Texture analysis of the developing human brain using customization of a knowledge-based system

Abstract

Background: Pattern recognition software originally designed for geospatial and other technical applications could be trained by physicians and used as texture analysis tools for evidence-based practice, in order to improve diagnostic imaging examination during pregnancy. Methods: Various machine-learning techniques and customized datasets were assessed for training of an integrable knowledge-based system (KBS) to determine a hypothetical methodology for texture classification of closely related anatomical structures in fetal brain magnetic resonance (MR) images. Samples were manually categorized according to the magnetic field of the MRI scanner (i.e., 1.5-tesla [1.5T], 3-tesla [3T]), rotational planes (i.e., coronal, sagittal, and axial), and signal weighting (i.e., spin-lattice, spin-spin, relaxation, and proton density). In the machine-learning sessions, the operator manually selected relevant regions of interest (ROI) in 1.5/3T MR images. Semi-automatic procedures in MaZda/B11 were performed to determine optimal parameter sets for ROI classification. Four classes were defined: ventricles, thalamus, gray matter, and white matter. Various texture analysis methods were tested. The KBS performed automatic data preprocessing and semi-automatic classification of ROI. Results: After testing 3456 ROI, statistical binary classification revealed that the combination of reduction techniques with linear discriminant algorithms (LDA) or nonlinear discriminant algorithms (NDA) yielded the best scoring in terms of sensitivity (both 100%, 95% CI: 99.79–100), specificity (both 100%, 95% CI: 99.79–100), and Fisher coefficient (≈E+4 and ≈E+5, respectively). Conclusions: LDA and NDA in MaZda can be useful data mining tools for screening a population of interest subjected to a clinical test.