An Accurate Recognition of Infrared Retro-Reflective Markers in Surgical Navigation.

Marker-based optical tracking systems (OTS) are widely used in clinical image-guided therapy. However, the emergence of ghost markers, which is caused by the mistaken recognition of markers and the incorrect correspondences between marker projections, may lead to tracking failures for these systems. Therefore, this paper proposes a strategy to prevent the emergence of ghost markers by identifying markers based on the features of their projections, finding the correspondences between marker projections based on the geometric information provided by markers, and fast-tracking markers in a 2D image between frames based on the sizes of their projections. Apart from validating its high robustness, the experimental results show that the proposed strategy can accurately recognize markers, correctly identify their correspondences, and meet the requirements of real-time tracking.

Convolutional neural network application for supply-demand matching in Zhuang ethnic clothing image classification.

This study aims to design a classification technique suitable for Zhuang ethnic clothing images by integrating the concept of supply-demand matching and convolutional neural networks. Firstly, addressing the complex structure and unique visual style of Zhuang ethnic clothing, this study proposes an image resolution model based on supply-demand matching and convolutional networks. By integrating visual style and label constraints, this model accurately extracts local features. Secondly, the model's effectiveness and resolution performance are analyzed through various performance metrics in experiments. The results indicate a significant improvement in detection accuracy at different annotation points. The model outperforms other comparative methods in pixel accuracy (90.5%), average precision (83.7%), average recall (80.1%), and average F1 score (81.2%). Next, this study introduces a clothing image classification algorithm based on key points and channel attention. Through key point detection and channel attention mechanisms, image features are optimized, enabling accurate classification and attribute prediction of Zhuang ethnic clothing. Experimental results demonstrate a notable enhancement in category classification and attribute prediction, with classification accuracy and recall exceeding 90% in top-k tasks, showcasing outstanding performance. In conclusion, this study provides innovative approaches and effective solutions for deep learning classification of Zhuang ethnic clothing images.

Biomechanical behavior of deep anterior lamellar keratoplasty: a finite element analysis.

Deep Anterior Lamellar Keratoplasty (DALK) is a surgical procedure used to restore sight and manage corneal diseases by replacing cloudy corneal tissue with allogeneic normal corneal tissue or artificial corneal material. However, the limited availability and mechanical defects of artificial corneal materials pose challenges in DALK. To predicting postoperative mechanical behavior of Deep Anterior Lamellar Keratoplasty (DALK), a three-dimensional finite element model of the postoperative DALK cornea with suture holes was developed. The postoperative corneal displacement and von Mises (VM) stress changes were also simulated under varying depths of cut (DOC: 0.16-0.26 µm), intraocular pressure (IOP: 12, 15, 18 mmHg), and central corneal thickness (CCT: 420-620 µm). The model indicated that higher IOP and CCT were associated with improved postoperative corneal stability. The postoperative corneal displacement increased from the edge to the center, while the maximum VM stress value occurs at the corneal suture hole. Corneal displacement and VM stress decrease with increasing CCT and decreasing IOP. DOC has a slight effect on corneal displacement and VM stress, with an overall positive relationship. The model has potential application in the preoperative assessment of risk in keratoplasty.

Prediction of acute kidney injury in ICU with gradient boosting decision tree algorithms.

PURPOSE: To predict acute kidney injury (AKI) in a large intensive care unit (ICU) database. MATERIALS AND METHODS: A total of 30,020 ICU admissions with 17,222 AKI episodes were extracted from the Medical Information Mart from Intensive Care (MIMIC)-III database. These were randomly divided into a training set and an independent testing set in a ratio of 4:1. Data pertaining to demographics, admission information, vital signs, laboratory tests, critical illness scores, medications, comorbidities, and intervention measures were collected. Logistic regression, random forest, LightGBM, XGBoost, and an ensemble model was used for early prediction of AKI occurrence and important feature extraction. The SHAP analysis was adopted to reveal the impact of prediction for each feature. RESULTS: The ensemble model had the best overall performance for predicting AKI before 24 h, 48 h and 72 h. The F1 values were 0.915, 0.893, and 0.878, respectively. AUCs were 0.923, 0.903, and 0.895, respectively. CONCLUSIONS: Based on readily available electronic medical record (EMR) data, gradient boosting decision tree models are highly accurate at early AKI prediction in critically ill patients.

Rupture Risk Assessment of Cervical Spinal Manipulations on Carotid Atherosclerotic Plaque by a 3D Fluid-Structure Interaction Model.

METHOD: The FSI model, based on MRI data of an atherosclerosis patient, was used to simulate the deformations of the plaque and lumen during the process of two kinds of typical cSMT (the high-speed, low-amplitude spinal manipulation and the cervical rotatory manipulation). The biomechanical parameters were recorded, such as the highest wall shear stress (WSS), the maximum plaque wall stress (PWS), the wall tensile stress (Von mises stress, VWTS), and the strain. RESULT: The max_WSS was 33.77 kPa in the most extensive deformation. The highest WSS region on the plaque surface was also the highest PWS region. The max_PWS in a 12% stretch was 55.11 kPa, which was lower than the rupture threshold. The max_VWTS of the cap in 12% stretch which approached the fracture stress level was 116.75 kPa. Moreover, the vessel's max_VWTS values in 10% and 12% stretch were 554.21 and 855.19 kPa. They were higher than the fracture threshold, which might cause media fracture. Meanwhile, the 7% stretched strain was 0.29, closed to the smallest experimental green strains at rupture. CONCLUSION: The carotid arteries' higher stretch generated the higher stress level of the plaque. Cervical rotatory manipulation might cause plaque at a high risk of rupture in deformation after 12% stretch and more. Lower deformation of the plaque and artery caused by the high-speed, low-amplitude spinal manipulation might be safer.