Retinal image registration is important to assist diagnosis and monitor retinal diseases, such as diabetic retinopathy and glaucoma. However, registering retinal images for various registration applications requires the detection and distribution of feature points on the low-quality region that consists of vessels of varying contrast and sizes. A recent feature detector known as Saddle detects feature points on vessels that are poorly distributed and densely positioned on strong contrast vessels. Therefore, we propose a multiresolution difference of Gaussian pyramid with Saddle detector (D-Saddle) to detect feature points on the low-quality region that consists of vessels with varying contrast and sizes. D-Saddle is tested on Fundus Image Registration (FIRE) Dataset that consists of 134 retinal image pairs. Experimental results show that D-Saddle successfully registered 43% of retinal image pairs with average registration accuracy of 2.329 pixels while a lower success rate is observed in other four state-of-the-art retinal image registration methods GDB-ICP (28%), Harris-PIIFD (4%), H-M (16%), and Saddle (16%). Furthermore, the registration accuracy of D-Saddle has the weakest correlation (Spearman) with the intensity uniformity metric among all methods. Finally, the paired t-test shows that D-Saddle significantly improved the overall registration accuracy of the original Saddle.

Mass detection in mammograms has a limited approach to the presence of a mass in overlapping denser fibroglandular breast regions. In addition, various breast density levels could decrease the learning system’s ability to extract sufficient feature descriptors and may result in lower accuracy performance. Therefore, this study is proposing a textural-based image enhancement technique named Spatial-based Breast Density Enhancement for Mass Detection (SbBDEM) to boost textural features of the overlapped mass region based on the breast density level. This approach determines the optimal exposure threshold of the images’ lower contrast limit and optimizes the parameters by selecting the best intensity factor guided by the best Blind/Reference-less Image Spatial Quality Evaluator (BRISQUE) scores separately for both dense and non-dense breast classes prior to training. Meanwhile, a modified You Only Look Once v3 (YOLOv3) architecture is employed for mass detection by specifically assigning an extra number of higher-valued anchor boxes to the shallower detection head using the enhanced image. The experimental results show that the use of SbBDEM prior to training mass detection promotes superior performance with an increase in mean Average Precision (mAP) of 17.24% improvement over the non-enhanced trained image for mass detection, mass segmentation of 94.41% accuracy, and 96% accuracy for benign and malignant mass classification. Enhancing the mammogram images based on breast density is proven to increase the overall system’s performance and can aid in an improved clinical diagnosis process.

This paper proposes a new image enhancement technique known as Average Intensity Replacement based on Adaptive Histogram Equalization (AIR-AHE) for FLAIR image based on intensities and contrast mapping techniques. The proposed algorithm consists of partial contrast stretching, contrast limiting enhancement, window sliding neighborhood operation and new pixel centroid replacement. The fluid attenuated inversion recovery (FLAIR) sequences of MRI images which are used for segmentation have low contrast. Therefore, contrast stretching is used to improve the quality of the image. After improving the quality of image, the regions of high intensity are determined to represent potential WMH areas. The result shows that the image has a moderate enhancement on the WMH region which is significant to the image contrast enhancement. With complete brightness preservation, the proposed method gives a relatively natural brightness improvement on the WMH of the periventricular region.

This paper presents a comparative study between 3 segmentation techniques compared against ‘the ground truth’ obtained from manual segmentation from the oncologist applied for lung cancer detection. Lung cancer is the common cause of death among people throughout the world. Lung cancer detection can be done in several ways, such as Radiography, Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). These methods use a lot of resources in terms of time and money. However, CT has good detection of classification, offers a lower cost, short imaging time and widespread availability. Early diagnosis of lung cancer can help doctors to treat patients in order to reduce number of mortalities. Therefore, the primary aim of this research is to establish an image processing method to segment CT scan images of lung cancer using image segmentation algorithms. The proposed method comprises the following steps which involves using image processing technique: data collection, image segmentation and region growing. Lastly, the performance evaluation was calculated by referring to accuracy, precision, recall and F-score test. Data were collected from the Advance Medical and Dental Institute (AMDI), Universiti Sains Malaysia, Penang. Image segmentation algorithms such as k-means clustering, Otsu's thresholding and watershed segmentation were applied to segment the lung image. Then, region growing was applied to detect the lung area. The segmentation algorithm performance was evaluated by using the above mentioned performance analysis. Based on the analysis, the watershed segmentation had produced better image segmentation performance which was 99.8553% for accuracy, 99.9886% for precision, 98.3919% for recall and F-score test was 99.1499%.

Feature-based retinal fundus image registration (RIR) technique aligns fundus images according to geometrical transformations estimated between feature point correspondences. To ensure accurate registration, the feature points extracted must be from the retinal vessels and throughout the image. However, noises in the fundus image may resemble retinal vessels in local patches. Therefore, this paper introduces a feature extraction method based on a local feature of retinal vessels (CURVE) that incorporates retinal vessels and noises characteristics to accurately extract feature points on retinal vessels and throughout the fundus image. The CURVE performance is tested on CHASE, DRIVE, HRF and STARE datasets and compared with six feature extraction methods used in the existing feature-based RIR techniques. From the experiment, the feature extraction accuracy of CURVE (86.021%) significantly outperformed the existing feature extraction methods (p ≤ 0.001*). Then, CURVE is paired with a scale-invariant feature transform (SIFT) descriptor to test its registration capability on the fundus image registration (FIRE) dataset. Overall, CURVE-SIFT successfully registered 44.030% of the image pairs while the existing feature-based RIR techniques (GDB-ICP, Harris-PIIFD, Ghassabi’s-SIFT, H-M 16, H-M 17 and D-Saddle-HOG) only registered less than 27.612% of the image pairs. The one-way ANOVA analysis showed that CURVE-SIFT significantly outperformed GDB-ICP (p = 0.007*), Harris-PIIFD, Ghassabi’s-SIFT, H-M 16, H-M 17 and D-Saddle-HOG (p ≤ 0.001*).