SELECTED APPLICATIONS OF DEEP NEURAL NETWORKS IN SKIN LESION DIAGNOSTIC

The article provides an overview of selected applications of deep neural networks in the diagnosis of skin lesions from human dermatoscopic images, including many dermatological diseases, including very dangerous malignant melanoma. The lesion segmentation process, features selection and classification was described. Application examples of binary and multiclass classification are given. The described algorithms have been widely used in the diagnosis of skin lesions. The effectiveness, specificity, and accuracy of classifiers were compared and analysed based on available datasets.

A Semiautomatic Multi-Label Color Image Segmentation Coupling Dirichlet Problem and Colour Distances

Image segmentation is an essential but critical component in low level vision, image analysis, pattern recognition, and now in robotic systems. In addition, it is one of the most challenging tasks in image processing and determines the quality of the final results of the image analysis. Colour based segmentation could hence offer more significant extraction of information as compared to intensity or texture based segmentation. In this work, we propose a new local or global method for multi-label segmentation that combines a random walk based model with a direct label assignment computed using a suitable colour distance. Our approach is a semi-automatic image segmentation technique, since it requires user interaction for the initialisation of the segmentation process. The random walk part involves a combinatorial Dirichlet problem for a weighted graph, where the nodes are the pixel of the image, and the positive weights are related to the distances between pixels: in this work we propose a novel colour distance for computing such weights. In the random walker model we assign to each pixel of the image a probability quantifying the likelihood that the node belongs to some subregion. The computation of the colour distance is pursued by employing the coordinates in a colour space (e.g., RGB, XYZ, YCbCr) of a pixel and of the ones in its neighbourhood (e.g., in a 8–neighbourhood). The segmentation process is, therefore, reduced to an optimisation problem coupling the probabilities from the random walker approach, and the similarity with respect the labelled pixels. A further investigation involves an adaptive preprocess strategy using a regression tree for learning suitable weights to be used in the computation of the colour distance. We discuss the properties of the new method also by comparing with standard random walk and k−means approaches. The experimental results carried on the White Blood Cell (WBC) dataset and GrabCut datasets show the remarkable performance of the proposed method in comparison with state-of-the-art methods, such as normalised random walk and normalised lazy random walk, with respect to segmentation quality and computational time. Moreover, it reveals to be very robust with respect to the presence of noise and to the choice of the colourspace.

Semi-Automatic Image Segmentation on X-ray Image of Spine using Active Contour Method

Currently, many image analysis methods have been developed on X-Ray of scoliotic patients. However, segmentation of spinal curvature is still a challenge, and needs to be improved. In this research, we proposed a semi-automatic spinal image segmentation of scoliotic patients from X-Ray images. This method is divided into 2 steps: preprocessing and segmentation process. A conversion process from RGB to grayscale and CLAHE (Contrast Limited Adequate Histogram Equalization) method was used in image preprocessing. The active contour method was used for the segmentation process. The result shows that segmentation of spinal X-ray images of scoliotic patients using active contour method interactively, can give better results. The average of ME and RAE values are 12.98% and 26.75 %. instead of using the interactive region splitting method which gets 21.17% and 89.27%. Keywords: active contour, interactive segmentation, pre-processing, scoliosis.

Fuzzy C-Means Technique for Band Reduction and Segmentation of Hyperspectral Satellite Image

This paper put forward for the segmentation process on the hyperspectral remote sensing satellite scene. The prevailing algorithm, fuzzy c-means, is performed on this scene. Moreover, this algorithm is performed in both inter band as well as intra band clustering (i.e., band reduction and segmentation are performed by this algorithm). Furthermore, a band that has topmost variance is selected from every cluster. This structure diminishes these bands into three bands. This reduced band is de-correlated, and subsequently segmentation is carried out using this fuzzy algorithm.

APPLICATION OF LAPAN A3 SATELLITE DATA FOR THE IDENTIFICATION OF PADDY FIELDS USING OBJECT BASED IMAGE ANALYSIS (OBIA)

The role of agriculture is directly related to SDG No.2, which is running a programme until 2030 to reduce national poverty, eradicate hunger by increasing food security and improving nutrition and support sustainable agriculture. Problems faced include the reduction in agricultural land, which results in lower rice production, and the limited information on the monitoring of paddy fields using spatial data. The purpose of this study is to identify paddy fields using LAPAN A3 satellite imagery based on OBIA classification. The data used were from LAPAN A3 multispectral imagery dated 19 June 2017, Landsat 8 imagery dated 17 June 2017, DEM SRTM (BIG), and the Administrative Boundary Map (BIG). The analysis method was segmentation by grouping image pixels, and supervised classification by taking several sample areas based on Random Stratified Sampling. The results will be carried using a confusion matrix. The classification results produced four classes; watery paddy fields, vegetation paddy fields, fallow paddy fields, and non-paddy fields, using of the green, red, and NIR bands for the LAPAN A3 data. From the results of the segmentation process, there remain some oversegmented features in the appearance of the same object. Oversegmentation is due to an inaccurate value assignment to each algorithm parameter when the segmentation process is performed. For example, watery paddy fields appear almost the same as open land (fallow paddy fields), the water object is darker purple. The visual classification results (Landsat 8 data) are considered as the reference for the digital classification results (LAPAN A3). Forty-eight samples were taken and divided into four classes, with each class consisting of 12 samples. The results of the accuracy test show that the total accuracy of the object-based digital classification for visual classification is 62.5% with a Kappa accuracy value of 0.5. The conclusion is that LAPAN A3 data can be used to identify paddy fields based on spectral resolution and to complement Landsat 8 data. To improve the accuracy of the classification results, more samples and the correct RGB composition are needed.

Segmentation atrioventricular septal defect by using convolutional neural networks based on U-NET architecture

Congenital heart disease often occurs, especially in infants and fetuses. Fetal image is one of the issues that can be related to the segmentation process. The fetal heart is an important indicator in the process of structural segmentation and functional assessment of congenital heart disease. This study is very challenging due to the fetal heart has a relatively unclear structural anatomical appearance, especially in the artifacts in ultrasound images. There are several types of congenital heart disease that often occurs namely in septal defects it consists of the atrial septal defect, ventricular septal defect, and atrioventricular septal defect. The process of identifying the standard of the heart, especially the fetus, can be identified with a 2D ultrasound video in the initial steps to diagnose congenital heart disease. The process of diagnosis of fetal heart standards can be seen from a variety of spaces, i.e., 4 chamber views. In this study, the standard semantic segmentation process of the fetal heart is abnormal and normal in terms of the perspective of 4 chamber views. The validation evaluation results obtained in this study amounted to 99.79% pixel accuracy, mean iou 96.10%, mean accuracy 97.82%, precision 96.41% recall 95.72% and F1 score 96.02%.

Segmentasi Citra Pembuluh Darah Retina Menggunakan Operasi Morfologi Iteratif

Retinal vessel segmentation is part of the morphological extraction of retinal blood vessels that plays an essential role in medical image processing. Manual segmentation is possible to do, but it is time-consuming and requires special operators. Moreover, the possibility of variability between operators is vast. This study aims to answer the shortcomings of the manual segmentation process by automatically segmenting retinal blood vessels. The main contribution of this study is the use of a simple method to iteratively segment retinal blood vessels. All processes in the segmentation are simulated using Matlab. The algorithm was evaluated by comparing the results of the automatic segmentation with 20 manually segmented images from the STARE dataset. The result show specificity 98.13%, accuracy 93.60%, sensitivity 56.42%, precision 80.48%, and the dice coefficient 64.06%. In conclusion, the automatic retinal blood vessel image segmentation process worked well.

ExpanDrogram: Dynamic Visualization of Big Data Segmentation over Time

In dynamic and big data environments the visualization of a segmentation process over time often does not enable the user to simultaneously track entire pieces. The key points are sometimes incomparable, and the user is limited to a static visual presentation of a certain point. The proposed visualization concept, called ExpanDrogram, is designed to support dynamic classifiers that run in a big data environment subject to changes in data characteristics. It offers a wide range of features that seek to maximize the customization of a segmentation problem. The main goal of the ExpanDrogram visualization is to improve comprehensiveness by combining both the individual and segment levels, illustrating the dynamics of the segmentation process over time, providing “version control” that enables the user to observe the history of changes, and more. The method is illustrated using different datasets, with which we demonstrate multiple segmentation parameters, as well as multiple display layers, to highlight points such as new trend detection, outlier detection, tracking changes in original segments, and zoom in/out for more/less detail. The datasets vary in size from a small one to one of more than 12 million records.

On Image Segmentation Based on Local Entropy Fitting Under Nonconvex Regularization Term Constraints

The energy functional of the CV and LBF model is single, which makes the curve to get into the local minimum easily during the evolution process, and results inaccurate segmentation of the images with nonuniform grayscale and nonsmooth edges. The proposed algorithm, which is based on local entropy fitting under the constraint of nonconvex regularization term, is used to deal with such problems. In this algorithm, global information and local entropy are fitted to avoid segmentation falling into local optimum, and nonconvex regularization term is imported for constraint to protect edge smoothing. First, global information is used to evolve the approximate contour curve of the target segmentation. Then, a local energy functional with local entropy information is constructed to avoid the segmentation process from falling into a local minimum, and to precisely segment the image. Finally, nonconvex regularization terms are used in the energy functional to protect the smoothness of edge information during image segmentation process. The experimental results clearly indicate that the new algorithm can effectively resist noise, precisely segment images with nonuniform grayscale, and achieve the global optimal.