Properties of Uncommon Indirect Immunofluorescence Staining Patterns Determined during Antinuclear Antibody Detection on HEp-2 Cells

Recognition of rare antinuclear antibody patterns based on a novel attention-based enhancement framework

Rare antinuclear antibody (ANA) pattern recognition has been a widely applied technology for routine ANA screening in clinical laboratories. In recent years, the application of deep learning methods in recognizing ANA patterns has witnessed remarkable advancements. However, the majority of studies in this field have primarily focused on the classification of the most common ANA patterns, while another subset has concentrated on the detection of mitotic metaphase cells. To date, no prior research has been specifically dedicated to the identification of rare ANA patterns. In the present paper, we introduce a novel attention-based enhancement framework, which was designed for the recognition of rare ANA patterns in ANA-indirect immunofluorescence images. More specifically, we selected the algorithm with the best performance as our target detection network by conducting comparative experiments. We then further developed and enhanced the chosen algorithm through a series of optimizations. Then, attention mechanism was introduced to facilitate neural networks in expediting the learning process, extracting more essential and distinctive features for the target features that belong to the specific patterns. The proposed approach has helped to obtained high precision rate of 86.40%, 82.75% recall, 84.24% F1 score and 84.64% mean average precision for a 9-category rare ANA pattern detection task on our dataset. Finally, we evaluated the potential of the model as medical technologist assistant and observed that the technologist's performance improved after referring to the results of the model prediction. These promising results highlighted its potential as an efficient and reliable tool to assist medical technologists in their clinical practice.

Complex patterns on HEp-2 indirect immunofluorescence assay in a large sample referred for anti-cell autoantibodies detection

Introduction

The combination of patterns is a frequent and challenging situation in the daily laboratory routine of autoantibodies testing using HEp-2 cells indirect immunofluorescence assay (HEp-2-IFA). Recently, the Brazilian Consensus on Autoantibodies (BCA) named these combinations as complex patterns (CPs) and organized them into 3 subtypes: multiple, mixed, and composite. This study aimed to describe the most frequent combinations of HEp-2-IIF patterns according to this new nomenclature.

Methods

Routine HEp-2-IFA results reported in January and June 2017 were reviewed using the new BCA classification. Visual pattern recognition was performed by experts on HEp-2-IFA readings, using the International Consensus on Antinuclear Antibodies (ANA) Patterns (ICAP) and BCA recommendations.

Results

54,990 serum samples from different patients were tested for ANA-HEp-2, and 11,478 (20.9%) were positive at a titer ≥ 1/80. Among these positive samples, 1,111 (9.7%) displayed CPs, divided into 95 different combinations. A higher proportion of CPs was observed in the pediatric age group. Multiple, mixed, and composite patterns were present in 85.3, 5.4, and 9.5% of the samples, respectively. In the multiple/mixed pattern group (n=1,005), double, triple, and quadruple combinations (ICAP/BCA codes) were observed in 97.7%, 2.2%, and 0.1%, respectively. The double nuclear pattern was the most prevalent combination observed (67.6%). The most common CPs registered were AC-4 (nuclear fine speckled) + AC-6,7 (nuclear discrete dots) (n=264); AC-2 (nuclear dense fine speckled) + AC-6,7 (n=201); AC-4+AC-8,9,10 (nucleolar) (n=129); and AC-3 (centromere)+AC-4 (n=124). All of these combinations were in the multiple subgroup.

Conclusion

Almost 10% of positive results in the HEp-2 procedure displayed CPs. Among the 3 subtypes of CPs proposed, the multiple pattern was the most prevalent, especially in the pediatric population. The AC-4, AC-2, and AC-6,7 were the most prevalent single patterns observed in the combinations described in this study. There was a significant association between age and the prevalence of most combined patterns. The AC-4+AC-6,7 combination was the most prevalent complex pattern detected regardless of the age group. The AC-2+AC-6,7 was more prevalent in younger individuals. The concepts involved in the CPs definition should add value to the reading and interpretation of the HEp-2-IIF assay.

Autoantibodies in COVID-19, a possible role in the pathogenesis of the disease

OBJECTIVES

In this study, we investigated whether SARS-CoV-2 stimulates autoantibody production.

METHODS

The study included 91 patients hospitalized due to COVID 19, with no previous history of immunological diseases. Immunofluorescence assays were performed to detect antinuclear antibodies (ANAs) and antineutrophil cytoplasmic antibodies (ANCAs), along with tests for specific autoantibodies.

RESULTS

The median age (57% male) was 74 years (range 38-95 years). Autoantibodies were positive in 67 (74%), ANA in 65 (71%), and ANCA in 11 (12%) patients. Female gender (p = 0.01), age (p = 0.005), and Charlson comorbidity index (p = 0.004) were significant predictors for the development of ANA/ANCA antibodies (p = 0.004). Nuclear mitotic apparatus (NuMA)-like, positivity was the strongest predictor of acute kidney injury (AKI), together with noninvasive ventilation and eGFR (χ2  = 49.01, P < 0.001).

CONCLUSION

Positive autoantibodies in a large proportion of patients suggest a role of autoimmunity in the pathophysiology of acute COVID-19 disease. NuMA was the strongest predictor of AKI.