Matheus Calil Faleiros1, Marcello Henrique Nogueira-Barbosa2,3,4,5, Vitor Faeda Dalto6, José Raniery Ferreira Júnior7,8, Ariane Priscilla Magalhães Tenório7, Rodrigo Luppino-Assad7, Paulo Louzada-Junior7, Rangaraj Mandayam Rangayyan9, Paulo Mazzoncini de Azevedo-Marques7,8. 1. São Carlos School of Engineering, University of São Paulo, São Carlos, SP, Brazil. 2. Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, SP, Brazil. marcello@fmrp.usp.br. 3. MAInLab Medical Artificial Intelligence Laboratory, Ribeirão Preto Medical School, Ribeirão Preto, Brazil. marcello@fmrp.usp.br. 4. Ribeirão Preto Medical School Musculoskeletal Imaging Research Laboratory, Ribeirão Preto, Brazil. marcello@fmrp.usp.br. 5. Radiology Division / CCIFM, Ribeirão Preto Medical School, Av. Bandeirantes, 3900, Ribeirão Preto, SP, CEP 14048-900, Brazil. marcello@fmrp.usp.br. 6. Ribeirão Preto Medical School Musculoskeletal Imaging Research Laboratory, Ribeirão Preto, Brazil. 7. Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, SP, Brazil. 8. MAInLab Medical Artificial Intelligence Laboratory, Ribeirão Preto Medical School, Ribeirão Preto, Brazil. 9. Electrical and Computer Engineering Schulich School of Engineering University of Calgary, Calgary, Alberta, Canada.
Abstract
BACKGROUND: Currently, magnetic resonance imaging (MRI) is used to evaluate active inflammatory sacroiliitis related to axial spondyloarthritis (axSpA). The qualitative and semiquantitative diagnosis performed by expert radiologists and rheumatologists remains subject to significant intrapersonal and interpersonal variation. This encouraged us to use machine-learning methods for this task. METHODS: In this retrospective study including 56 sacroiliac joint MRI exams, 24 patients had positive and 32 had negative findings for inflammatory sacroiliitis according to the ASAS group criteria. The dataset was randomly split with ~ 80% (46 samples, 20 positive and 26 negative) as training and ~ 20% as external test (10 samples, 4 positive and 6 negative). After manual segmentation of the images by a musculoskeletal radiologist, multiple features were extracted. The classifiers used were the Support Vector Machine, the Multilayer Perceptron (MLP), and the Instance-Based Algorithm, combined with the Relief and Wrapper methods for feature selection. RESULTS: Based on 10-fold cross-validation using the training dataset, the MLP classifier obtained the best performance with sensitivity = 100%, specificity = 95.6% and accuracy = 84.7%, using 6 features selected by the Wrapper method. Using the test dataset (external validation) the same MLP classifier obtained sensitivity = 100%, specificity = 66.7% and accuracy = 80%. CONCLUSIONS: Our results show the potential of machine learning methods to identify SIJ subchondral bone marrow edema in axSpA patients and are promising to aid in the detection of active inflammatory sacroiliitis on MRI STIR sequences. Multilayer Perceptron (MLP) achieved the best results.
BACKGROUND: Currently, magnetic resonance imaging (MRI) is used to evaluate active inflammatory sacroiliitis related to axial spondyloarthritis (axSpA). The qualitative and semiquantitative diagnosis performed by expert radiologists and rheumatologists remains subject to significant intrapersonal and interpersonal variation. This encouraged us to use machine-learning methods for this task. METHODS: In this retrospective study including 56 sacroiliac joint MRI exams, 24 patients had positive and 32 had negative findings for inflammatory sacroiliitis according to the ASAS group criteria. The dataset was randomly split with ~ 80% (46 samples, 20 positive and 26 negative) as training and ~ 20% as external test (10 samples, 4 positive and 6 negative). After manual segmentation of the images by a musculoskeletal radiologist, multiple features were extracted. The classifiers used were the Support Vector Machine, the Multilayer Perceptron (MLP), and the Instance-Based Algorithm, combined with the Relief and Wrapper methods for feature selection. RESULTS: Based on 10-fold cross-validation using the training dataset, the MLP classifier obtained the best performance with sensitivity = 100%, specificity = 95.6% and accuracy = 84.7%, using 6 features selected by the Wrapper method. Using the test dataset (external validation) the same MLP classifier obtained sensitivity = 100%, specificity = 66.7% and accuracy = 80%. CONCLUSIONS: Our results show the potential of machine learning methods to identify SIJ subchondral bone marrow edema in axSpA patients and are promising to aid in the detection of active inflammatory sacroiliitis on MRI STIR sequences. Multilayer Perceptron (MLP) achieved the best results.