Dataset Information

Sparse Contribution Feature Selection and Classifiers Optimized by Concave-Convex Variation for HCC Image Recognition.

ABSTRACT: Accurate classification of hepatocellular carcinoma (HCC) image is of great importance in pathology diagnosis and treatment. This paper proposes a concave-convex variation (CCV) method to optimize three classifiers (random forest, support vector machine, and extreme learning machine) for the more accurate HCC image classification results. First, in preprocessing stage, hematoxylin-eosin (H&E) pathological images are enhanced using bilateral filter and each HCC image patch is obtained under the guidance of pathologists. Then, after extracting the complete features of each patch, a new sparse contribution (SC) feature selection model is established to select the beneficial features for each classifier. Finally, a concave-convex variation method is developed to improve the performance of classifiers. Experiments using 1260 HCC image patches demonstrate that our proposed CCV classifiers have improved greatly compared to each original classifier and CCV-random forest (CCV-RF) performs the best for HCC image recognition.

SUBMITTER: Pang W

PROVIDER: S-EPMC5535756 | biostudies-other | 2017

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:Background and Aims Progress has been made in understanding the physiological and molecular basis of root response to mechanical stress, especially in the model plant Arabidopsis thaliana, in which bending causes the initiation of lateral root primordia toward the convex side of the bent root. In the case of woody roots, it has been reported that mechanical stress induces an asymmetric distribution of lateral roots and reaction wood formation, but the mechanisms underlying these responses are largely unknown. In the present work, the hypothesis was tested that bending could determine an asymmetric response in the two sides of the main root axis as cells are stretched on the convex side and compressed on the concave side. Methods Woody taproots of 20 seedlings were bent to an angle of 90° using a steel net. Changes in the anatomy, lignin and phytohormone content and proteome expression in the two sides of the bent root were analysed; anatomical changes, including dissimilarities and similarities to those found in poplar bent woody stem, were also considered. Key Results Compression forces at the concave side of poplar root induced the formation of reaction wood which presented a high lignin content and was associated with the induction of cambium cell activity. Auxin seemed to be the main hormone triggering lignin deposition and cell wall strengthening in the concave sides. Abscisic acid appeared to function in the water stress response induced by xylem structures and/or osmotic alterations in the compression sides, whereas gibberellins may control cell elongation and gravitropisms. Conclusions Poplar root reaction wood showed characteristics different from those produced in bent stem. Besides providing biomechanical functions, a bent root ensures water uptake and transport in the deforming condition induced by tension and compression forces by two different strategies: an increase in xylem thickness in the compressed side, and lateral root formation in the tension side.

Dataset Information

Sparse Contribution Feature Selection and Classifiers Optimized by Concave-Convex Variation for HCC Image Recognition.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets