The seminal work of [LMN’93] established a cornerstone result for classical complexity, with profound implications for learning theory. By proving low-degree Fourier concentration of AC0, the work demonstrated that Boolean functions computed by constant-depth circuits can be efficiently PAC-learned via low-degree Fourier sampling. This breakthrough provided the first sample- and time-efficient (quasi-polynomial) algorithm for learning AC0. Proposed by [Moore’99] as a natural quantum analog of AC0, QAC0 is the class of constant-depth quantum circuits composed of arbitrary single-qubit gates and polynomial $CZ$ gates of unbounded width. In this work, we present the first algorithm for efficient average-case learning of QAC0 circuits with logarithmic ancilla. Namely, our algorithm achieves quasi-polynomial sample- and time-complexity for learning unknown QAC0 unitaries to inverse-polynomially small error. We further show that these learned unitaries can be efficiently synthesized via poly-logarithmic depth circuits, making progress towards proper learning of QAC0. Since in finite-dimensional circuit geometries QAC0 circuits require polynomial depth to implement, this result significantly expands the family of efficiently learnable quantum circuits.

Accurate tracking of tissues and instruments in videos is crucial for Robotic-Assisted Minimally Invasive Surgery (RAMIS), as it enables the robot to comprehend the surgical scene with precise locations and interactions of tissues and tools. Traditional keypoint-based sparse tracking is limited by featured points, while flow-based dense two-view matching suffers from long-term drifts. Recently, the Tracking Any Point (TAP) algorithm was proposed to overcome these limitations and achieve dense accurate long-term tracking. However, its efficacy in surgical scenarios remains untested, largely due to the lack of a comprehensive surgical tracking dataset for evaluation. To address this gap, we introduce a new annotated surgical tracking dataset for benchmarking tracking methods for surgical scenarios, comprising real-world surgical videos with complex tissue and instrument motions. We extensively evaluate state-of-the-art (SOTA) TAP-based algorithms on this dataset and reveal their limitations in challenging surgical scenarios, including fast instrument motion, severe occlusions, and motion blur, etc. Furthermore, we propose a new tracking method, namely SurgMotion, to solve the challenges and further improve the tracking performance. Our proposed method outperforms most TAP-based algorithms in surgical instruments tracking, and especially demonstrates significant improvements over baselines in challenging medical videos. Our code and dataset are available at https://github.com/zhanbh1019/SurgicalMotion.

The field of computer vision applied to videos of minimally invasive surgery is ever-growing. Workflow recognition pertains to the automated recognition of various aspects of a surgery, including: which surgical steps are performed; and which surgical instruments are used. This information can later be used to assist clinicians when learning the surgery or during live surgery. The Pituitary Vision (PitVis) 2023 Challenge tasks the community to step and instrument recognition in videos of endoscopic pituitary surgery. This is a particularly challenging task when compared to other minimally invasive surgeries due to: the smaller working space, which limits and distorts vision; and higher frequency of instrument and step switching, which requires more precise model predictions. Participants were provided with 25-videos, with results presented at the MICCAI-2023 conference as part of the Endoscopic Vision 2023 Challenge in Vancouver, Canada, on 08-Oct-2023. There were 18-submissions from 9-teams across 6-countries, using a variety of deep learning models. The top performing model for step recognition utilised a transformer based architecture, uniquely using an autoregressive decoder with a positional encoding input. The top performing model for instrument recognition utilised a spatial encoder followed by a temporal encoder, which uniquely used a 2-layer temporal architecture. In both cases, these models outperformed purely spatial based models, illustrating the importance of sequential and temporal information. This PitVis-2023 therefore demonstrates state-of-the-art computer vision models in minimally invasive surgery are transferable to a new dataset. Benchmark results are provided in the paper, and the dataset is publicly available at: https://doi.org/10.5522/04/26531686.

Fetoscopy laser photocoagulation is a widely adopted procedure for treating Twin-to-Twin Transfusion Syndrome (TTTS). The procedure involves photocoagulation pathological anastomoses to restore a physiological blood exchange among twins. The procedure is particularly challenging, from the surgeon's side, due to the limited field of view, poor manoeuvrability of the fetoscope, poor visibility due to amniotic fluid turbidity, and variability in illumination. These challenges may lead to increased surgery time and incomplete ablation of pathological anastomoses, resulting in persistent TTTS. Computer-assisted intervention (CAI) can provide TTTS surgeons with decision support and context awareness by identifying key structures in the scene and expanding the fetoscopic field of view through video mosaicking. Research in this domain has been hampered by the lack of high-quality data to design, develop and test CAI algorithms. Through the Fetoscopic Placental Vessel Segmentation and Registration (FetReg2021) challenge, which was organized as part of the MICCAI2021 Endoscopic Vision (EndoVis) challenge, we released the first large-scale multi-center TTTS dataset for the development of generalized and robust semantic segmentation and video mosaicking algorithms with a focus on creating drift-free mosaics from long duration fetoscopy videos. For this challenge, we released a dataset of 2060 images, pixel-annotated for vessels, tool, fetus and background classes, from 18 in-vivo TTTS fetoscopy procedures and 18 short video clips of an average length of 411 frames for developing placental scene segmentation and frame registration for mosaicking techniques. Seven teams participated in this challenge and their model performance was assessed on an unseen test dataset of 658 pixel-annotated images from 6 fetoscopic procedures and 6 short clips. For the segmentation task, overall baseline performed was the top performing (aggregated mIoU of 0.6763) and was the best on the vessel class (mIoU of 0.5817) while team RREB was the best on the tool (mIoU of 0.6335) and fetus (mIoU of 0.5178) classes. For the registration task, overall the baseline performed better than team SANO with an overall mean 5-frame SSIM of 0.9348. Qualitatively, it was observed that team SANO performed better in planar scenarios, while baseline was better in non-planner scenarios. The detailed analysis showed that no single team outperformed on all 6 test fetoscopic videos. The challenge provided an opportunity to create generalized solutions for fetoscopic scene understanding and mosaicking. In this paper, we present the findings of the FetReg2021 challenge, alongside reporting a detailed literature review for CAI in TTTS fetoscopy. Through this challenge, its analysis and the release of multi-center fetoscopic data, we provide a benchmark for future research in this field.

Feature detection and matching is a computer vision problem that underpins different computer assisted techniques in endoscopy, including anatomy and lesion recognition, camera motion estimation, and 3D reconstruction. This problem is made extremely challenging due to the abundant presence of specular reflections. Most of the solutions proposed in the literature are based on filtering or masking out these regions as an additional processing step. There has been little investigation into explicitly learning robustness to such artefacts with single-step end-to-end training. In this paper, we propose an augmentation technique (CycleSTTN) that adds temporally consistent and realistic specularities to endoscopic videos. Such videos can act as ground truth data with known texture occluded behind the added specularities. We demonstrate that our image generation technique produces better results than a standard CycleGAN model. Additionally, we leverage this data augmentation to re-train a deep-learning based feature extractor (SuperPoint) and show that it improves. CycleSTTN code is made available here .

Expanding training and evaluation data is a major step towards building and deploying reliable localization and 3D reconstruction techniques during colonoscopy screenings. However, training and evaluating pose and depth models in colonoscopy is hard as available datasets are limited in size. This paper proposes a method for generating new pose and depth datasets by fitting NeRFs in already available colonoscopy datasets. Given a set of images, their associated depth maps and pose information, we train a novel light source location-conditioned NeRF to encapsulate the 3D and color information of a colon sequence. Then, we leverage the trained networks to render images from previously unobserved camera poses and simulate different camera systems, effectively expanding the source dataset. Our experiments show that our model is able to generate RGB images and depth maps of a colonoscopy sequence from previously unobserved poses with high accuracy. Code and trained networks can be accessed at https://github.com/surgical-vision/REIM-NeRF .

Video streams are utilised to guide minimally-invasive surgery and diagnosis in a wide range of procedures, and many computer-assisted techniques have been developed to automatically analyse them. These approaches can provide additional information to the surgeon such as lesion detection, instrument navigation, or anatomy 3D shape modelling. However, the necessary image features to recognise these patterns are not always reliably detected due to the presence of irregular light patterns such as specular highlight reflections. In this paper, we aim at removing specular highlights from endoscopic videos using machine learning. We propose using a temporal generative adversarial network (GAN) to inpaint the hidden anatomy under specularities, inferring its appearance spatially and from neighbouring frames, where they are not present in the same location. This is achieved using in-vivo data from gastric endoscopy (Hyper Kvasir) in a fully unsupervised manner that relies on the automatic detection of specular highlights. System evaluations show significant improvements to other methods through direct comparison and ablation studies that depict the importance of the network's temporal and transfer learning components. The generalisability of our system to different surgical setups and procedures was also evaluated qualitatively on in-vivo data of gastric endoscopy and ex-vivo porcine data (SERV-CT, SCARED). We also assess the effect of our method in comparison to other methods on computer vision tasks that underpin 3D reconstruction and camera motion estimation, namely stereo disparity, optical flow, and sparse point feature matching. These are evaluated quantitatively and qualitatively and results show a positive effect of our specular inpainting method on these tasks in a novel comprehensive analysis. Our code and dataset are made available at https://github.com/endomapper/Endo-STTN.

We propose an endoscopic image mosaicking algorithm that is robust to light conditioning changes, specular reflections, and feature-less scenes. These conditions are especially common in minimally invasive surgery where the light source moves with the camera to dynamically illuminate close range scenes. This makes it difficult for a single image registration method to robustly track camera motion and then generate consistent mosaics of the expanded surgical scene across different and heterogeneous environments. Instead of relying on one specialised feature extractor or image registration method, we propose to fuse different image registration algorithms according to their uncertainties, formulating the problem as affine pose graph optimisation. This allows to combine landmarks, dense intensity registration, and learning-based approaches in a single framework. To demonstrate our application we consider deep learning-based optical flow, hand-crafted features, and intensity-based registration, however, the framework is general and could take as input other sources of motion estimation, including other sensor modalities. We validate the performance of our approach on three datasets with very different characteristics to highlighting its generalisability, demonstrating the advantages of our proposed fusion framework. While each individual registration algorithm eventually fails drastically on certain surgical scenes, the fusion approach flexibly determines which algorithms to use and in which proportion to more robustly obtain consistent mosaics.

Surgical instrument segmentation can be used in a range of computer assisted interventions and automation in surgical robotics. While deep learning architectures have rapidly advanced the robustness and performance of segmentation models, most are still reliant on supervision and large quantities of labelled data. In this paper, we present a novel method for surgical image generation that can fuse robotic instrument simulation and recent domain adaptation techniques to synthesize artificial surgical images to train surgical instrument segmentation models. We integrate attention modules into well established image generation pipelines and propose a novel cost function to support supervision from simulation frames in model training. We provide an extensive evaluation of our method in terms of segmentation performance along with a validation study on image quality using evaluation metrics. Additionally, we release a novel segmentation dataset from real surgeries that will be shared for research purposes. Both binary and semantic segmentation have been considered, and we show the capability of our synthetic images to train segmentation models compared with the latest methods from the literature.

Reconstructing the 3D geometry of the surgical site and detecting instruments within it are important tasks for surgical navigation systems and robotic surgery automation. Traditional approaches treat each problem in isolation and do not account for the intrinsic relationship between segmentation and stereo matching. In this paper, we present a learning-based framework that jointly estimates disparity and binary tool segmentation masks. The core component of our architecture is a shared feature encoder which allows strong interaction between the aforementioned tasks. Experimentally, we train two variants of our network with different capacities and explore different training schemes including both multi-task and single-task learning. Our results show that supervising the segmentation task improves our network's disparity estimation accuracy. We demonstrate a domain adaptation scheme where we supervise the segmentation task with monocular data and achieve domain adaptation of the adjacent disparity task, reducing disparity End-Point-Error and depth mean absolute error by 77.73% and 61.73% respectively compared to the pre-trained baseline model. Our best overall multi-task model, trained with both disparity and segmentation data in subsequent phases, achieves 89.15% mean Intersection-over-Union in RIS and 3.18 millimetre depth mean absolute error in SCARED test sets. Our proposed multi-task architecture is real-time, able to process ( 1280×1024 ) stereo input and simultaneously estimate disparity maps and segmentation masks at 22 frames per second. The model code and pre-trained models are made available: https://github.com/dimitrisPs/msdesis.

Recovering 3D geometry from cameras in underwater applications involves the Refractive Structure-from-Motion problem where the non-linear distortion of light induced by a change of medium density invalidates the single viewpoint assumption. The pinhole-plus-distortion camera projection model suffers from a systematic geometric bias since refractive distortion depends on object distance. This leads to inaccurate camera pose and 3D shape estimation. To account for refraction, it is possible to use the axial camera model or to explicitly consider one or multiple parallel refractive interfaces whose orientations and positions with respect to the camera can be calibrated. Although it has been demonstrated that the refractive camera model is well-suited for underwater imaging, Refractive Structure-from-Motion remains particularly difficult to use in practice when considering the seldom studied case of a camera with a flat refractive interface. Our method applies to the case of underwater imaging systems whose entrance lens is in direct contact with the external medium. By adopting the refractive camera model, we provide a succinct derivation and expression for the refractive fundamental matrix and use this as the basis for a novel two-view reconstruction method for underwater imaging. For validation we use synthetic data to show the numerical properties of our method and we provide results on real data to demonstrate its practical application within laboratory settings and for medical applications in fluid-immersed endoscopy. We demonstrate our approach outperforms classic two-view Structure-from-Motion method relying on the pinhole-plus-distortion camera model.

In robotic surgery the motion of instruments and the laparoscopic camera is constrained by their insertion ports, i. e. a remote centre of motion (RCM). We propose a Simultaneous Localisation and Mapping (SLAM) approach that estimates laparoscopic camera motion under RCM constraints. To achieve this we derive a minimal solver for the absolute camera pose given two 2D-3D point correspondences (RCM-PnP) and also a bundle adjustment optimiser that refines camera poses within an RCM-constrained parameterisation. These two methods are used together with previous work on relative pose estimation under RCM [1] to assemble a SLAM pipeline suitable for robotic surgery. Our simulations show that RCM-PnP outperforms conventional PnP for a wide noise range in the RCM position. Results with video footage from a robotic prostatectomy show that RCM constraints significantly improve camera pose estimation.

Accounting for 26% of all new cancer cases worldwide, breast cancer remains the most common form of cancer in women. Although early breast cancer has a favourable long-term prognosis, roughly a third of patients suffer from a suboptimal aesthetic outcome despite breast conserving cancer treatment. Clinical-quality 3D modelling of the breast surface therefore assumes an increasingly important role in advancing treatment planning, prediction and evaluation of breast cosmesis. Yet, existing 3D torso scanners are expensive and either infrastructure-heavy or subject to motion artefacts. In this paper we employ a single consumer-grade RGBD camera with an ICP-based registration approach to jointly align all points from a sequence of depth images non-rigidly. Subtle body deformation due to postural sway and respiration is successfully mitigated leading to a higher geometric accuracy through regularised locally affine transformations. We present results from 6 clinical cases where our method compares well with the gold standard and outperforms a previous approach. We show that our method produces better reconstructions qualitatively by visual assessment and quantitatively by consistently obtaining lower landmark error scores and yielding more accurate breast volume estimates.

Robot-assisted laparoscopic prostatectomy (RALP) is a treatment for prostate cancer that involves complete or nerve sparing removal prostate tissue that contains cancer. After removal the bladder neck is successively sutured directly with the urethra. The procedure is called urethrovesical anastomosis and is one of the most dexterity demanding tasks during RALP. Two suturing instruments and a pair of needles are used in combination to perform a running stitch during urethrovesical anastomosis. While robotic instruments provide enhanced dexterity to perform the anastomosis, it is still highly challenging and difficult to learn. In this paper, we presents a vision-guided needle grasping method for automatically grasping the needle that has been inserted into the patient prior to anastomosis. We aim to automatically grasp the suturing needle in a position that avoids hand-offs and immediately enables the start of suturing. The full grasping process can be broken down into: a needle detection algorithm; an approach phase where the surgical tool moves closer to the needle based on visual feedback; and a grasping phase through path planning based on observed surgical practice. Our experimental results show examples of successful autonomous grasping that has the potential to simplify and decrease the operational time in RALP by assisting a small component of urethrovesical anastomosis.

We propose a new method to add an uncalibrated node into a network of calibrated cameras using only pairwise point correspondences. While previous methods perform this task using triple correspondences, these are often difficult to establish when there is limited overlap between different views. In such challenging cases we must rely on pairwise correspondences and our solution becomes more advantageous. Our method includes an 11-point minimal solution for the intrinsic and extrinsic calibration of a camera from pairwise correspondences with other two calibrated cameras, and a new inlier selection framework that extends the traditional RANSAC family of algorithms to sampling across multiple datasets. Our method is validated on different application scenarios where a lack of triple correspondences might occur: addition of a new node to a camera network; calibration and motion estimation of a moving camera inside a camera network; and addition of views with limited overlap to a Structure-from-Motion model.

Recovering 3D scene geometry from underwater images involves the Refractive Structure-from-Motion (RSfM) problem, where the image distortions caused by light refraction at the interface between different propagation media invalidates the single view point assumption. Direct use of the pinhole camera model in RSfM leads to inaccurate camera pose estimation and consequently drift. RSfM methods have been thoroughly studied for the case of a thick glass interface that assumes two refractive interfaces between the camera and the viewed scene. On the other hand, when the camera lens is in direct contact with the water, there is only one refractive interface. By explicitly considering a refractive interface, we develop a succinct derivation of the refractive fundamental matrix in the form of the generalised epipolar constraint for an axial camera. We use the refractive fundamental matrix to refine initial pose estimates obtained by assuming the pinhole model. This strategy allows us to robustly estimate underwater camera poses, where other methods suffer from poor noise-sensitivity. We also formulate a new four view constraint enforcing camera pose consistency along a video which leads us to a novel RSfM framework. For validation we use synthetic data to show the numerical properties of our method and we provide results on real data to demonstrate performance within laboratory settings and for applications in endoscopy.

The problem of estimating the relative pose between axial cameras from pairwise point correspondences is still open to improvement. The state-of-the-art solutions are either too specific in its scope, assuming certain types of correspondences; too broad, dealing with all types of generalized cameras and failing to address the specific issues of axial cameras; or non-minimal linear solutions. The aim of this paper is to pursue new insights on axial cameras that can lead to a suitable minimal solution for this problem. We propose a new formulation for modeling the intersection of back-projection rays of axial cameras through a 5×5 essential matrix that enables a better understanding of some particular axial configurations and leads to a new set of polynomial equations that proves to be useful in constraining the motion estimation. These equations enable to compute a solution from 10 correspondences, an improvement over the 16-point algorithm, which is the state-of-the-art solution within our aimed scope. Both synthetic and real experiments show that our algorithm achieves a better performance than the 16-point algorithm in the context of robust optimization with RANSAC.

This paper presents a new algorithm for the extrinsic calibration of a perspective camera and an invisible 2D laser-rangefinder (LRF). The calibration is achieved by freely moving a checkerboard pattern in order to obtain plane poses in camera coordinates and depth readings in the LRF reference frame. The problem of estimating the rigid displacement between the two sensors is formulated as one of registering a set of planes and lines in the 3D space. It is proven for the first time that the alignment of three plane-line correspondences has at most eight solutions that can be determined by solving a standard p3p problem and a linear system of equations. This leads to a minimal closed-form solution for the extrinsic calibration that can be used as hypothesis generator in a RANSAC paradigm. Our calibration approach is validated through simulation and real experiments that show the superiority with respect to the current state-of-the-art method requiring a minimum of five input planes.

Keypoint detection and matching is of fundamental importance for many applications in computer and robot vision. The association of points across different views is problematic because image features can undergo significant changes in appearance. Unfortunately, state-of-the-art methods, like the scale-invariant feature transform (SIFT), are not resilient to the radial distortion that often arises in images acquired by cameras with microlenses and/or wide field-of-view. This paper proposes modifications to the SIFT algorithm that substantially improve the repeatability of detection and effectiveness of matching under radial distortion, while preserving the original invariance to scale and rotation. The scale-space representation of the image is obtained using adaptive filtering that compensates the local distortion, and the keypoint description is carried after implicit image gradient correction. Unlike competing methods, our approach avoids image resampling (the processing is carried out in the original image plane), it does not require accurate camera calibration (an approximate modeling of the distortion is sufficient), and it adds minimal computational overhead. Extensive experiments show the advantages of our method in establishing point correspondence across images with radial distortion.

Rigid motion estimation from image point correspondences is an overconstrained problem that can be solved by minimizing an adequate cost function. Given the unreliable nature of image point correspondences, they must be divided into two categories: inliers and outliers. Finding the correct camera motion and discarding the outliers is a coupled problem usually solved by a random search of the solution space. This article proposes adaptive and hybrid genetic approaches to improve the efficiency of this search. We build on top of the GASAC algorithm that has been recently presented for solving problems in geometric computer vision. GASAC is modified to address the specific issues of camera motion estimation such as outlier ratios above 50% due to wide-baseline image acquisition and an adequate choice of a fitness function. In order to avoid local minima, we propose three adaptive strategies: varying the mutation probability, resampling the lowest ranked individuals, and using a hybrid approach that combines GASAC with simulated annealing. Results are validated on publicly available benchmark images, and it is shown that the proposed genetic approaches outperform the standard RANSAC search used among computer vision practitioners.