Osteoporosis Recognition in Rats under Low-Power Lens Based on Convexity Optimization Feature Fusion

Abstract

Considering the poor medical conditions in some regions of China, this paper attempts to develop a simple and easy way to extract and process the bone features of blurry medical images and improve the diagnosis accuracy of osteoporosis as much as possible. After reviewing the previous studies on osteoporosis, especially those focusing on texture analysis, a convexity optimization model was proposed based on intra-class dispersion, which combines texture features and shape features. Experimental results show that the proposed model boasts a larger application scope than Lasso, a popular feature selection method that only supports generalized linear models. The research findings ensure the accuracy of osteoporosis diagnosis and enjoy good potentials for clinical application.

Statistical Image Analysis of Drying Bovine Serum Albumin Droplets in Phosphate Buffered Saline

“…The GLCM (Gray Level Co-occurrence Matrix) parameters are the second-order statistics calculated from the spatial relationship between two neighboring pixels [32]. This makes GLCM parameters complicated and different from the first-order statistics (FOS), which solely depends on the individual pixel values [47][48]. Before establishing any relationship between two neighboring pixels, it is crucial to address a few things.…”

“…The images of any droplets captured at different drying stages are potential pattern recognizing tools, nonetheless, the data extraction procedure of those images is very complex and sensitive task. For example, the GLCM of an image is highly dependent on its orientation and pixel displacement [47][48]. To the best of our knowledge, no study till date attempted to examine these (initialized) factors of the GLCM parameters.…”

A hierarchical opportunistic screening model for osteoporosis using machine learning applied to clinical data and CT images

“…In our study, several texture features deriving from GLCM, GLGM, and HI were extracted from CT images. Moreover, shape analysis was also employed to quantify the microarchitecture of trabecular bone, which probably could enhance the classification accuracy [ 29 ]. The results demonstrated that texture features were more important than shape features in detecting osteoporotic individuals, and the model performance was not improved utilizing both texture and shape features compared with that of texture features alone (Table 2 ).…”

“…It’s obvious that the individual with osteoporosis has larger inter-trabecular space and more notable permeability of vertebral body than the health. Shape parameters describing the outline of inter-trabecular space were utilized, which includes perimeter, area, regional density (the ratio of the area to the squared perimeter), circularity, solidity, length–width ratio (the aspect ratio of the regional minimum bounding rectangle), rectangularity (the ratio of the area to the area of regional minimum bounding rectangle) and 7 Hu’s invariant moments [ 29 ]. The maximum between-class variance (Otsu) method [ 33 ] was utilized to acquire binary images that represented trabecular and inter-trabecular space ahead of calculating shape features [ 34 ].…”

Survival Time Prediction of Breast Cancer Patients Using Feature Selection Algorithm Crystall

“…Eight feature selection algorithms were utilized. The regression-based feature weighting algorithms L1 penalization (Lasso) [58,59], L2 penalization (Ridge) [60] and Elastic Net (E-net) [61], TriVote [62] were evaluated. Lasso [63], Ridge [64] and E-net [65] were widely used to select features by regularization.…”