Citation

Ang, Jinger (2026) Adaptive Contrast Enhancement algorithm for improved visualisation of brain lesions. Masters thesis, Multimedia University.

Full text not available from this repository.

Abstract

Despite advancements in medical imaging technologies, the early detection and accurate visualisation of brain anomalies remain challenging due to the limitations in contrast and detail resolution of current techniques. This thesis addresses these challenges by presenting a novel adaptive algorithm and a comprehensive diagnostic interface to resolve these visibility deficits. The first contribution introduces the Adaptive Contrast Enhancement with Lesion Focusing (ACELF) algorithm. ACELF employs a multi-stage processing strategy combining intensity threshold-based segmentation, custom histogram matching for contrast enhancement, and gamma correction for brightness adjustment. Lesion identification is refined through pixel intensity comparison against standard tissue norms, with visibility further optimised by modulating intensity using calculated scaling factors. Quantitative validation demonstrated that ACELF yielded superior performance in Entropy, Enhancement Measure Estimation (EME), and Contrast Improvement Index (CII) compared to conventional methods. Second, an Enhanced Diagnostic Visualisation (EDV) system, a graphical interface designed for clinical workflow integration, is created. The EDV system supports batch processing of DICOM files and introduces a Dynamic Scan Layer Navigation (DSLN) mechanism that facilitates seamless navigation of brain scans across different axial planes. A key feature of the system is its automated visualisation engine, which allows healthcare professionals to efficiently compare multiple contrast enhancement techniques alongside colourisation methods. These results validate ACELF as a robust method for resolving low-contrast anomalies and establish EDV as an effective solution for streamlining the clinical review process. By addressing both the algorithmic limitations of image quality and the practical hurdles of data navigation, this thesis offers a two-solution approach to the challenges of medical image analysis.

Item Type:	Thesis (Masters)
Additional Information:	Call No.: TA1637 .A54 2026
Uncontrolled Keywords:	Image processing—Digital techniques
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	22 Jul 2026 08:39
Last Modified:	22 Jul 2026 08:39
URII:	http://shdl.mmu.edu.my/id/eprint/16378

Downloads

Edit (login required)