Download full-text PDF |
Source |
|---|
Publication Analysis
Top Keywords
Similar Publications
Multilevel perception boundary-guided network for breast lesion segmentation in ultrasound images.
Med Phys
January 2025
Engineering Research Center of Text Computing & Cognitive Intelligence, Ministry of Education, Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province, State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang, China.
Background: Automatic segmentation of breast tumors from the ultrasound images is essential for the subsequent clinical diagnosis and treatment plan. Although the existing deep learning-based methods have achieved considerable progress in automatic segmentation of breast tumors, their performance on tumors with similar intensity to the normal tissues is still not satisfactory, especially for the tumor boundaries.
Purpose: To accurately segment the non-enhanced lesions with more accurate boundaries, a novel multilevel perception boundary-guided network (PBNet) is proposed to segment breast tumors from ultrasound images.
Towards a decision support system for post bariatric hypoglycaemia: development of forecasting algorithms in unrestricted daily-life conditions.
BMC Med Inform Decis Mak
January 2025
Department of Information Engineering (DEI), University of Padova, Via G. Gradenigo 6/B, Padua, 35131, Italy.
Background: Post bariatric hypoglycaemic (PBH) is a late complication of weight loss surgery, characterised by critically low blood glucose levels following meal-induced glycaemic excursions. The disabling consequences of PBH underline the need for the development of a decision support system (DSS) that can warn individuals about upcoming PBH events, thus enabling preventive actions to avoid impending episodes. In view of this, we developed various algorithms based on linear and deep learning models to forecast PBH episodes in the short-term.
View Article and Find Full Text PDFManaging emergency crises using secure information through educational awareness: COVID-19 case study.
Comput Biol Med
January 2025
LMA Laboratory, University of Bejaia, Bejaia 06000, Algeria. Electronic address:
Social networks are increasingly taking over daily life, creating a volume of unsecured data and making it very difficult to capture safe data, especially in times of crisis. This study aims to use a Convolutional Neural Network (CNN)-Long Short-Term Memory (LSTM)-based hybrid model for health monitoring and health crisis forecasting. It consists of efficiently retrieving safe content from multiple social media sources.
View Article and Find Full Text PDFPseudoaneurysm of the descending aorta two decades after aortic coarctation repair: a case report.
J Cardiothorac Surg
January 2025
Department of Cardiovascular Surgery, West China Hospital of Sichuan University, 37# Guoxue Xiang, Chengdu, 610041, Sichuan, China.
Background: Pseudoaneurysm after coarctation of the aorta (CoA) repair is a rare but severe complication. Contributing factors may include infection, hypertension, aortic wall weakness, and turbulent blood flow at the repair site.
Case Presentation: A 35-year-old male presented with recurrent episodes of epistaxis and dizziness was admitted to the emergency department.
No Right Way: Removal of a Pencil Foreign Body From a Male Urethra.
Cureus
November 2024
Urology, Sunderland Royal Hospital, Sunderland, GBR.
Foreign body insertion into the urethra is uncommonly encountered in urology practice. Such insertion can result in a myriad of problems including bleeding, infectious sequelae, urinary retention, urethral injury or rupture, and resultant urethral stricture formation. This article describes a case in which an elderly male inserted a pencil into his urethra, which subsequently became lodged and required removal under regional anesthesia in the operating theater.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!