Pathological Brain Detection Using Weiner Filtering, 2D-Discrete Wavelet Transform, Probabilistic PCA, and Random Subspace Ensemble Classifier

Brain pathology identification using computer aided diagnostic tool: A systematic review

Computer aided diagnostic (CAD) has become a significant tool in expanding patient quality-of-life by reducing human errors in diagnosis. CAD can expedite decision-making on complex clinical data automatically. Since brain diseases can be fatal, rapid identification of brain pathology to prolong patient life is an important research topic. Many algorithms have been proposed for efficient brain pathology identification (BPI) over the past decade. Constant refinement of the various image processing algorithms must take place to expand performance of the automatic BPI task. In this paper, a systematic survey of contemporary BPI algorithms using brain magnetic resonance imaging (MRI) is presented. A summarization of recent literature provides investigators with a helpful synopsis of the domain. Furthermore, to enhance the performance of BPI, future research directions are indicated.

Subjective analysis of the application of enhancement filters on magnetic resonance imaging of the temporomandibular joint

OBJECTIVE

The aim of this study was to investigate the effect of enhancement filters on magnetic resonance imaging (MRI) of the temporomandibular joint (TMJ).

STUDY DESIGN

In total, 66 MRI scans of the TMJ were analyzed without filtration and with the application of 2 filters: Sharpen 1 and Sharpen 2 (OnDemand software). Two dentomaxillofacial radiologists examined the original and filtered images individually. Intra- and interobserver concordance was measured by using generalized estimating equations. The observers evaluated the subjective image quality and the visibility of 3 components of the TMJ: disk, condyle, and articular eminence. The images were ranked on a 4-point scale, from poor to excellent. The image quality of all filtered images was compared by using the χ² test and Bonferroni correction for multiple comparisons.

RESULTS

Intra- and interobserver concordance was good. The images filtered with Sharpen 1 and Sharpen 2 provided better definition of the structures compared with nonfiltered images, providing the highest scores for subjective image quality for all structures (P < .0001).

CONCLUSIONS

The use of enhancement filters led to improved subjective quality and may improve the diagnostic efficacy of MRI in TMJ evaluation.