arXiv subjects

Fabio Carrillo

Publications and source records attributed to Fabio Carrillo.

16 recordsLinked to original sources

arXiv2026

Open-H-Embodiment: A Large-Scale Dataset for Enabling Foundation Models in Medical Robotics

Autonomous medical robots hold promise to improve patient outcomes, reduce provider workload, democratize access to care, and enable superhuman precision. However, autonomous medical robotics has been limited by a fundamental data problem: existing medical robotic datasets are small, single-embodiment, and rarely shared openly, restricting the development of foundation models that the field needs to advance. We introduce Open-H-Embodiment, the largest open dataset of medical robotic video with synchronized kinematics to date, spanning more than 50 institutions and multiple robotic platforms including the CMR Versius, Intuitive Surgical's da Vinci, da Vinci Research Kit (dVRK), Rob Surgical BiTrack, Virtual Incision's MIRA, Moon Surgical Maestro, and a variety of custom systems, spanning surgical manipulation, robotic ultrasound, and endoscopy procedures. We demonstrate the research enabled by this dataset through two foundation models. GR00T-H is the first open foundation vision-language-action model for medical robotics, which is the only evaluated model to achieve full end-to-end task completion on a structured suturing benchmark (25% of trials vs. 0% for all others) and achieves 64% average success across a 29-step ex vivo suturing sequence. We also train Cosmos-H-Surgical-Simulator, the first action-conditioned world model to enable multi-embodiment surgical simulation from a single checkpoint, spanning nine robotic platforms and supporting in silico policy evaluation and synthetic data generation for the medical domain. These results suggest that open, large-scale medical robot data collection can serve as critical infrastructure for the research community, enabling advances in robot learning, world modeling, and beyond.

cs.RO↗

arXiv2025

Localising under the drape: proprioception in the era of distributed surgical robotic system

Despite their mechanical sophistication, surgical robots remain blind to their surroundings. This lack of spatial awareness causes collisions, system recoveries, and workflow disruptions, issues that will intensify with the introduction of distributed robots with independent interacting arms. Existing tracking systems rely on bulky infrared cameras and reflective markers, providing only limited views of the surgical scene and adding hardware burden in crowded operating rooms. We present a marker-free proprioception method that enables precise localisation of surgical robots under their sterile draping despite associated obstruction of visual cues. Our method solely relies on lightweight stereo-RGB cameras and novel transformer-based deep learning models. It builds on the largest multi-centre spatial robotic surgery dataset to date (1.4M self-annotated images from human cadaveric and preclinical in vivo studies). By tracking the entire robot and surgical scene, rather than individual markers, our approach provides a holistic view robust to occlusions, supporting surgical scene understanding and context-aware control. We demonstrate an example of potential clinical benefits during in vivo breathing compensation with access to tissue dynamics, unobservable under state of the art tracking, and accurately locate in multi-robot systems for future intelligent interaction. In addition, and compared with existing systems, our method eliminates markers and improves tracking visibility by 25%. To our knowledge, this is the first demonstration of marker-free proprioception for fully draped surgical robots, reducing setup complexity, enhancing safety, and paving the way toward modular and autonomous robotic surgery.

cs.RO↗

arXiv2025

Robust-Sub-Gaussian Model Predictive Control for Safe Ultrasound-Image-Guided Robotic Spinal Surgery

Safety-critical control using high-dimensional sensory feedback from optical data (e.g., images, point clouds) poses significant challenges in domains like autonomous driving and robotic surgery. Control can rely on low-dimensional states estimated from high-dimensional data. However, the estimation errors often follow complex, unknown distributions that standard probabilistic models fail to capture, making formal safety guarantees challenging. In this work, we introduce a novel characterization of these general estimation errors using sub-Gaussian noise with bounded mean. We develop a new technique for uncertainty propagation of proposed noise characterization in linear systems, which combines robust set-based methods with the propagation of sub-Gaussian variance proxies. We further develop a Model Predictive Control (MPC) framework that provides closed-loop safety guarantees for linear systems under the proposed noise assumption. We apply this MPC approach in an ultrasound-image-guided robotic spinal surgery pipeline, which contains deep-learning-based semantic segmentation, image-based registration, high-level optimization-based planning, and low-level robotic control. To validate the pipeline, we developed a realistic simulation environment integrating real human anatomy, robot dynamics, efficient ultrasound simulation, as well as in-vivo data of breathing motion and drilling force. Evaluation results in simulation demonstrate the potential of our approach for solving complex image-guided robotic surgery task while ensuring safety.

cs.RO↗

arXiv2025

SonoGym: High Performance Simulation for Challenging Surgical Tasks with Robotic Ultrasound

Ultrasound (US) is a widely used medical imaging modality due to its real-time capabilities, non-invasive nature, and cost-effectiveness. Robotic ultrasound can further enhance its utility by reducing operator dependence and improving access to complex anatomical regions. For this, while deep reinforcement learning (DRL) and imitation learning (IL) have shown potential for autonomous navigation, their use in complex surgical tasks such as anatomy reconstruction and surgical guidance remains limited -- largely due to the lack of realistic and efficient simulation environments tailored to these tasks. We introduce SonoGym, a scalable simulation platform for complex robotic ultrasound tasks that enables parallel simulation across tens to hundreds of environments. Our framework supports realistic and real-time simulation of US data from CT-derived 3D models of the anatomy through both a physics-based and a generative modeling approach. Sonogym enables the training of DRL and recent IL agents (vision transformers and diffusion policies) for relevant tasks in robotic orthopedic surgery by integrating common robotic platforms and orthopedic end effectors. We further incorporate submodular DRL -- a recent method that handles history-dependent rewards -- for anatomy reconstruction and safe reinforcement learning for surgery. Our results demonstrate successful policy learning across a range of scenarios, while also highlighting the limitations of current methods in clinically relevant environments. We believe our simulation can facilitate research in robot learning approaches for such challenging robotic surgery applications. Dataset, codes, and videos are publicly available at https://sonogym.github.io/.

cs.RO↗

arXiv2025

A Modular Edge Device Network for Surgery Digitalization

Future surgical care demands real-time, integrated data to drive informed decision-making and improve patient outcomes. The pressing need for seamless and efficient data capture in the OR motivates our development of a modular solution that bridges the gap between emerging machine learning techniques and interventional medicine. We introduce a network of edge devices, called Data Hubs (DHs), that interconnect diverse medical sensors, imaging systems, and robotic tools via optical fiber and a centralized network switch. Built on the NVIDIA Jetson Orin NX, each DH supports multiple interfaces (HDMI, USB-C, Ethernet) and encapsulates device-specific drivers within Docker containers using the Isaac ROS framework and ROS2. A centralized user interface enables straightforward configuration and real-time monitoring, while an Nvidia DGX computer provides state-of-the-art data processing and storage. We validate our approach through an ultrasound-based 3D anatomical reconstruction experiment that combines medical imaging, pose tracking, and RGB-D data acquisition.

eess.SY↗

arXiv2025

Acquiring Submillimeter-Accurate Multi-Task Vision Datasets for Computer-Assisted Orthopedic Surgery

Advances in computer vision, particularly in optical image-based 3D reconstruction and feature matching, enable applications like marker-less surgical navigation and digitization of surgery. However, their development is hindered by a lack of suitable datasets with 3D ground truth. This work explores an approach to generating realistic and accurate ex vivo datasets tailored for 3D reconstruction and feature matching in open orthopedic surgery. A set of posed images and an accurately registered ground truth surface mesh of the scene are required to develop vision-based 3D reconstruction and matching methods suitable for surgery. We propose a framework consisting of three core steps and compare different methods for each step: 3D scanning, calibration of viewpoints for a set of high-resolution RGB images, and an optical-based method for scene registration. We evaluate each step of this framework on an ex vivo scoliosis surgery using a pig spine, conducted under real operating room conditions. A mean 3D Euclidean error of 0.35 mm is achieved with respect to the 3D ground truth. The proposed method results in submillimeter accurate 3D ground truths and surgical images with a spatial resolution of 0.1 mm. This opens the door to acquiring future surgical datasets for high-precision applications.

cs.CV↗

arXiv2024

SurgPointTransformer: Vertebrae Shape Completion with RGB-D Data

State-of-the-art computer- and robot-assisted surgery systems heavily depend on intraoperative imaging technologies such as CT and fluoroscopy to generate detailed 3D visualization of the patient's anatomy. While imaging techniques are highly accurate, they are based on ionizing radiation and expose patients and clinicians. This study introduces an alternative, radiation-free approach for reconstructing the 3D spine anatomy using RGB-D data. Drawing inspiration from the 3D "mental map" that surgeons form during surgeries, we introduce SurgPointTransformer, a shape completion approach for surgical applications that can accurately reconstruct the unexposed spine regions from sparse observations of the exposed surface. Our method involves two main steps: segmentation and shape completion. The segmentation step includes spinal column localization and segmentation, followed by vertebra-wise segmentation. The segmented vertebra point clouds are then subjected to SurgPointTransformer, which leverages an attention mechanism to learn patterns between visible surface features and the underlying anatomy. For evaluation, we utilize an ex-vivo dataset of nine specimens. Their CT data is used to establish ground truth data that were used to compare to the outputs of our methods. Our method significantly outperforms the state-of-the-art baselines, achieving an average Chamfer Distance of 5.39, an F-Score of 0.85, an Earth Mover's Distance of 0.011, and a Signal-to-Noise Ratio of 22.90 dB. This study demonstrates the potential of our reconstruction method for 3D vertebral shape completion. It enables 3D reconstruction of the entire lumbar spine and surgical guidance without ionizing radiation or invasive imaging. Our work contributes to computer-aided and robot-assisted surgery, advancing the perception and intelligence of these systems.

eess.IV↗

arXiv2024

Virtual Reality for Immersive Education in Orthopedic Surgery Digital Twins

Virtual Reality technology, when integrated with Surgical Digital Twins (SDTs), offers significant potential in medical training and surgical planning. We present SurgTwinVR, a VR application that immerses users within an SDT and enables them to navigate a high-fidelity virtual replica of the surgical environment. SurgTwinVR is the first VR application to utilize a dynamic 3D environment that is a clone of a real surgery, encompassing the entire surgical scene, including the surgeon, anatomy, and instruments. Our system utilizes a SDT with important improvements for real-time rendering and features to showcase the potential benefits of such an application in surgical education.

cs.HC↗

arXiv2024

Creating a Digital Twin of Spinal Surgery: A Proof of Concept

Surgery digitalization is the process of creating a virtual replica of real-world surgery, also referred to as a surgical digital twin (SDT). It has significant applications in various fields such as education and training, surgical planning, and automation of surgical tasks. In addition, SDTs are an ideal foundation for machine learning methods, enabling the automatic generation of training data. In this paper, we present a proof of concept (PoC) for surgery digitalization that is applied to an ex-vivo spinal surgery. The proposed digitalization focuses on the acquisition and modelling of the geometry and appearance of the entire surgical scene. We employ five RGB-D cameras for dynamic 3D reconstruction of the surgeon, a high-end camera for 3D reconstruction of the anatomy, an infrared stereo camera for surgical instrument tracking, and a laser scanner for 3D reconstruction of the operating room and data fusion. We justify the proposed methodology, discuss the challenges faced and further extensions of our prototype. While our PoC partially relies on manual data curation, its high quality and great potential motivate the development of automated methods for the creation of SDTs.

cs.CV↗

arXiv2023

Safe Deep RL for Intraoperative Planning of Pedicle Screw Placement

Spinal fusion surgery requires highly accurate implantation of pedicle screw implants, which must be conducted in critical proximity to vital structures with a limited view of anatomy. Robotic surgery systems have been proposed to improve placement accuracy, however, state-of-the-art systems suffer from the limitations of open-loop approaches, as they follow traditional concepts of preoperative planning and intraoperative registration, without real-time recalculation of the surgical plan. In this paper, we propose an intraoperative planning approach for robotic spine surgery that leverages real-time observation for drill path planning based on Safe Deep Reinforcement Learning (DRL). The main contributions of our method are (1) the capability to guarantee safe actions by introducing an uncertainty-aware distance-based safety filter; and (2) the ability to compensate for incomplete intraoperative anatomical information, by encoding a-priori knowledge about anatomical structures with a network pre-trained on high-fidelity anatomical models. Planning quality was assessed by quantitative comparison with the gold standard (GS) drill planning. In experiments with 5 models derived from real magnetic resonance imaging (MRI) data, our approach was capable of achieving 90% bone penetration with respect to the GS while satisfying safety requirements, even under observation and motion uncertainty. To the best of our knowledge, our approach is the first safe DRL approach focusing on orthopedic surgeries.

cs.RO↗

arXiv2023

Next-generation Surgical Navigation: Marker-less Multi-view 6DoF Pose Estimation of Surgical Instruments

State-of-the-art research of traditional computer vision is increasingly leveraged in the surgical domain. A particular focus in computer-assisted surgery is to replace marker-based tracking systems for instrument localization with pure image-based 6DoF pose estimation using deep-learning methods. However, state-of-the-art single-view pose estimation methods do not yet meet the accuracy required for surgical navigation. In this context, we investigate the benefits of multi-view setups for highly accurate and occlusion-robust 6DoF pose estimation of surgical instruments and derive recommendations for an ideal camera system that addresses the challenges in the operating room. The contributions of this work are threefold. First, we present a multi-camera capture setup consisting of static and head-mounted cameras, which allows us to study the performance of pose estimation methods under various camera configurations. Second, we publish a multi-view RGB-D video dataset of ex-vivo spine surgeries, captured in a surgical wet lab and a real operating theatre and including rich annotations for surgeon, instrument, and patient anatomy. Third, we evaluate three state-of-the-art single-view and multi-view methods for the task of 6DoF pose estimation of surgical instruments and analyze the influence of camera configurations, training data, and occlusions on the pose accuracy and generalization ability. The best method utilizes five cameras in a multi-view pose optimization and achieves an average position and orientation error of 1.01 mm and 0.89{\deg} for a surgical drill as well as 2.79 mm and 3.33{\deg} for a screwdriver under optimal conditions. Our results demonstrate that marker-less tracking of surgical instruments is becoming a feasible alternative to existing marker-based systems.

cs.CV↗

arXiv2023

Automatic breach detection during spine pedicle drilling based on vibroacoustic sensing

Pedicle drilling is a complex and critical spinal surgery task. Detecting breach or penetration of the surgical tool to the cortical wall during pilot-hole drilling is essential to avoid damage to vital anatomical structures adjacent to the pedicle, such as the spinal cord, blood vessels, and nerves. Currently, the guidance of pedicle drilling is done using image-guided methods that are radiation intensive and limited to the preoperative information. This work proposes a new radiation-free breach detection algorithm leveraging a non-visual sensor setup in combination with deep learning approach. Multiple vibroacoustic sensors, such as a contact microphone, a free-field microphone, a tri-axial accelerometer, a uni-axial accelerometer, and an optical tracking system were integrated into the setup. Data were collected on four cadaveric human spines, ranging from L5 to T10. An experienced spine surgeon drilled the pedicles relying on optical navigation. A new automatic labeling method based on the tracking data was introduced. Labeled data was subsequently fed to the network in mel-spectrograms, classifying the data into breach and non-breach. Different sensor types, sensor positioning, and their combinations were evaluated. The best results in breach recall for individual sensors could be achieved using contact microphones attached to the dorsal skin (85.8\%) and uni-axial accelerometers clamped to the spinous process of the drilled vertebra (81.0\%). The best-performing data fusion model combined the latter two sensors with a breach recall of 98\%. The proposed method shows the great potential of non-visual sensor fusion for avoiding screw misplacement and accidental bone breaches during pedicle drilling and could be extended to further surgical applications.

cs.CV↗

arXiv2020

Three-Dimensional Automated Assessment of the Distal Radioulnar Joint Morphology according to Sigmoid Notch Surface Orientation

The aim of this study was to develop a new method for generating reproducible 3D measurements for the quantification of the distal radioulnar joint morphology. We hypothesized that automated 3D measurement of the ulnar variance and the sigmoid notch angle are comparable to those of the gold standard, while overcoming some of the drawbacks of conventional 2D measurements. Radiological data of healthy forearm bones of 53 adult subjects were included in the study. Automated measurements for the assessment of the sigmoid-notch morphology based on 3D landmarks were developed incorporating the subject-specific estimation of the cartilage surface orientation. A common anatomical reference was defined among the different imaging modalities and a comparison between the sigmoid notch angle and UV measurements was performed in radiographs, CT scans and 3D models. Finally, the developed UV measurements in 3D were compared to the method by radiographs in an experimental setup with 3D printed bone models. The proposed automated 3D analysis of notch subtype showed a significantly larger notch radius for negative notch angle compared to positive sigmoid notch angle subjects. Similar UV measurements were obtained in healthy joint morphologies with a high correlation between the radiographs and 3D measurements, for sigmoid notch angle and UV . In the experimental setup with a modified radial inclination, the UV was on average 1.13 mm larger in the radiographs compared to the 3D measurements, and 1.30 mm larger in the cases with a modified palmar tilt. The developed 3D measurements allowed to reliably quantify differences in the sigmoid notch subtypes.

physics.med-ph↗

arXiv2020

Digitalization of the IOM: A comprehensive cadaveric study for obtaining three-dimensional models and morphological properties of the forearm's interosseous membrane

State-of-the-art of preoperative planning for forearm orthopaedic surgeries is currently limited to simple bone procedures. The increasing interest of clinicians for more comprehensive analysis of complex pathologies often requires dynamic models, able to include the soft tissue influence into the preoperative process. Previous studies have shown that the interosseous membrane (IOM) influences forearm motion and stability, but due to the lack of morphological and biomechanical data, existing simulation models of the IOM are either too simple or clinically unreliable. This work aims to address this problematic by generating 3D morphological and tensile properties of the individual IOM structures. First, micro- and standard-CT acquisitions were performed on five fresh-frozen annotated cadaveric forearms for the generation of 3D models of the radius, ulna and each of the individual ligaments of the IOM. Afterwards, novel 3D methods were developed for the measurement of common morphological features, which were validated against established optical ex-vivo measurements. Finally, we investigated the individual tensile properties of each IOM ligament. The generated 3D morphological features can provide the basis for the future development of functional planning simulation of the forearm.

physics.med-ph↗

arXiv2020

Automatic Modelling of Human Musculoskeletal Ligaments -- Framework Overview and Model Quality Evaluation

Accurate segmentation of connective soft tissues is still a challenging task, which hinders the generation of corresponding geometric models for biomechanical computations. Alternatively, one could predict ligament insertion sites and then approximate the shapes, based on anatomical knowledge and morphological studies. Here, we describe a corresponding integrated framework for the automatic modelling of human musculoskeletal ligaments. We combine statistical shape modelling with geometric algorithms to automatically identify insertion sites, based on which geometric surface and volume meshes are created. For demonstrating a clinical use case, the framework has been applied to generate models of the interosseous membrane in the forearm. For the adoption to the forearm anatomy, ligament insertion sites in the statistical model were defined according to anatomical predictions following an approach proposed in prior work. For evaluation we compared the generated sites, as well as the ligament shapes, to data obtained from a cadaveric study, involving five forearms with a total of 15 ligaments. Our framework permitted the creation of 3D models approximating ligaments' shapes with good fidelity. However, we found that the statistical model trained with the state-of-the-art prediction of the insertion sites was not always reliable. Using that model, average mean square errors as well as Hausdorff distances of the meshes increased by more than one order of magnitude, as compared to employing the known insertion locations of the cadaveric study. Using the latter an average mean square error of 0.59 mm and an average Hausdorff distance of less than 7 mm resulted, for the complete set of ligaments. In conclusion, the presented approach for generating ligament shapes from insertion points appears to be feasible but the detection of the insertion sites with a SSM is too inaccurate.

cs.GR↗

arXiv2019

An Automatic Genetic Algorithm Framework for the Optimization of Three-dimensional Surgical Plans of Forearm Corrective Osteotomies

3D computer-assisted corrective osteotomy has become the state-of-the-art for surgical treatment of complex bone deformities. Despite available technologies, the automatic generation of clinically acceptable, ready-to-use preoperative planning solutions is currently not possible for such pathologies. Multiple contradicting and mutually dependent objectives have to be considered, as well as clinical and technical constraints, generally requiring iterative manual adjustments. This leads to unnecessary efforts and unbearable clinical costs, hindering also the quality of patient treatment. In this paper, we propose an optimization framework for the generation of ready-to-use preoperative planning solutions in a fully automatic fashion. An automatic diagnostic assessment using patient-specific 3D models is performed for 3D malunion quantification and definition of the optimization parameters. Afterward, clinical objectives are translated into the optimization module, and controlled through tailored fitness functions based on a weighted and multi-staged optimization approach. The optimization is based on a genetic algorithm capable of solving multi-objective optimization problems with non-linear constraints. The framework outputs a complete preoperative planning solution including position and orientation of the osteotomy plane, transformation to achieve the bone reduction, and position and orientation of the fixation plate and screws. A qualitative validation was performed on 36 consecutive cases of radius osteotomy where solutions generated by the optimization algorithm (OA) were compared against the gold standard (GS) solutions generated by experienced surgeons. Solutions were blinded and presented to 6 readers, who voted OA solutions to be better in 55% of the time. The quantitative evaluation was based on different error measurements, showing average improvements with respect to the GS.

physics.med-ph↗