Purpose: To improve detection of pulmonary and pleural abnormalities caused by pneumonia or tuberculosis (TB) in digital chest X-rays (CXRs).
Methods: A method was developed and tested by combining shape and texture features to classify CXRs into two categories: TB and non-TB cases. Based on observation that radiologist interpretation is typically comparative: between left and right lung fields, the algorithm uses shape features to describe the overall geometrical characteristics of the lung fields and texture features to represent image characteristics inside them.
Results: Our algorithm was evaluated on two different datasets containing tuberculosis and pneumonia cases.
Conclusions: Using our proposed algorithm, we were able to increase the overall performance, measured as area under the (ROC) curve (AUC) by 2.4 % over our previous work.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1007/s11548-015-1242-x | DOI Listing |
Microsc Res Tech
January 2025
School of Electrical & Control Engineering, Shenyang Jianzhu University, Shenyang, China.
The atomic force microscope (AFM) image will be inclined and bent due to the tilt angle between the probe and the sample surface. When the least squares fitting method is used to correct the horizontal distortion of the AFM image, the shape structure that is lower or higher than the sample base will affect the final fitting correction result. In view of the limitations of existing methods and the diversity of AFM images, an AFM image level distortion correction method based on automatic feature marking is proposed.
View Article and Find Full Text PDFMicrosc Res Tech
January 2025
Department of Anatomy, Erciyes University Faculty of Veterinary Medicine, Kayseri, Türkiye.
In this study, the kidneys of ground squirrels (hibernated and nonhibernated), rabbits, and rats were examined macro and microanatomically. Kidney morphology was investigated by stereo microscopy, light microscopy, and scanning electron microscopy. Triple and immunohistochemical staining were performed for light microscopic examinations.
View Article and Find Full Text PDFJ Biomed Mater Res A
January 2025
Faculty of Materials Science and Engineering, Warsaw University of Technology, Warsaw, Poland.
Bone tissue regeneration can be affected by various architectonical features of 3D porous scaffold, for example, pore size and shape, strut size, curvature, or porosity. However, the design of additively manufactured structures studied so far was based on uniform geometrical figures and unit cell structures, which often do not resemble the natural architecture of cancellous bone. Therefore, the aim of this study was to investigate the effect of architectonical features of additively manufactured (aka 3D printed) titanium scaffolds designed based on microtomographic scans of fragments of human femurs of individuals of different ages on in vitro response of human bone-derived mesenchymal stem cells (hMSC).
View Article and Find Full Text PDFInt J Womens Dermatol
March 2025
Private Practice, Pretoria, South Africa.
Background: Nevus of Hori (HN) has been primarily reported in patients of Eastern Asian descent, with a paucity of data regarding HN occurring in African patients. In this study, we report on South African patients with HN initially thought to have melasma.
Objective: To characterize the histopathological and clinical phenotypes of HN in African patients.
Vertebrate vision in dim-light environments is initiated by rod photoreceptor cells that express the photopigment rhodopsin, a G-protein coupled receptor (GPCR). To ensure efficient light capture, rhodopsin is densely packed into hundreds of membrane discs that are tightly stacked within the rod-shaped outer segment compartment. Along with its role in eliciting the visual response, rhodopsin serves as both a building block necessary for proper outer segment formation as well as a trafficking guide for a few outer segment resident membrane proteins.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!