With the advent of robot-assisted surgery, the role of data-driven approaches to integrate statistics and machine learning is growing rapidly with prominent interests in objective surgical skill assessment. However, most existing work requires translating robot motion kinematics into intermediate features or gesture segments that are expensive to extract, lack efficiency, and require significant domain-specific knowledge. We propose an analytical deep learning framework for skill assessment in surgical training. A deep convolutional neural network is implemented to map multivariate time series data of the motion kinematics to individual skill levels. We perform experiments on the public minimally invasive surgical robotic dataset, JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS). Our proposed learning model achieved a competitive accuracy of 92.5%, 95.4%, and 91.3%, in the standard training tasks: Suturing, Needle-passing, and Knot-tying, respectively. Without the need of engineered features or carefully-tuned gesture segmentation, our model can successfully decode skill information from raw motion profiles via end-to-end learning. Meanwhile, the proposed model is able to
We introduce the notion of round surgery diagrams in $S^3$ for representing 3-manifolds similar to Dehn surgery diagrams. We give a correspondence between a certain class of round surgery diagrams and Dehn surgery diagrams for 3-manifolds. As a consequence, we recover Asimov's result, stating that any closed connected oriented 3-manifold can be obtained by a round surgery on a framed link in $S^3$. There may be more than one round surgery diagram giving rise to the same 3-manifold. Thus, it is natural to ask whether there is a version of Kirby Calculus for round surgery diagrams, similar to the case of Dehn surgery diagrams with integral framings. In this direction, we define four types of moves on round surgery diagrams such that any two round surgery diagrams corresponding to the same 3-manifold can be obtained one from another by a finite sequence of these moves, thereby establishing a version of Kirby Calculus. As an application, we prove the existence of taut foliations, hence the existence of tight contact structures on 3-manifolds obtained by round 1-surgery on fibred links with two components on $S^3$.
We study the effect of surgery on transverse knots in contact 3-manifolds. In particular, we investigate the effect of such surgery on open books, the Heegaard Floer contact invariant, and tightness. The overarching theme of this paper is to show that in many contexts, surgery on transverse knots is more natural than surgery on Legendrian knots. Besides reinterpreting surgery on Legendrian knots in terms of transverse knots, our main results on are in two complementary directions: conditions under which inadmissible transverse surgery (\textit{cf.\@} positive contact surgery on Legendrian knots) preserves tightness, and conditions under which it creates overtwistedness. In the first direction, we give the first result on the tightness of inadmissible transverse surgery for contact manifolds with vanishing Heegaard Floer contact invariant. In particular, inadmissible transverse surgery on the connected binding of a genus $g$ open book that supports a tight contact structure preserves tightness if the surgery coefficient is greater than $2g-1$. In the second direction, along with more general statements, we deduce a partial generalisation to a result of Lisca and Stipsicz: when $L$ i
The recent Segment Anything Model (SAM) 2 has demonstrated remarkable foundational competence in semantic segmentation, with its memory mechanism and mask decoder further addressing challenges in video tracking and object occlusion, thereby achieving superior results in interactive segmentation for both images and videos. Building upon our previous empirical studies, we further explore the zero-shot segmentation performance of SAM 2 in robot-assisted surgery based on prompts, alongside its robustness against real-world corruption. For static images, we employ two forms of prompts: 1-point and bounding box, while for video sequences, the 1-point prompt is applied to the initial frame. Through extensive experimentation on the MICCAI EndoVis 2017 and EndoVis 2018 benchmarks, SAM 2, when utilizing bounding box prompts, outperforms state-of-the-art (SOTA) methods in comparative evaluations. The results with point prompts also exhibit a substantial enhancement over SAM's capabilities, nearing or even surpassing existing unprompted SOTA methodologies. Besides, SAM 2 demonstrates improved inference speed and less performance degradation against various image corruption. Although slightly u
Concept erasure in text-to-image diffusion models is crucial for mitigating harmful content, yet existing methods often compromise generative quality. We introduce Semantic Surgery, a novel training-free, zero-shot framework for concept erasure that operates directly on text embeddings before the diffusion process. It dynamically estimates the presence of target concepts in a prompt and performs a calibrated vector subtraction to neutralize their influence at the source, enhancing both erasure completeness and locality. The framework includes a Co-Occurrence Encoding module for robust multi-concept erasure and a visual feedback loop to address latent concept persistence. As a training-free method, Semantic Surgery adapts dynamically to each prompt, ensuring precise interventions. Extensive experiments on object, explicit content, artistic style, and multi-celebrity erasure tasks show our method significantly outperforms state-of-the-art approaches. We achieve superior completeness and robustness while preserving locality and image quality (e.g., 93.58 H-score in object erasure, reducing explicit content to just 1 instance, and 8.09 H_a in style erasure with no quality degradation).
Quantum error correction (QEC) plays a crucial role in correcting noise and paving the way for fault-tolerant quantum computing. This field has seen significant advancements, with new quantum error correction codes emerging regularly to address errors effectively. Among these, topological codes, particularly surface codes, stand out for their low error thresholds and feasibility for implementation in large-scale quantum computers. However, these codes are restricted to encoding a single qubit. Lattice surgery is crucial for enabling interactions among multiple encoded qubits or between the lattices of a surface code, ensuring that its sophisticated error-correcting features are maintained without significantly increasing the operational overhead. Lattice surgery is pivotal for scaling QECCs across more extensive quantum systems. Despite its critical importance, comprehending lattice surgery is challenging due to its inherent complexity, demanding a deep understanding of intricate quantum physics and mathematical concepts. This paper endeavors to demystify lattice surgery, making it accessible to those without a profound background in quantum physics or mathematics. This work explor
Surgery on a knot in $S^3$ is said to be an alternating surgery if it yields the double branched cover of an alternating link. The main theoretical contribution is to show that the set of alternating surgery slopes is algorithmically computable and to establish several structural results. Furthermore, we calculate the set of alternating surgery slopes for many examples of knots, including all hyperbolic knots in the SnapPy census. These examples exhibit several interesting phenomena including strongly invertible knots with a unique alternating surgery and asymmetric knots with two alternating surgery slopes. We also establish upper bounds on the set of alternating surgeries, showing that an alternating surgery slope on a hyperbolic knot satisfies $|p/q| \leq 3g(K)+4$. Notably, this bound applies to lens space surgeries, thereby strengthening the known genus bounds from the conjecture of Goda and Teragaito.
Benchmarking the performance of complex systems such as rail networks, renewable generation assets and national economies is central to transport planning, regulation and macroeconomic analysis. Classical frontier methods, notably Data Envelopment Analysis (DEA) and Stochastic Frontier Analysis (SFA), estimate an efficient frontier in the observed input-output space and define efficiency as distance to this frontier, but rely on restrictive assumptions on the production set and only indirectly address heterogeneity and scale effects. We propose Geometric Manifold Analysis (GeMA), a latent manifold frontier framework implemented via a productivity-manifold variational autoencoder (ProMan-VAE). Instead of specifying a frontier function in the observed space, GeMA represents the production set as the boundary of a low-dimensional manifold embedded in the joint input-output space. A split-head encoder learns latent variables that capture technological structure and operational inefficiency. Efficiency is evaluated with respect to the learned manifold, endogenous peer groups arise as clusters in latent technology space, a quotient construction supports scale-invariant benchmarking, and
It is known that any contact 3-manifold can be obtained by rational contact Dehn surgery along a Legendrian link L in the standard tight contact 3-sphere. We define and study various versions of contact surgery numbers, the minimal number of components of a surgery link L describing a given contact 3-manifold under consideration. In the first part of the paper, we relate contact surgery numbers to other invariants in terms of various inequalities. In particular, we show that the contact surgery number of a contact manifold is bounded from above by the topological surgery number of the underlying topological manifold plus three. In the second part, we compute contact surgery numbers of all contact structures on the 3-sphere. Moreover, we completely classify the contact structures with contact surgery number one on $S^1\times S^2$, the Poincaré homology sphere, and the Brieskorn sphere $Σ(2,3,7)$. We conclude that there exist infinitely many non-isotopic contact structures on each of the above manifolds which cannot be obtained by a single rational contact surgery from the standard tight contact $3$-sphere. We further obtain results for the 3-torus and lens spaces. As one ingredient
For a nullhomologous Legendrian knot in a closed contact 3-manifold Y we consider a contact structure obtained by positive rational contact surgery. We prove that in this situation the Heegaard Floer contact invariant of Y is mapped by a surgery cobordism to the contact invariant of the result of contact surgery. In addition we characterize the spin-c structure on the cobordism that induces the relevant map. As a consequence we determine necessary and sufficient conditions for the nonvanishing of the contact invariant after rational surgery when Y is the standard 3-sphere, generalizing previous results of Lisca-Stipsicz and Golla. In fact our methods allow direct calculation of the contact invariant in terms of the rational surgery mapping cone of Ozsváth and Szabó. The proof involves a construction called reducible open book surgery, which reduces in special cases to the capping-off construction studied by Baldwin.
BACKGROUND: Clinical factors influence surgery duration. This study also investigated non-clinical effects. METHODS: 22 months of data about thoracic operations in a large hospital in China were reviewed. Linear and nonlinear regression models were used to predict the duration of the operations. Interactions among predictors were also considered. RESULTS: Surgery duration decreased with the number of operations a surgeon performed in a day (P<0.001). Also, it was found that surgery duration decreased with the number of operations allocated to an OR as long as there were no more than four surgeries per day in the OR (P<0.001), but increased with the number of operations if it was more than four (P<0.01). The duration of surgery was affected by its position in a sequence of surgeries performed by a surgeon. In addition, surgeons exhibited different patterns of the effects of surgery type for surgeries in different positions in the day. CONCLUSIONS: Surgery duration was affected not only by clinical effects but also some non-clinical effects. Scheduling and allocation decisions significantly influenced surgery duration.
Purpose: Interventions at the otobasis operate in the narrow region of the temporal bone where several highly sensitive organs define obstacles with minimal clearance for surgical instruments. Nonlinear trajectories for potential minimally-invasive interventions can provide larger distances to risk structures and optimized orientations of surgical instruments, thus improving clinical outcomes when compared to existing linear approaches. In this paper, we present fast and accurate planning methods for such nonlinear access paths. Methods: We define a specific motion planning problem in SE(3) = R3 x SO(3) with notable constraints in computation time and goal pose that reflect the requirements of temporal bone surgery.We then present k-RRT-Connect: two suitable motion planners based on bidirectional Rapidly-exploring Random Trees (RRT) to solve this problem efficiently. Results: The benefits of k-RRT-Connect are demonstrated on real CT data of patients. Their general performance is shown on a large set of realistic synthetic anatomies. We also show that these new algorithms outperform state of the art methods based on circular arcs or Bezier-Splines when applied to this specific probl
Suppose $K$ is a hyperbolic knot in a solid torus $V$ intersecting a meridian disk $D$ twice. We will show that if $K$ is not the Whitehead knot and the frontier of a regular neighborhood of $K \cup D$ is incompressible in the knot exterior, then $K$ admits at most one exceptional surgery, which must be toroidal. Embedding $V$ in $S^3$ gives infinitely many knots $K_n$ with a slope $r_n$ corresponding to a slope $r$ of $K$ in $V$. If $r$ surgery on $K$ in $V$ is toroidal then either all but at most three $K_n(r_n)$ are toroidal, or they are all reducible or small Seifert fibered with two common singular fiber indices. These will be used to classify exceptional surgeries on wrapped Montesinos knots in solid torus, obtained by connecting the top endpoints of a Montesinos tangle to the bottom endpoints by two arcs wrapping around the solid torus.
This thesis is concerned with the question of when the double branched cover of an alternating knot can arise by Dehn surgery on a knot in $S^3$. We approach this problem using a surgery obstruction, first developed by Greene, which combines Donaldson's Diagonalization Theorem with the $d$-invariants of Ozsv{á}th and Szab{ó}'s Heegaard Floer homology. This obstruction shows that if the double branched cover of an alternating knot or link $L$ arises by surgery on $S^3$, then for any alternating diagram the lattice associated to the Goeritz matrix takes the form of a changemaker lattice. By analyzing the structure of changemaker lattices, we show that the double branched cover of $L$ arises by non-integer surgery on $S^3$ if and only if $L$ has an alternating diagram which can be obtained by rational tangle replacement on an almost-alternating diagram of the unknot. When one considers half-integer surgery the resulting tangle replacement is simply a crossing change. This allows us to show that an alternating knot has unknotting number one if and only if it has an unknotting crossing in every alternating diagram. These techniques also produce several other interesting results: they ha
Background Analyzing kinematic and video data can help identify potentially erroneous motions that lead to sub-optimal surgeon performance and safety-critical events in robot-assisted surgery. Methods We develop a rubric for identifying task and gesture-specific Executional and Procedural errors and evaluate dry-lab demonstrations of Suturing and Needle Passing tasks from the JIGSAWS dataset. We characterize erroneous parts of demonstrations by labeling video data, and use distribution similarity analysis and trajectory averaging on kinematic data to identify parameters that distinguish erroneous gestures. Results Executional error frequency varies by task and gesture, and correlates with skill level. Some predominant error modes in each gesture are distinguishable by analyzing error-specific kinematic parameters. Procedural errors could lead to lower performance scores and increased demonstration times but also depend on surgical style. Conclusions This study provides insights into context-dependent errors that can be used to design automated error detection mechanisms and improve training and skill assessment.
Deep neural networks power most recent successes of artificial intelligence, spanning from self-driving cars to computer aided diagnosis in radiology and pathology. The high-stake data intensive process of surgery could highly benefit from such computational methods. However, surgeons and computer scientists should partner to develop and assess deep learning applications of value to patients and healthcare systems. This chapter and the accompanying hands-on material were designed for surgeons willing to understand the intuitions behind neural networks, become familiar with deep learning concepts and tasks, grasp what implementing a deep learning model in surgery means, and finally appreciate the specific challenges and limitations of deep neural networks in surgery. For the associated hands-on material, please see https://github.com/CAMMA-public/ai4surgery.
Purpose: Accurate estimation of the position and orientation (pose) of surgical instruments is crucial for delicate minimally invasive temporal bone surgery. Current techniques lack in accuracy and/or line-of-sight constraints (conventional tracking systems) or expose the patient to prohibitive ionizing radiation (intra-operative CT). A possible solution is to capture the instrument with a c-arm at irregular intervals and recover the pose from the image. Methods: i3PosNet infers the position and orientation of instruments from images using a pose estimation network. Said framework considers localized patches and outputs pseudo-landmarks. The pose is reconstructed from pseudo-landmarks by geometric considerations. Results: We show i3PosNet reaches errors less than 0.05mm. It outperforms conventional image registration-based approaches reducing average and maximum errors by at least two thirds. i3PosNet trained on synthetic images generalizes to real x-rays without any further adaptation. Conclusion: The translation of Deep Learning based methods to surgical applications is difficult, because large representative datasets for training and testing are not available. This work empirica
Purpose: Common dense stereo Simultaneous Localization and Mapping (SLAM) approaches in Minimally Invasive Surgery (MIS) require high-end parallel computational resources for real-time implementation. Yet, it is not always feasible since the computational resources should be allocated to other tasks like segmentation, detection, and tracking. To solve the problem of limited parallel computational power, this research aims at a lightweight dense stereo SLAM system that works on a single-core CPU and achieves real-time performance (more than 30 Hz in typical scenarios). Methods: A new dense stereo mapping module is integrated with the ORB-SLAM2 system and named BDIS-SLAM. Our new dense stereo mapping module includes stereo matching and 3D dense depth mosaic methods. Stereo matching is achieved with the recently proposed CPU-level real-time matching algorithm Bayesian Dense Inverse Searching (BDIS). A BDIS-based shape recovery and a depth mosaic strategy are integrated as a new thread and coupled with the backbone ORB-SLAM2 system for real-time stereo shape recovery. Results: Experiments on in-vivo data sets show that BDIS-SLAM runs at over 30 Hz speed on modern single-core CPU in typ
Using the rational surgery formula for the Casson--Walker--Lescop invariant of links in the $3$-sphere, we show that any null-homologous knot in a rational homology sphere admits at most two pairs of integral purely cosmetic surgeries. We also present constraints for null-homologous knots in certain $3$-manifolds with the first Betti number one or two to admit purely cosmetic surgeries. As another application, we show that, for a null-homologous knot in some $3$-manifolds, including $S^2 \times S^1$, there are at most two knots which are inequivalent to the given one, but whose exteriors are orientation-preservingly homeomorphic to that of the given one.
Purpose: The facial recess is a delicate structure that must be protected in minimally invasive cochlear implant surgery. Current research estimates the drill trajectory by using endoscopy of the unique mastoid patterns. However, missing depth information limits available features for a registration to preoperative CT data. Therefore, this paper evaluates OCT for enhanced imaging of drill holes in mastoid bone and compares OCT data to original endoscopic images. Methods: A catheter-based OCT probe is inserted into a drill trajectory of a mastoid phantom in a translation-rotation manner to acquire the inner surface state. The images are undistorted and stitched to create volumentric data of the drill hole. The mastoid cell pattern is segmented automatically and compared to ground truth. Results: The mastoid pattern segmented on images acquired with OCT show a similarity of J = 73.6 % to ground truth based on endoscopic images and measured with the Jaccard metric. Leveraged by additional depth information, automated segmentation tends to be more robust and fail-safe compared to endoscopic images. Conclusion: The feasibility of using a clinically approved OCT probe for imaging the dri