Open Access Open Badges Research article

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

Francesca Buzzulini1*, Amelia Rigon1, Paolo Soda2, Leonardo Onofri2, Maria Infantino3, Luisa Arcarese1, Giulio Iannello2 and Antonella Afeltra1

Author Affiliations

1 Clinical Medicine and Rheumatology, Campus Bio-Medico University of Rome, via Alvaro del Portillo 21, 00128 Rome, Italy

2 Computer Science & Bioinformatics Laboratory, Campus Bio-Medico University of Rome, via Alvaro del Portillo 21, 00128 Rome, Italy

3 Immunology and Allergology Laboratory Unit, S. Giovanni di Dio Hospital, Via Torregalli 3, 50143 Florence, Italy

For all author emails, please log on.

Arthritis Research & Therapy 2014, 16:R71  doi:10.1186/ar4510

Published: 14 March 2014



In 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.


We 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%).


With 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%.


The data obtained show that automation is a viable alternative for Crithidia luciliae immunofluorescence test analysis.