Search

The perceived texture directionality is an important, not fully explored image characteristic. In many applications texture directionality detection is of fundamental importance. Several approaches have been proposed, such as the fast Fourier-based method. We recently proposed a method based on the interpolated grey-level co-occurrence matrix (iGLCM), robust to image blur and noise but slower than the Fourier-based method. Here we test the applicability of convolutional neural networks (CNNs) to texture directionality detection. To obtain the large amount of training data required, we built a training dataset consisting of synthetic textures with known directionality and varying perturbation levels. Subsequently, we defined and tested shallow and deep CNN architectures. We present the test results focusing on the CNN architectures and their robustness with respect to image perturbations. We identify the best performing CNN architecture, and compare it with the iGLCM, the Fourier and the local gradient orientation methods. We find that the accuracy of CNN is lower, yet comparable to the iGLCM, and it outperforms the other two methods. As expected, the CNN method shows the highest computing speed. Finally, we demonstrate the best performing CNN on real-life images. Visual analysis suggests that the learned patterns generalize to real-life image data. Hence, CNNs represent a promising approach for texture directionality detection, warranting further investigation.

Melanoma is one of the most lethal and rapidly growing cancers, causing many deaths each year. This cancer can be treated effectively if it is detected quickly. For this reason, many algorithms and systems have been developed to support automatic or semiautomatic detection of neoplastic skin lesions based on the analysis of optical images of individual moles. Recently, full-body systems have gained attention because they enable the analysis of the patient’s entire body based on a set of photos. This paper presents a prototype of such a system, focusing mainly on assessing the effectiveness of algorithms developed for the detection and segmentation of lesions. Three detection algorithms (and their fusion) were analyzed, one implementing deep learning methods and two classic approaches, using local brightness distribution and a correlation method. For fusion of algorithms, detection sensitivity = 0.95 and precision = 0.94 were obtained. Moreover, the values of the selected geometric parameters of segmented lesions were calculated and compared for all algorithms. The obtained results showed a high accuracy of the evaluated parameters (error of area estimation

Background: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is an imaging technique which helps in visualizing and quantifying perfusion—one of the most important indicators of an organ’s state. This paper focuses on perfusion and filtration in the kidney, whose performance directly influences versatile functions of the body. In clinical practice, kidney function is assessed by measuring glomerular filtration rate (GFR). Estimating GFR based on DCE-MRI data requires the application of an organ-specific pharmacokinetic (PK) model. However, determination of the model parameters, and thus the characterization of GFR, is sensitive to determination of the arterial input function (AIF) and the initial choice of parameter values. Methods: This paper proposes a multi-layer perceptron network for PK model parameter determination, in order to overcome the limitations of the traditional model’s optimization techniques based on non-linear least-squares curve-fitting. As a reference method, we applied the trust-region reflective algorithm to numerically optimize the model. The effectiveness of the proposed approach was tested for 20 data sets, collected for 10 healthy volunteers whose image-derived GFR scores were compared with ground-truth blood test values. Results: The achieved mean difference between the image-derived and ground-truth GFR values was 2.35 mL/min/1.73 m2, which is comparable to the result obtained for the reference estimation method (−5.80 mL/min/1.73 m2). Conclusions: Neural networks are a feasible alternative to the least-squares curve-fitting algorithm, ensuring agreement with ground-truth measurements at a comparable level. The advantages of using a neural network are twofold. Firstly, it can estimate a GFR value without the need to determine the AIF for each individual patient. Secondly, a reliable estimate can be obtained, without the need to manually set up either the initial parameter values or the constraints thereof.