Deep-Learning-Based Cerebral Artery Semantic Segmentation in Neurosurgical Operating Microscope Vision Using Indocyanine Green Fluorescence Videoangiography

There have been few anatomical structure segmentation studies using deep learning. Numbers of training and ground truth images applied were small and the accuracies of which were low or inconsistent. For a surgical video anatomy analysis, various obstacles, including a variable fast-changing view, large deformations, occlusions, low illumination, and inadequate focus occur. In addition, it is difficult and costly to obtain a large and accurate dataset on operational video anatomical structures, including arteries. In this study, we investigated cerebral artery segmentation using an automatic ground-truth generation method. Indocyanine green (ICG) fluorescence intraoperative cerebral videoangiography was used to create a ground-truth dataset mainly for cerebral arteries and partly for cerebral blood vessels, including veins. Four different neural network models were trained using the dataset and compared. Before augmentation, 35,975 training images and 11,266 validation images were used. After augmentation, 260,499 training and 90,129 validation images were used. A Dice score of 79% for cerebral artery segmentation was achieved using the DeepLabv3+ model trained using an automatically generated dataset. Strict validation in different patient groups was conducted. Arteries were also discerned from the veins using the ICG videoangiography phase. We achieved fair accuracy, which demonstrated the appropriateness of the methodology. This study proved the feasibility of operating field view of the cerebral artery segmentation using deep learning, and the effectiveness of the automatic blood vessel ground truth generation method using ICG fluorescence videoangiography. Using this method, computer vision can discern blood vessels and arteries from veins in a neurosurgical microscope field of view. Thus, this technique is essential for neurosurgical field vessel anatomy-based navigation. In addition, surgical assistance, safety, and autonomous surgery neurorobotics that can detect or manipulate cerebral vessels would require computer vision to identify blood vessels and arteries.

Wearable Technology for Assessment and Surgical Assistance in Minimally Invasive Surgery

Wearable technology is an emerging field that has the potential to revolutionize healthcare. Advances in sensors, augmented reality devices, the internet of things, and artificial intelligence offer clinically relevant and promising functionalities in the field of surgery. Apart from its well-known benefits for the patient, minimally invasive surgery (MIS) is a technically demanding surgical discipline for the surgeon. In this regard, wearable technology has been used in various fields of application in MIS such as the assessment of the surgeon’s ergonomic conditions, interaction with the patient or the quality of surgical performance, as well as in providing tools for surgical planning and assistance during surgery. The aim of this chapter is to provide an overview based on the scientific literature and our experience regarding the use of wearable technology in MIS, both in experimental and clinical settings.

A remote and immersive setup for pandemic-safe surgical education

Existing challenges in surgical education (See one, do one, teach one) as well as the Covid-19 pandemic make it necessary to develop new ways for surgical training. This is also crucial for the dissemination of new technological developments. As today’s live transmissions of surgeries to remote locations always come with high information loss, e.g. stereoscopic depth perception, and limited communication channels. This work describes the implementation of a scalable remote solution for surgical training, called TeleSTAR (Telepresence for Surgical Assistance and Training using Augmented Reality), using immersive, interactive and augmented reality elements with a bi-lateral audio pipeline to foster direct communication. The system uses a full digital surgical microscope with a modular software-based AR interface, which consists of an interactive annotation mode to mark anatomical landmarks using an integrated touch panel as well as an intraoperative image-based stereo-spectral algorithm unit to measure anatomical details and highlight tissue characteristics.We broadcasted three cochlea implant surgeries in the context of otorhinolaryngology. The intervention scaled to five different remote locations in Germany and the Netherlands with lowlatency. In total, more than 150 persons could be reached and included an evaluation of a participant’s questionnaire indicating that annotated AR-based 3D live transmissions add an extra level of surgical transparency and improve the learning outcome.

Does fluoroscopy improve baseplate position compared to conventional technique in reverse shoulder arthroplasty? A preliminary study

Background Accurate placement of glenoid component in reverse shoulder arthroplasty remains a challenge for surgeons of all levels of expertise; however, no studies have evaluated the utility of fluoroscopy as a surgical assistance method. Methods Prospective comparative study of 33 patients undergoing primary reverse shoulder arthroplasty during a 12-month period. Fifteen patients had a baseplate placed using the conventional “free hand” technique (control group), and 18 patients using intraoperative fluoroscopy assistance group, in a case–control design. Postoperative glenoid position was evaluated on postoperative Computed Tomography (CT) scan. Results The mean deviation of version and inclination for fluoroscopy assistance vs. control group was 1.75° (0.675–3.125) vs. 4.2° (1.975–10.45) (p = .015), and 3.85° (0–7.225) vs. 10.35° (4.35–18.75) (p = .009). The distance from the central peg midpoint to the inferior glenoid rim (fluoroscopy assistance 14.61 mm/control 4.75 mm, p = .581) and the surgical time (fluoroscopy assistance 1.93 ± 0.57/control 2.18 ± 0.44 h, p = .400) showed no differences, with an average radiation dose of 0.45 mGy and fluoroscopy time of 14 s. Conclusions Accurate axial and coronal scapular plane positioning of glenoid component is improved with intraoperative fluoroscopy at the cost of a greater radiation dose and without differences in surgical time. Comparative studies are needed to determine whether their use in relation to more expensive surgical assistance systems result in similar effectiveness. Level of evidence: Level III, therapeutic study.

Organization and implementation of emergency ophthalmic surgical assistance in a specialized ophthalmic clinic during the Pandemic period COVID-19

Purpose. Evaluation of the frequency, structure and severity of the eye injuries, the effectiveness of the implementation of primary surgical treatment (PST) and the outcomes of their surgical treatment. Material and methods. In just a period from the end of March to December 2020, in the Khabarovsk branch the S. Fyodorov Eye Microsurgery Federal State Institution received 51 patients with various as penetrating (48 eyes) and imperriburing injuries of the eyeball (3 eyes). Their age varied widespread from 5 to 56 years (on average 35.5 years). Men were dominated among them – 44 people, women – 7 people. Adults were 49 people, children – 2 people. Results. Under the conditions of obtaining penetrating injuries, household injuries were isolated – 33 eyes (65%), production – 15 eyes (29%). The contusion injury of the eye was criminal, which was 6% (3 eyes). According to the localization of penetrating injuries or the impact of mechanical damage, they were presented: corneal wounds – 12 eyes, rootless – 17 eyes, scleral – 18 eyes. In 13 eyes, there was an intraocular foreign bodies (IFB). Conclusion. Thus, for the period from April to December 2020, in our branch, PST eyes were performed about 47 heavy penetrating injuries, including the introduction of IFB in 13 eyes, 4 eyes with extensive damage to conjunctiva. Among the victims were 49 adults and 2 children. Key words: penetrating eye wound, intraocular foreign body, microgery surgery, traumatic retinal detachment.

Applications of Smart Glasses in Applied Sciences: A Systematic Review

The aim of this study is to review academic papers on the applications of smart glasses. Among 82 surveyed papers, 57 were selected through filtering. The papers were published from January 2014 to October 2020. Four research questions were set up using the systematic review method, and conclusions were drawn focusing on the research trends by year and application fields; product and operating system; sensors depending on the application purpose; and data visualization, processing, and transfer methods. It was found that the most popular commercial smart glass products are Android-based Google products. In addition, smart glasses are most often used in the healthcare field, particularly for clinical and surgical assistance or for assisting mentally or physically disabled persons. For visual data transfer, 90% of the studies conducted used a camera sensor. Smart glasses have mainly been used to visualize data based on augmented reality, in contrast with the use of mixed reality. The results of this review indicate that research related to smart glasses is steadily increasing, and technological research into the development of smart glasses is being actively conducted.

Adoption of Robotic Arm-Assisted Total Hip Arthroplasty Results in Reliable Clinical and Radiographic Outcomes at Minimum Two-Year Follow Up

Introduction: Longevity and success of total hip arthroplasty (THA) is largely dependent on component positioning. While use of robotic platforms can improve this positioning, published evidence on its clinical benefits is limited. Therefore, the aim of this study was to assess the clinical outcomes of THA with robotic surgical assistance. Materials and Methods: We conducted an analysis of robotic arm-assisted primary THAs performed by a single surgeon utilizing a posterior approach. A total of 99 patients (107 cases) who had a minimum two-year follow up were identified. Their mean age was 61 years (range, 33 to 84 years), and their mean body mass index was 30.5 kg/m2 (range, 18.5 to 49.1 kg/m2). There were 56% female patients and primary osteoarthritis was the principal hip diagnosis in 88.8%. Operative times, lengths of hospital stay, and discharge dispositions were recorded, along with any complications. Modified Harris Hip Scores (HHS) were calculated to quantify clinical outcomes. Results: Mean postoperative increases in HHS at 2- to 5.7-year follow up was 33 points (range, 6 to 77 points). There were no complications attributable to the use of robotic assistance. Surgical-site complications were rare; one case underwent a revision for prosthetic joint infection (0.93%) but there were no dislocations, periprosthetic fractures, or cases of mechanical implant loosening. There was no evidence of progressive radiolucencies or radiographic failure. Discussion: Robotic arm-assisted THA resulted in low complication rates at minimum two-year follow up, with clinical outcomes comparable to those reported with manual surgery.1–4 The haptically-guided acetabular bone preparation enabled reliable cementless acetabular fixation and there were no adverse events related to the use of the robot. Dislocations were avoided in this case series. Randomized controlled clinical trials are needed to compare manual to robotic surgery and to investigate whether the precision found with this functional planning will reliably reduce the incidence of dislocations.

833 Hyper Acute Dialysis Access Pathway (HADAP) – Undertaking Creation of Arteriovenous Fistulae in The Renal Ward

Introduction The impetus to apply the “lean method” to creation of arteriovenous fistulae came with the pandemic restricting access to theatres. Here we present HADAP implemented in a dedicated procedure room in the Renal ward. Method Between April and September 2020, 44 patients underwent ward-based arteriovenous fistula operations with no more than 3 people in the room – surgeon, runner and patient. The parameters assessed were duration of operation, complications, patency, patient and surgeon feedback and financial implications. Results The service was predominantly registrar-led who created 91% of the fistulae. 95% operations were completed successfully with a 2-week primary patency of 73% and no surgical site infections. 40% of the procedures were radiocephalic fistulae. 14% procedures required surgical assistance by the runner. The average operating time reduced from 90 minutes for the first 10 cases to 50 minutes for the last 9. A structured questionnaire showed positive feedback from both patients and surgeons (4-5 out of 5). This service has cleared potentially 9 main theatre lists for more complex procedures. Conclusions Our study demonstrates the successful implementation of a novel operating environment allowing expedited care for renal failure patients. It has enhanced our ability to deliver a dialysis access program despite the challenges of COVID.

Spectroscopic Analysis of Parathyroid And Thyroid Tissues By Ground-State Diffuse Reflectance and Laser Induced Luminescence : A Preliminary Report

Intraoperative discrimination of thyroid and parathyroid tissues is fundamental in thyroid surgery. Recent fluorescence studies have shown stronger NIR emission in parathyroid tissue than in thyroid tissue, presenting a potential avenue for the development of a tool for surgical assistance. However, the fluorophore responsible for this emission has not yet been identified. In this work, spectroscopic analysis was performed to ascertain the origin of the emission peaks in parathyroid tissue. Ground-state diffuse reflectance (GSDR) absorption spectroscopy and laser-induced luminescence (LIL) emission spectroscopy were performed in parathyroid, thyroid, and fatty tissue samples and the resulting spectra were compared with the peaks of known fluorophores to identify the origin of each peak. The spectra of the different tissue types were also compared in order to evaluate the wavelength which presents the highest parathyroid emission relative to the emission of the surrounding tissues, representing the ideal wavelength for parathyroid detection. An emission peak in these conditions was observed for both thyroid and parathyroid tissue at 711 nm, with a higher intensity in parathyroid sample, making it suitable for detection applications. These results show a potential avenue for the development of a system allowing parathyroid detection in a surgical setting.