Abstract—Extraction of relevant features is of significant importance for brain tumor segmentation systems. In this paper, with the objective of improving brain tumor segmentation accuracy, we present an improved feature extraction component to take advantage of the correlation between intracranial structure deformation and the compression from brain tumor growth. Using 3-dimensional non-rigid registration and deformation modeling techniques, the component is capable of measuring lateral ventricular (LaV) deformation in the volumetric magnetic resonance (MR) images. By verifying the location of the extracted LaV deformation feature data and applying the features on brain tumor segmentation with widely used classification algorithms, the proposed component is evaluated qualitatively and quantitatively with promising results on 11 datasets comprising real patient and simulated images.

Pichia pinus was grown in a semi-continuous process on mango-peel extract medium. The yield was 8 g/litre after 12 h at the end of the logarithmic phase. The biomass of Pichia pinus contained 53·7% protein. Amino acid analyses of the protein revealed the presence of all amino acids in substantial amounts except for those containing sulphur, which were the limiting amino acids. When fed to rats the protein biomass exhibited good nutritional values (protein efficiency ratio, 2·77 ± 0·126; apparent digestibility, 71·54 ± 1·02) as compared to the casein diet (protein efficiency ratio, 2·913 ± 0·127; apparent digestibility, 90·156 ± 0·64). Alkaline phosphatase levels were insignificantly different from the control during the experimental period (21, 28, 35 and 42 feeding days). The transaminases, γ-glutamyl transferase activities and creatinine levels in the serum were significantly varied at the 35th and 42nd feeding days. The glutamate oxaloacetate transaminase, urea and uric acid levels in serum were significantly increased only after 35 feeding days. No histological changes were observed in either liver or kidney tissues.