Deep learning for automatic segmentation of vestibular schwannoma: a retrospective study from multi-center routine MRI.

Automatic segmentation of vestibular schwannoma (VS) from routine clinical MRI has potential to improve clinical workflow, facilitate treatment decisions, and assist patient management. Previous work demonstrated reliable automatic segmentation performance on datasets of standardized MRI images acquired for stereotactic surgery planning. However, diagnostic clinical datasets are generally more diverse and pose a larger challenge to automatic segmentation algorithms, especially when post-operative images are included. In this work, we show for the first time that automatic segmentation of VS on routine MRI datasets is also possible with high accuracy. We acquired and publicly release a curated multi-center routine clinical (MC-RC) dataset of 160 patients with a single sporadic VS. For each patient up to three longitudinal MRI exams with contrast-enhanced T1-weighted (ceT1w) (n = 124) and T2-weighted (T2w) (n = 363) images were included and the VS manually annotated. Segmentations were produced and verified in an iterative process: (1) initial segmentations by a specialized company; (2) review by one of three trained radiologists; and (3) validation by an expert team. Inter- and intra-observer reliability experiments were performed on a subset of the dataset. A state-of-the-art deep learning framework was used to train segmentation models for VS. Model performance was evaluated on a MC-RC hold-out testing set, another public VS datasets, and a partially public dataset. The generalizability and robustness of the VS deep learning segmentation models increased significantly when trained on the MC-RC dataset. Dice similarity coefficients (DSC) achieved by our model are comparable to those achieved by trained radiologists in the inter-observer experiment. On the MC-RC testing set, median DSCs were 86.2(9.5) for ceT1w, 89.4(7.0) for T2w, and 86.4(8.6) for combined ceT1w+T2w input images. On another public dataset acquired for Gamma Knife stereotactic radiosurgery our model achieved median DSCs of 95.3(2.9), 92.8(3.8), and 95.5(3.3), respectively. In contrast, models trained on the Gamma Knife dataset did not generalize well as illustrated by significant underperformance on the MC-RC routine MRI dataset, highlighting the importance of data variability in the development of robust VS segmentation models. The MC-RC dataset and all trained deep learning models were made available online.

A comparative study of analytical models of diffuse reflectance in homogeneous biological tissues: Gelatin-based phantoms and Monte Carlo experiments.

Information about tissue oxygen saturation (StO2) and other related important physiological parameters can be extracted from diffuse reflectance spectra measured through non-contact imaging. Three analytical optical reflectance models for homogeneous, semi-infinite, tissue have been proposed (Modified Beer-Lambert, Jacques 1999, Yudovsky 2009) but these have not been directly compared for tissue parameter extraction purposes. We compare these analytical models using Monte Carlo (MC) simulated diffuse reflectance spectra and controlled gelatin-based phantoms with measured diffuse reflectance spectra and known ground truth composition parameters. The Yudovsky model performed best against MC simulations and measured spectra of tissue phantoms in terms of goodness of fit and parameter extraction accuracy followed closely by Jacques' model. In this study, Yudovsky's model appeared most robust; however, our results demonstrated that both Yudovsky and Jacques models are suitable for modeling tissue that can be approximated as a single, homogeneous, semi-infinite slab.

The Use of the Suboccipital Transtentorial Approach to the Posterior Inferior Incisural Space.

Objective To describe our experience with the microsurgical technique of the suboccipital transtentorial (SOTT) approach in the removal of posterior fossa lesions located in the posterior incisural space. Method Between 2002 and 2020 we reviewed all patients who underwent microsurgical resection of lesions of the posterior incisural space at the Department of Neurosurgery, Essex Neuroscience Centre, London, England (eight patients, male to female 3:5, mean age: 51, range 35-69). We describe the preoperative symptoms, radiological findings, surgical techniques, histology and postoperative outcomes in this cohort of patients. Results Eight patients with tumours located in the posterior incisural space underwent surgery during the study period including four meningiomas (50%), two haemangioblastomas (25%), one metastasis (13%) and one giant prolactinoma (13%). Gross or near total resection was achieved in six patients (75%): the giant prolactinoma could not be radically removed and one of the meningiomas required a small fragment to be left in place to protect the Vein of Galen. No patient developed a visual field deficit due to occipital lobe retraction. One patient developed a temporary trochlear nerve palsy (13%). Five patients had mild disability (Glasgow Outcome Scale (GOS) = 5), and four had moderate disability (GOS = 4). Conclusion In our series, the SOTT approach provided excellent access for all cases of tumours in the posterior incisural space. The tumour's size and relationship to the deep venous system contributed to the choice of approach and in one patient who had previously undergone surgery via the supracerebellar route, the SOTT approach enabled the avoidance of gliotic scar tissue. Success is dependent on careful case selection, though from our series of 8 patients, we conclude that this approach allows safe access to the posterior incisural space, with acceptable outcomes with regard to postoperative disability and cranial nerve palsy. As such, the approach should be in the armamentarium of any neurosurgeon who regularly deals with posterior fossa pathology.

Lightfield hyperspectral imaging in neuro-oncology surgery: an IDEAL 0 and 1 study.

Introduction: Hyperspectral imaging (HSI) has shown promise in the field of intra-operative imaging and tissue differentiation as it carries the capability to provide real-time information invisible to the naked eye whilst remaining label free. Previous iterations of intra-operative HSI systems have shown limitations, either due to carrying a large footprint limiting ease of use within the confines of a neurosurgical theater environment, having a slow image acquisition time, or by compromising spatial/spectral resolution in favor of improvements to the surgical workflow. Lightfield hyperspectral imaging is a novel technique that has the potential to facilitate video rate image acquisition whilst maintaining a high spectral resolution. Our pre-clinical and first-in-human studies (IDEAL 0 and 1, respectively) demonstrate the necessary steps leading to the first in-vivo use of a real-time lightfield hyperspectral system in neuro-oncology surgery. Methods: A lightfield hyperspectral camera (Cubert Ultris ×50) was integrated in a bespoke imaging system setup so that it could be safely adopted into the open neurosurgical workflow whilst maintaining sterility. Our system allowed the surgeon to capture in-vivo hyperspectral data (155 bands, 350-1,000 nm) at 1.5 Hz. Following successful implementation in a pre-clinical setup (IDEAL 0), our system was evaluated during brain tumor surgery in a single patient to remove a posterior fossa meningioma (IDEAL 1). Feedback from the theater team was analyzed and incorporated in a follow-up design aimed at implementing an IDEAL 2a study. Results: Focusing on our IDEAL 1 study results, hyperspectral information was acquired from the cerebellum and associated meningioma with minimal disruption to the neurosurgical workflow. To the best of our knowledge, this is the first demonstration of HSI acquisition with 100+ spectral bands at a frame rate over 1Hz in surgery. Discussion: This work demonstrated that a lightfield hyperspectral imaging system not only meets the design criteria and specifications outlined in an IDEAL-0 (pre-clinical) study, but also that it can translate into clinical practice as illustrated by a successful first in human study (IDEAL 1). This opens doors for further development and optimisation, given the increasing evidence that hyperspectral imaging can provide live, wide-field, and label-free intra-operative imaging and tissue differentiation.

Generating Operative Workflows for Vestibular Schwannoma Resection: A Two-Stage Delphi's Consensus in Collaboration with the British Skull Base Society. Part 2: The Translabyrinthine Approach.

Objective An operative workflow systematically compartmentalizes operations into hierarchal components of phases, steps, instrument, technique errors, and event errors. Operative workflow provides a foundation for education, training, and understanding of surgical variation. In this Part 2, we present a codified operative workflow for the translabyrinthine approach to vestibular schwannoma resection. Methods A mixed-method consensus process of literature review, small-group Delphi's consensus, followed by a national Delphi's consensus was performed in collaboration with British Skull Base Society (BSBS). Each Delphi's round was repeated until data saturation and over 90% consensus was reached. Results Seventeen consultant skull base surgeons (nine neurosurgeons and eight ENT [ear, nose, and throat]) with median of 13.9 years of experience (interquartile range: 18.1 years) of independent practice participated. There was a 100% response rate across both the Delphi rounds. The translabyrinthine approach had the following five phases and 57 unique steps: Phase 1, approach and exposure; Phase 2, mastoidectomy; Phase 3, internal auditory canal and dural opening; Phase 4, tumor debulking and excision; and Phase 5, closure. Conclusion We present Part 2 of a national, multicenter, consensus-derived, codified operative workflow for the translabyrinthine approach to vestibular schwannomas. The five phases contain the operative, steps, instruments, technique errors, and event errors. The codified translabyrinthine approach presented in this manuscript can serve as foundational research for future work, such as the application of artificial intelligence to vestibular schwannoma resection and comparative surgical research.

Generating Operative Workflows for Vestibular Schwannoma Resection: A Two-Stage Delphi's Consensus in Collaboration with the British Skull Base Society. Part 1: The Retrosigmoid Approach.

Objective An operative workflow systematically compartmentalizes operations into hierarchal components of phases, steps, instrument, technique errors, and event errors. Operative workflow provides a foundation for education, training, and understanding of surgical variation. In this Part 1, we present a codified operative workflow for the retrosigmoid approach to vestibular schwannoma resection. Methods A mixed-method consensus process of literature review, small-group Delphi's consensus, followed by a national Delphi's consensus, was performed in collaboration with British Skull Base Society (BSBS). Each Delphi's round was repeated until data saturation and over 90% consensus was reached. Results Eighteen consultant skull base surgeons (10 neurosurgeons and 8 ENT [ear, nose, and throat]) with median 17.9 years of experience (interquartile range: 17.5 years) of independent practice participated. There was a 100% response rate across both Delphi's rounds. The operative workflow for the retrosigmoid approach contained three phases and 40 unique steps as follows: phase 1, approach and exposure; phase 2, tumor debulking and excision; phase 3, closure. For the retrosigmoid approach, technique, and event error for each operative step was also described. Conclusion We present Part 1 of a national, multicenter, consensus-derived, codified operative workflow for the retrosigmoid approach to vestibular schwannomas that encompasses phases, steps, instruments, technique errors, and event errors. The codified retrosigmoid approach presented in this manuscript can serve as foundational research for future work, such as operative workflow analysis or neurosurgical simulation and education.

TISS-net: Brain tumor image synthesis and segmentation using cascaded dual-task networks and error-prediction consistency.

Accurate segmentation of brain tumors from medical images is important for diagnosis and treatment planning, and it often requires multi-modal or contrast-enhanced images. However, in practice some modalities of a patient may be absent. Synthesizing the missing modality has a potential for filling this gap and achieving high segmentation performance. Existing methods often treat the synthesis and segmentation tasks separately or consider them jointly but without effective regularization of the complex joint model, leading to limited performance. We propose a novel brain Tumor Image Synthesis and Segmentation network (TISS-Net) that obtains the synthesized target modality and segmentation of brain tumors end-to-end with high performance. First, we propose a dual-task-regularized generator that simultaneously obtains a synthesized target modality and a coarse segmentation, which leverages a tumor-aware synthesis loss with perceptibility regularization to minimize the high-level semantic domain gap between synthesized and real target modalities. Based on the synthesized image and the coarse segmentation, we further propose a dual-task segmentor that predicts a refined segmentation and error in the coarse segmentation simultaneously, where a consistency between these two predictions is introduced for regularization. Our TISS-Net was validated with two applications: synthesizing FLAIR images for whole glioma segmentation, and synthesizing contrast-enhanced T1 images for Vestibular Schwannoma segmentation. Experimental results showed that our TISS-Net largely improved the segmentation accuracy compared with direct segmentation from the available modalities, and it outperformed state-of-the-art image synthesis-based segmentation methods.

Synthetic white balancing for intra-operative hyperspectral imaging.

Purpose: Hyperspectral imaging shows promise for surgical applications to non-invasively provide spatially resolved, spectral information. For calibration purposes, a white reference image of a highly reflective Lambertian surface should be obtained under the same imaging conditions. Standard white references are not sterilizable and so are unsuitable for surgical environments. We demonstrate the necessity for in situ white references and address this by proposing a novel, sterile, synthetic reference construction algorithm. Approach: The use of references obtained at different distances and lighting conditions to the subject were examined. Spectral and color reconstructions were compared with standard measurements qualitatively and quantitatively, using ΔE and normalized RMSE, respectively. The algorithm forms a composite image from a video of a standard sterile ruler, whose imperfect reflectivity is compensated for. The reference is modeled as the product of independent spatial and spectral components, and a scalar factor accounting for gain, exposure, and light intensity. Evaluation of synthetic references against ideal but non-sterile references is performed using the same metrics alongside pixel-by-pixel errors. Finally, intraoperative integration is assessed though cadaveric experiments. Results: Improper white balancing leads to increases in all quantitative and qualitative errors. Synthetic references achieve median pixel-by-pixel errors lower than 6.5% and produce similar reconstructions and errors to an ideal reference. The algorithm integrated well into surgical workflow, achieving median pixel-by-pixel errors of 4.77% while maintaining good spectral and color reconstruction. Conclusions: We demonstrate the importance of in situ white referencing and present a novel synthetic referencing algorithm. This algorithm is suitable for surgery while maintaining the quality of classical data reconstruction.

Diffusion MRI of the facial-vestibulocochlear nerve complex: a prospective clinical validation study.

OBJECTIVES: Surgical planning of vestibular schwannoma surgery would benefit greatly from a robust method of delineating the facial-vestibulocochlear nerve complex with respect to the tumour. This study aimed to optimise a multi-shell readout-segmented diffusion-weighted imaging (rs-DWI) protocol and develop a novel post-processing pipeline to delineate the facial-vestibulocochlear complex within the skull base region, evaluating its accuracy intraoperatively using neuronavigation and tracked electrophysiological recordings. METHODS: In a prospective study of five healthy volunteers and five patients who underwent vestibular schwannoma surgery, rs-DWI was performed and colour tissue maps (CTM) and probabilistic tractography of the cranial nerves were generated. In patients, the average symmetric surface distance (ASSD) and 95% Hausdorff distance (HD-95) were calculated with reference to the neuroradiologist-approved facial nerve segmentation. The accuracy of patient results was assessed intraoperatively using neuronavigation and tracked electrophysiological recordings. RESULTS: Using CTM alone, the facial-vestibulocochlear complex of healthy volunteer subjects was visualised on 9/10 sides. CTM were generated in all 5 patients with vestibular schwannoma enabling the facial nerve to be accurately identified preoperatively. The mean ASSD between the annotators' two segmentations was 1.11 mm (SD 0.40) and the mean HD-95 was 4.62 mm (SD 1.78). The median distance from the nerve segmentation to a positive stimulation point was 1.21 mm (IQR 0.81-3.27 mm) and 2.03 mm (IQR 0.99-3.84 mm) for the two annotators, respectively. CONCLUSIONS: rs-DWI may be used to acquire dMRI data of the cranial nerves within the posterior fossa. CLINICAL RELEVANCE STATEMENT: Readout-segmented diffusion-weighted imaging and colour tissue mapping provide 1-2 mm spatially accurate imaging of the facial-vestibulocochlear nerve complex, enabling accurate preoperative localisation of the facial nerve. This study evaluated the technique in 5 healthy volunteers and 5 patients with vestibular schwannoma. KEY POINTS: • Readout-segmented diffusion-weighted imaging (rs-DWI) with colour tissue mapping (CTM) visualised the facial-vestibulocochlear nerve complex on 9/10 sides in 5 healthy volunteer subjects. • Using rs-DWI and CTM, the facial nerve was visualised in all 5 patients with vestibular schwannoma and within 1.21-2.03 mm of the nerve's true intraoperative location. • Reproducible results were obtained on different scanners.

Intraoperative bowel perfusion assessment methods and their effects on anastomotic leak rates: meta-analysis.

BACKGROUND: Anastomotic leak is one of the most feared complications of colorectal surgery, and probably linked to poor blood supply to the anastomotic site. Several technologies have been described for intraoperative assessment of bowel perfusion. This systematic review and meta-analysis aimed to evaluate the most frequently used bowel perfusion assessment modalities in elective colorectal procedures, and to assess their associated risk of anastomotic leak. Technologies included indocyanine green fluorescence angiography, diffuse reflectance spectroscopy, laser speckle contrast imaging, and hyperspectral imaging. METHODS: The review was preregistered with PROSPERO (CRD42021297299). A comprehensive literature search was performed using Embase, MEDLINE, Cochrane Library, Scopus, and Web of Science. The final search was undertaken on 29 July 2022. Data were extracted by two reviewers and the MINORS criteria were applied to assess the risk of bias. RESULTS: Some 66 eligible studies involving 11 560 participants were included. Indocyanine green fluorescence angiography was most used with 10 789 participants, followed by diffuse reflectance spectroscopy with 321, hyperspectral imaging with 265, and laser speckle contrast imaging with 185. In the meta-analysis, the total pooled effect of an intervention on anastomotic leak was 0.05 (95 per cent c.i. 0.04 to 0.07) in comparison with 0.10 (0.08 to 0.12) without. Use of indocyanine green fluorescence angiography, hyperspectral imaging, or laser speckle contrast imaging was associated with a significant reduction in anastomotic leak. CONCLUSION: Bowel perfusion assessment reduced the incidence of anastomotic leak, with intraoperative indocyanine green fluorescence angiography, hyperspectral imaging, and laser speckle contrast imaging all demonstrating comparable results.

Imaging biomarkers associated with extra-axial intracranial tumors: a systematic review.

Extra-axial brain tumors are extra-cerebral tumors and are usually benign. The choice of treatment for extra-axial tumors is often dependent on the growth of the tumor, and imaging plays a significant role in monitoring growth and clinical decision-making. This motivates the investigation of imaging biomarkers for these tumors that may be incorporated into clinical workflows to inform treatment decisions. The databases from Pubmed, Web of Science, Embase, and Medline were searched from 1 January 2000 to 7 March 2022, to systematically identify relevant publications in this area. All studies that used an imaging tool and found an association with a growth-related factor, including molecular markers, grade, survival, growth/progression, recurrence, and treatment outcomes, were included in this review. We included 42 studies, comprising 22 studies (50%) of patients with meningioma; 17 studies (38.6%) of patients with pituitary tumors; three studies (6.8%) of patients with vestibular schwannomas; and two studies (4.5%) of patients with solitary fibrous tumors. The included studies were explicitly and narratively analyzed according to tumor type and imaging tool. The risk of bias and concerns regarding applicability were assessed using QUADAS-2. Most studies (41/44) used statistics-based analysis methods, and a small number of studies (3/44) used machine learning. Our review highlights an opportunity for future work to focus on machine learning-based deep feature identification as biomarkers, combining various feature classes such as size, shape, and intensity. Systematic Review Registration: PROSPERO, CRD42022306922.

Fat in the Fossa and the Sphenoid Sinus: A Simple and Effective Solution to CSF Leaks in Transsphenoidal Surgery. Cohort Study and Systematic Review.

Objectives Cerebrospinal fluid (CSF) leak following endoscopic transsphenoidal surgery (TSS) remains a challenge and is associated with high morbidity. We perform a primary repair with f at in the pituitary f ossa and further fat in the s phenoid sinus (FFS). We compare the efficacy of this FFS technique with other repair methods and perform a systematic review. Design, Patients, and Methods This is a retrospective analysis of patients undergoing standard TSS from 2009 to 2020, comparing the incidence of significant postoperative CSF rhinorrhea (requiring intervention) using the FFS technique compared with other intraoperative repair strategies. Systematic review of current repair methods described in the literature was performed following the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. Results In all, there were 439 patients, with 276 patients undergoing multilayer repair, 68 patients FFS repair, and 95 patients no repair. No significant differences were observed in baseline demographics between the groups. Postoperative CSF leak requiring intervention was significantly lower in the FFS repair group (4.4%) compared with the multilayer (20.3%) and no repair groups (12.6%, p < 0.01). This translated to fewer reoperations (2.9% FFS vs. 13.4% multilayer vs. 8.4% no repair, p < 0.05), fewer lumbar drains (2.9% FFS vs. 15.6% multilayer vs. 5.3% no repair, p < 0.01), and shorter hospital stay (median days: 4 [3-7] FFS vs. 6 (5-10) multilayer vs. 5 (3-7) no repair, p < 0.01). Risk factors for postoperative leak included female gender, perioperative lumbar drain, and intraoperative leak. Conclusion Autologous fat on fat graft for standard endoscopic transsphenoidal approach effectively reduces the risk of significant postoperative CSF leak with reduced reoperation and shorter hospital stay.

Tractography-Enhanced Biopsy of Central Core Motor Eloquent Tumours: A Simulation-Based Study.

Safe Trajectory planning for navigation guided biopsy (nBx) of motor eloquent tumours (METs) is important to minimise neurological morbidity. Preliminary clinical data suggest that visualisation of the corticospinal tract (CST) and its relation to the tumour may aid in planning a safe trajectory. In this article we assess the impact of tractography in nBx planning in a simulation-based exercise. This single centre cross-sectional study was performed in March 2021 including 10 patients with METs divided into 2 groups: (1) tractography enhanced group (T-nBx; n = 5; CST merged with volumetric MRI); (2) anatomy-based group (A-nBx; n = 5; volumetric MRI only). A biopsy target was chosen on each tumour. Volunteer neurosurgical trainees had to plan a suitable biopsy trajectory on a Stealth S8® workstation for all patients in a single session. A trajectory safety index (TSI) was devised for each trajectory. Data collection and analysis included a comparison of trajectory planning time, trajectory/lobe changes and TSI. A total of 190 trajectories were analysed based on participation from 19 trainees. Mean trajectory planning time for the entire cohort was 225.1 ± 21.97 s. T-nBx required shorter time for planning (p = 0.01). Mean trajectory changes and lobe changes made per biopsy were 3.28 ± 0.29 and 0.45 ± 0.08, respectively. T-nBx required fewer trajectory/lobe changes (p = 0.01). TSI was better in the presence of tractography than A-nBx (p = 0.04). Neurosurgical experience of trainees had no significant impact on the measured parameters despite adjusted analysis. Irrespective of the level of neurosurgical training, surgical planning of navigation guided biopsy for METs may be achieved in less time with a safer trajectory if tractography imaging is available.

Spatial gradient consistency for unsupervised learning of hyperspectral demosaicking: application to surgical imaging.

PURPOSE: Hyperspectral imaging has the potential to improve intraoperative decision making if tissue characterisation is performed in real-time and with high-resolution. Hyperspectral snapshot mosaic sensors offer a promising approach due to their fast acquisition speed and compact size. However, a demosaicking algorithm is required to fully recover the spatial and spectral information of the snapshot images. Most state-of-the-art demosaicking algorithms require ground-truth training data with paired snapshot and high-resolution hyperspectral images, but such imagery pairs with the exact same scene are physically impossible to acquire in intraoperative settings. In this work, we present a fully unsupervised hyperspectral image demosaicking algorithm which only requires exemplar snapshot images for training purposes. METHODS: We regard hyperspectral demosaicking as an ill-posed linear inverse problem which we solve using a deep neural network. We take advantage of the spectral correlation occurring in natural scenes to design a novel inter spectral band regularisation term based on spatial gradient consistency. By combining our proposed term with standard regularisation techniques and exploiting a standard data fidelity term, we obtain an unsupervised loss function for training deep neural networks, which allows us to achieve real-time hyperspectral image demosaicking. RESULTS: Quantitative results on hyperspetral image datasets show that our unsupervised demosaicking approach can achieve similar performance to its supervised counter-part, and significantly outperform linear demosaicking. A qualitative user study on real snapshot hyperspectral surgical images confirms the results from the quantitative analysis. CONCLUSION: Our results suggest that the proposed unsupervised algorithm can achieve promising hyperspectral demosaicking in real-time thus advancing the suitability of the modality for intraoperative use.

CrossMoDA 2021 challenge: Benchmark of cross-modality domain adaptation techniques for vestibular schwannoma and cochlea segmentation.

Domain Adaptation (DA) has recently been of strong interest in the medical imaging community. While a large variety of DA techniques have been proposed for image segmentation, most of these techniques have been validated either on private datasets or on small publicly available datasets. Moreover, these datasets mostly addressed single-class problems. To tackle these limitations, the Cross-Modality Domain Adaptation (crossMoDA) challenge was organised in conjunction with the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021). CrossMoDA is the first large and multi-class benchmark for unsupervised cross-modality Domain Adaptation. The goal of the challenge is to segment two key brain structures involved in the follow-up and treatment planning of vestibular schwannoma (VS): the VS and the cochleas. Currently, the diagnosis and surveillance in patients with VS are commonly performed using contrast-enhanced T1 (ceT1) MR imaging. However, there is growing interest in using non-contrast imaging sequences such as high-resolution T2 (hrT2) imaging. For this reason, we established an unsupervised cross-modality segmentation benchmark. The training dataset provides annotated ceT1 scans (N=105) and unpaired non-annotated hrT2 scans (N=105). The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 scans as provided in the testing set (N=137). This problem is particularly challenging given the large intensity distribution gap across the modalities and the small volume of the structures. A total of 55 teams from 16 countries submitted predictions to the validation leaderboard. Among them, 16 teams from 9 different countries submitted their algorithm for the evaluation phase. The level of performance reached by the top-performing teams is strikingly high (best median Dice score - VS: 88.4%; Cochleas: 85.7%) and close to full supervision (median Dice score - VS: 92.5%; Cochleas: 87.7%). All top-performing methods made use of an image-to-image translation approach to transform the source-domain images into pseudo-target-domain images. A segmentation network was then trained using these generated images and the manual annotations provided for the source image.

The incidence and prevalence of unruptured intracranial aneurysms in sickle cell disease patients: a systematic review.

BACKGROUND: Unruptured Intracranial Aneurysms (UIAs) pose a significant risk of morbidity in the general population and much more so among sickle cell disease (SCD) patients. Meanwhile, the proportion of these patients with UIAs is not established just as the course and characteristics of the aneurysms are not well known. AIM: To estimate the prevalence, incidence and characteristics of UIAs in SCD patients and compare same with the metrics and features in the general population. METHODS: The Data repositories, Medline (PubMed), Embase and Web of science were systematically searched from January 1st, 1990, to July 31st, 2021. Publications that passed an inclusion test were reviewed for data on the incidence and prevalence of UIAs, aneurysm characteristics and outcomes in SCD patients extracted. Findings from the included studies were appraised, using the Methodological Index for Non-randomized studies score (MINORS). The results were descriptively analysed. Given the marked heterogeneity of retrieved data, results were reported as standardized values, including the mean weighted annual incidence rate. RESULTS: 105 SCD patients with 186 UIAs were identified in 10 retrospective studies. Mean age ranged from 10.5 to 40.18 across studies with adult (>18 years) predominance. The prevalence of UIAs in SCD was 4.1% (95%CI 3.6 and 4.6) incidence rate was 1290.3/100,000 patient-years (95% CI 1018.0-1562.6). Aneurysms tended to be small (60%), anterior (76.1%), multiple (45.7%), and managed conservatively (62%) with mostly good outcomes (95%). The average MINORS score was 9.4 ± 3.1 for non-comparative studies (n = 8) and 19.5 ± 0.7 for comparative studies (n = 2). CONCLUSION: UIAs have a definite relationship with SCD, with higher incidence figures relative to the general population. Aneurysmal characteristics although largely similar, tend to be smaller in SCD patients. The low methodological quality of reviewed studies informs the need for well-designed prospective randomized controlled studies to better understand the mechanics of this relationship.

Fully Endoscopic Microvascular Decompression for Trigeminal Neuralgia: Technical Note Describing a Single-Center Experience.

BACKGROUND: Microscopic microvascular decompression (MVD) of the trigeminal nerve is the gold standard surgical treatment for medically refractory classical trigeminal neuralgia. Endoscopy has significantly advanced surgery and provides enhanced visualization of the cerebellopontine angle and its critical neurovascular structures. We present our initial experience of fully endoscopic microvascular decompression (e-MVD). METHODS: This retrospective case series investigated e-MVD performed from September 2016 to February 2020 at a single institution. Clinical data including presenting symptoms, medications, operative findings, postoperative complications, and outcomes were recorded. The 5-point Barrow Neurological Institute (BNI) pain intensity score was used to quantify patients' pain relief. RESULTS: During the study period, 25 patients with trigeminal neuralgia (10 males, 15 females; mean [SD] age = 63 [10.4] years) underwent e-MVD. All patients had a preoperative BNI score of V. The left side was affected in 15 patients. Complications occurred in 2 patients: both experienced hearing loss, and one experienced transient facial weakness 7 days after surgery. The facial weakness had resolved by the last follow-up. All patients were completely pain-free (BNI score I) immediately postoperatively. On latest follow-up, 22 patients have remained pain-free, and 3 patients have recurrent pain that is being controlled with medication (BNI score III). CONCLUSIONS: Our study demonstrated that e-MVD is a safe, possibly effective method of performing MVD with the added benefit of improved visualization of the operative field for the operating surgeon and the surgical team. Larger prospective studies are required to evaluate whether performing e-MVD confers any additional benefits in long-term clinical outcome of patients with trigeminal neuralgia.

Localisation of the petrous internal carotid artery relative to the vidian canal on computed tomography: a case-control study evaluating the impact of petroclival chondrosarcoma.

BACKGROUND: The vidian canal (VC) is normally a reliable anatomical landmark for locating the petrous internal carotid artery (pICA). This study determined the influence of petroclival chondrosarcoma on the relationship between the VC and pICA. METHODS: Nine patients (3 males, 6 females; median age 49) with petroclival chondrosarcoma, and depiction of the pICA on contrast-enhanced CT, were retrospectively studied. CT-based measurements were performed by two observers, both in the presence of the petroclival chondrosarcoma (case) and on the contralateral control side. The antero-posterior (AP) and craniocaudal (CC) measurements from the posterior VC to the pICA, whether the pICA was in the trajectory of the VC, and the coronal relationship of the pICA anterior genu with the VC were recorded. RESULTS: Chondrosarcoma usually displaced the pICA anteriorly (8/9 cases) and superiorly (6/9 cases) relative to the normal side with mean AP and CC measurements of 3.9 mm v 7.2 mm (p = 0.054) and 4.4 mm v 1.4 mm (p = 0.061). The VC trajectory less frequently intersected the pICA cross-section in the presence of chondrosarcoma however it was in the line of the eroded dorsal VC in one case. The anterior genu of the pICA was displaced more laterally by chondrosarcoma but usually remained superior to the VC. CONCLUSION: Petroclival chondrosarcoma variably influences the anatomical relationship between the VC and the pICA, hence requiring an individualised approach. The pICA is usually anterosuperiorly displaced, and the anterior genu remains superior to the VC, however it may be located in the line of the canal.

Artificial intelligence and medical education: A global mixed-methods study of medical students' perspectives.

Objective: Medical students, as clinicians and healthcare leaders of the future, are key stakeholders in the clinical roll-out of artificial intelligence-driven technologies. The authors aim to provide the first report on the state of artificial intelligence in medical education globally by exploring the perspectives of medical students. Methods: The authors carried out a mixed-methods study of focus groups and surveys with 128 medical students from 48 countries. The study explored knowledge around artificial intelligence as well as what students wished to learn about artificial intelligence and how they wished to learn this. A combined qualitative and quantitative analysis was used. Results: Support for incorporating teaching on artificial intelligence into core curricula was ubiquitous across the globe, but few students had received teaching on artificial intelligence. Students showed knowledge on the applications of artificial intelligence in clinical medicine as well as on artificial intelligence ethics. They were interested in learning about clinical applications, algorithm development, coding and algorithm appraisal. Hackathon-style projects and multidisciplinary education involving computer science students were suggested for incorporation into the curriculum. Conclusions: Medical students from all countries should be provided teaching on artificial intelligence as part of their curriculum to develop skills and knowledge around artificial intelligence to ensure a patient-centred digital future in medicine. This teaching should focus on the applications of artificial intelligence in clinical medicine. Students should also be given the opportunity to be involved in algorithm development. Students in low- and middle-income countries require the foundational technology as well as robust teaching on artificial intelligence to ensure that they can drive innovation in their healthcare settings.