Paolo Soda

Benchmarking HEp-2 Cells Classification Methods

In this paper, we report on the first edition of the HEp-2 Cells Classification contest, held at the 2012 edition of the International Conference on Pattern Recognition, and focused on indirect immunofluorescence (IIF) image analysis. The IIF methodology is used to detect autoimmune diseases by searching for antibodies in the patient serum but, unfortunately, it is still a subjective method that depends too heavily on the experience and expertise of the physician. This has been the motivation behind the recent initial developments of computer aided diagnosis systems in this field. The contest aimed to bring together researchers interested in the performance evaluation of algorithms for IIF image analysis: 28 different recognition systems able to automatically recognize the staining pattern of cells within IIF images were tested on the same undisclosed dataset. In particular, the dataset takes into account the six staining patterns that occur most frequently in the daily diagnostic practice: centromere, nucleolar, homogeneous, fine speckled, coarse speckled, and cytoplasmic. In the paper, we briefly describe all the submitted methods, analyze the obtained results, and discuss the design choices conditioning the performance of each method.

Aggregation of Classifiers for Staining Pattern Recognition in Antinuclear Autoantibodies Analysis

Indirect immunofluorescence is currently the recommended method for the detection of antinuclear autoantibodies (ANA). The diagnosis consists of both estimating the fluorescence intensity and reporting the staining pattern for positive wells only. Since resources and adequately trained personnel are not always available for these tasks, an evident medical demand is the development of computer-aided diagnosis (CAD) tools that can support the physician decisions. In this paper, we present a system that classifies the staining pattern of positive wells on the strength of the recognition of their cells. The core of the CAD is a multiple expert system (MES) based on the one-per-class approach devised to label the pattern of single cells. It employs a hybrid approach since each composing binary module is constituted by an ensemble of classifiers combined by a fusion rule. Each expert uses a set of stable and effective features selected from a wide pool of statistical and spectral measurements. In this framework, we present a novel parameter that measures the reliability of the final classification provided by the MES. This feature is used to introduce a reject option that allows to reduce the error rate in the recognition of the staining pattern of the whole well. The approach has been evaluated on 37 wells, for a total of 573 cells. The measured performance shows a low overall error rate (2.7%-5.8%), which is below the observed intralaboratory variability.

Indirect immunofluorescence in autoimmune diseases: Assessment of digital images for diagnostic purpose

Background: The recommended method for antinuclear antibodies (ANA) detection is indirect immunofluorescence (IIF). To pursue a high image quality without artefacts and reduce interobserver variability, this study aims at evaluating the reliability of automatically acquired digital images of IIF slides for diagnostic purposes. Methods: Ninety‐six sera were screened for ANA by IIF on HEp‐2 cells. Two expert physicians looking at both the fluorescence microscope and the digital images on computer monitor performed a blind study to evaluate fluorescence intensity and staining pattern. Cohens kappa was used as an agreement evaluator between methods and experts. Results: Considering fluorescence intensity, there is a substantial agreement between microscope and monitor analysis in both physicians. Agreement between physicians was substantial at the microscope and perfect at the monitor. Considering IIF pattern, there was a substantial and moderate agreement between microscope and monitor analysis in both physicians. Kappa between physicians was substantial both at the microscope and at the monitor. Conclusions: These preliminary results suggest that digital media is a reliable tool to help physicians in detecting autoantibodies in IIF. Our data represent a first step to validate the use of digital images, thus offering an opportunity for standardizing and automatizing the detection of ANA by IIF.

Early experiences in mitotic cells recognition on HEp-2 slides

Indirect immunofluorescence (IIF) imaging is the recommended laboratory technique to detect autoantibodies in patient serum, but it suffers from several issues limiting its reliability and reproducibility. IIF slides are observed by specialists at the fluorescence microscope, reporting fluorescence intensity and staining pattern and looking for mi-totic cells. Indeed, the presence of such cells is a key factor to assess the correctness of slide preparation process and the reported staining pattern. Therefore, the ability to detect mitotic cells is needed to develop a complete computer-aided-diagnosis system in IIF, which can support the specialists from image acquisition up to image classification. Although recent research in IIF has been directed to image acquisition, image segmentation, fluorescence intensity classification and staining pattern recognition, no works presented methods suited to classify such cells. Hence, this paper presents an heterogeneous set of features used to describe the peculiarities of mitotic cells and then tests five classifiers, belonging to different classification paradigms. The approach has been evaluated on an annotated dataset of mitotic cells. The measured performances are promising, achieving a classification accuracy of 86.5 %.

A multiple expert system for classifying fluorescent intensity in antinuclear autoantibodies analysis

At the present, Indirect Immunofluorescence (IIF) is the recommended method for the detection of antinuclear autoantibodies (ANA). IIF diagnosis requires both the estimation of the fluorescent intensity and the description of the staining pattern, but resources and adequately trained personnel are not always available for these tasks. In this respect, an evident medical demand is the development of computer-aided diagnosis (CAD) tools that can offer a support to physician decision. In this paper we first propose a strategy to reliably label the image data set by using the diagnoses performed by different physicians, and then we present a system to classify the fluorescent intensity. Such a system adopts a multiple expert system architecture (MES), based on the classifier selection paradigm. Two different selection rules are presented and, given the application domain, the convenience of using one of them is analyzed. Different sets of operating points are determined, making the recognition system suited to application in daily practice and in a wide spectrum of scenarios. The measured performance on an annotated database of IIF images shows a low overall miss rate (<1.5%, 0.00% of false negative).

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.

Color to grayscale staining pattern representation in IIF

Indirect immunofluorescence (IIF) is the recommended technique to detect rheumatic diseases through the analysis of images exhibiting a fluorescence in the green band. Since the request of such tests has recently increased, researches efforts have been directed towards the development of computer-aided diagnosis (CAD) tools supporting the specialists and improving the standardization of the method. Technological advances have made available color cameras for IIF image acquisition, but their use requires to determine which color to greyscale conversion method provides most useful information for the needs of CAD development. In this respect, we experimentally compare four different methods converting a color image into a greyscale one, analyzing wide features sets for each conversion method and applying four classification paradigms. Experiments have been carried out on an annotated dataset of HEp-2 cells, finding out a subset of features which is independent from the color model used and showing that a greyscale representation based on the HSI model better exploits information for IIF images analysis.

Large-scale automated identification of mouse brain cells in confocal light sheet microscopy images.

Motivation: Recently, confocal light sheet microscopy has enabled high-throughput acquisition of whole mouse brain 3D images at the micron scale resolution. This poses the unprecedented challenge of creating accurate digital maps of the whole set of cells in a brain. Results: We introduce a fast and scalable algorithm for fully automated cell identification. We obtained the whole digital map of Purkinje cells in mouse cerebellum consisting of a set of 3D cell center coordinates. The method is accurate and we estimated an F1 measure of 0.96 using 56 representative volumes, totaling 1.09 GVoxel and containing 4138 manually annotated soma centers. Availability and implementation: Source code and its documentation are available at http://bcfind.dinfo.unifi.it/. The whole pipeline of methods is implemented in Python and makes use of Pylearn2 and modified parts of Scikit-learn. Brain images are available on request. Contact: paolo.frasconi@unifi.it Supplementary information: Supplementary data are available at Bioinformatics online.

A classification-based approach to segment HEp-2 cells

In this paper we propose a new method for cells segmentation in HEp-2 images addressing and overcoming the main limitations of the existing approaches. The proposed method adopts image reconstruction for a preliminary image segmentation and, then, it employs a sort of classifier-controlled dilation for better determining the structure of the cells, where the classifier is trained using data of the image at hand. We compare the performance of the proposed method with the most representative approaches from the scientific literature on a common and publicly available dataset of HEp-2 images.

A Multi-Expert System to Classify Fluorescent Intensity in Antinuclear Autoantibodies Testing

Indirect immunofluorescence is the recommended method for antinuclear autoantibodies (ANA) detection. IIF diagnosis requires estimating fluorescent intensity and pattern description, but resources and adequately trained personnel are not always available for these tasks. In this respect, an evident medical demand is the development of computer aided diagnosis tools that can offer a support to physician decision. In this paper we propose a system to classify the fluorescent intensity: initially we discuss two classifiers based on artificial neural networks that can recognize intrinsically dubious samples and whose error tolerance can be flexibly set according to a given rule. Since such classifiers complement one other, we adopt a multiple expert system that aggregates the two experts. The final decision of the system results from the combination of the outputs of the single experts. Measured performance shows error rates less than 1%, which candidates the method to be used in daily medical practice