The Future of Endoscopic Navigation: A Review of Advanced Endoscopic Vision Technology

Automatic semantic segmentation of the osseous structures of the paranasal sinuses

Endoscopic sinus and skull base surgeries require the use of precise neuronavigation techniques, which may take advantage of accurate delimitation of surrounding structures. This delimitation is critical for robotic-assisted surgery procedures to limit volumes of no resection. In this respect, an accurate segmentation of the osseous structures of the paranasal sinuses is a relevant issue to protect critical anatomic structures during these surgeries. Currently, manual segmentation of these structures is a labour-intensive task and requires wide expertise, often leading to inconsistencies. This is due to the lack of publicly available automatic models specifically tailored for the automatic delineation of the complex osseous structures of the paranasal sinuses. To address this gap, we introduce an open source dataset and a UNet SwinTR model for the segmentation of these complex structures. The initial model was trained on nine complete ex vivo CT scans of the paranasal region and then improved with semi-supervised learning techniques. When tested on an external dataset recorded under different conditions, it achieved a DICE score of 98.25 ± 0.9. These results underscore the effectiveness of the model and its potential for broader research applications. By providing both the dataset and the model publicly available, this work aims to catalyse further research that could improve the precision of clinical interventions of endoscopic sinus and skull-based surgeries.

Seamless augmented reality integration in arthroscopy: a pipeline for articular reconstruction and guidance

Arthroscopy is a minimally invasive surgical procedure used to diagnose and treat joint problems. The clinical workflow of arthroscopy typically involves inserting an arthroscope into the joint through a small incision, during which surgeons navigate and operate largely by relying on their visual assessment through the arthroscope. However, the arthroscope's restricted field of view and lack of depth perception pose challenges in navigating complex articular structures and achieving surgical precision during procedures. Aiming at enhancing intraoperative awareness, a robust pipeline that incorporates simultaneous localization and mapping, depth estimation, and 3D Gaussian splatting (3D GS) is presented to realistically reconstruct intra-articular structures solely based on monocular arthroscope video. Extending 3D reconstruction to augmented reality (AR) applications, the solution offers AR assistance for articular notch measurement and annotation anchoring in a human-in-the-loop manner. Compared to traditional structure-from-motion and neural radiance field-based methods, the pipeline achieves dense 3D reconstruction and competitive rendering fidelity with explicit 3D representation in 7 min on average. When evaluated on four phantom datasets, our method achieves root-mean-square-error(RMSE) = 2.21 mm reconstruction error, peak signal-to-noise ratio(PSNR) = 32.86 and structure similarity index measure(SSIM) = 0.89 on average. Because the pipeline enables AR reconstruction and guidance directly from monocular arthroscopy without any additional data and/or hardware, the solution may hold the potential for enhancing intraoperative awareness and facilitating surgical precision in arthroscopy. The AR measurement tool achieves accuracy within1.59 ± 1.81 mm and the AR annotation tool achieves a mIoU of 0.721.

Taking measurement in every direction: Implicit scene representation for accurately estimating target dimensions under monocular endoscope

BACKGROUND AND OBJECTIVES

In endoscopy, measurement of target size can assist medical diagnosis. However, limited operating space, low image quality, and irregular target shape pose great challenges to traditional vision-based measurement methods.

METHODS

In this paper, we propose a novel approach to measure irregular target size under monocular endoscope using image rendering. Firstly synthesize virtual poses on the same main optical axis as known camera poses, and use implicit neural representation module that considers brightness and target boundaries to render images corresponding to virtual poses. Then, Swin-Unet and rotating calipers are utilized to obtain maximum pixel length of the target in image pairs with the same main optical axis. Finally, the similarity triangle relationship of the endoscopic imaging model is used to measure the size of the target.

RESULTS

The evaluation is conducted using renal stone fragments of patients which are placed in the kidney model and the isolated porcine kidney. The mean error of measurement is 0.12 mm.

CONCLUSIONS

The approached method can automatically measure object size within narrow body cavities in any visible direction. It improves the effectiveness and accuracy of measurement in limited endoscopic space.

Tissue palpation in endoscopy using EIT and soft actuators

The integration of soft robots in medical procedures has significantly improved diagnostic and therapeutic interventions, addressing safety concerns and enhancing surgeon dexterity. In conjunction with artificial intelligence, these soft robots hold the potential to expedite autonomous interventions, such as tissue palpation for cancer detection. While cameras are prevalent in surgical instruments, situations with obscured views necessitate palpation. This proof-of-concept study investigates the effectiveness of using a soft robot integrated with Electrical Impedance Tomography (EIT) capabilities for tissue palpation in simulated in vivo inspection of the large intestine. The approach involves classifying tissue samples of varying thickness into healthy and cancerous tissues using the shape changes induced on a hydraulically-driven soft continuum robot during palpation. Shape changes of the robot are mapped using EIT, providing arrays of impedance measurements. Following the fabrication of an in-plane bending soft manipulator, the preliminary tissue phantom design is detailed. The phantom, representing the descending colon wall, considers induced stiffness by surrounding tissues based on a mass-spring model. The shape changes of the manipulator, resulting from interactions with tissues of different stiffness, are measured, and EIT measurements are fed into a Long Short-Term Memory (LSTM) classifier. Train and test datasets are collected as temporal sequences of data from a single training phantom and two test phantoms, namely, A and B, possessing distinctive thickness patterns. The collected dataset from phantom B, which differs in stiffness distribution, remains unseen to the network, thus posing challenges to the classifier. The classifier and proposed method achieve an accuracy of 93 % and 88.1 % on phantom A and B, respectively. Classification results are presented through confusion matrices and heat maps, visualising the accuracy of the algorithm and corresponding classified tissues.

Best Practices for Measuring the Modulation Transfer Function of Video Endoscopes

Endoscopes are crucial for assisting in surgery and disease diagnosis, including the early detection of cancer. The effective use of endoscopes relies on their optical performance, which can be characterized with a series of metrics such as resolution, vital for revealing anatomical details. The modulation transfer function (MTF) is a key metric for evaluating endoscope resolution. However, the 2020 version of the ISO 8600-5 standard, while introducing an endoscope MTF measurement method, lacks empirical validation and excludes opto-electronic video endoscopes, the largest family of endoscopes. Measuring the MTF of video endoscopes requires tailored standards that address their unique characteristics. This paper aims to expand the scope of ISO 8600-5:2020 to include video endoscopes, by optimizing the MTF test method and addressing parameters affecting measurement accuracy. We studied the effects of intensity and uniformity of image luminance, chart modulation compensation, linearity of image digital values, auto gain control, image enhancement, image compression and the region of interest dimensions on images of slanted-edge test charts, and thus the MTF based on these images. By analyzing these effects, we provided recommendations for setting and controlling these factors to obtain accurate MTF curves. Our goal is to enhance the standard's relevance and effectiveness for measuring the MTF of a broader range of endoscopic devices, with potential applications in the MTF measurement of other digital imaging devices.

Surgical Tattoos in Infrared: A Dataset for Quantifying Tissue Tracking and Mapping

Quantifying performance of methods for tracking and mapping tissue in endoscopic environments is essential for enabling image guidance and automation of medical interventions and surgery. Datasets developed so far either use rigid environments, visible markers, or require annotators to label salient points in videos after collection. These are respectively: not general, visible to algorithms, or costly and error-prone. We introduce a novel labeling methodology along with a dataset that uses said methodology, Surgical Tattoos in Infrared (STIR). STIR has labels that are persistent but invisible to visible spectrum algorithms. This is done by labelling tissue points with IR-fluorescent dye, indocyanine green (ICG), and then collecting visible light video clips. STIR comprises hundreds of stereo video clips in both in vivo and ex vivo scenes with start and end points labelled in the IR spectrum. With over 3,000 labelled points, STIR will help to quantify and enable better analysis of tracking and mapping methods. After introducing STIR, we analyze multiple different frame-based tracking methods on STIR using both 3D and 2D endpoint error and accuracy metrics. STIR is available at https://dx.doi.org/10.21227/w8g4-g548.

Wide-field, high-resolution reconstruction in computational multi-aperture miniscope using a Fourier neural network

Traditional fluorescence microscopy is constrained by inherent trade-offs among resolution, field of view, and system complexity. To navigate these challenges, we introduce a simple and low-cost computational multi-aperture miniature microscope, utilizing a microlens array for single-shot wide-field, high-resolution imaging. Addressing the challenges posed by extensive view multiplexing and non-local, shift-variant aberrations in this device, we present SV-FourierNet, a multi-channel Fourier neural network. SV-FourierNet facilitates high-resolution image reconstruction across the entire imaging field through its learned global receptive field. We establish a close relationship between the physical spatially varying point-spread functions and the network's learned effective receptive field. This ensures that SV-FourierNet has effectively encapsulated the spatially varying aberrations in our system and learned a physically meaningful function for image reconstruction. Training of SV-FourierNet is conducted entirely on a physics-based simulator. We showcase wide-field, high-resolution video reconstructions on colonies of freely moving C. elegans and imaging of a mouse brain section. Our computational multi-aperture miniature microscope, augmented with SV-FourierNet, represents a major advancement in computational microscopy and may find broad applications in biomedical research and other fields requiring compact microscopy solutions.

Autonomous Magnetic Navigation in Endoscopic Image Mosaics

Endoscopes navigate within the human body to observe anatomical structures with minimal invasiveness. A major shortcoming of their use is their narrow field-of-view during navigation in large, hollow anatomical regions. Mosaics of endoscopic images can provide surgeons with a map of the tool's environment. This would facilitate procedures, improve their efficiency, and potentially generate better patient outcomes. The emergence of magnetically steered endoscopes opens the way to safer procedures and creates an opportunity to provide robotic assistance both in the generation of the mosaic map and in navigation within this map. This paper proposes methods to autonomously navigate magnetic endoscopes to 1) generate endoscopic image mosaics and 2) use these mosaics as user interfaces to navigate throughout the explored area. These are the first strategies, which allow autonomous magnetic navigation in large, hollow organs during minimally invasive surgeries. The feasibility of these methods is demonstrated experimentally both in vitro and ex vivo in the context of the treatment of twin-to-twin transfusion syndrome. This minimally invasive procedure is performed in utero and necessitates coagulating shared vessels of twin fetuses on the placenta. A mosaic of the vasculature in combination with autonomous navigation has the potential to significantly facilitate this challenging surgery.

Simultaneous photoacoustic and ultrasound imaging: A review

Photoacoustic imaging (PAI) is an emerging biomedical imaging technique that combines the advantages of optical and ultrasound imaging, enabling the generation of images with both optical resolution and acoustic penetration depth. By leveraging similar signal acquisition and processing methods, the integration of photoacoustic and ultrasound imaging has introduced a novel hybrid imaging modality suitable for clinical applications. Photoacoustic-ultrasound imaging allows for non-invasive, high-resolution, and deep-penetrating imaging, providing a wealth of image information. In recent years, with the deepening research and the expanding biomedical application scenarios of photoacoustic-ultrasound bimodal systems, the immense potential of photoacoustic-ultrasound bimodal imaging in basic research and clinical applications has been demonstrated, with some research achievements already commercialized. In this review, we introduce the principles, technical advantages, and biomedical applications of photoacoustic-ultrasound bimodal imaging techniques, specifically focusing on tomographic, microscopic, and endoscopic imaging modalities. Furthermore, we discuss the future directions of photoacoustic-ultrasound bimodal imaging technology.

Deep learning-based anatomical position recognition for gastroscopic examination

BACKGROUND

The gastroscopic examination is a preferred method for the detection of upper gastrointestinal lesions. However, gastroscopic examination has high requirements for doctors, especially for the strict position and quantity of the archived images. These requirements are challenging for the education and training of junior doctors.

OBJECTIVE

The purpose of this study is to use deep learning to develop automatic position recognition technology for gastroscopic examination.

METHODS

A total of 17182 gastroscopic images in eight anatomical position categories are collected. Convolutional neural network model MogaNet is used to identify all the anatomical positions of the stomach for gastroscopic examination The performance of four models is evaluated by sensitivity, precision, and F1 score.

RESULTS

The average sensitivity of the method proposed is 0.963, which is 0.074, 0.066 and 0.065 higher than ResNet, GoogleNet and SqueezeNet, respectively. The average precision of the method proposed is 0.964, which is 0.072, 0.067 and 0.068 higher than ResNet, GoogleNet, and SqueezeNet, respectively. And the average F1-Score of the method proposed is 0.964, which is 0.074, 0.067 and 0.067 higher than ResNet, GoogleNet, and SqueezeNet, respectively. The results of the t-test show that the method proposed is significantly different from other methods (p< 0.05).

CONCLUSION

The method proposed exhibits the best performance for anatomical positions recognition. And the method proposed can help junior doctors meet the requirements of completeness of gastroscopic examination and the number and position of archived images quickly.

Colonoscopy 3D video dataset with paired depth from 2D-3D registration

Screening colonoscopy is an important clinical application for several 3D computer vision techniques, including depth estimation, surface reconstruction, and missing region detection. However, the development, evaluation, and comparison of these techniques in real colonoscopy videos remain largely qualitative due to the difficulty of acquiring ground truth data. In this work, we present a Colonoscopy 3D Video Dataset (C3VD) acquired with a high definition clinical colonoscope and high-fidelity colon models for benchmarking computer vision methods in colonoscopy. We introduce a novel multimodal 2D-3D registration technique to register optical video sequences with ground truth rendered views of a known 3D model. The different modalities are registered by transforming optical images to depth maps with a Generative Adversarial Network and aligning edge features with an evolutionary optimizer. This registration method achieves an average translation error of 0.321 millimeters and an average rotation error of 0.159 degrees in simulation experiments where error-free ground truth is available. The method also leverages video information, improving registration accuracy by 55.6% for translation and 60.4% for rotation compared to single frame registration. 22 short video sequences were registered to generate 10,015 total frames with paired ground truth depth, surface normals, optical flow, occlusion, six degree-of-freedom pose, coverage maps, and 3D models. The dataset also includes screening videos acquired by a gastroenterologist with paired ground truth pose and 3D surface models. The dataset and registration source code are available at https://durr.jhu.edu/C3VD.

Technology-assisted anterior cruciate ligament reconstruction improves tunnel placement but leads to no change in clinical outcomes: a systematic review and meta-analysis

PURPOSE

To investigate the effect of technology-assisted Anterior Cruciate Ligament Reconstruction (ACLR) on post-operative clinical outcomes and tunnel placement compared to conventional arthroscopic ACLR.

METHODS

CENTRAL, MEDLINE, and Embase were searched from January 2000 to November 17, 2022. Articles were included if there was intraoperative use of computer-assisted navigation, robotics, diagnostic imaging, computer simulations, or 3D printing (3DP). Two reviewers searched, screened, and evaluated the included studies for data quality. Data were abstracted using descriptive statistics and pooled using relative risk ratios (RR) or mean differences (MD), both with 95% confidence intervals (CI), where appropriate.

RESULTS

Eleven studies were included with total 775 patients and majority male participants (70.7%). Ages ranged from 14 to 54 years (391 patients) and follow-up ranged from 12 to 60 months (775 patients). Subjective International Knee Documentation Committee (IKDC) scores increased in the technology-assisted surgery group (473 patients; P = 0.02; MD 1.97, 95% CI 0.27 to 3.66). There was no difference in objective IKDC scores (447 patients; RR 1.02, 95% CI 0.98 to 1.06), Lysholm scores (199 patients; MD 1.14, 95% CI - 1.03 to 3.30) or negative pivot-shift tests (278 patients; RR 1.07, 95% CI 0.97 to 1.18) between the two groups. When using technology-assisted surgery, 6 (351 patients) of 8 (451 patients) studies reported more accurate femoral tunnel placement and 6 (321 patients) of 10 (561 patients) studies reported more accurate tibial tunnel placement in at least one measure. One study (209 patients) demonstrated a significant increase in cost associated with use of computer-assisted navigation (mean 1158€) versus conventional surgery (mean 704€). Of the two studies using 3DP templates, production costs ranging from $10 to $42 USD were cited. There was no difference in adverse events between the two groups.

CONCLUSION

Clinical outcomes do not differ between technology-assisted surgery and conventional surgery. Computer-assisted navigation is more expensive and time consuming while 3DP is inexpensive and does not lead to greater operating times. ACLR tunnels can be more accurately located in radiologically ideal places by using technology, but anatomic placement is still undetermined because of variability and inaccuracy of the evaluation systems utilized.

LEVEL OF EVIDENCE

Level III.

Endoscopic image classification algorithm based on Poolformer

Image desmoking is a significant aspect of endoscopic image processing, effectively mitigating visual field obstructions without the need for additional surgical interventions. However, current smoke removal techniques tend to apply comprehensive video enhancement to all frames, encompassing both smoke-free and smoke-affected images, which not only escalates computational costs but also introduces potential noise during the enhancement of smoke-free images. In response to this challenge, this paper introduces an approach for classifying images that contain surgical smoke within endoscopic scenes. This classification method provides crucial target frame information for enhancing surgical smoke removal, improving the scientific robustness, and enhancing the real-time processing capabilities of image-based smoke removal method. The proposed endoscopic smoke image classification algorithm based on the improved Poolformer model, augments the model's capacity for endoscopic image feature extraction. This enhancement is achieved by transforming the Token Mixer within the encoder into a multi-branch structure akin to ConvNeXt, a pure convolutional neural network. Moreover, the conversion to a single-path topology during the prediction phase elevates processing speed. Experiments use the endoscopic dataset sourced from the Hamlyn Centre Laparoscopic/Endoscopic Video Dataset, augmented by Blender software rendering. The dataset comprises 3,800 training images and 1,200 test images, distributed in a 4:1 ratio of smoke-free to smoke-containing images. The outcomes affirm the superior performance of this paper's approach across multiple parameters. Comparative assessments against existing models, such as mobilenet_v3, efficientnet_b7, and ViT-B/16, substantiate that the proposed method excels in accuracy, sensitivity, and inference speed. Notably, when contrasted with the Poolformer_s12 network, the proposed method achieves a 2.3% enhancement in accuracy, an 8.2% boost in sensitivity, while incurring a mere 6.4 frames per second reduction in processing speed, maintaining 87 frames per second. The results authenticate the improved performance of the refined Poolformer model in endoscopic smoke image classification tasks. This advancement presents a lightweight yet effective solution for the automatic detection of smoke-containing images in endoscopy. This approach strikes a balance between the accuracy and real-time processing requirements of endoscopic image analysis, offering valuable insights for targeted desmoking process.

Application of Medical Image Navigation Technology in Minimally Invasive Puncture Robot

Microneedle puncture is a standard minimally invasive treatment and surgical method, which is widely used in extracting blood, tissues, and their secretions for pathological examination, needle-puncture-directed drug therapy, local anaesthesia, microwave ablation needle therapy, radiotherapy, and other procedures. The use of robots for microneedle puncture has become a worldwide research hotspot, and medical imaging navigation technology plays an essential role in preoperative robotic puncture path planning, intraoperative assisted puncture, and surgical efficacy detection. This paper introduces medical imaging technology and minimally invasive puncture robots, reviews the current status of research on the application of medical imaging navigation technology in minimally invasive puncture robots, and points out its future development trends and challenges.

Artificial intelligence meets medical robotics

Artificial intelligence (AI) applications in medical robots are bringing a new era to medicine. Advanced medical robots can perform diagnostic and surgical procedures, aid rehabilitation, and provide symbiotic prosthetics to replace limbs. The technology used in these devices, including computer vision, medical image analysis, haptics, navigation, precise manipulation, and machine learning (ML) , could allow autonomous robots to carry out diagnostic imaging, remote surgery, surgical subtasks, or even entire surgical procedures. Moreover, AI in rehabilitation devices and advanced prosthetics can provide individualized support, as well as improved functionality and mobility (see the figure). The combination of extraordinary advances in robotics, medicine, materials science, and computing could bring safer, more efficient, and more widely available patient care in the future. -Gemma K. Alderton.

Inpainting surgical occlusion from laparoscopic video sequences for robot-assisted interventions

Purpose

Medical technology for minimally invasive surgery has undergone a paradigm shift with the introduction of robot-assisted surgery. However, it is very difficult to track the position of the surgical tools in a surgical scene, so it is crucial to accurately detect and identify surgical tools. This task can be aided by deep learning-based semantic segmentation of surgical video frames. Furthermore, due to the limited working and viewing areas of these surgical instruments, there is a higher chance of complications from tissue injuries (e.g., tissue scars and tears).

Approach

With the aid of digital inpainting algorithms, we present an application that uses image segmentation to remove surgical instruments from laparoscopic/endoscopic video. We employ a modified U-Net architecture (U-NetPlus) to segment the surgical instruments. It consists of a redesigned decoder and a pre-trained VGG11 or VGG16 encoder. The decoder was modified by substituting an up-sampling operation based on nearest-neighbor interpolation for the transposed convolution operation. Furthermore, these interpolation weights do not need to be learned to perform upsampling, which eliminates the artifacts generated by the transposed convolution. In addition, we use a very fast and adaptable data augmentation technique to further enhance performance. The instrument segmentation mask is filled in (i.e., inpainted) by the tool removal algorithms using the previously acquired tool segmentation masks and either previous instrument-containing frames or instrument-free reference frames.

Results

We have shown the effectiveness of the proposed surgical tool segmentation/removal algorithms on a robotic instrument dataset from the MICCAI 2015 and 2017 EndoVis Challenge. We report a 90.20% DICE for binary segmentation, a 76.26% DICE for instrument part segmentation, and a 46.07% DICE for instrument type (i.e., all instruments) segmentation on the MICCAI 2017 challenge dataset using our U-NetPlus architecture, outperforming the results of earlier techniques used and tested on these data. In addition, we demonstrated the successful execution of the tool removal algorithm from surgical tool-free videos that contained moving surgical tools that were generated artificially.

Conclusions

Our application successfully separates and eliminates the surgical tool to reveal a view of the background tissue that was otherwise hidden by the tool, producing results that are visually similar to the actual data.

Scenario-Based Programming of Voice-Controlled Medical Robotic Systems

An important issue in medical robotics is communication between physicians and robots. Speech-based communication is of particular advantage in robot-assisted surgery. It frees the surgeon's hands; hence, he can focus on the principal tasks. Man-machine voice communication is the subject of research in various domains (industry, social robotics), but medical robots are very specific. They must precisely synchronize their activities with operators. Voice commands must be possibly short. They must be executed without significant delays. An important factor is the use of a vision system that provides visual information in direct synchronization with surgeon actions. Its functions could be also controlled using speech. The aim of the research presented in this paper was to develop a method facilitating creation of voice-controlled medical robotic systems, fulfilling the mentioned requirements and taking into account possible scenarios of man-machine collaboration in such systems. A robot skill description (RSD) format was proposed in order to facilitate programming of voice control applications. A sample application was developed, and experiments were conducted in order to draw conclusions regarding the usefulness of speech-based interfaces in medical robotics. The results show that a reasonable selection of system functions controlled by voice may lead to significant improvement of man-machine collaboration.

Multistage adaptive control strategy based on image contour data for autonomous endoscope navigation

The physician burnout, poor ergonomics are hardly conducive to the sustainability and high quality of colonoscopy. In order to reduce doctors' workload and improve patients' experiences during colonoscopy, this paper proposes a multistage adaptive control approach based on image contour data to guide the autonomous navigation of endoscopes. First, a fast image preprocessing and contour extraction algorithms are designed. Second, different processing algorithms are developed according to the different contour information that can be clearly extracted to compute the endoscope control parameters. Third, when a clear contour cannot be extracted, a triple control method inspired by the turning of a novice car driver is devised to help the endoscope capture clear contours. The proposed multistage adaptive control approach is tested in an intestinal model over a variety of curved configurations and verified on the actual colonoscopy image. The results reveal the success of the strategy in both straight sections of this intestinal model and in tightly curved sections as small as 6 cm in radius of curvature. In the experiment, processing time for a single image is 20-25 ms and the accuracy of judging steering based on intestinal model pictures is 96.7%. Additionally, the average velocity reaches 3.04 cm/s in straight sections and 2.49 cm/s in curved sections respectively.