Generation of synthetic intermediate slices in 3D OCT cubes for improving pathology detection and monitoring.

OCT is a non-invasive imaging technique commonly used to obtain 3D volumes of the ocular structure. These volumes allow the monitoring of ocular and systemic diseases through the observation of subtle changes in the different structures present in the eye. In order to observe these changes it is essential that the OCT volumes have a high resolution in all axes, but unfortunately there is an inverse relationship between the quality of the OCT images and the number of slices of the cube. This results in routine clinical examinations using cubes that generally contain high-resolution images with few slices. This lack of slices complicates the monitoring of changes in the retina hindering the diagnostic process and reducing the effectiveness of 3D visualizations. Therefore, increasing the cross-sectional resolution of OCT cubes would improve the visualization of these changes aiding the clinician in the diagnostic process. In this work we present a novel fully automatic methodology to perform the synthesis of intermediate slices of OCT image volumes in an unsupervised manner. To perform this synthesis, we propose a fully convolutional neural network architecture that uses information from two adjacent slices to generate the intermediate synthetic slice. We also propose a training methodology, where we use three adjacent slices to train the network by contrastive learning and image reconstruction. We test our methodology with three different types of OCT volumes commonly used in the clinical setting and validate the quality of the synthetic slices created with several medical experts and using an expert system.

A new generative approach for optical coherence tomography data scarcity: unpaired mutual conversion between scanning presets.

In optical coherence tomography (OCT), there is a trade-off between the scanning time and image quality, leading to a scarcity of high quality data. OCT platforms provide different scanning presets, producing visually distinct images, limiting their compatibility. In this work, a fully automatic methodology for the unpaired visual conversion of the two most prevalent scanning presets is proposed. Using contrastive unpaired translation generative adversarial architectures, low quality images acquired with the faster Macular Cube preset can be converted to the visual style of high visibility Seven Lines scans and vice-versa. This modifies the visual appearance of the OCT images generated by each preset while preserving natural tissue structure. The quality of original and synthetic generated images was compared using BRISQUE. The synthetic generated images achieved very similar scores to original images of their target preset. The generative models were validated in automatic and expert separability tests. These models demonstrated they were able to replicate the genuine look of the original images. This methodology has the potential to create multi-preset datasets with which to train robust computer-aided diagnosis systems by exposing them to the visual features of different presets they may encounter in real clinical scenarios without having to obtain additional data. Graphical Abstract Unpaired mutual conversion between scanning presets. Two generative adversarial models are trained for the conversion of OCT images into images of another scanning preset, replicating the visual features that characterise said preset.

Fully automatic detection and classification of phytoplankton specimens in digital microscopy images.

BACKGROUND AND OBJECTIVE: The proliferation of toxin-producing phytoplankton species can compromise the quality of the water sources. This contamination is difficult to detect, and consequently to be neutralised, since normal water purification techniques are ineffective. Currently, the water analyses about phytoplankton are commonly performed by the specialists with manual routine analyses, which represents a major limitation. The adequate identification and classification of phytoplankton specimens requires intensive training and expertise. Additionally, the performed analysis involves a lengthy process that exhibits serious problems of reliability and repeatability as inter-expert agreement is not always reached. Considering all those factors, the automatization of these analyses is, therefore, highly desirable to reduce the workload of the specialists and facilitate the process. METHODS: This manuscript proposes a novel fully automatic methodology to perform phytoplankton analyses in digital microscopy images of water samples taken with a regular light microscope. In particular, we propose a method capable of analysing multi-specimen images acquired using a simplified systematic protocol. In contrast with prior approaches, this enables its use without the necessity of an expert taxonomist operating the microscope. The system is able to detect and segment the different existing phytoplankton specimens, with high variability in terms of visual appearances, and to merge them into colonies and sparse specimens when necessary. Moreover, the system is capable of differentiating them from other similar objects like zooplankton, detritus or mineral particles, among others, and then classify the specimens into defined target species of interest using a machine learning-based approach. RESULTS: The proposed system provided satisfactory and accurate results in every step. The detection step provided a FNR of 0.4%. Phytoplankton detection, that is, differentiating true phytoplankton from similar objects (zooplankton, minerals, etc.), provided a result of 84.07% of precision at 90% of recall. The target species classification, reported an overall accuracy of 87.50%. The recall levels for each species are, 81.82% for W. naegeliana, 57.15% for A. spiroides, 85.71% for D. sociale and 95% for the "Other" group, a set of relevant toxic and interesting species widely spread over the samples. CONCLUSIONS: The proposed methodology provided accurate results in all the designed steps given the complexity of the problem, particularly in terms of specimen identification, phytoplankton differentiation as well as the classification of the defined target species. Therefore, this fully automatic system represents a robust and consistent tool to aid the specialists in the analysis of the quality of the water sources and potability.

Automatic Detection of Freshwater Phytoplankton Specimens in Conventional Microscopy Images.

Water safety and quality can be compromised by the proliferation of toxin-producing phytoplankton species, requiring continuous monitoring of water sources. This analysis involves the identification and counting of these species which requires broad experience and knowledge. The automatization of these tasks is highly desirable as it would release the experts from tedious work, eliminate subjective factors, and improve repeatability. Thus, in this preliminary work, we propose to advance towards an automatic methodology for phytoplankton analysis in digital images of water samples acquired using regular microscopes. In particular, we propose a novel and fully automatic method to detect and segment the existent phytoplankton specimens in these images using classical computer vision algorithms. The proposed method is able to correctly detect sparse colonies as single phytoplankton candidates, thanks to a novel fusion algorithm, and is able to differentiate phytoplankton specimens from other image objects in the microscope samples (like minerals, bubbles or detritus) using a machine learning based approach that exploits texture and colour features. Our preliminary experiments demonstrate that the proposed method provides satisfactory and accurate results.

Deep multi-instance heatmap regression for the detection of retinal vessel crossings and bifurcations in eye fundus images.

BACKGROUND AND OBJECTIVES: The analysis of the retinal vasculature plays an important role in the diagnosis of many ocular and systemic diseases. In this context, the accurate detection of the vessel crossings and bifurcations is an important requirement for the automated extraction of relevant biomarkers. In that regard, we propose a novel approach that addresses the simultaneous detection of vessel crossings and bifurcations in eye fundus images. METHOD: We propose to formulate the detection of vessel crossings and bifurcations in eye fundus images as a multi-instance heatmap regression. In particular, a deep neural network is trained in the prediction of multi-instance heatmaps that model the likelihood of a pixel being a landmark location. This novel approach allows to make predictions using full images and integrates into a single step the detection and distinction of the vascular landmarks. RESULTS: The proposed method is validated on two public datasets of reference that include detailed annotations for vessel crossings and bifurcations in eye fundus images. The conducted experiments evidence that the proposed method offers a satisfactory performance. In particular, the proposed method achieves 74.23% and 70.90% F-score for the detection of crossings and bifurcations, respectively, in color fundus images. Furthermore, the proposed method outperforms previous works by a significant margin. CONCLUSIONS: The proposed multi-instance heatmap regression allows to successfully exploit the potential of modern deep learning algorithms for the simultaneous detection of retinal vessel crossings and bifurcations. Consequently, this results in a significant improvement over previous methods, which will further facilitate the automated analysis of the retinal vasculature in many pathological conditions.

Automatic segmentation of the foveal avascular zone in ophthalmological OCT-A images.

Angiography by Optical Coherence Tomography (OCT-A) is a non-invasive retinal imaging modality of recent appearance that allows the visualization of the vascular structure at predefined depths based on the detection of the blood movement through the retinal vasculature. In this way, OCT-A images constitute a suitable scenario to analyze the retinal vascular properties of regions of interest as is the case of the macular area, measuring the characteristics of the foveal vascular and avascular zones. Extracted parameters of this region can be used as prognostic factors that determine if the patient suffers from certain pathologies (such as diabetic retinopathy or retinal vein occlusion, among others), indicating the associated pathological degree. The manual extraction of these biomedical parameters is a long, tedious and subjective process, introducing a significant intra and inter-expert variability, which penalizes the utility of the measurements. In addition, the absence of tools that automatically facilitate these calculations encourages the creation of computer-aided diagnosis frameworks that ease the doctor's work, increasing their productivity and making viable the use of this type of vascular biomarkers. In this work we propose a fully automatic system that identifies and precisely segments the region of the foveal avascular zone (FAZ) using a novel ophthalmological image modality as is OCT-A. The system combines different image processing techniques to firstly identify the region where the FAZ is contained and, secondly, proceed with the extraction of its precise contour. The system was validated using a representative set of 213 healthy and diabetic OCT-A images, providing accurate results with the best correlation with the manual measurements of two experts clinician of 0.93 as well as a Jaccard's index of 0.82 of the best experimental case in the experiments with healthy OCT-A images. The method also provided satisfactory results in diabetic OCT-A images, with a best correlation coefficient with the manual labeling of an expert clinician of 0.93 and a Jaccard's index of 0.83. This tool provides an accurate FAZ measurement with the desired objectivity and reproducibility, being very useful for the analysis of relevant vascular diseases through the study of the retinal micro-circulation.

Intraretinal fluid identification via enhanced maps using optical coherence tomography images.

Nowadays, among the main causes of blindness in developed countries are age-related macular degeneration (AMD) and the diabetic macular edema (DME). Both diseases present, as a common symptom, the appearance of cystoid fluid regions inside the retinal layers. Optical coherence tomography (OCT) image modality was one of the main medical imaging techniques for the early diagnosis and monitoring of AMD and DME via this intraretinal fluid detection and characterization. We present a novel methodology to identify these fluid accumulations by means of generating binary maps (offering a direct representation of these areas) and heat maps (containing the region confidence). To achieve this, a set of 312 intensity and texture-based features were studied. The most relevant features were selected using the sequential forward selection (SFS) strategy and tested with three archetypal classifiers: LDC, SVM and Parzen window. Finally, the most proficient classifier is used to create the proposed maps. All of the tested classifiers returned satisfactory results, the best classifier achieving a mean test accuracy higher than 94% in all of the experiments. The suitability of the maps was evaluated in a context of a screening issue with three different datasets obtained with two different devices, testing the capabilities of the system to work independently of the used OCT device. The experiments with the map creation were performed using 323 OCT images. Using only the binary maps, more than 91.33% of the images were correctly classified. With only the heat maps, the proposed methodology correctly separated 93.50% of the images.

Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis.

Cardiovascular diseases (CVDs) are the leading cause of death throughout the world. The total risk of developing CVD is determined by the combined effect of different cardiovascular risk factors (e.g., diabetes, raised blood pressure, unhealthy diet, tobacco use, stress, etc.) that commonly coexist and act multiplicatively. Most CVDs can be prevented by an early identification of the highest risk factors and an appropriate treatment. The stratification of cardiovascular risk factors involves a wide range of parameters and tests that specialists use in their clinical practice. In addition to cardiovascular (CV) risk stratification, ambulatory blood pressure monitoring (ABPM) also provides relevant information for diagnostic and treatment purposes. This work presents a list of protocols based on the Hydra platform, a web-based system for clinical decision support which incorporates a set of functionalities and services that are required for complete cardiovascular analysis, risk assessment, early diagnosis, treatment and monitoring of patients over time. The program includes tools for inputting and managing comprehensive patient data, organized into different checkups to track the evolution over time. It also has a risk stratification tool to compute a CV risk factor based upon several risk stratification tables of reference. Additionally, the program includes a tool that incorporates ABPM analysis and allows the extraction of valuable information by monitoring blood pressure over a specific period of time. Finally, the reporting service summarizes the most relevant information in a set of reports that aid clinicians in their clinical decision-making process.

Evaluation of an automatic dry eye test using MCDM methods and rank correlation.

Dry eye is an increasingly common disease in modern society which affects a wide range of population and has a negative impact on their daily activities, such as working with computers or driving. It can be diagnosed through an automatic clinical test for tear film lipid layer classification based on color and texture analysis. Up to now, researchers have mainly focused on the improvement of the image analysis step. However, there is still large room for improvement on the machine learning side. This paper presents a methodology to optimize this problem by means of class binarization, feature selection, and classification. The methodology can be used as a baseline in other classification problems to provide several solutions and evaluate their performance using a set of representative metrics and decision-making methods. When several decision-making methods are used, they may offer disagreeing rankings that will be solved by conflict handling in which rankings are merged into a single one. The experimental results prove the effectiveness of the proposed methodology in this domain. Also, its general purpose allows to adapt it to other classification problems in different fields such as medicine and biology.

iDEAS: A web-based system for dry eye assessment.

BACKGROUND AND OBJECTIVES: Dry eye disease is a public health problem, whose multifactorial etiology challenges clinicians and researchers making necessary the collaboration between different experts and centers. The evaluation of the interference patterns observed in the tear film lipid layer is a common clinical test used for dry eye diagnosis. However, it is a time-consuming task with a high degree of intra- as well as inter-observer variability, which makes the use of a computer-based analysis system highly desirable. This work introduces iDEAS (Dry Eye Assessment System), a web-based application to support dry eye diagnosis. METHODS: iDEAS provides a framework for eye care experts to collaboratively work using image-based services in a distributed environment. It is composed of three main components: the web client for user interaction, the web application server for request processing, and the service module for image analysis. Specifically, this manuscript presents two automatic services: tear film classification, which classifies an image into one interference pattern; and tear film map, which illustrates the distribution of the patterns over the entire tear film. RESULTS: iDEAS has been evaluated by specialists from different institutions to test its performance. Both services have been evaluated in terms of a set of performance metrics using the annotations of different experts. Note that the processing time of both services has been also measured for efficiency purposes. CONCLUSIONS: iDEAS is a web-based application which provides a fast, reliable environment for dry eye assessment. The system allows practitioners to share images, clinical information and automatic assessments between remote computers. Additionally, it save time for experts, diminish the inter-expert variability and can be used in both clinical and research settings.

CASDES: A Computer-Aided System to Support Dry Eye Diagnosis Based on Tear Film Maps.

Dry eye syndrome is recognized as a growing health problem, and one of the most frequent reasons for seeking eye care. Its etiology and management challenge clinicians and researchers alike, and several clinical tests can be used to diagnose it. One of the most frequently used tests is the evaluation of the interference patterns of the tear film lipid layer. Based on this clinical test, this paper presents CASDES, a computer-aided system to support the diagnosis of dry eye syndrome. Furthermore, CASDES is also useful to support the diagnosis of other eye diseases, such as meibomian gland dysfunction, since it provides a tear film map with highly useful information for eye practitioners. Experiments demonstrate the robustness of this novel tool, which outperforms the previous attempts to create tear film maps and provides reliable results in comparison with the clinicians' annotations. Note that the processing time is noticeably reduced with the proposed method, which will help to promote its clinical use in the diagnosis and treatment of dry eye.

Automatic Vessel Shade-Robust Segmentation of Retinal Layers in OCT Images.

Optical Coherence Tomography (OCT) is a promising imaging technique used by ophthalmologists to diagnose diseases. Since retinal morphology can be identified on these images, several image processing-based methods are emerging with the purpose of extracting their information. The first step to tackle any automatic method to extract pathological features from these images is delimiting retinal layers automatically. This is the aim of this paper, which presents an active contour-based method to segment layer boundaries in the retina. Results obtained by this method present high accuracy and robustness, even when some of these layers are low defined or vessel shades are present.

A methodology for improving tear film lipid layer classification.

Dry eye is a symptomatic disease which affects a wide range of population and has a negative impact on their daily activities. Its diagnosis can be achieved by analyzing the interference patterns of the tear film lipid layer and by classifying them into one of the Guillon categories. The manual process done by experts is not only affected by subjective factors but is also very time consuming. In this paper we propose a general methodology to the automatic classification of tear film lipid layer, using color and texture information to characterize the image and feature selection methods to reduce the processing time. The adequacy of the proposed methodology was demonstrated since it achieves classification rates over 97% while maintaining robustness and provides unbiased results. Also, it can be applied in real time, and so allows important time savings for the experts.

Retinal arteriole-to-venule ratio changes and target organ disease evolution in newly diagnosed hypertensive patients at 1-year follow-up.

There is no agreement on the systematic exploration of the fundus oculi (FO) in hypertensive patients, and it is unknown whether the evolution of retinal microcirculatory alterations has prognostic value or not. The aim of this study was to investigate whether the evolution of the arteriole-to-venule ratio (AVR) in newly-diagnosed hypertensive patients is associated with better or worse evolution of target organ damage (TOD) during 1 year. A cohort of 133 patients with newly-diagnosed untreated hypertension was followed for 1 year. At baseline and follow-up, all patients underwent a physical examination, self-blood pressure measurement, ambulatory blood pressure monitoring, blood and urine analysis, electrocardiogram, and retinography. The endpoint was the favourable evolution of TOD and the total amount of TOD, according to the baseline AVR and the baseline and final difference of the AVR. A total of 133 patients were analyzed (mean age, 57 ± 10.7 years; 59% men). No differences were found in the decrease in blood pressure or antihypertensive treatment between quartiles of baseline AVR or baseline-final AVR difference. Patients with a difference between baseline and final AVR in the highest quartile (>0.0817) had a favorable evolution of left ventricular hypertrophy (odds ratio, 14.9; 95% confidence interval, 1.08-206.8) and the amount of TOD (odds ratio, 2.22; 95% confidence interval, 1.03-6.05). No favorable evolution was found of glomerular filtration rate. There is an association between the evolution of the AVR and the favorable evolution of TOD. Patients with greater increase of AVR have significantly better evolution of left ventricular hypertrophy and amount of TOD.

Automatic detection and characterisation of retinal vessel tree bifurcations and crossovers in eye fundus images.

Analysis of retinal vessel tree characteristics is an important task in medical diagnosis, specially in cases of diseases like vessel occlusion, hypertension or diabetes. The detection and classification of feature points in the arteriovenous eye tree will increase the information about the structure allowing its use for medical diagnosis. In this work a method for detection and classification of retinal vessel tree feature points is presented. The method applies and combines imaging techniques such as filters or morphologic operations to obtain an adequate structure for the detection. Classification is performed by analysing the feature points environment. Detection and classification of feature points is validated using the VARIA database. Experimental results are compared to previous approaches showing a much higher specificity in the characterisation of feature points while slightly increasing the sensitivity. These results provide a more reliable methodology for retinal structure analysis.