Distributed visual positioning for surgical instrument tracking.

In clinical operations, it is crucial for surgeons to know the location of the surgical instrument. Traditional positioning systems have difficulty dealing with camera occlusion, marker occlusion, and environmental interference. To address these issues, we propose a distributed visual positioning system for surgical instrument tracking in surgery. First, we design the marker pattern with a black and white triangular grid and dot that can be adapted to various instrument surfaces and improve the marker location accuracy of the feature. The cross-points in the marker are the features that each feature has a unique ID. Furthermore, we proposed detection and identification for the position-sensing marker to realize the accurate location and identification of features. Second, we introduce multi Perspective-n-Point (mPnP) method, which fuses feature coordinates from all cameras to deduce the final result directly by the intrinsic and extrinsic parameters. This method provides a reliable initial value for the Bundle Adjustment algorithms. During instrument tracking, we assess the motion state of the instrument and select either dynamic or static Kalman filtering to mitigate any jitter in the instrument's movement. The core algorithms comparison experiment indicates our positioning algorithm has a lower reprojection error comparison to the mainstream algorithms. A series of quantitative experiments showed that the proposed system positioning error is below 0.207 mm, and the run time is below 118.842 ms. The results demonstrate the tremendous clinical application potential of our system providing accurate positioning of instruments promoting the efficiency and safety of clinical surgery.

Efficient intraoral photogrammetry using self-identifying projective invariant marker.

PURPOSE: The re-measurement of full-arch implant digital impressions is an important step in denture restoration. This paper provides an efficient oral photogrammetry technology using projective invariant marker, applied in the re-measurement of full-arch implant digital impressions. METHODS: We have developed a self-recognizing marker with projection invariance, along with its detection code. The marker is installed on the scanning body and used for photogrammetric measurements. Triangulation is utilized to determine the 3D coordinates of the marker, followed by a series of post-processing steps to obtain more accurate 3D coordinates. RESULTS: The experimental data indicate that the optimal working distance is between 200 and 250 mm, with a minimum measurement error of less than 0.05 mm and an average measurement error of 0.10 mm. The measurement time is less than 2 min. CONCLUSIONS: The experimental results show that the photogrammetric system can obtain reliable positions of full-arch implants with efficient photogrammetry, without the need to enter the patient's oral cavity, and has potential clinical application value.

Hemodynamic characteristics and mechanism for intracranial aneurysms initiation with the circle of Willis anomaly.

Clinically, circle of Willis (CoW) is prone to anomaly and is also the predominant incidence site of intracranial aneurysms (IAs). This study aims to investigate the hemodynamic characteristics of CoW anomaly, and ascertain the mechanism of IAs initiation from the perspective of hemodynamics. Thus, the flow of IAs and pre-IAs were analyzed for one type of cerebral artery anomaly, that is, anterior cerebral artery A1 segment (ACA-A1) unilateral absence. Three patient geometrical models with IAs were selected from Emory University Open Source Data Center. IAs were virtually removed from the geometrical models to simulate the pre-IAs geometry. For calculation methods, a one-dimensional (1-D) solver and a three-dimensional (3-D) solver were combined to obtain the hemodynamic characteristics. The numerical simulation revealed that the average flow of Anterior Communicating Artery (ACoA) is almost zero when CoW is complete. In contrast, ACoA flow increases significantly in the case of ACA-A1 unilateral absence. For per-IAs geometry, the jet flow is found at the bifurcation between contralateral ACA-A1 and ACoA, which exhibits characteristics of high Wall Shear Stress (WSS) and high wall pressure in the impact region. It triggers the initiation of IAs from the perspective of hemodynamics. The vascular anomaly that leads to jet flow should be considered as a risk factor for IAs initiation.

Quantitative Evaluation of Hemodynamic Changes After Multiple Intracranial Aneurysms Occlusion Using Computational Fluid Dynamics.

OBJECTIVE: Multiple intracranial aneurysms (MIA) are prevalent. This study conducted hemodynamic calculations on MIA to analyze the effects of occlusion of the internal carotid artery (ICA) and middle cerebral artery (MCA) aneurysms on the hemodynamics of other arteries, as well as the issue of the treatment order for these aneurysms. METHODS: The models of 9 patients with MIA were selected for the study. A computational fluid dynamics model combining 1-dimension and 3-dimension was used to obtain the vascular flow pattern and wall pressure. RESULTS: There was increased pressure at the MCA and anterior cerebral artery (ACA) after occlusion of the aneurysm at the ICA. However, the pressure at the ICA has hardly changed after the aneurysm occlusion at the MCA. Occlusion of the aneurysm of different sizes at the MCA had almost no impact on the pressure at the ICA and ACA. For small aneurysm, the pressure of the ACA and MCA increases with decreasing size of the aneurysm at the ICA. After occlusion of a large aneurysm at the ICA, the impact on the pressure of the ACA and MCA is almost the same as after occlusion of a medium-sized aneurysm. CONCLUSIONS: If the treatment order of ICA and MCA aneurysms cannot be determined based on patient factors and aneurysm characteristics, the MCA aneurysm should be treated as a priority.

A Low-Cost Mobile-Based Augmented Reality Neuronavigation System for Retrosigmoid Craniotomy.

BACKGROUND AND OBJECTIVES: The correct positioning of the transverse-sigmoid sinus junction (TSSJ) during retrosigmoid craniotomy (RC) is crucial for enhancing surgical efficiency and preventing complications. An augmented reality technology may provide low-cost guidance for the TSSJ position. The authors aimed to investigate the clinical application of a self-developed mobile augmented reality navigation system (MARNS) for TSSJ positioning during RC and present their findings. METHODS: This observational research enrolled patients who underwent RC at Fujian Provincial Hospital from May 2023 to June 2023. All patients had their TSSJs located by MARNS. The surgical incision and skull "keyhole" for drilling were determined separately based on the projections of TSSJ on the 3-dimensional model displayed by MARNS. This method was assessed using matching error, positioning time, integrity of the bone flap, incidence of transversal sigmoid sinus injury, and other complications. RESULTS: Seven patients diagnosed with acoustic neuroma, trigeminal neuralgia, and hemifacial spasm were enrolled in this study. The MARNS system exhibited a matching error with an average magnitude of 2.88 ± 0.69 mm. The positioning procedure necessitated an average duration of 279.71 ± 27.29 seconds. In every instance, the inner edge of the TSSJ was precisely identified and exposed while the bone flap was successfully formed and maintained an average integrity of 86.7%. CONCLUSION: This study demonstrated the efficacy of MARNS in the precise placement of the TSSJ during RC procedures. It offers advantages for convenience, cost-effectiveness, and reliability for neurosurgical navigation.

Numerical Analysis of Stress Force on Vessel Walls in Atherosclerotic Plaque Removal through Coronary Rotational Atherectomy.

Coronary rotational atherectomy is an effective technique for treating cardiovascular disease by removing calcified tissue using small rotary grinding tools. However, it is difficult to analyze the stress force on vessel walls using experiments directly. Using computational fluid dynamics is a better way to study the stress force characteristics of the burr grinding procedure from a fluid dynamics perspective. For this purpose, physical and simulation models of atherosclerotic plaque removal were constructed in this study. The simulation results show that smaller ratios between the burr and arterial diameter (B/A = 0.5) result in a more stable flow field domain. Additionally, the pressure and stress force generated by the 4.5 mm diameter grinding tool reach 92.77 kPa and 10.36 kPa, surpassing those of the 2.5 mm and 3.5 mm grinding tools. The study has demonstrated the use of computational fluid dynamics to investigate wall shear stress characteristics in medical procedures, providing valuable guidance for optimizing the procedure and minimizing complications.

Gesture Classification in Electromyography Signals for Real-Time Prosthetic Hand Control Using a Convolutional Neural Network-Enhanced Channel Attention Model.

Accurate and real-time gesture recognition is required for the autonomous operation of prosthetic hand devices. This study employs a convolutional neural network-enhanced channel attention (CNN-ECA) model to provide a unique approach for surface electromyography (sEMG) gesture recognition. The introduction of the ECA module improves the model's capacity to extract features and focus on critical information in the sEMG data, thus simultaneously equipping the sEMG-controlled prosthetic hand systems with the characteristics of accurate gesture detection and real-time control. Furthermore, we suggest a preprocessing strategy for extracting envelope signals that incorporates Butterworth low-pass filtering and the fast Hilbert transform (FHT), which can successfully reduce noise interference and capture essential physiological information. Finally, the majority voting window technique is adopted to enhance the prediction results, further improving the accuracy and stability of the model. Overall, our multi-layered convolutional neural network model, in conjunction with envelope signal extraction and attention mechanisms, offers a promising and innovative approach for real-time control systems in prosthetic hands, allowing for precise fine motor actions.

Role of peptide-cell surface interactions in cosmetic peptide application.

Cosmetic peptides have gained popularity in a wide range of skincare products due to their good biocompatibility, effective anti-oxidative properties, and anti-aging effects. However, low binding between peptides and the cell surface limits the efficacy of functional peptides. In this study, we designed two novel targeting peptide motifs to enhance the interaction between cosmetic peptides and the cell surface, thereby improving their performance for skin health. To achieve this, we optimized the well-known peptide tripeptide-1 (GHK) by separately grafting the integrin αvß3-binding motif RGD and the chondroitin sulfate (CS)-binding motif sOtx2 onto it, forming two chimeric targeting peptides, RGD-GHK and sOtx2-GHK. Comparative analysis showed that both RGD-GHK and sOtx2-GHK exhibited superior anti-oxidative and anti-apoptotic effects compared to the non-targeting peptide, GHK. Furthermore, RGD-GHK demonstrated exceptional anti-aging activity, and its potential for promoting wound healing and repairing the skin barrier was evaluated in vitro using cells and skin models. In vitro permeation and in vivo adsorption testing confirmed that RGD-GHK achieved a high local concentration in the skin layer, initiating peptide effects and facilitating in vivo wound healing, while maintaining excellent biocompatibility. The enhancement of signaling cosmetic peptides can be attributed to the specific interaction between the binding motif and cell surface components. Consequently, this targeting peptide holds promising potential as a novel functional peptide for application in cosmetics.

Research and application of a teaching platform for combined spinal-epidural anesthesia based on virtual reality and haptic feedback technology.

BACKGROUND: Intraspinal anesthesia poses significant teaching challenges and inadequate teaching resources, which ultimately limit students' opportunities for practice. To address this issue, we aimed to develop a virtual platform for combined spinal-epidural anesthesia that merges virtual reality technology with haptic feedback technology, while assessing its educational impact and learning outcomes. METHODS: We utilized MIMICS, 3Ds MAX, and UNITY 3D software to perform 3D reconstruction based on lumbar CT/MRI data from a standard male volunteer. The haptic coefficients were configured on each layer by 20 experienced anesthesiologists in accordance with the Geomagic Touch X force feedback device. A total of 20 anesthesiology interns completed 30 virtual puncture training sessions. Two experienced anesthetists evaluated the efficacy of the platform and the level of mastery achieved using the Global Rating Scale (GRS) and a Checklist score, respectively. Finally, a questionnaire survey was conducted to gather feedback on the virtual platform. RESULTS: After the 10th session, the puncture time stabilized at 2.4 min. As the number of sessions increased, the Global Rating Scale (GRS) score stabilized by the 8th session, and the Checklist scores tended to stabilize by the 10th session. Results from questionnaires indicated that over half of the anesthesiology interns (70%) believed that the platform, which exhibited strong repeatability, improved their anatomical recognition and provided a strong sense of breakthrough in identifying the ligamentum flavum. The majority of them (80%) expressed satisfaction with the virtual platform. CONCLUSIONS: The platform effectively facilitated the acquisition of basic and accurate puncture skills on a virtual patient.

Mandibular resection and defect reconstruction guided by a contour registration-based augmented reality system: A preclinical trial.

The aim of this study was to verify the feasibility and accuracy of a contour registration-based augmented reality (AR) system in jaw surgery. An AR system was developed to display the interaction between virtual planning and images of the surgical site in real time. Several trials were performed with the guidance of the AR system and the surgical guide. The postoperative cone beam CT (CBCT) data were matched with the preoperatively planned data to evaluate the accuracy of the system by comparing the deviations in distance and angle. All procedures were performed successfully. In nine model trials, distance and angular deviations for the mandible, reconstructed fibula, and fixation screws were 1.62 ± 0.38 mm, 1.86 ± 0.43 mm, 1.67 ± 0.70 mm, and 3.68 ± 0.71°, 5.48 ± 2.06°, 7.50 ± 1.39°, respectively. In twelve animal trials, results of the AR system were compared with the surgical guide. Distance deviations for the bilateral condylar outer poles were 0.93 ± 0.63 mm and 0.81 ± 0.30 mm, respectively (p = 0.68). Distance deviations for the bilateral mandibular posterior angles were 2.01 ± 2.49 mm and 2.89 ± 1.83 mm, respectively (p = 0.50). Distance and angular deviations for the mandible were 1.41 ± 0.61 mm, 1.21 ± 0.18 mm (p = 0.45), and 6.81 ± 2.21°, 6.11 ± 2.93° (p = 0.65), respectively. Distance and angular deviations for the reconstructed tibiofibular bones were 0.88 ± 0.22 mm, 0.84 ± 0.18 mm (p = 0.70), and 6.47 ± 3.03°, 6.90 ± 4.01° (p = 0.84), respectively. This study proposed a contour registration-based AR system to assist surgeons in intuitively observing the surgical plan intraoperatively. The trial results indicated that this system had similar accuracy to the surgical guide.

Application of an effective marker-less augmented reality image guidance method in dental implant surgery.

BACKGROUND: The existing augmented reality (AR) dental implant surgery navigation system usually uses markers to complete image guidance. However, markers often affect dentists' operations and make patients uncomfortable. METHODS: To solve the problems caused by markers, this paper proposes an effective marker-less image guidance method. After initialisation is completed by contour matching, the corresponding relationship is obtained by matching the feature points between the current frame and the preloaded initial frame. The camera pose is estimated by solving the Perspective-n-Point problem. RESULTS: The registration error of AR images is 0.731 ± 0.144 mm. The planting errors are 1.174 ± 0.241 mm at the neck, 1.433 ± 0.389 mm at the apex and 5.566 ± 2.102° for the angle. The maximum error and standard deviation meet the clinical requirements. CONCLUSIONS: We demonstrate that the proposed method can accurately guide dentists to perform dental implant surgery.

A cationic motif upstream Engrailed2 homeodomain controls cell internalization through selective interaction with heparan sulfates.

Engrailed2 (En2) is a transcription factor that transfers from cell to cell through unconventional pathways. The poorly understood internalization mechanism of this cationic protein is proposed to require an initial interaction with cell-surface glycosaminoglycans (GAGs). To decipher the role of GAGs in En2 internalization, we have quantified the entry of its homeodomain region in model cells that differ in their content in cell-surface GAGs. The binding specificity to GAGs and the influence of this interaction on the structure and dynamics of En2 was also investigated at the amino acid level. Our results show that a high-affinity GAG-binding sequence (RKPKKKNPNKEDKRPR), upstream of the homeodomain, controls En2 internalization through selective interactions with highly-sulfated heparan sulfate GAGs. Our data underline the functional importance of the intrinsically disordered basic region upstream of En2 internalization domain, and demonstrate the critical role of GAGs as an entry gate, finely tuning homeoprotein capacity to internalize into cells.

Image-guided navigation system for minimally invasive total hip arthroplasty (MITHA) using an improved position-sensing marker.

PURPOSE: Minimally invasive total hip arthroplasty (MITHA) is a treatment for hip arthritis, and it causes less tissue trauma, blood loss, and recovery time. However, the limited incision makes it difficult for surgeons to perceive the instruments' location and orientation. Computer-assisted navigation systems can help improve the medical outcome of MITHA. Directly applying existing navigation systems for MITHA, however, suffers from problems of bulky fiducial marker, severe feature-loss, multiple instruments tracking confusion, and radiation exposure. To tackle these problems, we propose an image-guided navigation system for MITHA using a novel position-sensing marker. METHODS: A position-sensing marker is proposed to serve as the fiducial marker with high-density and multi-fold ID tags. It results in less feature span and enables the use of ID for each feature, overcoming the problem of bulky fiducial markers and multiple instruments tracking confusion. And the marker can be recognized even when a large part of locating features is obscured. As for the elimination of intraoperative radiation exposure, we propose a point-based method to achieve patient-image registration based on anatomical landmarks. RESULTS: Quantitative experiments are conducted to evaluate the feasibility of our system. The accuracy of instrument positioning is achieved at 0.33 ± 0.18 mm, and that of patient-image registration is achieved at 0.79 ± 0.15 mm. And qualitative experiments are also performed, verifying that our system can be used in compact surgical spatial volume and can address severe feature-loss and tracking confusion problems. In addition, our system does not require any intraoperative medical scans. CONCLUSION: Experimental results indicate that our proposed system can assist surgeons without larger space occupations, radiation exposure, and extra incision, showing its potential application value in MITHA.

HydraMarker: Efficient, Flexible, and Multifold Marker Field Generation.

An n-order marker field is a special binary matrix whose n×n subregions are all distinct from each other in four orientations. It is commonly used to guide the composing process of position-sensing markers, which can be detected and identified in a camera image with very limited scope or severe visibility problems. Despite the advantages, position-sensing markers are rare and overlooked because generating marker fields is difficult. In this article, we broaden the definition of marker field, making it more powerful and flexible. Then, we propose bWFC (binary wave function collapse) and its high-speed version, fast-bWFC, to solve the generation problem. The methods are packaged into an open-sourced toolkit named HydraMarker, with which, users not only can generate marker fields on laptops within a short period of time, but also can highly customize them: preset values; fields and subregions in any shape; multifold local uniqueness. Comparative results indicate that the proposed method has superior efficiency, quality, and capability. It makes marker field generation accessible to common marker designers, opening up more possibilities for fiducial markers.

Evolution of novel grinding tool in removing coronary artery calcification tissue process.

Coronary rotational atherectomy (CRA) means of use a tiny grinding tool to rotate at high speed in the blood vessels, so as to remove calcified tissue, effectively enlarge the inner diameter of the vessels, which is an important tool for the treatment of cardiovascular calcified blockage. However, excessive grinding force, temperature and debris size can lead to serious surgical complications and endanger the patient life during CRA. This study introduces the design, fabrication and performance verification process of a novel grinding tool, and investigates the influence of tool geometrical parameters and grinding parameters The experimental results showed that: the novel grinding tool can effectively remove the simulated calcified tissue by grinding. The geometrical size of tools plays an important effect on the grinding properties, which can result in increasing grinding force, temperature and debris size with the increase of tool diameters. In addition, with the increase of rotational speed, the grinding force and temperature increase gradually, while the debris size decreases as the rotational speed increases. The increasing inner diameter of bone can also lead to a decrease in grinding force and temperature slightly. All the obtained results can give effective guidance for clinical operations.

Anti-Inflammatory and Antioxidant Properties of Physalis alkekengi L. Extracts In Vitro and In Vivo: Potential Application for Skin Care.

Objective: Inflammatory skin disorders are becoming major issues threatening public health with increasing prevalence. This study was to evaluate the anti-inflammatory, antioxidant, and antisenescent activities of traditional folk medicinal plant, Physalis alkekengi L. extracts to alleviate skin inflammation and its possible mechanisms. Methods: Lipopolysaccharides (LPS)-treated murine macrophages RAW264.7 and human skin keratinocytes HaCaT were incubated with the plant extracts, respectively. The production of nitric oxide (NO) was tested by using Griess reagents. The activity of nitric oxide synthase (NOS) was detected through a fluorescence microplate reader. Reactive oxygen species (ROS) production and cell apoptosis were quantified by flow cytometry. The proinflammatory cytokines were measured using ELISA and qRT-PCR. Human skin fibroblasts (HFF-1) were coincubated with D-galactose (D-gal) and the plant extracts. The senescence associated-galactosidase (SA-ß-gal) was stained to evaluate cellular senescence. The senescence-associated secretory phenotype (SASP), IL-1ß, was measured through ELISA. The mRNA of IL-1α in SLS-stimulated and PGE2 in UV-radiated 3D skin models were detected by qRT-PCR. In vivo ROS production and neutrophil recruitment in CuSO4-treated zebrafish models were observed by fluorescence microscopy. Inflammation-related factors were measured by qRT-PCR. Results. In vitro, Physalis alkekengi L. significantly reduced NO production, NOS activity, cell apoptosis, transcription of TNF-α, IL-6, IL-1ß and ROS production. These plant extracts markedly attenuated SA-ß-gal and IL-1ß and downregulated the production of IL-1α and PGE2. In vivo, the plant extracts dramatically dampened ROS production, the number of neutrophils, and proinflammatory cytokines. Conclusions: Cumulatively, this work systematically demonstrated the anti-inflammatory, antioxidant, and antisenescent properties of Physalis alkekengi L. and proposed the possible roles of Physalis alkekengi L. in inflammatory signaling pathways, providing an effective natural product for the treatment of inflammatory skin disorders.

Augmented reality for oral and maxillofacial surgery: The feasibility of a marker-free registration method.

BACKGROUND: Recognition of markers in the augmented reality system can reduce the additional cost of a guide plate required for the removal of benign tumours in oral and maxillofacial surgery, but the use of markers often has complex problems. METHOD: In order to avoid the complex problem of using markers, an augmented reality system based on a marker-free registration method was proposed to track the contour of the mandible edge. Use the computer to perform preoperative planning on the jaw model, select and mark the path of maxillofacial lesion resection. RESULTS: This method has an error of the surface matching was 0.6453 ± 0.2826 $0.6453\pm 0.2826$ mm, and an error of the surgical resection was 0.4858 ± 0.3712 $0.4858\pm 0.3712$ mm. CONCLUSIONS: We demonstrate that the system can accurately enhance the display of the surgical path and provide guidance for the tradition of maxillofacial surgery.

Large-area flexible MWCNT/PDMS pressure sensor for ergonomic design with aid of deep learning learning.

The achievement of well-performing pressure sensors with low pressure detection, high sensitivity, large-scale integration, and effective analysis of the subsequent data remains a major challenge in the development of flexible piezoresistive sensors. In this study, a simple and extendable sensor preparation strategy was proposed to fabricate flexible sensors on the basis of multiwalled carbon nanotube/polydimethylsiloxane (MWCNT/PDMS) composites. A dispersant of tetrahydrofuran (THF) was added to solve the agglomeration of MWCNTs in PDMS, and the resistance of the obtained MWCNT/PDMS conductive unit with 7.5 wt.% MWCNTs were as low as 180 Ω/hemisphere. Sensitivity (0.004 kPa-1), excellent response stability, fast response time (36 ms), and excellent electromechanical properties were demonstrated within the pressure range from 0 to 100 kPa. A large-area flexible sensor with 8 × 10 pixels was successfully adopted to detect the pressure distribution on the human back and to verify its applicability. Combining the sensor array with deep learning, inclination of human sitting was easily recognized with high accuracy, indicating that the combined technology can be used to guide ergonomic design.

Immersive Virtual Reality-Based Cognitive Intervention for the Improvement of Cognitive Function, Depression, and Perceived Stress in Older Adults With Mild Cognitive Impairment and Mild Dementia: Pilot Pre-Post Study.

BACKGROUND: The incidence of dementia is increasing annually, resulting in varying degrees of adverse effects for individuals, families, and society. With the continuous development of computer information technology, cognitive interventions are constantly evolving. The use of immersive virtual reality (IVR) as a cognitive intervention for older adults with mild cognitive impairment (MCI) and mild dementia (MD) is promising, although only few studies have focused on its use. OBJECTIVE: The Chinese virtual supermarket (CVSM) IVR system was developed to provide a comprehensive and individual cognitive intervention program for older patients with MCI and MD. The aim of this study was to explore the feasibility and clinical effectiveness of this 5-week IVR-based cognitive intervention. METHODS: A pretest-posttest study design was conducted with 31 older adults with MCI and MD from August 2020 to January 2021. All participants participated in a 5-week immersive virtual cognitive training program using the CVSM system. Feasibility was assessed as the incidence and severity of cybersickness symptoms and participant satisfaction based on questionnaires conducted after the intervention. Clinical effectiveness was evaluated using neuropsychological assessments, including several commonly used measures of cognitive function, depression, perceived stress, and activities of daily living. Measurements were obtained at baseline and after the intervention period. RESULTS: A total of 18 patients with MCI (mean age 82.94 [SD 5.44] years; 12 females) and 13 patients with MD (mean age 85.7 [SD 4.67] years, 10 females) participated in this pilot study. Both groups showed significant improvements in all cognitive function measurements (P<.001). The MD group had a significantly greater improvement in general cognitive function compared to the MCI group in Montreal Cognitive Assessment Scale, Symbol Digit Modalities Test, Shape Trail Test, and Auditory Verbal Learning Test. Furthermore, an intervention effect was observed in the improvement of perceived stress (P=.048 for MD group, P=.03 for MCI group ). CONCLUSIONS: The use of the CVSM system may be effective in enhancing the cognitive function of patients with MCI and MD, including general cognitive function, memory, executive function, and attention. IVR technology enriches cognitive intervention approaches and provides acceptable, professional, personalized, and interesting cognitive training for older adults with cognitive impairment. TRIAL REGISTRATION: ClinicalTrials ChiCTR2100043753; https://trialsearch.who.int/Trial2.aspx?TrialID=ChiCTR2100043753.

Coarse-to-fine airway segmentation using multi information fusion network and CNN-based region growing.

BACKGROUND AND OBJECTIVES: Automatic airway segmentation from chest computed tomography (CT) scans plays an important role in pulmonary disease diagnosis and computer-assisted therapy. However, low contrast at peripheral branches and complex tree-like structures remain as two mainly challenges for airway segmentation. Recent research has illustrated that deep learning methods perform well in segmentation tasks. Motivated by these works, a coarse-to-fine segmentation framework is proposed to obtain a complete airway tree. METHODS: Our framework segments the overall airway and small branches via the multi-information fusion convolution neural network (Mif-CNN) and the CNN-based region growing, respectively. In Mif-CNN, atrous spatial pyramid pooling (ASPP) is integrated into a u-shaped network, and it can expend the receptive field and capture multi-scale information. Meanwhile, boundary and location information are incorporated into semantic information. These information are fused to help Mif-CNN utilize additional context knowledge and useful features. To improve the performance of the segmentation result, the CNN-based region growing method is designed to focus on obtaining small branches. A voxel classification network (VCN), which can entirely capture the rich information around each voxel, is applied to classify the voxels into airway and non-airway. In addition, a shape reconstruction method is used to refine the airway tree. RESULTS: We evaluate our method on a private dataset and a public dataset from EXACT09. Compared with the segmentation results from other methods, our method demonstrated promising accuracy in complete airway tree segmentation. In the private dataset, the Dice similarity coefficient (DSC), Intersection over Union (IoU), false positive rate (FPR), and sensitivity are 93.5%, 87.8%, 0.015%, and 90.8%, respectively. In the public dataset, the DSC, IoU, FPR, and sensitivity are 95.8%, 91.9%, 0.053% and 96.6%, respectively. CONCLUSION: The proposed Mif-CNN and CNN-based region growing method segment the airway tree accurately and efficiently in CT scans. Experimental results also demonstrate that the framework is ready for application in computer-aided diagnosis systems for lung disease and other related works.