Leonardo Onofri

A versatile clearing agent for multi-modal brain imaging

Extensive mapping of neuronal connections in the central nervous system requires high-throughput µm-scale imaging of large volumes. In recent years, different approaches have been developed to overcome the limitations due to tissue light scattering. These methods are generally developed to improve the performance of a specific imaging modality, thus limiting comprehensive neuroanatomical exploration by multi-modal optical techniques. Here, we introduce a versatile brain clearing agent (2,2′-thiodiethanol; TDE) suitable for various applications and imaging techniques. TDE is cost-efficient, water-soluble and low-viscous and, more importantly, it preserves fluorescence, is compatible with immunostaining and does not cause deformations at sub-cellular level. We demonstrate the effectiveness of this method in different applications: in fixed samples by imaging a whole mouse hippocampus with serial two-photon tomography; in combination with CLARITY by reconstructing an entire mouse brain with light sheet microscopy and in translational research by imaging immunostained human dysplastic brain tissue.

Novel opportunities in automated classification of antinuclear antibodies on HEp-2 cells.

The recommended method for antinuclear antibodies (ANA) detection is IIF but it is influenced by many different factors. In order to pursue a high image quality without artefacts and to reduce inter-observer variability, this study aims to evaluate the reliability of using automatically acquired digital images for diagnostic purposes. In this paper we present SLIM-system a comprehensive system that supports the two sides of IIF tests classification. It is based on two systems: the first labels the fluorescence intensity, whereas the second recognizes the staining pattern of positive wells. We populated a dataset of 600 images obtained from sera screened for ANA by IIF on Hep-2 cells. The error rate has been evaluated according to eight-fold cross validation method; the rates reported in the following are the mean of the tests. Performance of the system in positive/negative recognition ranges from 87% up to more than 94%. Staining pattern classification accuracy of main classes ranges from 71% to 74%. The system provides high and reliable identification of negative samples and a flexibility that permits to use this application for different purposes. The analysis of its perspective performance shows the system potential in lowering the method variability, in increasing the level of standardization and in reducing the specialist workload of more than 80%. Our data represent a first step to validate the use of Computer Aided Diagnosis (CAD), thus offering an opportunity for standardizing and automatizing the detection of ANA by IIF.

A decision support system for Crithidia Luciliae image classification

OBJECTIVE Systemic lupus erythematosus is a connective tissue disease affecting multiple organ systems and characterised by a chronic inflammatory process. It is considered a very serious sickness, further to be classified as an invalidating chronic disease. The recommended method for its detection is the indirect immunofluorescence (IIF) based on Crithidia Luciliae (CL) substrate. Hoverer, IIF is affected by several issues limiting tests reliability and reproducibility. Hence, an evident medical demand is the development of computer-aided diagnosis tools that can offer a support to physician decision. METHODS In this paper we propose a system that classifies CL wells integrating information extracted from different images. It is based on three main decision phases. Two steps, named as threshold-based classification and single cells recognition, are applied for image classification. They minimise false negative and false positive classifications, respectively. Feature extraction and selection have been carried out to determine a compact set of descriptors to distinguish between positive and negative cells. The third step applies majority voting rule at well recognition level, enabling us to recover possible errors provided by previous phases. RESULTS The system performance have been evaluated on an annotated database of IIF CL wells, composed of 63 wells for a total of 342 images and 1487 cells. Accuracy, sensitivity and specificity of image recognition step are 99.4%, 98.6% and 99.6%, respectively. At level of well recognition, accuracy, sensitivity and specificity are 98.4%, 93.3% and 100.0%, respectively. The system has been also validated in a daily routine fashion on 48 consecutive analyses of hospital outpatients and inpatients. The results show very good performance for well recognition (100% of accuracy, sensitivity and specificity), due to the integration of cells and images information. CONCLUSIONS The described recognition system can be applied in daily routine in order to improve the reliability, standardisation and reproducibility of CL readings in IIF.

A bag of visual words approach for centromere and cytoplasmic staining pattern classification on HEp-2 images

Antinuclear autoantibodies (ANAs) are important markers to diagnose autoimmune diseases, very serious and also invalidating illnesses. The benchmark procedure for ANAs diagnosis is the indirect immunofluorescence (IIF) assay performed on the HEp-2 substrate. Medical doctors first determine the fluorescence intensity exhibited by HEp-2 cells, and then report the staining pattern for positive wells only. With reference to staining pattern recognition, in the literature we found works recognizing five main patterns characterized by well-defined cell edges. These approaches are based on cell segmentation, a task that should be harder than the classification itself. We present here a method extending the panel of detectable HEp-2 staining patterns, introducing the centromere and cytoplasmic patterns, which do not show well-defined cell edges, and where a segmentation-based classification may fail. We apply a local approach which extracts SIFT descriptors and then classifies an image through the bag of visual words approach. This permits to represent complex image contents without applying the segmentation procedure. We test our approach on a dataset of HEp-2 images with large variability in both fluorescence intensity and staining patterns. Despite the large skew of the a-priori class distribution, our system correctly recognizes the 98.3% of samples, with a F-measure equal to 92.3%, 95.2% and 99.0%, for each class.

A survey on using domain and contextual knowledge for human activity recognition in video streams

We focus on activity recognition methods in video streams.We survey methods that incorporate a priori knowledge and context information.We categorize the surveyed works by the method use for handling the knowledge.We discuss the surveyed contributions and provide future directions. Human activity recognition has gained an increasing relevance in computer vision and it can be tackled with either non-hierarchical or hierarchical approaches. The former, also known as single-layered approaches, are those that represent and recognize human activities directly from the extracted descriptors, building a model that distinguishes among the activities contained in the training data. The latter represent and recognize human activities in terms of subevents, which are usually recognized my means of single-layered approaches. Alongside of non-hierarchical and hierarchical approaches, we observe that methods incorporating a priori knowledge and context information on the activity are getting growing interest within the community. In this work we refer to this emerging trend in computer vision as knowledge-based human activity recognition with the objective to cover the lack of a summary of these methodologies. More specifically, we survey methods and techniques used in the literature to represent and integrate knowledge and reasoning into the recognition process. We categorize them as statistical approaches, syntactic approaches and description-based approaches. In addition, we further discuss public and private datasets used in this field to promote their use and to enable the interest readers in finding useful resources. This review ends proposing main future research directions in this field.

Multiple subsequence combination in human action recognition

Human action recognition is an active research area with applications in several domains such as visual surveillance, video retrieval and human–computer interaction. Current approaches assign action labels to video streams considering the whole video as a single sequence but, in some cases, the large variability between frames may lead to misclassifications. The authors propose a multiple subsequence combination (MSC) method that divides the video into several consecutive subsequences. It applies part-based and bag of visual words approaches to classify each subsequence. Then, it combines subsequence labels to assign an action label to the video. The proposed approach was tested on the KTH, UCF sports, Youtube and Robo-Kitchen datasets, which have large differences in terms of video length, object appearance and pose, object scale, viewpoint, background, as well as number, type and complexity of actions performed. Two main results were achieved. First, the MSC approach shows better performances compared to classify the video as a whole, even when few subsequences are used. Second, the approach is robust and stable since, for each dataset, its performances are comparable to the part-based approach at the state-of-the-art.

TeraFly: real-time three-dimensional visualization and annotation of terabytes of multidimensional volumetric images

networks, coexpression to rescue RNA interference– or CRISPRCAS9–induced reduction of endogenous transcripts, and expression of ORFs carrying a mutation of interest to allow measurement of the mutation effect in the absence of the wild-type background. High-level gene coverage, combined with the versatility of Gateway cloning, and full access to OC clones make this collection a unique and valuable resource for the scientific community that should aid in the functional characterization of new protein targets and testing of disease-relevant mutations on a large scale. The OC resource will continue to be expanded in the future to increase human gene coverage, provide additional isoforms where available, provide clones with medically relevant mutations and add additional species, including ORFs from Xenopus and Drosophila.

The classification of Crithidia luciliae immunofluorescence test (CLIFT) using a novel automated system

IntroductionIn recent years, there has been an increased demand for computer-aided diagnosis (CAD) tools to support clinicians in the field of indirect immunofluorescence. To this aim, academic and industrial research is focusing on detecting antinuclear, anti-neutrophil, and anti-double-stranded (anti-dsDNA) antibodies. Within this framework, we present a CAD system for automatic analysis of dsDNA antibody images using a multi-step classification approach. The final classification of a well is based on the classification of all its images, and each image is classified on the basis of the labeling of its cells.MethodsWe populated a database of 342 images—74 positive (21.6%) and 268 negative (78.4%)— belonging to 63 consecutive sera: 15 positive (23.8%) and 48 negative (76.2%). We assessed system performance by using k-fold cross-validation. Furthermore, we successfully validated the recognition system on 83 consecutive sera, collected by using different equipment in a referral center, counting 279 images: 92 positive (33.0%) and 187 negative (67.0%).ResultsWith respect to well classification, the system correctly classified 98.4% of wells (62 out of 63). Integrating information from multiple images of the same wells recovers the possible misclassifications that occurred at the previous steps (cell and image classification). This system, validated in a clinical routine fashion, provides recognition accuracy equal to 100%.ConclusionThe data obtained show that automation is a viable alternative for Crithidia luciliae immunofluorescence test analysis.

An efficient autofocus algorithm for indirect immunofluorescence applications

Photobleaching effect is a major issue in developing autofocus algorithms for indirect immunofluorescence (IIF) assay since it quickly flattens the fluorescence intensity of the samples. To overcome this limitation we propose an autofocus algorithm, suited for IIF, aiming at minimizing the number of images required to focus the sample. We test our algorithm with an heterogeneous set of IIF images containing the substrates most widely used in clinical practice, comparing popular focus functions in order to find out the most appropriate for our procedure. Experimental results prove that our algorithm focus the sample using less images than other popular algorithms proposed in the literature.

A Slightly Supervised Approach for Positive/Negative Classification of Fluorescence Intensity in HEp-2 Images

Indirect Immunofluorescence on HEp-2 slides is the recommended technique to detect antinuclear autoantibodies in patient serum. Such slides are read at the fluorescence microscope by experts of IIF, who classify the fluorescence intensity, recognize mitotic cells and classify the staining patterns for each well. The crucial need of accurately performed and correctly reported laboratory determinations has motivated recent research on computer-aided diagnosis tools in IIF to support the HEp-2 image classification. Such systems adopt a fully supervised classification approach and, hence, their chance of success depends on the quality of ground truth used to train the classification algorithms. Besides being expensive and time consuming, collecting a large and reliable ground truth in IIF is intrinsically hard due to the inter- and intra-observer variability. In order to overcome such limitations, this paper presents a slightly supervised approach for positive/negative fluorescence intensity classification. The classification phase consists in matching parts of interest automatically detected in the test image with a Gaussian mixture model built over few control images. The approach, whose operating configuration can be adapted to the cost of misclassifications, has been tested over a database with 914 images acquired from 304 different wells, achieving remarkable results on positive/negative screening task.