esion Volume Quantification Using Two Convolutional Neural Networks in MRIs of Multiple Sclerosis Patient

Autor(es)

de Oliveira, Marcela ^[1] ; Piacenti-Silva, Marina ^[1] ; da Rocha, Fernando Coronetti Gomes ^[2] ; Santos, Jorge Manuel ^[3] ; Cardoso, Jaime dos Santos ^{[4, 5]} ; Lisboa-Filho, Paulo Noronha ^[1]

Afiliação do(s) autor(es)

^[1] Sao Paulo State Univ Unesp, Sch Sci, Dept Phys, BR-17033360 Bauru, SP - Brazil

^[2] Sao Paulo State Univ, Med Sch, Dept Neurol Psychol & Psychiat, BR-18618687 Botucatu, SP - Brazil

^[3] Polytech Porto ISEP, Sch Engn, Dept Math, P-4249015 Porto - Portugal

^[4] Univ Porto, Inst Syst & Comp Engn Technol & Sci INESC TEC, P-4200465 Porto - Portugal

^[5] Univ Porto, Fac Engn, P-4200465 Porto - Portugal

• Tipo de documento: Artigo Científico
• Fonte: IAGNOSTIC; v. 12, n. 2 FEB 2022.
• Citações Web of Science: 0

Resumo

Background: Multiple sclerosis (MS) is a neurologic disease of the central nervous system which affects almost three million people worldwide. MS is characterized by a demyelination process that leads to brain lesions, allowing these affected areas to be visualized with magnetic resonance imaging (MRI). Deep learning techniques, especially computational algorithms based on convolutional neural networks (CNNs), have become a frequently used algorithm that performs feature self-learning and enables segmentation of structures in the image useful for quantitative analysis of MRIs, including quantitative analysis of MS. To obtain quantitative information about lesion volume, it is important to perform proper image preprocessing and accurate segmentation. Therefore, we propose a method for volumetric quantification of lesions on MRIs of MS patients using automatic segmentation of the brain and lesions by two CNNs. Methods: We used CNNs at two different moments: the first to perform brain extraction, and the second for lesion segmentation. This study includes four independent MRI datasets: one for training the brain segmentation models, two for training the lesion segmentation model, and one for testing. Results: The proposed brain detection architecture using binary cross-entropy as the loss function achieved a 0.9786 Dice coefficient, 0.9969 accuracy, 0.9851 precision, 0.9851 sensitivity, and 0.9985 specificity. In the second proposed framework for brain lesion segmentation, we obtained a 0.8893 Dice coefficient, 0.9996 accuracy, 0.9376 precision, 0.8609 sensitivity, and 0.9999 specificity. After quantifying the lesion volume of all patients from the test group using our proposed method, we obtained a mean value of 17,582 mm(3). Conclusions: We concluded that the proposed algorithm achieved accurate lesion detection and segmentation with reproducibility corresponding to state-of-the-art software tools and manual segmentation. We believe that this quantification method can add value to treatment monitoring and routine clinical evaluation of MS patients. (AU)

• Processo FAPESP: 19/16362-5 - Detecção e quantificação de lesões encefálicas em imagens de ressonância magnética de pacientes com esclerose múltipla
• Beneficiário: Marcela de Oliveira
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Pós-Doutorado
• Processo FAPESP: 17/20032-5 - Identificação e caracterização de nanopartículas metálicas: um estudo da neurotoxicidade em pacientes com esclerose múltipla
• Beneficiário: Marcela de Oliveira
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado