Several radiological patterns associated with pulmonary tuberculosis (TB) have been identified on chest X-rays (CXR) used for screening purposes. As a result, several automatic computational tools have emerged for this purpose. We propose a new algorithm, two-dimensional multiscale symbolic dynamic entropy (MSDE2D), to develop a computational tool sensitive to these subtle patterns variations and noise robustness for evaluating CXR images from healthy and TB-diagnosed individuals. The one-dimensional SDE algorithm was previously shown to be more efficient in detecting amplitude variations and in computational calculations (compared to other entropy algorithms). Additionally, we also extracted first-order statistical parameters like standard deviation (SD), and mean of positive pixels (MPP), among others. These MSDE2D and first-order texture features were used to detect TB in each lung individually. The MSDE2D was validated using a synthetic dataset and optimized for the best set of parameters. We verified that, for both lungs, the MSDE2D values were significantly different between healthy and TB CXR images (P < 0.05), and the effect size was |d| >0.23. From the first-order parameters, only the mean, SD, entropy, and MPP were statistically different between both groups for the left lung (P < 0.05; |d| >0.22). For the right lung, all first-order features significantly differentiated TB patients (P < 0.05; |d| >0.28). Finally, we show that a multi-layer perceptron obtained 86.4 and 85.2% accuracy in detecting TB in the left and right lungs, respectively. The highest sensitivity values achieved in this study were 71.4% and 81.8% for the left and right lungs, respectively.

BACKGROUND AND OBJECTIVE:Bidimensional entropy algorithms provide meaningful quantitative information on image textures. These algorithms have the advantage of relying on well-known one-dimensional entropy measures dedicated to the analysis of time series. However, uni- and bidimensional algorithms require the adjustment of some parameters that influence the obtained results or even findings. To address this, ensemble entropy techniques have recently emerged as a solution for signal analysis, offering greater stability and reduced bias in data patterns during entropy estimation. However, such algorithms have not yet been extended to their two-dimensional forms.METHODS:We therefore propose six bidimensional algorithms, namely ensemble sample entropy, ensemble permutation entropy, ensemble dispersion entropy, ensemble distribution entropy, and two versions of ensemble fuzzy entropy based on different models or parameters initialization of an entropy algorithm. These new measures are first tested on synthetic images and further applied to a biomedical dataset.RESULTS:The results suggest that ensemble techniques are able to detect different levels of image dynamics and their degrees of randomness. These methods lead to more stable entropy values (lower coefficients of variations) for the synthetic data. The results also show that these new measures can obtain up to 92.7% accuracy and 88.4% sensitivity when classifying patients with pulmonary emphysema through a k-nearest neighbors algorithm.CONCLUSIONS:This is a further step towards the potential clinical deployment of bidimensional ensemble approaches to detect different levels of image dynamics and their successful performance on emphysema lung computerized tomography scans. These bidimensional ensemble entropy algorithms have potential to be used in various imaging applications thanks to their ability to distinguish more stable and less biased image patterns compared to their original counterparts.

Imaging through scattering media using conventional systems is a significant challenge. Pixaleted systems struggle to handle the light wavefront scrambling that occurs when light is scattered before reaching the detector. This paper presents an imaging technique called single-pixel imaging which is more robust to scattering and allows better image quality when imaging through scattering media. Simulation and experimental works are used to show the capacities of SPI to reconstruct images acquired when a scattering medium is placed between the imaging sensor and the sample. Their results are compared with the images taken using a conventional pixelated system. The implications and limitations of these results are then discussed.

This paper presents a novel image analysis strategy that increases the potential of macular Optical Coherence Tomography (OCT) by using speckle features as biomarkers in different stages of glaucoma. A large pool of features (480) were computed for a subset of macular OCT volumes of the Leuven eye study cohort. The dataset contained 258 subjects that were divided into four groups based on their glaucoma severity: Healthy (56), Mild (94), Moderate (48), and Severe (60). The OCT speckle features were categorized as statistical properties, statistical distributions, contrast, spatial gray-level dependence matrices, and frequency domain features. The averaged thicknesses of ten retinal layers were also collected. Kruskal-Wallis H test and multivariable regression models were used to infer the most significant features related to glaucoma severity classification and to the correlation with visual field mean deviation. Four features were selected as being the most relevant: the ganglion cell layer (GCL) and the inner plexiform layer (IPL) thicknesses, and two OCT speckle features, the data skewness computed on the retinal nerve fiber layer (RNFL) and the scale parameter (a) of the generalized gamma distribution fitted to the GCL data. Based on a significance level of 0.05, the regression models revealed that RNFL skewness exhibited the highest significance among the features considered for glaucoma severity staging (p-values of 8.6×10-6 for the logistic model and 2.8×10-7 for the linear model). Furthermore, it demonstrated a strong negative correlation with the visual field mean deviation (ρ=-0.64). The post hoc analysis revealed that, when distinguishing healthy controls from glaucoma subjects, GCL thickness is the most relevant feature (p-value of 8.7×10-5). Conversely, when comparing the Mild versus Moderate stages of glaucoma, RNFL skewness emerged as the only feature exhibiting statistical significance (p-value = 0.001). This work shows that macular OCT speckle contains information that is currently not used in clinical practice, and not only complements structural measurements (thickness) but also has a potential for glaucoma staging.

Significance: Speckle has historically been considered a source of noise in coherent light imaging. However, a number of works in optical coherence tomography (OCT) imaging have shown that speckle patterns may contain relevant information regarding sub-resolution and structural properties of the tissues from which it is originated. Aim: The objective of this work is to provide a comprehensive overview of the methods developed for retrieving speckle information in biomedical OCT applications. Approach: PubMed and Scopus databases were used to perform a systematic review on studies published until April 2021. From 134-screened studies, 37 were eligible for this review. Results: The studies have been clustered according to the nature of their analysis, namely static or dynamic, and all features were described and analysed. The results show that features retrieved from speckle can be used successfully in different applications, such as classification and segmentation. However, the results also show that speckle analysis is highly application-dependant, and the best approach varies between applications. Conclusions: Several of the reviewed analysis were only performed in a theoretical context or using phantoms, showing that signal-carrying speckle analysis in OCT imaging is still in its early stage, and further work is needed to validate its applicability and reproducibility in a clinical context.

Entropy algorithms have been applied extensively for time series analysis. The entropy value given by the algorithm quantifies the irregularity of the data structure. For higher irregular data structures, the entropy is higher. Both permutation entropy (PE) and amplitude-aware permutation entropy (AAPE) have been previously used to analyze time series. These two metrics have the advantage, over others, of being computationally fast and simple. However, fewer entropy measures have been proposed to process images. Two-dimensional entropy algorithms can be used to study texture and analyze the irregular structure of images. Herein, we propose the extension of AAPE for two-dimensional analysis (AAPE(2D)). To the best of our knowledge, AAPE(2D) has never been proposed to analyze texture of images. For comparison purposes, we also study the two-dimensional permutation entropy (PE2D) to analyze the effect of the amplitude consideration in texture analysis. In this study, we compare AAPE(2D) method with PE2D in terms of irregularity discrimination, parameters sensitivity, and artificial texture differentiation. Both AAPE(2D) and PE2D appear to be interesting entropy-based approaches for image texture analysis. When applied to a biomedical dataset of chest X-rays with healthy subjects and pneumonia patients, both methods showed to statistically differentiate both groups for P < 0.01. Finally, using a SVM model and multiscale entropy values as features, AAPE(2D) achieves an average of 75.7% accuracy which is slightly better than the results of PE2D. Overall, both entropy algorithms are promising and achieve similar conclusions. This work is a new step towards the development of other entropy-based texture measures. (C) 2022 Elsevier B.V. All rights reserved.

The optic nerve head (ONH) represents the intraocular section of the optic nerve, which is prone to damage by intraocular pressure (IOP). The advent of optical coherence tomography (OCT) has enabled the evaluation of novel ONH parameters, namely the depth and curvature of the lamina cribrosa (LC). Together with the Bruch's membrane minimum-rim-width (BMO-MRW), these seem to be promising ONH parameters for diagnosis and monitoring of retinal diseases such as glaucoma. Nonetheless, these OCT derived biomarkers are mostly extracted through manual segmentation, which is time-consuming and prone to bias, thus limiting their usability in clinical practice. The automatic segmentation of ONH in OCT scans could further improve the current clinical management of glaucoma and other diseases. This review summarizes the current state-of-the-art in automatic segmentation of the ONH in OCT. PubMed and Scopus were used to perform a systematic review. Additional works from other databases (IEEE, Google Scholar and ARVO IOVS) were also included, resulting in a total of 29 reviewed studies. For each algorithm, the methods, the size and type of dataset used for validation, and the respective results were carefully analysed. The results show a lack of consensus regarding the definition of segmented regions, extracted parameters and validation approaches, highlighting the importance and need of standardized methodologies for ONH segmentation. Only with a concrete set of guidelines, these automatic segmentation algorithms will build trust in data-driven segmentation models and be able to enter clinical practice.

Texture analysis is a subject of intensive focus in research due to its significant role in the field of image processing. However, few studies focus on colored texture analysis and even fewer use information theory concepts. Entropy measures have been proven competent for gray scale images. However, to the best of our knowledge, there are no well-established entropy methods that deal with colored images yet. Therefore, we propose the recent colored bidimensional fuzzy entropy measure, FuzEnC2D, and introduce its new multi-channel approaches, FuzEnV2D and FuzEnM2D, for the analysis of colored images. We investigate their sensitivity to parameters and ability to identify images with different irregularity degrees, and therefore different textures. Moreover, we study their behavior with colored Brodatz images in different color spaces. After verifying the results with test images, we employ the three methods for analyzing dermoscopic images of malignant melanoma and benign melanocytic nevi. FuzEnC2D, FuzEnV2D, and FuzEnM2D illustrate a good differentiation ability between the two-similar in appearance-pigmented skin lesions. The results outperform those of a well-known texture analysis measure. Our work provides the first entropy measure studying colored images using both single and multi-channel approaches.

One of the most active research fields in single-pixel imaging is the influence of the sampling basis and its order in the quality of the reconstructed images. This paper presents two new orders, ascending scale (AS) and ascending inertia (AI), of the Hadamard basis and test their performance, using simulation and experimental methods, for low sampling ratios (0.5 to 0.01) in low resolution images (up to $128\,{\times }\,128$ ). These orders were compared with two state-of-the-art orders, cake-cutting (CC) and total gradient (TG), using TVAL3 as the reconstruction algorithm and three noise levels. These newly proposed orders have better reconstructed image quality on the simulation data set (110 images) and achieved structure similarity index values higher than CC order. The experimental data set (2 images) showed that the AS and AI orders performed better with a sampling ratio of 0.5, while for lower sampling ratio the performance of AS, AI and CC was similar. The TG order performed worst in the majority of the cases. Finally, the simulation results present clear evidence that peak signal-to-noise ratio (PSNR) is not a reliable image quality assessment (IQA) metric to assess image reconstruction quality in the context of single pixel imaging.

Compressive single pixel imaging (C-SPI) is a novel imaging technique able to reconstruct images using only a single pixel detector and a partial measurement of the scene. This technique uses different structured illumination, generated by a spatial modulator, to illuminate the scene and measures the reflected or transmitted light intensities. This compressive stage allows for a sub-Nyquist set of measurements, which significantly increases the technique efficiency, while maintaining a good reconstruction image quality. An experimental setup was developed to study the ability of C-SPI to determine the lifetime and mean intensity of an oxygen sensitive biomarker (Pt(II) ring-fused chlorins). This biomarker phosphorescence is quenched in the presence of oxygen resulting in smaller intensity and lifetime. A structured illumination system was used to stimulate the sample with Hadamard patterns, in the range between 428 nm and 620 nm, while a photodiode collected the emitted light peaking at 756nm. The imaged scene was composed of two toluene solutions with the same biomarker concentration (1 μM), one in the presence of oxygen and the other in its absence. The images were reconstructed using total variation minimization by augmented lagrangian and alternating direction algorithms (TVAL3) with compressive ratios of 25%, 10% and 5%. The proposed method was able to spatially locate the sample contained in a deoxygenated environment in two distinct spatial locations. The deoxygenated sample lifetime and mean intensity of the reconstructed images were, respectively, approximate 20 μs and 2.1×10-3 AU, for the first location, and 20 μs and 4.0×10-3 AU for the second location. Regarding the oxygenated sample, the results were scattered in a long range for lifetime but achieved a mean intensity of approximately 4.8×10-5 AU. Consistent results were obtained for the three compression ratios without major loss in image quality. The proposed method showed that SPI has the ability to perform simultaneous phosphorescence lifetime and intensity imaging. The introduction of compressive sensing makes this technology more attractive to practical applications because it lowers the amount of time necessary to image the sample. The C-SPI is a simple and less expensive technique because it dismisses the use of a fast two dimensional detector (CCD) and the associated electronics, as well as mechanical scanning procedures. Also, multiple single pixel detectors, sensitive to different wavelengths, can make these instruments versatile and allow for simultaneous phosphorescence biomarkers analysis. The next steps in the research will be to study changes in the sample concentration and different percentages of dissolved oxygen.

Idiopathic Pulmonary Fibrosis (IPF) is a chronic, severe, and progressive lung disease with short life expectancy. Based on information theory and entropy measurement, a three-dimensional multiscale fuzzy entropy (MFE3D) algorithm is proposed to identify IPF patients from their computed tomography (CT) volumetric data. First, the validation of the algorithm was performed by analyzing several volumetric synthetic noises (white, blue, brown, and pink), MIX(p) processes-based volumes, and texture-based volumes. The entropy values obtained by MFE3D were consistent with the values obtained using the one, and two-dimensional versions, validating its use in biomedical data. Hence, MFE3D was applied to CT scans to identify the existence of IPF within two different groups, one of healthy subjects (26) and another of IPF patients (26). Statistical differences were found (p < 0.05) between the entropy values of each group in 5 scale factors out of 10. These results demonstrate that MFE(3D)could be an interesting metric to identify IPF in CT scans.

The lamina cribrosa (LC) is an active structure that responds to the strain by changing its morphology. Abnormal changes in LC morphology are usually associated with, and indicative of, certain pathologies such as glaucoma, intraocular hypertension, and myopia. Recent developments in optical coherence tomography (OCT) have enabled detailed in vivo studies about the architectural characteristics of the LC. Structural characteristics of the LC have been widely explored in glaucoma management. However, information about which LC biomarkers could be useful for the diagnosis, and follow-up, of other diseases besides glaucoma is scarce. Hence, this literature review aims to summarize the role of the LC in nonophthalmic and ophthalmic diseases other than glaucoma. PubMed was used to perform a systematic review on the LC features that can be extracted from OCT images. All imaging features are presented and discussed in terms of their importance and applicability in clinical practice. A total of 56 studies were included in this review. Overall, LC depth (LCD) and thickness (LCT) have been the most studied features, appearing in 75% and 45% of the included studies, respectively. These biomarkers were followed by the prelaminar tissue thickness (21%), LC curvature index (5.4%), LC global shape index (3.6%), LC defects (3.6%), and LC strains/deformations (1.8%). Overall, the disease groups showed a thinner LC (smaller LCT) and a deeper ONH cup (larger LCD), with some exceptions. A large variability between approaches used to compute LC biomarkers has been observed, highlighting the importance of having automated and standardized methodologies in LC analysis. Moreover, further studies are needed to identify the pathologies where LC features have a diagnostic and/or prognostic value.

Recently, a bi-dimensional fuzzy entropy measure has been proposed for image texture evaluation. Herein, a new bi-dimensional fuzzy entropy is proposed to process colored images. Our algorithm, FuzEnC2D, in opposition to dos Santos et al. (2018) definition, evaluates each color channel individually with consideration of global and local characteristics. We propose to apply it for the characterization of melanoma's dermoscopic images. In this work, FuzEnC2D is tested by evaluating its sensitivity to change of parameters, rotation sensitivity, ability to determine irregularity through shuffling pixels, and consistency according to different image sizes. For those purposes, white noise and colored Brodatz textures are used. The algorithm is also applied to dermoscopic images of the public PH2 dataset to evaluate its performance in distinguishing common nevi, atypical nevi, and melanoma lesions. The results reveal a relative decrease of, at most, 29.97 % for FuzEnC2D-values when considering different parameters values. On the other hand, the consistency and low rotation sensitivity of the algorithm are revealed by analyzing the same texture with different sizes (maximum relative difference of 4.34%) and when comparing the entropy of an image upon rotation (maximum relative difference of 0.36%). Besides, after shuffling the pixels of an image, FuzEnC2D-values of shuffled images increases up to 8.9 times of the original values. Moreover, using the red channel's entropy, a common nevi lesion is statistically different from an atypical one (p = 0.004 with the Kruskal-Wallis test). Regarding the green channel, a statistical difference (p = 0.034) is observed between atypical nevi lesions and melanoma. Also, differentiating a common nevi lesion from lesions diagnosed as melanoma is possible regardless the RGB channels. Finally, the FuzEnC2D algorithm appears as a promising algorithm to analyze, through an entropy-based measure, the texture of colored images.

Radiologists, and doctors in general, need relevant information for the quantification and characterization of pulmonary structures damaged by severe diseases, such as the Coronavirus disease 2019 (COVID-19). Texturebased analysis in scope of other pulmonary diseases has been used to screen, monitor, and provide valuable information for several kinds of diagnoses. To differentiate COVID-19 patients from healthy subjects and patients with other pulmonary diseases is crucial. Our goal is to quantify lung modifications in two pulmonary pathologies: COVID-19 and idiopathic pulmonary fibrosis (IPF). For this purpose, we propose the use of a threedimensional multiscale fuzzy entropy (MFE3D) algorithm. The three groups tested (COVID-19 patients, IPF, and healthy subjects) were found to be statistically different for 9 scale factors (p < 0.01). A complexity index (CI) based on the sum of entropy values is used to classify healthy subjects and COVID-19 patients showing an accuracy of 89.6%, a sensitivity of 96.1%, and a specificity of 76.9%. Moreover, 4 different machine-learning models were also used to classify the same COVID-19 dataset for comparison purposes.

Single-pixel imaging is an imaging technique that has recently attracted a lot of attention from several areas. This paper presents a study on the influence of the Hadamard basis ordering on the image reconstruction quality, using simulation and experimental methods. During this work, five different orderings, Natural, Walsh, Cake-cutting, High Frequency and Random orders, along with two different reconstruction algorithms, TVAL3 and NESTA, were tested. Also, three different noise levels and compression ratios from 0.1 to 1 were evaluated. A single-pixel camera was developed using a digital micromirror device for the experimental phase. For a compression ratio of 0.1, the Cake-cutting order achieved the best reconstruction quality, while the best contrast was achieved by Walsh order. For compression ratios of 0.5, the Walsh and Cake-cutting orders achieved similar results. Both Walsh and Cake-cutting orders reconstructed the images with good quality using compression ratios from 0.3. Finally, the TVAL3 algorithm showed better image reconstruction quality, in comparison with NESTA, when considering compression ratios from 0.1 to 0.5.

Since the start of the COVID-19 pandemic, there has been an urgent need to develop protective measures to ensure patient and healthcare worker safety in clinical situations. Direct/monocular ophthalmoscopy is particularly difficult to perform safely, given the very close proximity of the patient and the clinician. However, ophthalmoscopy is an important and on occasion an irreplaceable element of the neurological examination. It is particularly important for identifying papilloedema in headache, optic disc oedema and/or other retinal findings in acute visual loss, temporal disc atrophy in suspected multiple sclerosis or simply for reassuring someone with primary headache where the examination is otherwise normal or there are only superficial optic nerve drusen.1 Using an ophthalmoscope when wearing adequate personal protective equipment can be challenging. From our experience, it is impractical to visualise the optic fundi while wearing …

Parkinson's disease is a neurodegenerative disorder that degrades the motor performance of patients. Specific motor symptoms, including tremor and bradykinesia, are clinically evaluated through the Unified Parkinson's disease Rating Scale (UPDRS), but with limited reproducibility and accuracy due to its intrinsic qualitative nature. A free-field and non-contact movement assessment method, based on stereoscopic imaging (Leap Motion controller) has been explored to precisely quantify supination/pronation (SUPRO) hand movements. A bench experiment was designed using a hand phantom to test its linearity. The Leap Motion controller presented a linear response considering rotation angles from -45 degrees to 45 degrees (r(2) = 0.995). A serious game was developed to guide the data acquisition procedure, with a protocol similar to that of UPDRS, in 31 healthy subjects. The SUPRO hand movement was characterized in terms of root mean square values, predominant frequency, total spectral power and number of zero crossings. The control group achieved root mean square values of 9.60 +/- 2.87 rad/s, a predominant frequency of 2.43 +/- 0.52 Hz, a total spectral power of 927 +/- 571 (rad/s)(2) and a number of zero crossings of 275 +/- 101. Also, a patient with Parkinson's disease was tested with a similar fashion, obtaining significantly different parameters. (C) 2020 Elsevier Ltd. All rights reserved.

In this study, we propose a new irregularity measure for colored images, the so-called bidimensional colored fuzzy entropy, FuzEnC 2D . This measure is based on information theory and fuzzy concept. We test its sensitivity to parameters such as tolerance level and window size, as well as its ability to quantify different degrees of irregularity in image textures. Afterwards, we evaluate dermoscopic images of two different microcirculatory states obtained at rest and upon contact heating. The goal of comparing these dermoscopic images is to test if the method is able to distinguish two kinds of microcirculation states. The results show that FuzEnC 2D is a proper colored image irregularity measure having low sensitivity to the choice of parameters. We also show its significance in identifying relaxed and vasodilated microcirculatory states in dermoscopic images. This work creates new opportunities in medical applications for colored images with a specific importance for bedridden patients microcirculatory assessment.

Diabetic Retinopathy (DR) is the leading cause of visual disability worldwide. Although it is highly treatable when diagnosed in its earlier stages, there is currently a need of cheaper and more accurate ways to do so. Medical images have been used in diagnosis for a long time. Recent advancements in the computer vision field have shown remarkable results through the use of Convolutional Neural Networks, that have been able to reach state-of-the-art results in image segmentation. In this master’s thesis, we implemented a V-Net like architecture in Python and study how image preprocessing techniques to highlight lesions associated with DR, and different optimization metrics have an impact on its results. The results show that the impact of this variables changes according to the lesion that we try to segment and that the V-Net is capable of obtaining good results for some of the segmentation problems.

This work presents an analysis of the performances for four different implementations used to compute laser speckle contrast on images. Laser speckle contrast is a widely used imaging technique for biomedical applications. These implementations were tested using synthetic laser speckle patterns with different resolutions, speckle sizes, and contrasts. From the applied methods, three implementations are already known in the literature. A new alternative is proposed herein, which relies on two-dimensional convolutions, in order to improve the image processing time without compromising the contrast assessment. The proposed implementation achieves a processing time two orders of magnitude lower than the analytical evaluation. The goal of this technical manuscript is to help the developers and researchers in computing laser speckle contrast images.