Luca Giancardo

Exudate-based diabetic macular edema detection in fundus images using publicly available datasets

Diabetic macular edema (DME) is a common vision threatening complication of diabetic retinopathy. In a large scale screening environment DME can be assessed by detecting exudates (a type of bright lesions) in fundus images. In this work, we introduce a new methodology for diagnosis of DME using a novel set of features based on colour, wavelet decomposition and automatic lesion segmentation. These features are employed to train a classifier able to automatically diagnose DME through the presence of exudation. We present a new publicly available dataset with ground-truth data containing 169 patients from various ethnic groups and levels of DME. This and other two publicly available datasets are employed to evaluate our algorithm. We are able to achieve diagnosis performance comparable to retina experts on the MESSIDOR (an independently labelled dataset with 1200 images) with cross-dataset testing (e.g., the classifier was trained on an independent dataset and tested on MESSIDOR). Our algorithm obtained an AUC between 0.88 and 0.94 depending on the dataset/features used. Additionally, it does not need ground truth at lesion level to reject false positives and is computationally efficient, as it generates a diagnosis on an average of 4.4s (9.3s, considering the optic nerve localisation) per image on an 2.6 GHz platform with an unoptimised Matlab implementation.

Chronic and Acute Intranasal Oxytocin Produce Divergent Social Effects in Mice

Intranasal administration of oxytocin (OXT) might be a promising new adjunctive therapy for mental disorders characterized by social behavioral alterations such as autism and schizophrenia. Despite promising initial studies in humans, it is not yet clear the specificity of the behavioral effects induced by chronic intranasal OXT and if chronic intranasal OXT could have different effects compared with single administration. This is critical for the aforementioned chronic mental disorders that might potentially involve life-long treatments. As a first step to address these issues, here we report that chronic intranasal OXT treatment in wild-type C57BL/6J adult mice produced a selective reduction of social behaviors concomitant to a reduction of the OXT receptors throughout the brain. Conversely, acute intranasal OXT treatment produced partial increases in social behaviors towards opposite-sex novel-stimulus female mice, while on the other hand, it decreased social exploration of same-sex novel stimulus male mice, without affecting social behavior towards familiar stimulus male mice. Finally, prolonged exposure to intranasal OXT treatments did not alter, in wild-type animals, parameters of general health such as body weight, locomotor activity, olfactory and auditory functions, nor parameters of memory and sensorimotor gating abilities. These results indicate that a prolonged over-stimulation of a ‘healthy’ oxytocinergic brain system, with no inherent deficits in social interaction and normal endogenous levels of OXT, results in specific detrimental effects in social behaviors.

Automatic retina exudates segmentation without a manually labelled training set

Diabetic macular edema (DME) is a common vision threatening complication of diabetic retinopathy which can be assessed by detecting exudates (a type of bright lesion) in fundus images. In this work, two new methods for the detection of exudates are presented which do not use a supervised learning step; therefore, they do not require labelled lesion training sets which are time consuming to create, difficult to obtain and prone to human error. We introduce a new dataset of fundus images from various ethnic groups and levels of DME which we have made publicly available. We evaluate our algorithm with this dataset and compare our results with two recent exudate segmentation algorithms. In all of our tests, our algorithms perform better or comparable with an order of magnitude reduction in computational time.

Elliptical local vessel density: A fast and robust quality metric for retinal images

A great effort of the research community is geared towards the creation of an automatic screening system able to promptly detect diabetic retinopathy with the use of fundus cameras. In addition, there are some documented approaches for automatically judging the image quality. We propose a new set of features independent of field of view or resolution to describe the morphology of the patients vessels. Our initial results suggest that these features can be used to estimate the image quality in a time one order of magnitude shorter than previous techniques.

Validating retinal fundus image analysis algorithms: Issues and a proposal

This paper concerns the validation of automatic retinal image analysis (ARIA) algorithms. For reasons of space and consistency, we concentrate on the validation of algorithms processing color fundus camera images, currently the largest section of the ARIA literature. We sketch the context (imaging instruments and target tasks) of ARIA validation, summarizing the main image analysis and validation techniques. We then present a list of recommendations focusing on the creation of large repositories of test data created by international consortia, easily accessible via moderated Web sites, including multicenter annotations by multiple experts, specific to clinical tasks, and capable of running submitted software automatically on the data stored, with clear and widely agreed-on performance criteria, to provide a fair comparison.

Microaneurysm detection with radon transform-based classification on retina images

The creation of an automatic diabetic retinopathy screening system using retina cameras is currently receiving considerable interest in the medical imaging community. The detection of microaneurysms is a key element in this effort. In this work, we propose a new microaneurysms segmentation technique based on a novel application of the radon transform, which is able to identify these lesions without any previous knowledge of the retina morphological features and with minimal image preprocessing. The algorithm has been evaluated on the Retinopathy Online Challenge public dataset, and its performance compares with the best current techniques. The performance is particularly good at low false positive ratios, which makes it an ideal candidate for diabetic retinopathy screening systems.

Microaneurysms Detection with the Radon Cliff Operator in Retinal Fundus Images

Diabetic Retinopathy (DR) is one of the leading causes of blindness in the industrialized world. Early detection is the key in providing effective treatment. However, the current number of trained eye care specialists is inadequate to screen the increasing number of diabetic patients. In recent years, automated and semi-automated systems to detect DR with color fundus images have been developed with encouraging, but not fully satisfactory results. In this study we present the initial results of a new technique for the detection and localization of microaneurysms, an early sign of DR. The algorithm is based on three steps: candidates selection, the actual microaneurysms detection and a final probability evaluation. We introduce the new Radon Cliff operator which is our main contribution to the field. Making use of the Radon transform, the operator is able to detect single noisy Gaussian-like circular structures regardless of their size or strength. The advantages over existing microaneurysms detectors are manifold: the size of the lesions can be unknown, it automatically distinguishes lesions from the vasculature and it provides a fair approach to microaneurysm localization even without post-processing the candidates with machine learning techniques, facilitating the training phase. The algorithm is evaluated on a publicly available dataset from the Retinopathy Online Challenge.

Automatic Visual Tracking and Social Behaviour Analysis with Multiple Mice

Social interactions are made of complex behavioural actions that might be found in all mammalians, including humans and rodents. Recently, mouse models are increasingly being used in preclinical research to understand the biological basis of social-related pathologies or abnormalities. However, reliable and flexible automatic systems able to precisely quantify social behavioural interactions of multiple mice are still missing. Here, we present a system built on two components. A module able to accurately track the position of multiple interacting mice from videos, regardless of their fur colour or light settings, and a module that automatically characterise social and non-social behaviours. The behavioural analysis is obtained by deriving a new set of specialised spatio-temporal features from the tracker output. These features are further employed by a learning-by-example classifier, which predicts for each frame and for each mouse in the cage one of the behaviours learnt from the examples given by the experimenters. The system is validated on an extensive set of experimental trials involving multiple mice in an open arena. In a first evaluation we compare the classifier output with the independent evaluation of two human graders, obtaining comparable results. Then, we show the applicability of our technique to multiple mice settings, using up to four interacting mice. The system is also compared with a solution recently proposed in the literature that, similarly to us, addresses the problem with a learning-by-examples approach. Finally, we further validated our automatic system to differentiate between C57B/6J (a commonly used reference inbred strain) and BTBR T+tf/J (a mouse model for autism spectrum disorders). Overall, these data demonstrate the validity and effectiveness of this new machine learning system in the detection of social and non-social behaviours in multiple (>2) interacting mice, and its versatility to deal with different experimental settings and scenarios.

Textureless Macula Swelling Detection With Multiple Retinal Fundus Images

Retinal fundus images acquired with nonmydriatic digital fundus cameras are versatile tools for the diagnosis of various retinal diseases. Because of the ease of use of newer camera models and their relatively low cost, these cameras can be employed by operators with limited training for telemedicine or point-of-care (PoC) applications. We propose a novel technique that uses uncalibrated multiple-view fundus images to analyze the swelling of the macula. This innovation enables the detection and quantitative measurement of swollen areas by remote ophthalmologists. This capability is not available with a single image and prone to error with stereo fundus cameras. We also present automatic algorithms to measure features from the reconstructed image, which are useful in PoC automated diagnosis of early macular edema, e.g., before the appearance of exudation. The technique presented is divided into three parts: first, a preprocessing technique simultaneously enhances the dark microstructures of the macula and equalizes the image; second, all available views are registered using nonmorphological sparse features; finally, a dense pyramidal optical flow is calculated for all the images and statistically combined to build a naive height map of the macula. Results are presented on three sets of synthetic images and two sets of real-world images. These preliminary tests show the ability to infer a minimum swelling of 300 and to correlate the reconstruction with the swollen location.

Using a patient image archive to diagnose retinopathy

Diabetes has become an epidemic that is expected to impact 365 Million people worldwide by 2025. Consequently, diabetic retinopathy is the leading cause of blindness in the industrialized world today. If detected early, treatments can preserve vision and significantly reduce debilitating blindness. Through this research we are developing and testing a method for automating the diagnosis of retinopathy in a screening environment using a patient archive and digital fundus imagery. We present an overview of our content-based image retrieval (CBIR) approach and provide performance results for a dataset of 98 images from a study in Canada when compared to an archive of 1,355 patients from a study in the Netherlands. An aggregate performance of 89% correct diagnosis is achieved, demonstrating the potential of automated, web-based diagnosis for a broad range of imagery collected under different conditions and with different cameras.