Search

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.

Currently, lung cancer is the most lethal in the world. In order to make screening and follow-up a little more systematic, guidelines have been proposed. Therefore, this study aimed to create a diagnostic support approach by providing a patient label based on the LUNG-RADS™ guidelines. The only input required by the system is the nodule centroid to take the region of interest for the input of the classification system. With this in mind, two deep learning networks were evaluated: a Wide Residual Network and a DenseNet. Taking into account the annotation uncertainty we proposed to use sample weights that are introduced in the loss function, allowing nodules with a high agreement in the annotation process to take a greater impact on the training error than its counterpart. The best result was achieved with the Wide Residual Network with sample weights achieving a nodule-wise LUNG-RADS™ labelling accuracy of $0.735\pm 0.003$ .

Ovarian cancer is one of the most commonly occurring cancer in women. Transvaginal ultrasound is used as a screening test to detect the presence of tumors but, for specific types of ovarian tumors, malignancy can only be asserted through surgery. An automatic method to perform the detection and malignancy assessment of these tumours is thus necessary to prevent unnecessary oophorectomies.This work explores the U-Net’s architecture and investigates the selection of different hyperparameters for the ovary and the ovarian follicles segmentation. The effect of applying different post-processing methods on beam-formed radio-frequency (BRF) data is also investigated.Results show that models trained only with BRF data have the worst performance. On the other hand, the combination of B-mode with BRF data performs better for ovary segmentation. As for the hyperparameter study, results show that the U-Net with 4 levels is the architecture with the worst performance. This shows that to achieve better performance in the segmentation of ovarian structures, it is important to select an architecture that takes into account the spatial context of the regions of interest. It is also possible to conclude that the method used to analyse BRF data should be designed to take advantage of the fine-resolution of BRF data.

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.

Visual exploration of the larynx represents a relevant technique for the early diagnosis of laryngeal disorders. However, visualizing an endoscopy for finding abnormalities is a time-consuming process, and for this reason much research has been dedicated to the automatic analysis of endoscopic video data. In this work we address the particular task of discriminating among informative laryngoscopic frames and those that carry insufficient diagnostic information. In the latter case, the goal is also to determine the reason for this lack of information. To this end, we analyze the possibility of training three different state-of-the-art Convolutional Neural Networks, but initializing their weights from configurations that have been previously optimized for solving natural image classification problems. Our findings show that the simplest of these three architectures not only is the most accurate (outperforming previously proposed techniques), but also the fastest and most efficient, with the lowest inference time and minimal memory requirements, enabling real-time application and deployment in portable devices.

The automatic differentiation of retinal vessels into arteries and veins (A/V) is a highly relevant task within the field of retinal image analysis. However, due to limitations of retinal image acquisition devices, specialists can find it impossible to label certain vessels in eye fundus images. In this paper, we introduce a method that takes into account such uncertainty by design. For this, we formulate the A/V classification task as a four-class segmentation problem, and a Convolutional Neural Network is trained to classify pixels into background, A/V, or uncertain classes. The resulting technique can directly provide pixelwise uncertainty estimates. In addition, instead of depending on a previously available vessel segmentation, the method automatically segments the vessel tree. Experimental results show a performance comparable or superior to several recent A/V classification approaches. In addition, the proposed technique also attains state-of-the-art performance when evaluated for the task of vessel segmentation, generalizing to data that was not used during training, even with considerable differences in terms of appearance and resolution.

Lung volume segmentation is a key step in the design of Computer-Aided Diagnosis systems for automated lung pathology analysis. However, isolating the lung from CT volumes can be a challenging process due to considerable deformations and the potential presence of pathologies. Convolutional Neural Networks (CNN) are effective tools for modeling the spatial relationship between lung voxels. Unfortunately, they typically require large quantities of annotated data, and manually delineating the lung from volumetric CT scans can be a cumbersome process. We propose to train a 3D CNN to solve this task based on semi-automatically generated annotations. For this, we introduce an extension of the well-known V-Net architecture that can handle higher-dimensional input data. Even if the training set labels are noisy and contain errors, our experiments show that it is possible to learn to accurately segment the lung relying on them. Numerical comparisons on an external test set containing lung segmentations provided by a medical expert demonstrate that the proposed model generalizes well to new data, reaching an average 98.7% Dice coefficient. The proposed approach results in a superior performance with respect to the standard V-Net model, particularly on the lung boundary.

This study describes a novel dataset with retinal image quality annotation, defined by three different retinal experts, and presents an inter-observer analysis for quality assessment that can be used as gold-standard for future studies. A state-of-the-art algorithm for retinal image quality assessment is also analysed and compared against the specialists performance. Results show that, for 71% of the images present in the dataset, the three experts agree on the given image quality label. The results obtained for accuracy, specificity and sensitivity when comparing one expert against another were in the ranges [83.0 − 85.2]%, [72.7 − 92.9]% and [80.0 − 94.7]%, respectively. The evaluated automatic quality assessment method, despite not being trained on the novel dataset, presents a performance which is within inter-observer variability.

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.

Deep learning models have been successfully used in medical image analysis problems but they require a large amount of labeled images to obtain good performance. However, such large labeled datasets are costly to acquire. Active learning techniques can be used to minimize the number of required training labels while maximizing the model's performance. In this work, we propose a novel sampling method that queries the unlabeled examples that maximize the average distance to all training set examples in a learned feature space. We then extend our sampling method to define a better initial training set, without the need for a trained model, by using Oriented FAST and Rotated BRIEF (ORB) feature descriptors. We validate MedAL on 3 medical image datasets and show that our method is robust to different dataset properties. MedAL is also efficient, achieving 80% accuracy on the task of Diabetic Retinopathy detection using only 425 labeled images, corresponding to a 32% reduction in the number of required labeled examples compared to the standard uncertainty sampling technique, and a 40% reduction compared to random sampling.

Lung cancer diagnosis is made by radiologists through nodule search in chest Computed Tomography (CT) scans. This task is known to be difficult and prone to errors that can lead to late diagnosis. Although Computer-Aided Diagnostic (CAD) systems are promising tools to be used in clinical practice, experienced radiologists continue to perform better diagnosis than CADs. This paper proposes a methodology for characterizing the radiologist's gaze during nodules search in chest CT scans. The main goals are to identify regions that attract the radiologists' attention, which can then be used for improving a lung CAD system, and to create a tool to assist radiologists during the search task. For that purpose, the methodology processes the radiologists' gaze and their mouse coordinates during the nodule search. The resulting data is then processed to obtain a 3D gaze path from which relevant attention studies can be derived. To better convey the found information, a reference model of the lung that eases the communication of the location of relevant anatomical/pathological findings is also proposed. The methodology is tested on a set of 24 real-practice gazes, recorded via an Eye tracker, from 3 radiologists.

Image dehazing tries to solve an undesired loss of visibility in outdoor images due to the presence of fog. Recently, machine-learning techniques have shown great dehazing ability. However, in order to be trained, they require training sets with pairs of foggy images and their clean counterparts, or a depth-map. In this paper, we propose to learn the appearance of fog from weakly-labeled data. Specifically, we only require a single label per-image stating if it contains fog or not. Based on the Multiple-Instance Learning framework, we propose a model that can learn from image-level labels to predict if an image contains haze reasoning at a local level. Fog detection performance of the proposed method compares favorably with two popular techniques, and the attention maps generated by the model demonstrate that it effectively learns to disregard sky regions as indicative of the presence of fog, a common pitfall of current image dehazing techniques.

The segmentation and characterization of the lung lobes are important tasks for Computer Aided Diagnosis (CAD) systems related to pulmonary disease. The detection of the fissures that divide the lung lobes is non-trivial when using classical methods that rely on anatomical information like the localization of the airways and vessels. This work presents a fully automatic and supervised approach to the problem of the segmentation of the five pulmonary lobes from a chest Computer Tomography (CT) scan using a Fully RegularizedV-Net (FRV- Net), a 3D Fully Convolutional Neural Network trained end-to- end. Our network was trained and tested in a custom dataset that we make publicly available. It can correctly separate the lobes even in cases when the fissure is not well delineated, achieving 0.93 in per-lobe Dice Coefficient and 0.85 in the inter-lobar Dice Coefficient in the test set. Both quantitative and qualitative results show that the proposed method can learn to produce correct lobe segmentations even when trained on a reduced dataset.

Given a retinal image, can we automatically determine whether it is of high quality (suitable for medical diagnosis)? Can we also explain our decision, pinpointing the region or regions that led to our decision? Images from human retinas are vital for the diagnosis of multiple health issues, like hypertension, diabetes, and Alzheimer’s; low quality images may force the patient to come back again for a second scanning, wasting time and possibly delaying treatment. However, existing retinal image quality assessment methods are either black boxes without explanations of the results or depend heavily on feature engineering or on complex and error-prone anatomical structures’ segmentation. Therefore, we propose EyeQual, that solves exactly this problem. EyeQual is novel, fast for inference, accurate and explainable, pinpointing low-quality regions on the image. We evaluated EyeQual on two real datasets where it achieved 100% accuracy taking just 36 milliseconds for each image.

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%.

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 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.

This paper presents a new method for automatic common carotid artery detection in B-mode ultrasonography. The proposed method is based on the location of phase symmetry patterns at apropriate scale of analysis. The local phase information is derived from the monogenic signal and isotropic log-normal band-pass filters, and the resulting common carotid artery is located using a dynamic programming optimization algorithm. The experiments show that the proposed method is more robust to noise than previous approaches, although additional research is required for robust common carotid artery detection on the more complicated cases.

Cell tracking is a fundamental problem for studying live cell dynamics. A novel approach for low frame rate cell tracking in fluorescent microscopy image is herein proposed. The method is based on sliding band filter detection and Delaunay triangulation sub-graph matching. With this approach we can track a large amount of small cells without their motion model and not relying on cell motion continuity between consecutive images. The effectiveness and robustness of the method were validated by visual inspection and on a ground truth dataset.

Plant development is orchestrated by transcription factors whose expression has become observable in living plants through the use of fluorescence microscopy. However, the exact quantification of expression levels is still not solved and most analysis is only performed through visual inspection. With the objective of automating the quantification of cell nuclei fluorescence we present a new approach to detect cell nuclei in 3D fluorescence confocal microscopy, based on the use of the sliding band convergence filter (SBF). The SBF filter detects cell nuclei and estimate their shape with high accuracy in each 2D image plane. For 3D detection, individual 2D shapes are joined into 3D estimates and then corrected based on the analysis of the fluorescence profile. The final nuclei detection’s precision/recall are of 0.779/0.803 respectively, and the average Dice’s coefficient of 0.773.

This paper proposes a new framework to image segmentation which combines edge- and region-based information with spectral techniques through the morphological algorithm of watersheds. A pre-processing step is used to reduce the spatial resolution without losing important image information. An initial partitioning of the image into primitive regions is set by applying a rainfalling watershed algorithm on the image gradient magnitude. This initial partition is the input to a computationally efficient region segmentation process which produces the final segmentation. The latter process uses a region-based similarity graph representation of the image regions. The experimental results clearly demonstrate the effectiveness of the proposed approach to produce simpler segmentations and to compare favourably with state-of-the-art methods.

In vivo observation of cells in the Arabidopsis thaliana root, by time-lapse confocal microscopy, is central to biology research. The research herein described is based on large amount of image data, which must be analyzed to determine the location and state of individual cells. Automating the process of cell tracking is an important step to create tools which will facilitate the analysis of cellspsila evolution through time. Here we introduce a confocal tracking system designed in two stages. At the image acquisition stage, we track the area under analysis based on point-to-point correspondences and motion estimation. After image acquisition, we compute cell-to-cell correspondences through time. The final result is a temporal structured information about each cell.

It is known that neurons in the primary visual cortex are characterized by receptive fields that are selective for specific spatial orientations. It is believed that the sense of object motion and velocity are also related to these fields, as objects in natural scenes are represented by a sparse set of statistically independent components, such as edges. Currently, computational models of receptive fields consider only spatial components, and thus cannot account for time-varying sensory stimuli. A model based on independent component analysis and cellular neural networks is proposed. This approach extends existing models to incorporate temporal aspects of sequences of images of natural scenes.

In this paper we present an evaluation of optical flow techniques applied to a case study in the perception of visual motion. This case study is being conducted in a project for the evaluation of human factors in road traffic, specifically, concerning the processing of visual information. We present the goals of the case study, discuss the need to apply optical flow techniques to synthesized image sequences and evaluate some limitations encountered in their use.

A 3-D data acquisition and scene segmentation system is described. For 3-D data acquisition a structured light technique based on the ratio of two intensity images is used. This technique avoids the correspondence problem, that appears in other structured light techniques, and allows the acquisition of dense range images. The calibration steps of the system are described. Measurement results with different scenes are presented and system accuracy is evaluated. Taking into account that this system allows the acquisition of a dense range image and an intensity image, registered with it, a new approach to the segmentation of 3-D scenes using both range and intensity information is proposed. The two images are segmented separately and iteratively. At each iteration, the segmentation results are combined. The segmentation proceeds until all segments are planar or no more splits are possible. A two-step merging procedure follows: first, planar surfaces that may have been split are "reconstructed", by merging adjacent planar regions that satisfy some constraints; then, regions belonging to curved surfaces are identified and merged, using a curvature analysis along line segments delimited by edge points, combined from both images. Finally, the resulting surfaces are described, using adequate functions.