6533b7d3fe1ef96bd1261697
RESEARCH PRODUCT
Deep CNN for IIF Images Classification in Autoimmune Diagnostics
Vincenzo TaorminaGiuseppe RasoDonato Casciosubject
Computer science02 engineering and technologyConvolutional neural networklcsh:TechnologyIIF imageAlexNetlcsh:Chemistry03 medical and health sciencesconvolutional neural networks (CNNs)Autoimmune diseaseClassifier (linguistics)0202 electrical engineering electronic engineering information engineeringGeneral Materials Scienceautoimmune diseasesInstrumentationlcsh:QH301-705.5030304 developmental biologyIIF imagesFluid Flow and Transfer Processes0303 health sciencesDeep cnnIndirect immunofluorescenceaccuracybusiness.industrylcsh:TProcess Chemistry and Technologyk-nearest neighbors (KNN)General EngineeringPattern recognitionIIfClass (biology)lcsh:QC1-999Computer Science ApplicationsSupport vector machinelcsh:Biology (General)lcsh:QD1-999lcsh:TA1-2040System parameters020201 artificial intelligence & image processingsupport vector machine (SVM)Artificial intelligencebusinesslcsh:Engineering (General). Civil engineering (General)lcsh:Physicsdescription
The diagnosis and monitoring of autoimmune diseases are very important problem in medicine. The most used test for this purpose is the antinuclear antibody (ANA) test. An indirect immunofluorescence (IIF) test performed by Human Epithelial type 2 (HEp-2) cells as substrate antigen is the most common methods to determine ANA. In this paper we present an automatic HEp-2 specimen system based on a convolutional neural network method able to classify IIF images. The system consists of a module for features extraction based on a pre-trained AlexNet network and a classification phase for the cell-pattern association using six support vector machines and a k-nearest neighbors classifier. The classification at the image-level was obtained by analyzing the pattern prevalence at cell-level. The layers of the pre-trained network and various system parameters were evaluated in order to optimize the process. This system has been developed and tested on the HEp-2 images indirect immunofluorescence images analysis (I3A) public database. To test the generalisation performance of the method, the leave-one-specimen-out procedure was used in this work. The performance analysis showed an accuracy of 96.4% and a mean class accuracy equal to 93.8%. The results have been evaluated comparing them with some of the most representative works using the same database.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2019-04-18 | Applied Sciences |