximum surface error, respectively. With 5% of the iliac crest retained, the smoothly estimated surface had an RMS surface error of 2.21 mm, an improvement of 1.25 mm when retaining none of the iliac crest. This anatomical estimation method creates the possibility of a patient and surgeon benefiting from the use of a CAS system and simultaneously reducing the patient's radiation exposure.

Robert Grupp, Mehran Armand, Russell Taylor

Periacetabular osteotomy is a challenging surgical procedure for treating developmental hip dysplasia, providing greater coverage of the femoral head via relocation of a patient's acetabulum. Since fluoroscopic imaging is frequently used in the surgical workflow, computer-assisted X-Ray navigation of osteotomes and the relocated acetabular fragment should be feasible. We use intensity-based 2D/3D registration to estimate the pelvis pose with respect to fluoroscopic images, recover relative poses of multiple views, and triangulate landmarks which may be used for navigation. Existing similarity metrics are unable to consistently account for the inherent mismatch between the preoperative intact pelvis, and the intraoperative reality of a fractured pelvis. To mitigate the effect of this mismatch, we continuously estimate the relevance of each pixel to solving the registration and use these values as weightings in a patch-based similarity metric. Limiting computation to randomly selected subsets of patches results in faster runtimes than existing patch-based methods. A simulation study was conducted with random fragment shapes, relocations, and fluoroscopic views, and the proposed method achieved a 1.7 mm mean triangulation error over all landmarks, compared to mean errors of 3 mm and 2.8 mm for the non-patched and image-intensity-variance-weighted patch similarity metrics, respectively.

Robert Grupp, Hsin-Hong Chiang, Yoshito Otake et al.

Several methods to perform extrapolation of unknown anatomy were evaluated. The primary application is to enhance surgical procedures that may use partial medical images or medical images of incomplete anatomy. Le Fort-based, face-jaw-teeth transplant is one such procedure. From CT data of 36 skulls and 21 mandibles separate Statistical Shape Models of the anatomical surfaces were created. Using the Statistical Shape Models, incomplete surfaces were projected to obtain complete surface estimates. The surface estimates exhibit non-zero error in regions where the true surface is known; it is desirable to keep the true surface and seamlessly merge the estimated unknown surface. Existing extrapolation techniques produce non-smooth transitions from the true surface to the estimated surface, resulting in additional error and a less aesthetically pleasing result. The three extrapolation techniques evaluated were: copying and pasting of the surface estimate (non-smooth baseline), a feathering between the patient surface and surface estimate, and an estimate generated via a Thin Plate Spline trained from displacements between the surface estimate and corresponding vertices of the known patient surface. Feathering and Thin Plate Spline approaches both yielded smooth transitions. However, feathering corrupted known vertex values. Leave-one-out analyses were conducted, with 5% to 50% of known anatomy removed from the left-out patient and estimated via the proposed approaches. The Thin Plate Spline approach yielded smaller errors than the other two approaches, with an average vertex error improvement of 1.46 mm and 1.38 mm for the skull and mandible respectively, over the baseline approach.

Jan-Nico Zaech, Cong Gao, Bastian Bier et al.

Metal artifacts in computed tomography (CT) arise from a mismatch between physics of image formation and idealized assumptions during tomographic reconstruction. These artifacts are particularly strong around metal implants, inhibiting widespread adoption of 3D cone-beam CT (CBCT) despite clear opportunity for intra-operative verification of implant positioning, e.g. in spinal fusion surgery. On synthetic and real data, we demonstrate that much of the artifact can be avoided by acquiring better data for reconstruction in a task-aware and patient-specific manner, and describe the first step towards the envisioned task-aware CBCT protocol. The traditional short-scan CBCT trajectory is planar, with little room for scene-specific adjustment. We extend this trajectory by autonomously adjusting out-of-plane angulation. This enables C-arm source trajectories that are scene-specific in that they avoid acquiring "poor images", characterized by beam hardening, photon starvation, and noise. The recommendation of ideal out-of-plane angulation is performed on-the-fly using a deep convolutional neural network that regresses a detectability-rank derived from imaging physics.

Cong Gao, Mathias Unberath, Russell Taylor et al.

X-ray image based surgical tool navigation is fast and supplies accurate images of deep seated structures. Typically, recovering the 6 DOF rigid pose and deformation of tools with respect to the X-ray camera can be accurately achieved through intensity-based 2D/3D registration of 3D images or models to 2D X-rays. However, the capture range of image-based 2D/3D registration is inconveniently small suggesting that automatic and robust initialization strategies are of critical importance. This manuscript describes a first step towards leveraging semantic information of the imaged object to initialize 2D/3D registration within the capture range of image-based registration by performing concurrent segmentation and localization of dexterous surgical tools in X-ray images. We presented a learning-based strategy to simultaneously localize and segment dexterous surgical tools in X-ray images and demonstrate promising performance on synthetic and ex vivo data. We currently investigate methods to use semantic information extracted by the proposed network to reliably and robustly initialize image-based 2D/3D registration. While image-based 2D/3D registration has been an obvious focus of the CAI community, robust initialization thereof (albeit critical) has largely been neglected. This manuscript discusses learning-based retrieval of semantic information on imaged-objects as a stepping stone for such initialization and may therefore be of interest to the IPCAI community. Since results are still preliminary and only focus on localization, we target the Long Abstract category.

Shahriar Sefati, Ryan Murphy, Farshid Alambeigi et al.

Tracking and controlling the shape of continuum dexterous manipulators (CDM) in constraint environments is a challenging task. The imposed constraints and interaction with unknown obstacles may conform the CDM's shape and therefore demands for shape sensing methods which do not rely on direct line of sight. To address these issues, we integrate a novel Fiber Bragg Grating (FBG) shape sensing unit into a CDM, reconstruct the shape in real-time, and develop an optimization-based control algorithm using FBG tip position feedback. The CDM is designed for less-invasive treatment of osteolysis (bone degradation). To evaluate the performance of the feedback control algorithm when the CDM interacts with obstacles, we perform a set of experiments similar to the real scenario of the CDM interaction with soft and hard lesions during the treatment of osteolysis. In addition, we propose methods for identification of the CDM collisions with soft or hard obstacles using the jacobian information. Results demonstrate successful control of the CDM tip based on the FBG feedback and indicate repeatability and robustness of the proposed method when interacting with unknown obstacles.

Mathias Unberath, Javad Fotouhi, Jonas Hajek et al.

Interventional C-arm imaging is crucial to percutaneous orthopedic procedures as it enables the surgeon to monitor the progress of surgery on the anatomy level. Minimally invasive interventions require repeated acquisition of X-ray images from different anatomical views to verify tool placement. Achieving and reproducing these views often comes at the cost of increased surgical time and radiation dose to both patient and staff. This work proposes a marker-free "technician-in-the-loop" Augmented Reality (AR) solution for C-arm repositioning. The X-ray technician operating the C-arm interventionally is equipped with a head-mounted display capable of recording desired C-arm poses in 3D via an integrated infrared sensor. For C-arm repositioning to a particular target view, the recorded C-arm pose is restored as a virtual object and visualized in an AR environment, serving as a perceptual reference for the technician. We conduct experiments in a setting simulating orthopedic trauma surgery. Our proof-of-principle findings indicate that the proposed system can decrease the 2.76 X-ray images required per desired view down to zero, suggesting substantial reductions of radiation dose during C-arm repositioning. The proposed AR solution is a first step towards facilitating communication between the surgeon and the surgical staff, improving the quality of surgical image acquisition, and enabling context-aware guidance for surgery rooms of the future. The concept of technician-in-the-loop design will become relevant to various interventions considering the expected advancements of sensing and wearable computing in the near future.

Shahriar Sefati, Farshid Alambeigi, Iulian Iordachita et al.

Fiber Bragg Grating (FBG) has shown great potential in shape and force sensing of continuum manipulators (CM) and biopsy needles. In the recent years, many researchers have studied different manufacturing and modeling techniques of FBG-based force and shape sensors for medical applications. These studies mainly focus on obtaining shape and force information in a static (or quasi-static) environment. In this paper, however, we study and evaluate dynamic environments where the FBG data is affected by vibration caused by a harmonic force e.g. a rotational debriding tool harmonically exciting the CM and the FBG-based shape sensor. In such situations, appropriate pre-processing of the FBG signal is necessary in order to infer correct information from the raw signal. We look at an example of such dynamic environments in the less invasive treatment of osteolysis by studying the FBG data both in time- and frequency-domain in presence of vibration due to a debriding tool rotating inside the lumen of the CM.