Search

Backed by more powerful computational resources and optimized training routines, deep learning models have proven unprecedented performance and several benefits to extract information from chest X-ray data. This is one of the most common imaging exams, whose increasing demand is reflected in the aggravated radiologists’ workload. Consequently, healthcare would benefit from computer-aided diagnosis systems to prioritize certain exams and further identify possible pathologies. Pioneering work in chest X-ray analysis has focused on the identification of specific diseases, but to the best of the authors' knowledge no paper has specifically reviewed relevant work on abnormality detection and multi-label thoracic pathology classification. This paper focuses on those issues, selecting the leading chest X-ray based deep learning strategies for comparison. In addition, the paper discloses the current annotated public chest X-ray databases, covering the common thorax diseases.

HIDRALERTA is a forecast and early warning system for coastal and port regions capable of predicting emergency situations, as well as carrying out risk assessment. The system concentrates on evaluating wave overtopping and flooding scenarios. It uses offshore sea-wave and wind forecast data, as well as tide data, as input to determine wave overtopping at specific locations. The calculation of the mean overtopping discharge over a structure is made through artificial neural network tools and/or empirical formulae, which are able to define the spatial distribution of the flow behind the structure. The HIDRALERTA system is composed of four modules developed in Open Source Web Technology, mainly using the Python Language. The Warning System can be configured and adapted for specific scenarios. The system has been successfully tested for the Port and Bay of Praia da Vitória, Terceira Island, Azores, Portugal, and is now under development and being implemented at the ports of Madalena do Pico and S. Roque do Pico. This paper describes the work carried out to date on the system and its application to these two ports in the Pico Island, Azores.

Proliferative diabetic retinopathy (PDR) is an advanced diabetic retinopathy stage, characterized by neovascularization, which leads to ocular complications and severe vision loss. However, the available DR-labeled retinal image datasets have a small representation of images of the severest DR grades, and thus there is lack of PDR cases for training DR grading models. Additionally, the criteria for labelling these images in the publicly available datasets is not always clear, with some images which do not show typical PDR lesions being labeled as PDR due to the presence of photo-coagulation treatment and laser marks. This problem, together with the datasets' high class imbalance, leads to a limited variability of the samples, which the typical data augmentation and class balancing cannot fully mitigate. We propose a heuristic-based data augmentation scheme based on the synthesis of neovessel (NV)-like structures that compensates for the lack of PDR cases in DR-labeled datasets. The proposed neovessel generation algorithm relies on the general knowledge of common location and shape of these structures. NVs are generated and introduced in pre-existent retinal images which can then be used for enlarging deep neural networks' training sets. The data augmentation scheme was tested on multiple datasets, and allows to improve the model's capacity to detect NVs.

The worldwide pandemic caused by the new coronavirus (COVID-19) has encouraged the development of multiple computer-aided diagnosis systems to automate daily clinical tasks, such as abnormality detection and classification. Among these tasks, the segmentation of COVID lesions is of high interest to the scientific community, enabling further lesion characterization. Automating the segmentation process can be a useful strategy to provide a fast and accurate second opinion to the physicians, and thus increase the reliability of the diagnosis and disease stratification. The current work explores a CNN-based approach to segment multiple COVID lesions. It includes the implementation of a U-Net structure with a ResNet34 encoder able to deal with the highly imbalanced nature of the problem, as well as the great variability of the COVID lesions, namely in terms of size, shape, and quantity. This approach yields a Dice score of 64.1%, when evaluated on the publicly available COVID-19-20 Lung CT Lesion Segmentation GrandChallenge data set.

Diabetic retinopathy (DR) is a diabetes complication, which in extreme situations may lead to blindness. Since the first stages are often asymptomatic, regular eye examinations are required for an early diagnosis. As microaneurysms (MAs) are one of the first signs of DR, several automated methods have been proposed for their detection in order to reduce the ophthalmologists' workload. Although local convergence filters (LCFs) have already been applied for feature extraction, their potential as MA enhancement operators was not explored yet. In this work, we propose a sliding band filter for MA enhancement aiming at obtaining a set of initial MA candidates. Then, a combination of the filter responses with color, contrast and shape information is used by an ensemble of classifiers for final candidate classification. Finally, for each eye fundus image, a score is computed from the confidence values assigned to the MAs detected in the image. The performance of the proposed methodology was evaluated in four datasets. At the lesion level, sensitivities of 64% and 81% were achieved for an average of 8 false positives per image (FPIs) in e-ophtha MA and SCREEN-DR, respectively. In the last dataset, an AUC of 0.83 was also obtained for DR detection.

Lung cancer is considered one of the deadliest diseases in the world. An early and accurate diagnosis aims to promote the detection and characterization of pulmonary nodules, which is of vital importance to increase the patients' survival rates. The mentioned characterization is done through a segmentation process, facing several challenges due to the diversity in nodular shape, size, and texture, as well as the presence of adjacent structures. This paper tackles pulmonary nodule segmentation in computed tomography scans proposing three distinct methodologies. First, a conventional approach which applies the Sliding Band Filter (SBF) to estimate the filter's support points, matching the border coordinates. The remaining approaches are Deep Learning based, using the U-Net and a novel network called SegU-Net to achieve the same goal. Their performance is compared, as this work aims to identify the most promising tool to improve nodule characterization. All methodologies used 2653 nodules from the LIDC database, achieving a Dice score of 0.663, 0.830, and 0.823 for the SBF, U-Net and SegU-Net respectively. This way, the U-Net based models yield more identical results to the ground truth reference annotated by specialists, thus being a more reliable approach for the proposed exercise. The novel network revealed similar scores to the U-Net, while at the same time reducing computational cost and improving memory efficiency. Consequently, such study may contribute to the possible implementation of this model in a decision support system, assisting the physicians in establishing a reliable diagnosis of lung pathologies based on this segmentation task.

Several systemic diseases affect the retinal blood vessels, and thus, their assessment allows an accurate clinical diagnosis. This assessment entails the estimation of the arteriolar-to-venular ratio (AVR), a predictive biomarker of cerebral atrophy and cardiovascular events in adults. In this context, different automatic and semiautomatic image-based approaches for artery/vein (A/V) classification and AVR estimation have been proposed in the literature, to the point of having become a hot research topic in the last decades. Most of these approaches use a wide variety of image properties, often redundant and/or irrelevant, requiring a training process that limits their generalization ability when applied to other datasets. This paper presents a new automatic method for A/V classification that just uses the local contrast between blood vessels and their surrounding background, computes a graph that represents the vascular structure, and applies a multilevel thresholding to obtain a preliminary classification. Next, a novel graph propagation approach was developed to obtain the final A/V classification and to compute the AVR. Our approach has been tested on two public datasets (INSPIRE and DRIVE), obtaining high classification accuracy rates, especially in the main vessels, and AVR ratios very similar to those provided by human experts. Therefore, our fully automatic method provides the reliable results without any training step, which makes it suitable for use with different retinal image datasets and as part of any clinical routine.

Diabetic macular edema is a leading cause of visual loss for patients with diabetes. While diagnosis can only be performed by optical coherence tomography, diabetic macular edema risk assessment is often performed in eye fundus images in screening scenarios through the detection of hard exudates. Such screening scenarios are often associated with large amounts of data, high costs and high burden on specialists, motivating then the development of methodologies for automatic diabetic macular edema risk prediction. Nevertheless, significant dataset domain bias, due to different acquisition equipment, protocols and/or different populations can have significantly detrimental impact on the performance of automatic methods when transitioning to a new dataset, center or scenario. As such, in this study, a method based on residual neural networks is proposed for the classification of diabetic macular edema risk. This method is then validated across multiple public datasets, simulating the deployment in a multi-center setting and thereby studying the method’s generalization capability and existing dataset domain bias. Furthermore, the method is tested on a private dataset which more closely represents a realistic screening scenario. An average area under the curve across all public datasets of 0.891 ± 0.013 was obtained with a ResNet50 architecture trained on a limited amount of images from a single public dataset (IDRiD). It is also shown that screening scenarios are significantly more challenging and that training across multiple datasets leads to an improvement of performance (area under the curve of 0.911 ± 0.009).

The optic disc (OD) and the fovea are relevant landmarks in fundus images. Their localization and segmentation can facilitate the detection of some retinal lesions and the assessment of their importance to the severity and progression of several eye disorders. Distinct methodologies have been developed for detecting these structures, mainly based on color and vascular information. The methodology herein described combines the entropy of the vessel directions with the image intensities for finding the OD center and uses a sliding band filter for segmenting the OD. The fovea center corresponds to the darkest point inside a region defined from the OD position and radius. Both the Messidor and the IDRiD datasets are used for evaluating the performance of the developed methods. In the first one, a success rate of 99.56% and 100.00% are achieved for OD and fovea localization. Regarding the OD segmentation, the mean Jaccard index and Dice’s coefficient obtained are 0.87 and 0.94, respectively. The proposed methods are also amongst the top-3 performing solutions submitted to the IDRiD online challenge.

This paper proposes a conventional approach for pulmonary nodule segmentation, that uses the Sliding Band Filter to estimate the center of the nodule, and consequently the filter’s support points, matching the initial border coordinates. This preliminary segmentation is then refined to try to include mainly the nodular area, and no other regions (e.g. vessels and pleural wall). The algorithm was tested on 2653 nodules from the LIDC database and achieved a Dice score of 0.663, yielding similar results to the ground truth reference, and thus being a promising tool to promote early lung cancer screening and improve nodule characterization.

Diabetic Retinopathy (DR) is one of the leading causes of preventable blindness in the developed world. With the increasing number of diabetic patients there is a growing need of an automated system for DR detection. We propose Eye WeS, a method that not only detects DR in eye fundus images but also pinpoints the regions of the image that contain lesions, while being trained with image labels only. We show that it is possible to convert any pre-trained convolutional neural network into a weakly-supervised model while increasing their performance and efficiency. EyeWeS improved the results of Inception V3 from 94.9% Area Under the Receiver Operating Curve (AUC) to 95.8% AUC while maintaining only approximately 5% of the Inception V3's number of parameters. The same model is able to achieve 97.1% AUC in a cross-dataset experiment.

Purpose: The goal was to compare the micronucleus (MN) and dicentric plus ring chromosomes (D + R) assays for dose assessment in cases of partial body irradiations (PBI). Materials and methods: We constructed calibration curves for each assay at doses ranging from 0 to 5 Gy of X-rays at dose rate of 0.275 Gy/min. To simulate partial-body exposures, blood samples from two donors were irradiated with 0.5, 1, 2 and 4 Gy and the ratios of irradiated to unirradiated blood were 25, 50, and 100%. Different tests were used to confirm if all samples were overdispersed or zero-inflated and for partial-body dose assessment we used the Qdr, Dolphin and Bayesian model. Results: In our samples for D + R calibration curve, practically all doses agreed with Poisson assumption, but MN exhibited overdispersed and zero-inflated cellular distributions. The exact Poisson tests and zero-inflated tests demonstrate that virtually all samples of D + R from PBI simulation fit the Poisson distribution and were not zero-inflated, but the MN samples were also overdispersed and zero-inflated. In the partial-body estimation, when Qdr and Dolphin methods were used the D + R results were better than MN, but the doses estimation defined by the Bayesian methodology were more accurate than the classical methods. Conclusions: Dicentric chromosomes continue to prove to be the best biological marker for dose assessment. However exposure scenarios of partial-body estimation, overdispersion and zero-inflation may not occur, it being a critical point not only for dose assessment, but also to confirm partial-body exposure. MN could be used as alternative assay for partial-body dose estimation, but in case of an accident without any information, the MN assay could not define whether the accident was a whole-body irradiation (WBI) or a PBI.

Central serous chorioretinopathy is a retinal disease in which there is a leak of fluid into the subretinal space resulting in mild to moderate loss of visual acuity. Sequences of images from a fluorescein angiography exam are most of the times used for analyzing these leaks. This work presents a diagnostic aid method to detect and characterize the progression of fluid area along the exam, in order to provide a second opinion and increase the focus and the speed of analysis of the ophthalmologists. The method is based on a comparative approach by image subtraction between the late and early frames. The obtained segmentation results are quite promising with an average Dice coefficient of 0.801±0.106 for the training set and 0.774±0.106 for the test set.

Lung cancer has an increasing preponderance in worldwide mortality, demanding for the development of efficient screening methods. With this in mind, a binary classification method using Lung-RADSTM guidelines to warn changes in the screening management is proposed. First, having into account the lack of public datasets for this task, the lung nodules in the LIDC-IDRI dataset were re-annotated to include a Lung-RADSTM-based referral label. Then, a wide residual network is used for automatically assessing lung nodules in 3D chest computed tomography exams. Unlike the standard malignancy prediction approaches, the proposed method avoids the need to segment and characterize lung nodules, and instead directly defines if a patient should be submitted for further lung cancer tests. The system achieves a nodule-wise accuracy of 0.87±0.02.

Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is challenging due to the scarcity of medical professionals able to screen a growing global diabetic population at risk for DR. Computer-aided disease diagnosis in retinal image analysis could provide a sustainable approach for such large-scale screening effort. The recent scientific advances in computing capacity and machine learning approaches provide an avenue for biomedical scientists to reach this goal. Aiming to advance the state-of-the-art in automatic DR diagnosis, a grand challenge on "Diabetic Retinopathy - Segmentation and Grading" was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI - 2018). In this paper, we report the set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD). There were three principal sub-challenges: lesion segmentation, disease severity grading, and localization of retinal landmarks and segmentation. These multiple tasks in this challenge allow to test the generalizability of algorithms, and this is what makes it different from existing ones. It received a positive response from the scientific community with 148 submissions from 495 registrations effectively entered in this challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top-performing participating solutions. The top-performing approaches utilized a blend of clinical information, data augmentation, and an ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.

Lung cancer is among the deadliest diseases in the world. The detection and characterization of pulmonary nodules are crucial for an accurate diagnosis, which is of vital importance to increase the patients’ survival rates. The segmentation process contributes to the mentioned characterization, but faces several challenges, due to the diversity in nodular shape, size, and texture, as well as the presence of adjacent structures. This paper proposes two methods for pulmonary nodule segmentation in Computed Tomography (CT) scans. First, a conventional approach which applies the Sliding Band Filter (SBF) to estimate the center of the nodule, and consequently the filter’s support points, matching the initial border coordinates. This preliminary segmentation is then refined to include mainly the nodular area, and no other regions (e.g. vessels and pleural wall). The second approach is based on Deep Learning, using the U-Net to achieve the same goal. This work compares both performances, and consequently identifies which one is the most promising tool to promote early lung cancer screening and improve nodule characterization. Both methodologies used 2653 nodules from the LIDC database: the SBF based one achieved a Dice score of 0.663, while the U-Net achieved 0.830, yielding more similar results to the ground truth reference annotated by specialists, and thus being a more reliable approach.

Lung cancer is one of the most common causes of death in the world. The early detection of lung nodules allows an appropriate follow-up, timely treatment and potentially can avoid greater damage in the patient health. The texture is one of the nodule characteristics that is correlated with the malignancy. We developed convolutional neural network architectures to classify automatically the texture of nodules into the non-solid, part-solid and solid classes. The different architectures were tested to determine if the context, the number of slices considered as input and the relation between slices influence on the texture classification performance. The architecture that obtained better performance took into account different scales, different rotations and the context of the nodule, obtaining an accuracy of 0.833 ± 0.041.

This paper proposes a new methodology to automatically segment and measure the volume of pulmonary nodules in lung computed tomography (CT) scans. Estimating the malignancy likelihood of a pulmonary nodule based on lesion characteristics motivated the development of an unsupervised pulmonary nodule segmentation and volume measurement as a preliminary stage for pulmonary nodule characterization. The idea is to optimally cluster a set of feature vectors composed by intensity and shape-related features in a given feature data space extracted from a pre-detected nodule. For that purpose, a metaheuristic search based on evolutionary computation is used for clustering the corresponding feature vectors. The proposed method is simple, unsupervised and is able to segment different types of nodules in terms of location and texture without the need for any manual annotation. We validate the proposed segmentation and volume measurement on the Lung Image Database Consortium and Image Database Resource Initiative – LIDC-IDRI dataset. The first dataset is a group of 705 solid and sub-solid (assessed as part-solid and non-solid) nodules located in different regions of the lungs, and the second, more challenging, is a group of 59 sub-solid nodules. The average Dice scores of 82.35% and 71.05% for the two datasets show the good performance of the segmentation proposal. Comparisons with previous state-of-the-art techniques also show acceptable and comparable segmentation results. The volumes of the segmented nodules are measured via ellipsoid approximation. The correlation and statistical significance between the measured volumes of the segmented nodules and the ground-truth are obtained by Pearson correlation coefficient value, obtaining an R-value ≥ 92.16% with a significance level of 5%.

The design of certain seawalls / breakwaters has often been required to achieve very low targetovertopping discharges when these structures protect vulnerable infrastructure or activities. Thebalance between economically viable protection and performance requirements is often difficult toachieve without good knowledge on low overtopping. The paucity of data in this space and the highuncertainties associated with existing methods, increase the challenge. The occurrence of a lownumber of overtopping waves has the consequence that any test results are substantially moreaffected by the inherent variation of random waves, therefore more uncertain. The physical model testresults presented hereafter were successful in obtaining low to very low overtopping discharge data.For low / very low overtopping, these test data present considerable scatter relative to the latestempirical prediction. A number of repetitions was performed for conditions giving very low overtoppingdischarges, which illustrated the inherent uncertainty associated with low overtopping.

Background Changes in the retinal vessel caliber are associated with a variety of major diseases, namely diabetes, hypertension and atherosclerosis. The clinical assessment of these changes in fundus images is tiresome and prone to errors and thus automatic methods are desirable for objective and precise caliber measurement. However, the variability of blood vessel appearance, image quality and resolution make the development of these tools a non-trivial task. Metholodogy A method for the estimation of vessel caliber in eye fundus images via vessel cross-sectional intensity profile model fitting is herein proposed. First, the vessel centerlines are determined and individual segments are extracted and smoothed by spline approximation. Then, the corresponding cross-sectional intensity profiles are determined, post-processed and ultimately fitted by newly proposed parametric models. These models are based on Difference-of-Gaussians (DoG) curves modified through a multiplying line with varying inclination. With this, the proposed models can describe profile asymmetry, allowing a good adjustment to the most difficult profiles, namely those showing central light reflex. Finally, the parameters of the best-fit model are used to determine the vessel width using ensembles of bagged regression trees with random feature selection. Results and conclusions The performance of our approach is evaluated on the REVIEW public dataset by comparing the vessel cross-sectional profile fitting of the proposed modified DoG models with 7 and 8 parameters against a Hermite model with 6 parameters. Results on different goodness of fitness metrics indicate that our models are constantly better at fitting the vessel profiles. Furthermore, our width measurement algorithm achieves a precision close to the observers, outperforming state-of-the art methods, and retrieving the highest precision when evaluated using cross-validation. This high performance supports the robustness of the algorithm and validates its use in retinal vessel width measurement and possible integration in a system for retinal vasculature assessment.

In medical image analysis applications, the availability of the large amounts of annotated data is becoming increasingly critical. However, annotated medical data is often scarce and costly to obtain. In this paper, we address the problem of synthesizing retinal color images by applying recent techniques based on adversarial learning. In this setting, a generative model is trained to maximize a loss function provided by a second model attempting to classify its output into real or synthetic. In particular, we propose to implement an adversarial autoencoder for the task of retinal vessel network synthesis. We use the generated vessel trees as an intermediate stage for the generation of color retinal images, which is accomplished with a generative adversarial network. Both models require the optimization of almost everywhere differentiable loss functions, which allows us to train them jointly. The resulting model offers an end-to-end retinal image synthesis system capable of generating as many retinal images as the user requires, with their corresponding vessel networks, by sampling from a simple probability distribution that we impose to the associated latent space. We show that the learned latent space contains a well-defined semantic structure, implying that we can perform calculations in the space of retinal images, e.g., smoothly interpolating new data points between two retinal images. Visual and quantitative results demonstrate that the synthesized images are substantially different from those in the training set, while being also anatomically consistent and displaying a reasonable visual quality.

The classification of retinal vessels into arteries and veins in eye fundus images is a relevant task for the automatic assessment of vascular changes. This paper presents a new approach to solve this problem by means of a Fully-Connected Convolutional Neural Network that is specifically adapted for artery/vein classification. For this, a loss function that focuses only on pixels belonging to the retinal vessel tree is built. The relevance of providing the model with different chromatic components of the source images is also analyzed. The performance of the proposed method is evaluated on the RITE dataset of retinal images, achieving promising results, with an accuracy of \(96\%\) on large caliber vessels, and an overall accuracy of \(84\%\).

We propose UOLO, a novel framework for the simultaneous detection and segmentation of structures of interest in medical images. UOLO consists of an object segmentation module which intermediate abstract representations are processed and used as input for object detection. The resulting system is optimized simultaneously for detecting a class of objects and segmenting an optionally different class of structures. UOLO is trained on a set of bounding boxes enclosing the objects to detect, as well as pixel-wise segmentation information, when available. A new loss function is devised, taking into account whether a reference segmentation is accessible for each training image, in order to suitably backpropagate the error. We validate UOLO on the task of simultaneous optic disc (OD) detection, fovea detection, and OD segmentation from retinal images, achieving state-of-the-art performance on public datasets.

Due to inevitable differences between the data used for training modern CAD systems and the data encountered when they are deployed in clinical scenarios, the ability to automatically assess the quality of predictions when no expert annotation is available can be critical. In this paper, we propose a new method for quality assessment of retinal vessel tree segmentations in the absence of a reference ground-truth. For this, we artificially degrade expert-annotated vessel map segmentations and then train a CNN to predict the similarity between the degraded images and their corresponding ground-truths. This similarity can be interpreted as a proxy to the quality of a segmentation. The proposed model can produce a visually meaningful quality score, effectively predicting the quality of a vessel tree segmentation in the absence of a manually segmented reference. We further demonstrate the usefulness of our approach by applying it to automatically find a threshold for soft probabilistic segmentations on a per-image basis. For an independent state-of-the-art unsupervised vessel segmentation technique, the thresholds selected by our approach lead to statistically significant improvements in F1-score \((+2.67\%)\) and Matthews Correlation Coefficient (+\(3.11\%\)) over the thresholds derived from ROC analysis on the training set. The score is also shown to correlate strongly with F1 and MCC when a reference is available.

The creation of retinal mosaics from sets of fundus photographs can significantly reduce the time spent on the diabetic retinopathy (DR) screening, because through mosaic analysis the ophthalmologists can examine several portions of the eye at a single glance and, consequently, detect and grade DR more easily. Like most of the methods described in the literature, this methodology includes two main steps: image registration and image blending. In the registration step, relevant keypoints are detected on all images, the transformation matrices are estimated based on the correspondences between those keypoints and the images are reprojected into the same coordinate system. However, the main contributions of this work are in the blending step. In order to combine the overlapping images, a color compensation is applied to those images and a distance-based map of weights is computed for each one. The methodology is applied to two different datasets and the mosaics obtained for one of them are visually compared with the results of two state-of-the-art methods. The mosaics obtained with our method present good quality and they can be used for DR grading.

This paper introduces a novel strategy for the task of simultaneously locating two key anatomical landmarks in retinal images of the eye fundus, namely the optic disc and the fovea. For that, instead of attempting to classify each pixel as belonging to the background, the optic disc, or the fovea center, which would lead to a highly class-imbalanced setting, the problem is reformulated as a pixelwise regression task. The regressed quantity consists of the distance from the closest landmark of interest. A Fully-Convolutional Deep Neural Network is optimized to predict this distance for each image location, implicitly casting the problem into a per-pixel Multi-Task Learning approach by which a globally consistent distribution of distances across the entire image can be learned. Once trained, the two minimal distances predicted by the model are selected as the locations of the optic disc and the fovea. The joint learning of every pixel position relative to the optic disc and the fovea favors an automatic understanding of the overall anatomical distribution. This results in an effective technique that can detect both locations simultaneously, as opposed to previous methods that handle both tasks separately. Comprehensive experimental results on a large public dataset validate the proposed approach.

The automatic assessment of visual quality on images of the eye fundus is an important task in retinal image analysis. A novel quality assessment technique is proposed in this paper. We propose to compute Mean-Subtracted Contrast-Normalized (MSCN) coefficients on local spatial neighborhoods of a given image and analyze their distribution. It is known that for natural images, such distribution behaves normally, while distortions of different kinds perturb this regularity. The combination of MSCN coefficients with a simple measure of local contrast allows us to design a simple but effective retinal image quality assessment algorithm that successfully discriminates between good and low-quality images, while delivering a meaningful quality score. The proposed technique is validated on a recent database of quality-labeled retinal images, obtaining results aligned with state-of-the-art approaches at a low computational cost.

This paper studies novel ways to evaluate armour damage in physical models of coastal structures. High-resolution damage data for reference rubble mound breakwaters obtained under the HYDRALAB+ joint-research project are analysed and discussed. These tests are used to analyse the way to describe damage, the influence of the sequence of testing, and touches on the possible influence of sea level rise. Results of two test programmes were used. Firstly, 3D physical model tests carried out at the University of Porto, in cooperation with Deltares, were used. Here a wide breakwater trunk was used for statistical reasons. Additionally, 2D test results from LNEC were analysed. Tests for a sea level rise scenario resulted in less damage to the seaside slope. In addition, clear differences between “cumulative damage” and “rebuild” test series were noticed. However, significant scatter was also observed in the result of tests carried out under identical conditions. It was also concluded that the damage to the trunk was lower in the tests with short-crested waves. The design values for the damage depth E2D proposed by Hofland et al. (2011) were partly in line with the experimental results presented. Since the relation between S and the depth of damage E does not hold true for non-standard cases, it seems better to use a parameter based on the local damage depth when testing such a structure. The reliability of a damage number for a test on the stability of a trunk can be improved by either increasing the relative size (width) of the test section or repeating the test.

Image quality assessment has been a topic of intense research over the last decades. Although its application to other disciplines is growing tremendously, its use in retinal imaging is still immature and some fundamental challenges remain unsolved. Thus, we present a research methodology for the objective assessment of the quality in retinal images. The methodology can be used as a preliminary step in any computer-aided system, and is composed of four main steps: the location of the region-of-interest, the extraction of relevant image properties and their analysis by feature selection, and the final binary classification into two classes (good and poor quality). The experimental results demonstrate the adequacy of the proposed methodology in this context, being able to objectively assess the quality of retinal images with an accuracy over 99%.

Retinal vessel caliber changes are associated with several major diseases, such as diabetes and hypertension. These caliber changes can be evaluated using eye fundus images. However, the clinical assessment is tiresome and prone to errors, motivating the development of automatic methods. An automatic method based on vessel crosssection intensity profile model fitting for the estimation of vessel caliber in retinal images is herein proposed. First, vessels are segmented from the image, vessel centerlines are detected and individual segments are extracted and smoothed. Intensity profiles are extracted perpendicularly to the vessel, and the profile lengths are determined. Then, model fitting is applied to the smoothed profiles. A novel parametric model (DoG-L7) is used, consisting on a Difference-of-Gaussians multiplied by a line which is able to describe profile asymmetry. Finally, the parameters of the best-fit model are used for determining the vessel width through regression using ensembles of bagged regression trees with random sampling of the predictors (random forests). The method is evaluated on the REVIEW public dataset. A precision close to the observers is achieved, outperforming other state-of-the-art methods. The method is robust and reliable for width estimation in images with pathologies and artifacts, with performance independent of the range of diameters.

Retinal vessel segmentation is a fundamental and well-studied problem in the retinal image analysis field. The standard images in this context are color photographs acquired with standard fundus cameras. Several vessel segmentation techniques have been proposed in the literature that perform successfully on this class of images. However, for other retinal imaging modalities, blood vessel extraction has not been thoroughly explored. In this paper, we propose a vessel segmentation technique for Scanning Laser Opthalmoscopy (SLO) retinal images. Our method adapts a Deep Neural Network (DNN) architecture initially devised for segmentation of biological images (U-Net), to perform the task of vessel segmentation. The model was trained on a recent public dataset of SLO images. Results show that our approach efficiently segments the vessel network, achieving a performance that outperforms the current state-of-the-art on this particular class of images.

An unsupervised method for convolutional neural network (CNN) architecture design is proposed. The method relies on a variable neighborhood search-based approach for finding CNN architectures and hyperparameter values that improve classification performance. For this purpose, t-Distributed Stochastic Neighbor Embedding (t-SNE) is applied to effectively represent the solution space in 2D. Then, k-Means clustering divides this representation space having in account the relative distance between neighbors. The algorithm is tested in the CIFAR-10 image dataset. The obtained solution improves the CNN validation loss by over \(15\%\) and the respective accuracy by \(5\%\). Moreover, the network shows higher predictive power and robustness, validating our method for the optimization of CNN design.

Synthesizing images of the eye fundus is a challenging task that has been previously approached by formulating complex models of the anatomy of the eye. New images can then be generated by sampling a suitable parameter space. Here we propose a method that learns to synthesize eye fundus images directly from data. For that, we pair true eye fundus images with their respective vessel trees, by means of a vessel segmentation technique. These pairs are then used to learn a mapping from a binary vessel tree to a new retinal image. For this purpose, we use a recent image-to-image translation technique, based on the idea of adversarial learning. Experimental results show that the original and the generated images are visually different in terms of their global appearance, in spite of sharing the same vessel tree. Additionally, a quantitative quality analysis of the synthetic retinal images confirms that the produced images retain a high proportion of the true image set quality.

The classification of retinal vessels into artery/vein (A/V) is an important phase for automating the detection of vascular changes, and for the calculation of characteristic signs associated with several systemic diseases such as diabetes, hypertension, and other cardiovascular conditions. This paper presents an automatic approach for A/V classification based on the analysis of a graph extracted from the retinal vasculature. The proposed method classifies the entire vascular tree deciding on the type of each intersection point (graph nodes) and assigning one of two labels to each vessel segment (graph links). Final classification of a vessel segment as A/V is performed through the combination of the graph-based labeling results with a set of intensity features. The results of this proposed method are compared with manual labeling for three public databases. Accuracy values of 88.3%, 87.4%, and 89.8% are obtained for the images of the INSPIRE-AVR, DRIVE, and VICAVR databases, respectively. These results demonstrate that our method outperforms recent approaches for A/V classification.

Computational methods used in microscopy cell image analysis have largely augmented the impact of imaging techniques, becoming fundamental for biological research. The understanding of cell regulation processes is very important in biology, and in particular confocal fluorescence imaging plays a relevant role for the in vivo observation of cells. However, most biology researchers still analyze cells by visual inspection alone, which is time consuming and prone to induce subjective bias. This makes automatic cell image analysis essential for large scale, objective studies of cells. While the classic approach for automatic cell analysis is to use image segmentation, for in vivo confocal fluorescence microscopy images of plants, such approach is neither trivial nor is it robust to image quality variations. To analyze plant cells in in vivo confocal fluorescence microscopy images with robustness and increased performance, we propose the use of local convergence filters (LCF). These filters are based in gradient convergence and as such can handle illumination variations, noise and low contrast. We apply a range of existing convergence filters for cell nuclei analysis of the Arabidopsis thaliana plant root tip. To further increase contrast invariance, we present an augmentation to local convergence approaches based on image phase information. Through the use of convergence index filters we improved the results for cell nuclei detection and shape estimation when compared with baseline approaches. Using phase congruency information we were able to further increase performance by 11% for nuclei detection accuracy and 4% for shape adaptation. Shape regularization was also applied, but with no significant gain, which indicates shape estimation was good for the applied filters.

Crataeva tapia bark lectin was evaluated for its antitumor activity against sarcoma 180 in Swiss albino mice. The anti-inflammatory and analgesic properties were investigated in models of inflammation and nociception. The anti-inflammatory assay was induced by carrageenan induced peritonitis and the analgesic activity was induced by acetic acid-induced writhing response. The lectin presents low toxicity with a LD50 of 2,500 mg/kg body weight and significant antitumor activity causing inhibition of tumor growth. The lectin also promoted significant reduction (35.4%) in the number of neutrophil migration induced by carrageenan. Concerning its analgesic property, the lectin inhibits abdominal contractions induced by acetic acid. The current results revealed a lectin with significant antitumoral, anti-inflammatory and antinociceptive activities. Further investigations to unveil the exact mechanisms are needed.

Microscopy cell image analysis is a fundamental tool for biological research. In particular, multivariate fluorescence microscopy is used to observe different aspects of cells in cultures. It is still common practice to perform analysis tasks by visual inspection of individual cells which is time consuming, exhausting and prone to induce subjective bias. This makes automatic cell image analysis essential for large scale, objective studies of cell cultures. Traditionally the task of automatic cell analysis is approached through the use of image segmentation methods for extraction of cells' locations and shapes. Image segmentation, although fundamental, is neither an easy task in computer vision nor is it robust to image quality changes. This makes image segmentation for cell detection semi-automated requiring frequent tuning of parameters. We introduce a new approach for cell detection and shape estimation in multivariate images based on the sliding band filter (SBF). This filter's design makes it adequate to detect overall convex shapes and as such it performs well for cell detection. Furthermore, the parameters involved are intuitive as they are directly related to the expected cell size. Using the SBF filter we detect cells' nucleus and cytoplasm location and shapes. Based on the assumption that each cell has the same approximate shape center in both nuclei and cytoplasm fluorescence channels, we guide cytoplasm shape estimation by the nuclear detections improving performance and reducing errors. Then we validate cell detection by gathering evidence from nuclei and cytoplasm channels. Additionally, we include overlap correction and shape regularization steps which further improve the estimated cell shapes. The approach is evaluated using two datasets with different types of data: a 20 images benchmark set of simulated cell culture images, containing 1000 simulated cells; a 16 images Drosophila melanogaster Kc167 dataset containing 1255 cells, stained for DNA and actin. Both image datasets present a difficult problem due to the high variability of cell shapes and frequent cluster overlap between cells. On the Drosophila dataset our approach achieved a precision/recall of 95%/69% and 82%/90% for nuclei and cytoplasm detection respectively and an overall accuracy of 76%.

To obtain development information of individual plant cells, it is necessary to perform in vivo imaging of the specimen under study, through time-lapse confocal microscopy. Automation of cell detection/marking process is important to provide research tools in order to ease the search for special events, such as cell division. In this paper we discuss an automatic cell detection approach for Arabidopsis thaliana based on segmentation, which selects the best cell candidates from a starting watershed-based image segmentation and improves the result by merging adjacent regions. The selection of individual cells is obtained using a support vector machine (SVM) classifier, based on a cell descriptor constructed from the shape and edge strength of the cells' contour. In addition we proposed a novel cell merging criterion based on edge strength along the line that connects adjacent cells' centroids, which is a valuable tool in the reduction of cell over-segmentation. The result is largely pruned of badly segmented and over-segmented cells, thus facilitating the study of cells. When comparing the results after merging with the basic watershed segmentation, we obtain 1.5% better coverage (increase in F-measure) and up to 27% better precision in correct cell segmentation.

Lung cancer is mainly diagnosed by the identification of malignant nodules in the lung parenchyma. For that purpose, the identification of all the possible structures that could be suspicious of lung nodules became a crucial task in any lung cancer computer aided diagnosis (CAD) system. In this paper, a new approach for lung nodule candidate identification is proposed. This method uses a 3D medialness Hessian-based filtering to identify round shape structures that could be identified as nodules. This technique, that demonstrated its accuracy in lung vesselness extraction, provides clearer candidates than other approaches, providing less response in the presence of noise artifacts and returns a better continuity in vessels, mostly responsible for false positives. That way, they will be better distinguishable from the nodules in posterior analysis. This approach was validated in 120 scans from the LIDC/IDRI image database. They include 212 nodules with diameters in the range 3 mm to 30 mm. The results demonstrate that our approach is capable of identifying most of the nodules and include less false positives than other approaches, facilitating a posterior task for false positive removal.

This paper presents an automatic application that provides several retinal image analysis functionalities, namely vessel segmentation, vessel width estimation, artery/vein classification and optic disc segmentation. A pipeline of these methods allows the computation of important vessel related indexes, namely the Central Retinal Arteriolar Equivalent (CRAE), Central Retinal Venular Equivalent (CRVE) and Arteriolar-to-Venular Ratio (AVR), as well as various geometrical features associated with vessel bifurcations. The results for AVR estimation were assessed using the images of INSPIRE-AVR dataset; for this dataset, the mean error of the measured AVR values with respect to the reference was identical to the one achieved by a medical expert. The estimation of the CRAE, CRVE and AVR values on 480 images from 120 subjects have shown a significant correlation between right and left eyes and also between images of same eye acquired with different camera fields of view.

Background: The optic disc (OD) centre and boundary are important landmarks in retinal images and are essential for automating the calculation of health biomarkers related with some prevalent systemic disorders, such as diabetes, hypertension, cerebrovascular and cardiovascular diseases.Methods: This paper presents an automatic approach for OD segmentation using a multiresolution sliding band filter (SBF). After the preprocessing phase, a low-resolution SBF is applied on a downsampled retinal image and the locations of maximal filter response are used for focusing the analysis on a reduced region of interest (ROI). A high-resolution SBF is applied to obtain a set of pixels associated with the maximum response of the SBF, giving a coarse estimation of the OD boundary, which is regularized using a smoothing algorithm.Results: Our results are compared with manually extracted boundaries from public databases (ONHSD, MESSIDOR and INSPIRE-AVR datasets) outperforming recent approaches for OD segmentation. For the ONHSD, 44% of the results are classified as Excellent, while the remaining images are distributed between the Good (47%) and Fair (9%) categories. An average overlapping area of 83%, 89% and 85% is achieved for the images in ONHSD, MESSIDOR and INSPIR-AVR datasets, respectively, when comparing with the manually delineated OD regions.Discussion: The evaluation results on the images of three datasets demonstrate the better performance of the proposed method compared to recently published OD segmentation approaches and prove the independence of this method when from changes in image characteristics such as size, quality and camera field of view.

This paper introduces RetinaCAD, a system, for the fast, reliable and automatic measurement of the Central Retinal Arteriolar Equivalent (CRAE), the Central Retinal Venular Equivalent (CRVE), and the Arteriolar-to-Venular Ratio (AVR) values, as well as several geometrical features of the retinal vasculature. RetinaCAD identifies important landmarks in the retina, such as the blood vessels and optic disc, and performs artery/vein classification and vessel width measurement. The estimation of the CRAE, CRVE and AVR values on 480 images from 120 subjects has shown a significant correlation between right and left eyes and also between images of same eye acquired with different camera fields of view. AVR estimation in retinal images of 54 subjects showed the lowest values in people with diabetes or high blood pressure thus demonstrating the potential of the system as a CAD tool for early detection and follow-up of diabetes, hypertension or cardiovascular pathologies.

The Arteriolar-to-Venular Ratio (AVR) is a well known index for the early diagnosis of diseases such as diabetes, hypertension or cardio-vascular pathologies. This paper presents an automatic approach for the estimation of the AVR in retinal images. The proposed method includes vessel segmentation, vessel caliber estimation, optic disc detection, region of interest determination, artery/vein classification and finally AVR calculation. This method was evaluated using the images of the INSPIRE-AVR dataset. The mean error of the measured AVR values with respect to the reference ones was 0.05, which is identical to the one achieved by a medical expert using a semi-automated system, thus demonstrating the reliability of the herein proposed solution for AVR estimation.

In a lung nodule detection task, parenchyma segmentation is crucial to obtain the region of interest containing all the nodules. Thus, the challenge is to devise a methodology that includes all the lung nodules, particularly those close to the walls, as the juxtapleural nodules. In this paper, different region growing approaches are proposed for the automatic segmentation of the lung parenchyma. The methodology is organized in five different steps: first, the image intensity is corrected to improve the contrast of the lungs. With that, the fat area is obtained, automatically deriving the interior of the lung region. Then, the traquea is extracted by a 3D region growing, being subtracted from the lung region results. The next step is the division of the two lungs to guarantee that both are separated. And finally, the lung contours are refined to provide appropriate final results.

This paper describes a new methodology for lane detection in Thin-Layer Chromatography images. An approach based on the continuous wavelet transform is used to enhance the relevant lane information contained in the intensity profile obtained from image data projection. Lane detection proceeds in three phases: the first obtains a set of candidate lanes, which are validated or removed in the second phase; in the third phase, lane limits are calculated, and subtle lanes are recovered. The superior performance of the new solution was confirmed by a comparison with three other methodologies previously described in the literature.

Submitted by Helena Donato (bibliotecaria@hospitaldebraga.com.pt) on 2014-02-14T15:39:09Z No. of bitstreams: 1 Automatic localization of the optic disc.pdf: 1617392 bytes, checksum: 94a8ac84cec344f1ac6b2bbdc8169c95 (MD5) Approved for entry into archive by Helena Donato (bibliotecaria@hospitaldebraga.com.pt) on 2014-02-14T15:39:16Z (GMT) No. of bitstreams: 1 Automatic localization of the optic disc.pdf: 1617392 bytes, checksum: 94a8ac84cec344f1ac6b2bbdc8169c95 (MD5) Made available in DSpace on 2014-02-14T15:39:16Z (GMT). No. of bitstreams: 1 Automatic localization of the optic disc.pdf: 1617392 bytes, checksum: 94a8ac84cec344f1ac6b2bbdc8169c95 (MD5) Previous issue date: 2013 Restored into DSpace on 2014-05-09T12:13:17Z (GMT).

The Arteriolar-to-Venular Ratio (AVR) is a well known index for the diagnosis of diseases such as diabetes, hypertension or cardiovascular pathologies. This paper presents a fully automatic AVR estimation method which uses a graph-based artery/vein classification approach to classify the retinal vessels by a combination of structural information taken from the vasculature graph with intensity features from the original color image. This method was evaluated on the images of the INSPIRE-AVR dataset. The mean error and the correlation coefficient of obtained results with respect to the reference AVR values were identical to the ones obtained by the second observer using a semi-automated system, which demonstrate the potential of the herein proposed solution for clinical application.

This paper describes a methodology to remove the background of the lanes in Thin Layer Chromatography (TLC) images, aiming at improving band detection and classification. The storage of the biological samples to be analyzed by TLC is usually done via plastic containers. Filter paper is an alternative that allows reduced costs and higher portability, but it increases the complexity of the image analysis stage due to lane background alteration. In order to overcome this problem, a negative control lane is included in every chromatographic plate. After image preprocessing and lane detection stages, a background profile is generated by processing the negative control lane using the Discrete Wavelet Transform (DWT). This profile is then subtracted to the profiles of all other sample lanes in order to overcome the data degradation introduced by filter paper usage. For assessing the proposed background removal process, 105 TLC lanes, with and without background, were used as input for three one-class classifiers. In all cases, the best results were achieved for the lanes after background removal.

This paper presents an automatic approach for artery/vein (A/V) classification based on the analysis of a graph representing the structure of the retinal vasculature. The entire vascular tree is classified by deciding on the type of each intersection point (graph node) and assigning one of two classes to each vessel segment (graph link). The final label for each vessel segment is accomplished by a combination of structural information taken from the graph (link class) with intensity features measured in the original color image. An accuracy of 88.0% was achieved for the 40 images of the INSPIRE-AVR dataset, thus demonstrating that our method outperforms state-of-the-art approaches for A/V classification.

Submarine outfalls need to be evaluated as part of an integrated environmental protection system for coastal areas. Although outfalls are tight with the diversity of economic activities along a densely populated coastline being effluent treatment and effluent reuse a sign of economic prosperity, precautions must be taken in the construction of these structures. They must be designed so as to have the least possible impact on the environment and at the same time be economically viable. This paper outlines the initial phases of a risk assessment procedure for submarine outfall projects. This approach includes a cost-benefit analysis in which risks are systematically minimized or eliminated. The methods used in this study also allow for randomness and uncertainty. The input for the analysis is a wide range of information and data concerning the failure probability of outfalls and the consequences of an operational stoppage or failure. As part of this risk assessment, target design levels of reliability, functionality, and operationality were defined for the outfalls. These levels were based on an inventory of risks associated with such construction projects, and thus afforded the possibility of identifying possible failure modes. This assessment procedure was then applied to four case studies in Portugal. The results obtained were the values concerning the useful life of the outfalls at the four sites and their joint probability of failure against the principal failure modes assigned to ultimate and serviceability limit states. Also defined were the minimum operationality of these outfalls, the average number of admissible technical breakdowns, and the maximum allowed duration of a stoppage mode. It was found that these values were in consonance with the nature of the effluent (tourist-related, industrial, or mixed) as well as its importance for the local economy. Even more important, this risk assessment procedure was able to measure the impact of the outfalls on human health and the environment.