1. Computer-Assisted Classification Patterns in Autoimmune Diagnostics: The AIDA Project
- Author
-
Francesco Fauci, Khouloud Hamdi, Raja Marrakchi Triki, Maria Cristina Ciaccio, Rossella Morgante, Maria Vasile Simone, Sadok Yalaoui, Walid Bedhiafi, Trai Neila, Koudhi Soumaya, Hechmi Louzir, Yassine Issaoui, Alessandro Fauci, Haouami Youssra, Donato Cascio, R. Bouhaha, Maria Catanzaro, Gaetano Amato, Ignazio Brusca, Marco Cipolla, Vincenza Barbara, Sfar Imene, Giuseppe Raso, M. Ammar, Yousr Gorgi, Raja Rekik, Mariano Lucchese, Bilel Neili, Hayet Bouokez, Vincenzo Taormina, Amel Benammar Elgaaied, Salvatore Bruno, Maria Fregapane, Melika Ben Ahmed, Oussama Ben Fraj, Souayeh Turkia, Ahmed Abidi, Giuseppe Friscia, Gati Asma, Benammar Elgaaied A, Cascio D, Bruno S, Ciaccio M C, Cipolla C, Fauci A, Morgante R, Taormina V, Gorgi Y, Marrakchi Triki R, Ben Ahmed M, Louzir H, Yalaoui S, Imene S, Issaoui Y, Abidi A, Ammar M, Bedhiafi W, Ben Fraj O, Bouhaha R, Hamdi K, Soumaya K, Neili B, Gati A, Lucchese M, Catanzaro M, Barbara V, Brusca I, Fregapane M, Amato G, Friscia G, Neila T, Turkia S, Youssra H, Rekik R, Bouokez H, Vasile Simone M, Fauci F, Raso G, Université de Tunis El Manar (UTM), Laboratoire de Transmission, Contrôle et Immunobiologie des Infections - Laboratory of Transmission, Control and Immunobiology of Infection (LR11IPT02), Institut Pasteur de Tunis, Réseau International des Instituts Pasteur (RIIP)-Réseau International des Instituts Pasteur (RIIP), Laboratory of medical biology, Hospital A. Mami. Ariana, and Laboratory of Genetics, Immunology and Human Pathology
- Subjects
Pathology ,medicine.medical_specialty ,Tunisia ,Article Subject ,Anti-nuclear antibody ,[SDV]Life Sciences [q-bio] ,lcsh:Medicine ,CAD ,02 engineering and technology ,General Biochemistry, Genetics and Molecular Biology ,030218 nuclear medicine & medical imaging ,Autoimmune Diseases ,03 medical and health sciences ,0302 clinical medicine ,0202 electrical engineering, electronic engineering, information engineering ,Image Processing, Computer-Assisted ,Medicine ,Humans ,Fluorescent Antibody Technique, Indirect ,Indirect immunofluorescence ,General Immunology and Microbiology ,business.industry ,lcsh:R ,IIf ,Pattern recognition ,General Medicine ,Gold standard (test) ,Computer aided detection ,Settore FIS/07 - Fisica Applicata(Beni Culturali, Ambientali, Biol.e Medicin) ,3. Good health ,Fluorescence intensity ,Italy ,Computer-aided diagnosis ,Antibodies, Antinuclear ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,Computer Aided Diagnosis, Immunofluorescence, Pattern Classification, IIF images, Autoimmune diseases, SVM, ANN, HEp-2 ,Research Article - Abstract
International audience; Antinuclear antibodies (ANAs) are significant biomarkers in the diagnosis of autoimmune diseases in humans, done by mean of Indirect ImmunoFluorescence (IIF) method, and performed by analyzing patterns and fluorescence intensity. This paper introduces the AIDA Project (autoimmunity: diagnosis assisted by computer) developed in the framework of an Italy-Tunisia cross-border cooperation and its preliminary results. A database of interpreted IIF images is being collected through the exchange of images and double reporting and a Gold Standard database, containing around 1000 double reported images, has been settled. The Gold Standard database is used for optimization of a CAD(Computer Aided Detection) solution and for the assessment of its added value, in order to be applied along with an Immunologist as a second Reader in detection of autoantibodies. This CAD system is able to identify on IIF images the fluorescence intensity and the fluorescence pattern. Preliminary results show that CAD, used as second Reader, appeared to perform better than Junior Immunologists and hence may significantly improve their efficacy; compared with two Junior Immunologists, the CAD system showed higher Intensity Accuracy (85,5% versus 66,0% and 66,0%), higher Patterns Accuracy (79,3% versus 48,0% and 66,2%), and higher Mean Class Accuracy (79,4% versus 56,7% and 64.2%).
- Published
- 2015