AI Article Synopsis
- - The study focuses on using the YOLOv8 deep learning model to automate the grading of germinal matrix hemorrhage (GMH) in premature infants, diagnosed via cranial ultrasound.
- - A dataset of 586 infants' ultrasound images was analyzed, categorizing them into five grades of GMH: Normal, Grade 1, Grade 2, Grade 3, and Grade 4.
- - The YOLOv8 model performed exceptionally well with high accuracy rates, achieving a mean average precision of 0.979, which could improve diagnosis efficiency for radiologists.
Article Abstract
Germinal matrix hemorrhage (GMH) is a critical condition affecting premature infants, commonly diagnosed through cranial ultrasound imaging. This study presents an advanced deep learning approach for automated GMH grading using the YOLOv8 model. By analyzing a dataset of 586 infants, we classified ultrasound images into five distinct categories: Normal, Grade 1, Grade 2, Grade 3, and Grade 4. Utilizing transfer learning and data augmentation techniques, the YOLOv8 model achieved exceptional performance, with a mean average precision (mAP50) of 0.979 and a mAP50-95 of 0.724. These results indicate that the YOLOv8 model can significantly enhance the accuracy and efficiency of GMH diagnosis, providing a valuable tool to support radiologists in clinical settings.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11548650 | PMC |
| http://dx.doi.org/10.3390/s24217052 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A small object detection model in aerial images based on CPDD-YOLOv8.
Sci Rep
January 2025
School of Cyberspace Security, Hebei University of Engineering Science, Shijiazhuang, 050091, China.
Aerial images can cover a wide area and capture rich scene information. These images are often taken from a high altitude and contain many small objects. It is difficult to detect small objects accurately because their features are not obvious and are susceptible to background interference.
View Article and Find Full Text PDFEfficient detection of eyes on potato tubers using deep-learning for robotic high-throughput sampling.
Front Plant Sci
December 2024
Center for Precision and Automated Agricultural Systems, Department of Biological Systems Engineering, Washington State University, Prosser, WA, United States.
Molecular-based detection of pathogens from potato tubers hold promise, but the initial sample extraction process is labor-intensive. Developing a robotic tuber sampling system, equipped with a fast and precise machine vision technique to identify optimal sampling locations on a potato tuber, offers a viable solution. However, detecting sampling locations such as eyes and stolon scar is challenging due to variability in their appearance, size, and shape, along with soil adhering to the tubers.
View Article and Find Full Text PDFA novel method for intelligent operation and maintenance of transformers using deep visual large model DETR + X and digital twin.
Sci Rep
January 2025
School of Intelligent Manufacturing Modern Industry, Xinjiang University, Urumqi, 830046, Xinjiang, China.
To achieve real-time monitoring and intelligent maintenance of transformers, a framework based on deep vision and digital twin has been developed. An enhanced visual detection model, DETR + X, is proposed, implementing multidimensional sample data augmentation through Swin2SR and GAN networks. This model converts one-dimensional DGA data into three-dimensional feature images based on Gram angle fields, facilitating the transformation and fusion of heterogeneous modal information.
View Article and Find Full Text PDFAutomatic detection, classification, and segmentation of sagittal MR images for diagnosing prolapsed lumbar intervertebral disc.
Sci Rep
January 2025
Khulna University of Engineering and Technology, Khulna, 9203, Bangladesh.
Magnetic resonance (MR) images are commonly used to diagnose prolapsed lumbar intervertebral disc (PLID). However, for a computer-aided diagnostic (CAD) system, distinguishing between pathological abnormalities of PLID in MR images is a challenging and intricate task. Here, we propose a comprehensive model for the automatic detection and cropping of regions of interest (ROI) from sagittal MR images using the YOLOv8 framework to solve this challenge.
View Article and Find Full Text PDFSmall target detection in UAV view based on improved YOLOv8 algorithm.
Sci Rep
January 2025
School of Electronic Information Engineering, Lang Fang Normal University, Langfang, 065000, Hebei, China.
Article Synopsis
- The main challenges of detecting targets with UAVs include small image sizes, dense distributions of targets, and uneven category representation, along with hardware constraints affecting model complexity and accuracy.
- A new small target detection method using an improved YOLOv8 algorithm is introduced, enhancing feature fusion with a bi-directional feature pyramid network (BiFPN), and replacing the C2f module with a C3Ghost module to lower computational demands.
- Additional enhancements like a channel attention mechanism and an improved MPDIoU loss function boost the model's ability to learn from difficult samples, yielding significant improvements in mean accuracy, precision, and recall on the VisDrone dataset.
Want 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!