Search Results (6)

This paper presents FWStab, a specialized video stabilization dataset tailored for flapping-wing platforms. The dataset encompasses five typical flight scenarios, featuring 48 video clips with intense dynamic jitter. The corresponding Inertial Measurement Unit (IMU) sensor data are synchronously collected, which jointly provide reliable support for multimodal modeling. Based on this, to address the issue of poor image acquisition quality due to severe vibrations in aerial vehicles, this paper proposes a multi-modal signal fusion video stabilization framework. This framework effectively integrates image features and inertial sensor features to predict smooth and stable camera poses. During the video stabilization process, the true camera motion originally estimated based on sensors is warped to the smooth trajectory predicted by the network, thereby optimizing the inter-frame stability. This approach maintains the global rigidity of scene motion, avoids visual artifacts caused by traditional dense optical flow-based spatiotemporal warping, and rectifies rolling shutter-induced distortions. Furthermore, the network is trained in an unsupervised manner by leveraging a joint loss function that integrates camera pose smoothness and optical flow residuals. When coupled with a multi-stage training strategy, this framework demonstrates remarkable stabilization adaptability across a wide range of scenarios. The entire framework employs Long Short-Term Memory (LSTM) to model the temporal characteristics of camera trajectories, enabling high-precision prediction of smooth trajectories. Full article

Background and Objectives: Microvascular flap surgery is a widely used reconstructive technique for the repair of various defects. Biomarkers have become an essential tool for monitoring flap viability, early detection of complications, and prediction of surgical outcomes. Studies focusing on immunomodulatory cytokines in the early prediction of microvascular flap complications are lacking. We aimed to investigate the predictive value of postoperative changes in transforming growth factor beta-1 (TGF-β1) for microvascular flap complications. Materials and Methods: This prospective observational study comprised 44 adults scheduled for elective microvascular flap surgery. Preoperative blood samples for analysis were obtained before surgery, prior to the administration of intravenous fluids. Postoperative blood draws were collected after surgery, before leaving the operating room. Preoperative and postoperative serum concentrations of TGF-β1, as well as preoperative plasma albumin, total protein, total cholesterol, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, full blood count, albumin, interleukin-6, C-reactive protein, and fibrinogen, were determined. Results: Postoperative changes in TGF-β1 were higher in cases with flap loss compared to patients with healthy recovery or patients with minor flap complications (0.403 log10 of ng/mL [0.024–0.782] vs. 0.157 [0.029–0.285] vs. −0.089 [−0.233–0.056], p = 0.002). Increased postoperative TGF-β1 was positively linked to preoperative C-reactive protein (p = 0.021), fibrinogen (p = 0.020), hematocrit (p = 0.039), and hemoglobin (p = 0.009). Conclusions: The postoperative increase in circulating TGF-β1 was associated with microvascular flap complications. Assessment of the postoperative changes in circulating TGF-β1 may be valuable for the early postoperative prediction of true flap loss. Full article

Background: Microvascular flap surgery has become a routine option for defect correction. The role of von Willebrand factor antigen (VWF:Ag) in the pathophysiology of flap complications is not fully understood. We aim to investigate the predictive value of VWF:Ag for microvascular flap complications and explore the relationship between chronic inflammation and VWF:Ag. Methods: This prospective cohort study included 88 adult patients undergoing elective microvascular flap surgery. Preoperative blood draws were collected on the day of surgery before initiation of crystalloids. The plasma concentration of VWF:Ag as well as albumin, neutrophil-to-lymphocyte ratio (NLR), interleukin-6, and fibrinogen were determined. Results: The overall complication rate was 27.3%, and true flap loss occurred in 11.4%. VWF:Ag levels were higher in true flap loss when compared to patients without complications (217.94 IU/dL [137.27–298.45] vs. 114.14 [95.67–132.71], p = 0.001). Regression analysis revealed the association between VWF:Ag and true flap loss at the cutoff of 163.73 IU/dL (OR 70.22 [10.74–485.28], p = 0.043). Increased VWF:Ag concentrations were linked to increases in plasma fibrinogen (p < 0.001), C-reactive protein (p < 0.001), interleukin-6 (p = 0.032), and NLR (p = 0.019). Conclusions: Preoperative plasma VWF:Ag concentration is linked to biomarkers of inflammation and may be valuable in predicting complications in microvascular flap surgery. Full article

Purpose: Type A aortic dissection (TAAD) is a life-threatening aortic disease. The tear involves the ascending aorta and progresses into the separation of the layers of the aortic wall and the occurrence of a false lumen. Accurate segmentation of TAAD could provide assistance for disease assessment and guidance for clinical treatment. Methods: This study applied nnU-Net, a state-of-the-art biomedical segmentation network architecture, to segment contrast-enhanced CT images and quantify the morphological features for TAAD. CT datasets were acquired from 24 patients with TAAD. Manual segmentation and annotation of the CT images was used as the ground-truth. Two-dimensional (2D) nnU-Net and three-dimensional (3D) nnU-Net architectures with Dice- and cross entropy-based loss functions were utilized to segment the true lumen (TL), false lumen (FL), and intimal flap on the images. Four-fold cross validation was performed to evaluate the performance of the two nnU-Net architectures. Six metrics, including accuracy, precision, recall, Intersection of Union, Dice similarity coefficient (DSC), and Hausdorff distance, were calculated to evaluate the performance of the 2D and 3D nnU-Net algorithms in TAAD datasets. Aortic morphological features from both 2D and 3D nnU-Net algorithms were quantified based on the segmented results and compared. Results: Overall, 3D nnU-Net architectures had better performance in TAAD CT datasets, with TL and FL segmentation accuracy up to 99.9%. The DSCs of TLs and FLs based on the 3D nnU-Net were 88.42% and 87.10%. For the aortic TL and FL diameters, the FL area calculated from the segmentation results of the 3D nnU-Net architecture had smaller relative errors (3.89–6.80%), compared to the 2D nnU-Net architecture (relative errors: 4.35–9.48%). Conclusions: The nnU-Net architectures may serve as a basis for automatic segmentation and quantification of TAAD, which could aid in rapid diagnosis, surgical planning, and subsequent biomechanical simulation of the aorta. Full article

Microvascular flap surgery is a widely acknowledged procedure for significant defect reconstruction. Multiple flap complication risk factors have been identified, yet there are limited data on laboratory biomarkers for the prediction of flap loss. The controlling nutritional status (CONUT) score has demonstrated good postoperative outcome assessment ability in diverse surgical populations. We aim to assess the predictive value of the CONUT score for complications in microvascular flap surgery. This prospective cohort study includes 72 adult patients undergoing elective microvascular flap surgery. Preoperative blood draws for analysis of full blood count, total plasma cholesterol, and albumin concentrations were collected on the day of surgery before crystalloid infusion. Postoperative data on flap complications and duration of hospitalization were obtained. The overall complication rate was 15.2%. True flap loss with vascular compromise occurred in 5.6%. No differences in flap complications were found between different areas of reconstruction, anatomical flap types, or indications for surgery. Obesity was more common in patients with flap complications (p = 0.01). The CONUT score had an AUC of 0.813 (0.659–0.967, p = 0.012) for predicting complications other than true flap loss due to vascular compromise. A CONUT score > 2 was indicated as optimal during cut-off analysis (p = 0.022). Patients with flap complications had a longer duration of hospitalization (13.55, 10.99–16.11 vs. 25.38, 14.82–35.93; p = 0.004). Our findings indicate that the CONUT score has considerable predictive value in microvascular flap surgery. Full article

Primary restoration of the mandibular continuity remains the standard of care for defects, and yet several constraints preclude this objective. Interim reconstructions with plate and nonvascular bone grafts have high failure rates. The secondary reconstruction, when becomes inevitable, remains a formidable task. This retrospective study evaluates various issues to address secondary reconstruction. Twenty-one patients following mandibulectomy presented with various complications between 2012 and 2016 were included in the study. The profile of primary reconstruction includes reconstruction plate (n = 9), reconstruction plate with rib graft (n = 3), soft tissue only reconstruction (n = 4), free fibula (n = 2), inadequate growth of reconstructed free fibula during adolescence (n = 1), nonvascular bone graft alone (n = 1), and no reconstruction (n = 1). All had problems or complications related to unsatisfactory primary reconstruction such as plate fracture, recurrent infection, plate exposure, deformity, malocclusion, and failed fibula reconstruction. All were reconstructed with osteocutaneous free fibula flap with repair of soft-tissue loss. All flaps survived and had satisfactory outcome functionally and aesthetically. Dental rehabilitation was done in four patients. One flap was reexplored for thrombosis and salvaged. The challenges in secondary reconstruction include difficulty in recreating true defects, extensive fibrosis and loss of planes, unanticipated soft-tissue and skeletal defects, reestablishing the contour and occlusion, insufficient bone strength, dearth of suitable recipient vessels, nonpliable skin, tissue contraction to accommodate new mandible, need of additional flap for defect closure, and postirradiation effects. Notwithstanding them, the reasonable successful outcome can be attainable. Full article