Autoimmune bullous dermatoses (AIBD) are rare diseases that affect human skin and mucous membranes. Clinically, they are characterized by blister formation and/or erosions. Depending on the structures involved and the depth of blister formation, they are grouped into pemphigus diseases, pemphigoid diseases, and dermatitis herpetiformis. Classification of AIBD into their sub-entities is crucial to guide treatment decisions. One of the most sensitive screening methods for initial differentiation of AIBD is the indirect immunofluorescence (IIF) microscopy on tissue sections of monkey esophagus and primate salt-split skin, which are used to detect disease-specific autoantibodies. Interpretation of IIF patterns requires a detailed examination of the image by trained professionals automating this process is a challenging task with these highly complex tissue substrates, but offers the great advantage of an objective result. Here, we present computer-aided classification of esophagus and salt-split skin IIF images. We show how deep networks can be adapted to the specifics and challenges of IIF image analysis by incorporating segmentation of relevant regions into the prediction process, and demonstrate their high accuracy. Using this semi-automatic extension can reduce the workload of professionals when reading tissue sections in IIF testing. Furthermore, these results on highly complex tissue sections show that further integration of semi-automated workflows into the daily workflow of diagnostic laboratories is promising.

PURPOSE:Indirect immunofluorescence (IIF) on the human epithelial cell-line HEp-2 (or derivatives) serves as the gold standard in antinuclear antibody (ANA) screening. IIF, and its evaluation, is a labor-intensive method, making ANA testing a major challenge for present clinical laboratories. Nowadays, several automated ANA pattern recognition systems are on the market. In the current study, the EUROPattern Suite is evaluated for its use in daily practice in a routine setting.METHODS:A total of 1033 consecutive routine samples was used to screen for ANA. Results (positive/negative ANA screening, pattern identification and titer) were compared between software-generated results (EUROPattern) and visual interpretation (observer) of automatically acquired digital images.RESULTS:Considering the visual interpretation as reference, a relative sensitivity of 99.3% and a relative specificity of 88.9% were obtained for negative and positive discrimination by the software (EPa). A good agreement between visual and software-based interpretation was observed with respect to pattern recognition (mean kappa: for 7 patterns: 0.7). Interestingly, EPa software distinguished more patterns per positive sample than the observer (on average 1.5 and 1.2, respectively). Finally, a concordance of 99.3% was observed within the range of 1 titer step difference between EPa and observer.CONCLUSIONS:The ANA IIF results reported by the EPa software are in very good agreement with the results reported by the observer with respect to being negative/positive, pattern recognition and titer, making automated ANA IIF evaluation an objective and time-efficient tool for routine testing.

Systemic lupus erythematosus (SLE) is a severe rheumatic autoimmune disease with various clinical manifestations. Anti-dsDNA antibodies are an important immunological hallmark of SLE and their occurrence represents a major criterion for the diagnosis. Among the commonly applied test systems for determination of anti-dsDNA antibodies, the indirect immunofluorescence test (IIFT) using the flagellated kinetoplastida Crithidia luciliae is considered to be highly disease specific at moderate sensitivity. Since IIFT, however, is claimed to be affected by subjective interpretation and a lack of standardization, there has been an increasing demand for automated pattern interpretation of immunofluorescence reactions in recent years. Corresponding platforms are already available for evaluation of anti-nuclear antibody (ANA) IIFT on HEp-2 cells, the recommended “gold standard” for ANA screening in the diagnosis of various systemic rheumatic autoimmune diseases. For one of these systems, the “EUROPattern-Suite” computer-aided immunofluorescence microscopy (CAIFM), automated interpretation of microscopic fluorescence patterns was extended to the Crithidia luciliae based anti-dsDNA IIFT.

Indirect immunofluorescence (IIF) on human epithelial (HEp-2) cells is considered as the gold standard screening method for the detection of antinuclear autoantibodies (ANA). However, in terms of automation and standardization, it has not been able to keep pace with most other analytical techniques used in diagnostic laboratories. Although there are already some automation solutions for IIF incubation in the market, the automation of result evaluation is still in its infancy. Therefore, the EUROPattern Suite has been developed as a comprehensive automated processing and interpretation system for standardized and efficient ANA detection by HEp-2 cell-based IIF. In this study, the automated pattern recognition was compared to conventional visual interpretation in a total of 351 sera. In the discrimination of positive from negative samples, concordant results between visual and automated evaluation were obtained for 349 sera (99.4%, kappa = 0.984). The system missed out none of the 272 antibody-positive samples and identified 77 out of 79 visually negative samples (analytical sensitivity/specificity: 100%/97.5%). Moreover, 94.0% of all main antibody patterns were recognized correctly by the software. Owing to its performance characteristics, EUROPattern enables fast, objective, and economic IIF ANA analysis and has the potential to reduce intra- and interlaboratory variability.

We present a model for predicting eye movements of an observer viewing dynamic scenes. Supervised-learning techniques are used to tune the model for a particular observer. The approach builds on earlier work [3], adding a saccade detector that is used to switch between two di(cid:11)erent algorithms for saccade and inter-saccade prediction, respectively. This separation yields a signi(cid:12)cant improvement in prediction quality. The predictor for saccade targets operates on a list of salient locations. These are obtained by evaluating the intrinsic dimension of the image using the structure tensor. Prediction of eye movements between two saccades uses a model that operates on a limited history of locations attended in the past. Both models learn by minimizing the quadratic prediction error using gradient descent. Our work is motivated by applications that involve gaze-contingent interactive displays on which information is displayed as a function of gaze direction. The approach therefore di(cid:11)ers from standard approaches in two ways: (i) we deal with dynamic scenes, and (ii) we provide means for adapting the model to a particular observer.

Organic Computing is beginning to provide computer systems with organic and biological properties. We believe these systems will benefit from user interfaces that integrate the user more tightly with the system and optimize the way the user absorbs information. To this end, we propose gaze-contingent interactive displays that monitor and guide the user's gaze to make interaction with the system more effective and enjoyable. A vital prerequisite for such a system is the ability to predict one or several salient locations that the user is likely to attend to in a dynamic display, with the goal of then modifying the display to influence the user's direction of gaze. In this paper, we present a structure-tensor-based saliency measure and a novel algorithm for extracting salient locations from saliency maps by using the mechanism of selective lateral inhibition. We assess the quality of the extracted locations by comparing them to the locations actually attended by test subjects.