Search

Quantification of parasitemia is an important part of a microscopic malaria diagnosis. Giemsa-stained thin blood smear is the gold standard method for detecting malaria parasite enumeration. However, manual counting reveals the limitations of human inconsistency and fatigue, as well as the unreliability of accuracy and non-reproducibility. Inaccurate parasitemia affects clinical diagnosis and therapeutic procedure. Automated quantification is therefore useful to improve the performance of quantifying parasite density. In this paper, the texture-based classification approach is investigated. The methods consist of the following processes: pre-processing, segmentation, feature extraction and the classification of erythrocytes. The pre-processing is applied for image conversion and enhancement. The segmentation combines local adaptive thresholding, morphological process and watershed transform to extract red blood cells, separate touching and overlapping cells. Texture analysis is performed to establish parameters obtained from first-order, second-order and higher-order statistical analysis and wavelet transform. Two feature selection approaches, the sequential forward selection method and sequential backward elimination method, integrated with a support vector machine classifier are examined to obtain the optimal feature set for identifying the Plasmodium falciparum stages. We found that gray-level co-occurrence matrices based textural features were highly selected. The optimal feature set selected by the sequential forward selection yields lesser number of features and tends to give a higher degree of accuracy than the feature set selected by sequential backward elimination. The proposed method produces 98.87% accuracy for binary classification, 99.56% accuracy for ring stage classification, and 99.48% accuracy for tropozoite stage classification. Grey-level co-occurrence matrices based texture analysis is the dominant method compared to first-order and higher-order statistical texture analysis as well as wavelet transform.

Urinary stone is the most common abnormality occurring in human urinary system. Early detection in medical imaging is important for promptly treatment or surgery planning. Recently, deep learning methods have been proposed and played a major role in medical image applications. The performance of deep learning model largely depends on the size of training samples. However, the number of samples of patient having urinary stones is limited, and the process of labeling preparation is time-consuming and need experts. In this research, we used a combination of real stone-contained images and synthesized stone-embedded images to train U-Net model to segment urinary stones in abdominal x-ray images. Furthermore, the simple augmentation methods which appear realistic in x-ray images were also implemented in these combined datasets. From the comparative experiments, the proposed method can achieve higher F 2 score than U-Net trained with only real images. This method not only helps to reduce the requirement of training data and labels of positive samples, but also increase the number and variability of training data to improve deep learning performance.

Natural and medical images may have a variety of distortions which may result in a degradation of visual quality. Image quality assessment (IQA) plays an important role in many image processing tasks to quantitatively measure image quality. Although several IQA methods have been developed for decades, each method has its individual characteristic and there is a few researches focusing on the development of quality assessment in a specific type of image such as medical images. We propose a new IQA method based on image gradient which is sensitive to the changed detail in images. This metric computed the similarity of gradient direction and also apply gradient magnitude information to weight these similarity values in pooling process. Experimental results demonstrate that this metric performs well especially in the distortion types that effect to image detail and can be used as the complementary part to the other IQA metrics for evaluating medical images quality.

Image quality assessment (IQA) plays an important role in many image processing tasks. Although several IQA methods have been developed for decades, each matric has its individual characteristic for evaluation. In this paper, we compare popular IQA methods including peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), mean structural similarity index (MSSIM) and feature similarity index (FSIM) on validating 3 different test images with various image degradation factors. The results of comparative experiment show that although each method has different sensitivity for different distortion, MSSIM is a good metric among them in overall performance. It can be used for a wide variety of image degradation. The parameters can be adjusted for different purposes.

This paper investigates automated detection of malaria parasites in images of Giemsa-stained thin blood films. We aim to determine parasitemia based on automatic segmentation, feature extraction and classification methods. Segmentation relies on adaptive thresholding and watershed methods. Statistical features are then computed for each cell and classified using SVM binary classifier. Accuracy of classification is validated based on the leave-one-out cross-validation technique. This processing pipeline is applied on total 15 images of Giemsa-stained thin blood films and yields 92.71% sensitivity, 97.35% specificity and 97.17% accuracy.