Background:
Digital mammograms with appropriate image enhancement techniques will improve breast cancer
detection, and thus increase the survival rates. The objectives of this study were to systematically review and compare
various image enhancement techniques in digital mammograms for breast cancer detection.
Methods:
A literature search was conducted with the use of three online databases namely, Web of Science, Scopus, and
ScienceDirect. Developed keywords strategy was used to include only the relevant articles. A Population Intervention
Comparison Outcomes (PICO) strategy was used to develop the inclusion and exclusion criteria. Image quality was
analyzed quantitatively based on peak signal-noise-ratio (PSNR), Mean Squared Error (MSE), Absolute Mean Brightness
Error (AMBE), Entropy, and Contrast Improvement Index (CII) values.
Results:
Nine studies with four types of image enhancement techniques were included in this study. Two studies used
histogram-based, three studies used frequency-based, one study used fuzzy-based and three studies used filter-based. All
studies reported PSNR values whilst only four studies reported MSE, AMBE, Entropy and CII values. Filter-based was
the highest PSNR values of 78.93, among other types. For MSE, AMBE, Entropy, and CII values, the highest were
frequency-based (7.79), fuzzy-based (93.76), filter-based (7.92), and frequency-based (6.54) respectively.
Conclusion:
In summary, image quality for each image enhancement technique is varied, especially for breast cancer
detection. In this study, the frequency-based of Fast Discrete Curvelet Transform (FDCT) via the UnequiSpaced Fast
Fourier Transform (USFFT) shows the most superior among other image enhancement techniques.
Fingerprint Image Enhancement based on Threshold Fast Discrete Curvelet Transform (FDCT) and Gabor Filters