A new diagnostic system combining conventional gray-scale ultrasonography (US) and computer-assisted texture analysis of sonograms makes it possible to differentiate more easily between specific neuromuscular diseases. The first step involves myosonography with strictly standardized US. In a group of 72 patients with histologically and molecular-genetically confirmed diagnosis 63 patients (88%) were diagnosed by conventional US as having Duchenne's muscular dystrophy, spinal muscular atrophy, hereditary sensomotor neuropathy or inflammatory myopathy. Secondly, in a double blind setting computer-assisted texture analysis was used on the same sample of subjects. Tissue Texture can be characterized by the brightness as well as the micro- and macro-structure of the tissue. The use of these parameters leads to a sensitivity of 77 to 94% and a specificity of 81 to 98%. In conclusion, the combination of both techniques allows us to avoid invasive diagnostic procedures in a substantial group of patients.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1055/s-2000-9118 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A fusion model of manually extracted visual features and deep learning features for rebleeding risk stratification in peptic ulcers.
Nan Fang Yi Ke Da Xue Xue Bao
January 2025
Department of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou 510515, China.
Objectives: We propose a multi-feature fusion model based on manually extracted features and deep learning features from endoscopic images for grading rebleeding risk of peptic ulcers.
Methods: Based on the endoscopic appearance of peptic ulcers, color features were extracted to distinguish active bleeding (Forrest I) from non-bleeding ulcers (Forrest II and III). The edge and texture features were used to describe the morphology and appearance of the ulcers in different grades.
A framework for assessing reliability of observer annotations of aerial wildlife imagery, with insights for deep learning applications.
PLoS One
January 2025
Division of Biological Sciences, US Fish and Wildlife Southwest Regional Office, Albuquerque, New Mexico, United States of America.
There is growing interest in using deep learning models to automate wildlife detection in aerial imaging surveys to increase efficiency, but human-generated annotations remain necessary for model training. However, even skilled observers may diverge in interpreting aerial imagery of complex environments, which may result in downstream instability of models. In this study, we present a framework for assessing annotation reliability by calculating agreement metrics for individual observers against an aggregated set of annotations generated by clustering multiple observers' observations and selecting the mode classification.
View Article and Find Full Text PDFRobust Multi-Subtype Identification of Breast Cancer Pathological Images Based on a Dual-Branch Frequency Domain Fusion Network.
Sensors (Basel)
January 2025
School of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou 310018, China.
Breast cancer (BC) is one of the most lethal cancers worldwide, and its early diagnosis is critical for improving patient survival rates. However, the extraction of key information from complex medical images and the attainment of high-precision classification present a significant challenge. In the field of signal processing, texture-rich images typically exhibit periodic patterns and structures, which are manifested as significant energy concentrations at specific frequencies in the frequency domain.
View Article and Find Full Text PDFData-Efficient Bone Segmentation Using Feature Pyramid- Based SegFormer.
Sensors (Basel)
December 2024
Master's Program in Information and Computer Science, Doshisha University, Kyoto 610-0394, Japan.
The semantic segmentation of bone structures demands pixel-level classification accuracy to create reliable bone models for diagnosis. While Convolutional Neural Networks (CNNs) are commonly used for segmentation, they often struggle with complex shapes due to their focus on texture features and limited ability to incorporate positional information. As orthopedic surgery increasingly requires precise automatic diagnosis, we explored SegFormer, an enhanced Vision Transformer model that better handles spatial awareness in segmentation tasks.
View Article and Find Full Text PDFInvestigations on segmentation-based fractal texture for texture classification in the presence of Gaussian noise.
PLoS One
January 2025
Department of Information Technology, Politeknik Negeri Padang, Padang, Sumatera Barat, Indonesia.
Texture is a significant component used for several applications in content-based image retrieval. Any texture classification method aims to map an anonymously textured input image to one of the existing texture classes. Extensive ranges of methods for labeling image texture were proposed earlier.
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!