Traditionally, tool tracking involves two subtasks: (i) detecting the tool in the initial image in which it appears, and (ii) predicting and refining the configuration of the detected tool in subsequent images. With retinal microsurgery in mind, we propose a unified tool detection and tracking framework, removing the need for two separate systems. The basis of our approach is to treat both detection and tracking as a sequential entropy minimization problem, where the goal is to determine the parameters describing a surgical tool in each frame. The resulting framework is capable of both detecting and tracking in situations where the tool enters and leaves the field of view regularly. We demonstrate the benefits of this method in the context of retinal tool tracking. Through extensive experimentation on a phantom eye, we show that this method provides efficient and robust tool tracking and detection.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1007/978-3-642-23623-5_1 | DOI Listing |
Cureus
December 2024
Emergency Medicine, King Abdulaziz University Hospital, Jeddah, SAU.
Background: Elevated blood pressure (BP) prompts immediate emergency department (ED) visits instead of outpatient care, thus constituting a high-weight concern for the ED. This study investigated the short- and long-term outcomes of high BP patients in the ED.
Methods: A retrospective cohort study was conducted at King Abdulaziz University Hospital (KAUH), reviewing ED visits from January to December 2022.
Exp Ther Med
March 2025
Department of Neurosurgery, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang Uygur Autonomous Region 830000, P.R. China.
Spinal cord injury (SCI) is a severe condition that often leads to permanent functional impairments. The current treatment options are limited and there is a need for more effective treatments. Human umbilical cord mesenchymal stem cells (hUCMSCs) have shown promise in promoting neuroregeneration and modulating immune response.
View Article and Find Full Text PDFMol Pharm
January 2025
School of Pharmaceutical Sciences, Shanghai Jiao Tong University, Shanghai 200240, China.
Early detection and precise treatment for breast cancer are crucial, given its high global incidence rate. Hence, the development of novel imaging targets is essential for diagnosing and monitoring resistance to chemotherapy, which is pivotal for achieving precise and personalized treatment for breast cancer patients. In our previous work, we successfully developed a near-infrared (NIR) probe for CYP1B1-targeted imaging.
View Article and Find Full Text PDFPlant Mol Biol
January 2025
Graduate School of Science and Technology, Kumamoto University, 2-39-1 Kurokami, Chuo-Ku, Kumamoto, 860-8555, Japan.
The applicability of a deep learning model for the virtual staining of plant cell structures using bright-field microscopy was investigated. The training dataset consisted of microscopy images of tobacco BY-2 cells with the plasma membrane stained with the fluorescent dye PlasMem Bright Green and the cell nucleus labeled with Histone-red fluorescent protein. The trained models successfully detected the expansion of cell nuclei upon aphidicolin treatment and a decrease in the cell aspect ratio upon propyzamide treatment, demonstrating its utility in cell morphometry.
View Article and Find Full Text PDFInfect Genet Evol
January 2025
Agri-Food and Biosciences Institute, AFBI Stormont, Veterinary Sciences Division, Belfast, UK.
Mycobacterium bovis, the causative agent of animal tuberculosis, exhibits a broad host range - infecting, inducing pathology and transmitting from both bovine and wildlife hosts. Considerable effort has been extended to understanding the role wildlife may play in persistence and spread of infection. Infected cervids can spread infection to conspecifics and sympatric livestock as observed in the white-tailed deer (Odocoileus virginanus) population of Michigan, USA.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!