ABSTRACT
BACKGROUND: In complex agricultural environments, the presence of shadows, leaf debris, and uneven illumination can hinder the performance of leaf segmentation models for cucumber disease detection. This is further exacerbated by the imbalance in pixel ratios between background and lesion areas, which affects the accuracy of lesion extraction. RESULTS: An original image segmentation framework, the LS-ASPP model, which utilizes a two-stage Atrous Spatial Pyramid Pooling (ASPP) approach combined with adaptive loss to address these challenges has been proposed. The Leaf-ASPP stage employs attention modules and residual structures to capture multi-scale semantic information and enhance edge perception, allowing for precise extraction of leaf contours from complex backgrounds. In the Spot-ASPP stage, we adjust the dilation rate of ASPP and introduce a Convolutional Attention Block Module (CABM) to accurately segment lesion areas. CONCLUSIONS: The LS-ASPP model demonstrates improved performance in semantic segmentation accuracy under complex conditions, providing a robust solution for precise cucumber lesion segmentation. By focusing on challenging pixels and adapting to the specific requirements of agricultural image analysis, our framework has the potential to enhance disease detection accuracy and facilitate timely and effective crop management decisions.
Subject(s)
Cucumis sativus , Image Processing, Computer-Assisted , Plant Diseases , Image Processing, Computer-Assisted/methods , Plant Leaves , AlgorithmsABSTRACT
PURPOSE: Midline abdominal wall hernia repair is among the most common surgical interventions performed worldwide. However, the optimal surgical technique remains controversial. To overcome the disadvantages of both open and transabdominal procedures, we developed a totally endoscopic preperitoneal approach (eTPA) with placement of a large mesh. METHODS: From December 2019 to October 2020, 20 consecutive patients with small to medium-sized midline ventral hernias underwent repair using a completely preperitoneal subxiphoid top-down approach. The preperitoneal space was entered directly below the xiphoid, and careful endoscopic development of the plane between the peritoneum and posterior sheath of the rectus fascia was then performed behind the linea alba. The hernia sac and its contents were identified and reduced. The hernia defect was closed with sutures, and a mesh with an adequate high defect: mesh ratio was placed in the newly created preperitoneal space. RESULTS: Twenty patients were enrolled in this study, including 14 with primary umbilical hernias, 4 with primary epigastric hernias, and 2 with recurrent umbilical hernias. 15 patients suffered from a mild concomitant diastasis recti. All operations were successfully completed without conversion to open repair. The mean operative time was 105.3 min (range, 60-220 min). Postoperative pain was mild, and the mean visual analog scale score for pain was 1.8 on the first postoperative day. The average postoperative hospital stay was 1.8 days (range, 1-4 days). One patient developed a minor postoperative seroma, but it had no adverse impact on the final outcome. No patients developed recurrence during the 3- to 10-month follow-up period. CONCLUSIONS: The subxiphoid top-down totally endoscopic preperitoneal approach (eTPA) technique is feasible and effective. It may become a valuable alternative for the treatment of primary small- (defect size < 2 cm) and medium-sized (2-4 cm) midline ventral hernias, particularly in presence of a concomitant diastasis recti.
Subject(s)
Abdominal Wall , Hernia, Ventral , Laparoscopy , Abdominal Wall/surgery , Endoscopy , Hernia, Ventral/surgery , Herniorrhaphy , Humans , Surgical MeshABSTRACT
Collision-free path planning and task scheduling optimization in multi-region operations of autonomous agricultural robots present a complex coupled problem. In addition to considering task access sequences and collision-free path planning, multiple factors such as task priorities, terrain complexity of farmland, and robot energy consumption must be comprehensively addressed. This study aims to explore a hierarchical decoupling approach to tackle the challenges of multi-region path planning. Firstly, we conduct path planning based on the A* algorithm to traverse paths for all tasks and obtain multi-region connected paths. Throughout this process, factors such as path length, turning points, and corner angles are thoroughly considered, and a cost matrix is constructed for subsequent optimization processes. Secondly, we reformulate the multi-region path planning problem into a discrete optimization problem and employ genetic algorithms to optimize the task sequence, thus identifying the optimal task execution order under energy constraints. We finally validate the feasibility of the multi-task planning algorithm proposed by conducting experiments in an open environment, a narrow environment and a large-scale environment. Experimental results demonstrate the method's capability to find feasible collision-free and cost-optimal task access paths in diverse and complex multi-region planning scenarios.
ABSTRACT
PURPOSE: The best way to reduce seroma formation after laparoscopic indirect hernia repair is debated. We noticed that internal ring defect closure in laparoscopic mesh hernioplasty could provide promising outcomes with an effect on diminishing seroma formation. We introduce our closure technique and report our experience. METHODS: This prospective study was conducted from May 2019 to May 2021. Patients with European Hernia Society classification L3 indirect or scrotal hernia were recruited and underwent laparoscopic transabdominal patch plasty (TAPP). Hernia defect closure was performed before mesh deployment. The primary outcomes were seroma formation, postoperative pain, and hernia recurrence. Perioperative data and postoperative complications were also recorded. RESULTS: Consecutive 77 patients with 89 indirect hernias (including 51 scrotal hernias) were recruited in two regional tertiary hospitals. All operations were successful without open conversion. The mean size of the hernia defect was 3.7 ± 0.5 cm (range, 2.5-5.0 cm). The mean operative time for each hernia repair (peritoneum to peritoneum) was 48.3 ± 10.8 min (range, 33-72 min), and the mean time required for internal ring closure was 6.7 ± 2.2 min (range, 4-10 min). Intraoperative bleeding was minimal. The mean visual analog scale pain score at rest on the first postoperative day was 2.2 (range, 1-4). The average postoperative length of hospital stay was 18 h (range, 14-46 h). During a mean follow-up period of 9.4 months (range, 3-23 months), no hernia recurrence or chronic pain were noted. Seroma formation was detected on six sides of unilateral hernias (6.7%) on postoperative day 7, with a mean volume of 45.8 ml (range, 24-80 ml). All seromas were mild and resolved spontaneously within 3 months, with no need for evacuation or other treatment and without major impact on the final outcome. CONCLUSIONS: Defect closure in laparoscopic mesh hernioplasty for large indirect hernias is safe and feasible and can significantly reduce postoperative seroma formation and relative complications. This approach is recommended in large indirect or scrotal hernia repair.