Classification of scleroderma patterns using deep learning
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1300Keywords:
Scleroderma, Classification, Deep LearningAbstract
Objective: Scleroderma is a disease whose cause is unknown and which results in the stiffening of the skin and internal organs. This study aims to develop deep learning models to help doctors assess the progression and mortality of the disease. Method: PIU and PINE pattern classification models were developed with the MobileNetV2, VGG16, ResNet50 and EfficientNet architecture for computerized tomography images of patients with scleroderma. Results: All the models achieved 100% accuracy in the training, validation and test sets and, therefore, it was possible to differentiate the patterns presented in the computerized tomography images of patients who were at the Pedro Ernesto Hospital between 2017 and 2022. Conclusion: Among the models evaluated, MobileNetV2 is the best because it has the fewest parameters of all the architectures evaluated in this study.
References
Sociedade Brasileira de Reumatologia (2017, October 27). Esclerodermia - Sociedade Brasileira de Reumatologia.
Leite, C, Maia, A. "Sintomas de doença e adaptação psicológica em pacientes brasileiros com esclerodermia". Revista Brasileira de Reumatologia 2013; 53(5):405–411.
Steen, V, Oddis, C, Conte, C, Janoski, J, Casterline, G, Medsger, T. "Incidence of systemic sclerosis in Allegheny County, Pennsylvania. A twenty-year study of hospital-diagnosed cases, 1963-1982". Arthritis Rheum 1997; 40(3):441–445.
Frank van den Hoogen, Dinesh Khanna, Jaap Fransen, Sindhu R Johnson, Murray Baron, Alan Tyndall, Marco Matucci-Cerinic, Raymond P Naden, Thomas A Medsger, J, Patricia E Carreira, Gabriela Riemekasten, Philip J Clements, Christopher P Denton, Oliver Distler, Yannick Allanore, Daniel E Furst, Armando Gabrielli, Maureen D Mayes, Jacob M van Laar, James R Seibold, Laszlo Czirjak, Virginia D Steen, Murat Inanc, Otylia Kowal-Bielecka, Ulf Muller-Ladner, Gabriele Valentini, Douglas J Veale, Madelon C Vonk, Ulrich A Walker, Lorinda Chung, David H Collier, Mary Ellen Csuka, Barri J Fessler, Serena Guiducci, Ariane Herrick, Vivien M Hsu, Sergio Jimenez, Bashar Kahaleh, Peter A Merkel, Stanislav Sierakowski, Richard M Silver, Robert W Simms, John Varga, Janet E Pope. "2013 classification criteria for systemic sclerosis: an American college of rheumatology/European league against rheumatism collaborative initiative". Annals of the Rheumatic Diseases 2013; 72(11):1747–1755.
Desai, S, Veeraraghavan, S, Hansell, D, Nikolakopolou, A, Goh, N, Nicholson, A, Colby, T, Denton, C, Black, C, Bois, R, Wells, A. "CT Features of Lung Disease in Patients with Systemic Sclerosis: Comparison with Idiopathic Pulmonary Fibrosis and Nonspecific Interstitial Pneumonia". Radiology 2004; 232(2):560-567.
Jonathan G. Goldin, David A. Lynch, Diane C. Strollo, Robert D. Suh, Dean E. Schraufnagel, Philip J. Clements, Robert M. Elashoff, Daniel E. Furst, Sarinnapha Vasunilashorn, Michael F. McNitt-Gray, Mathew S. Brown, Michael D. Roth, Donald P. Tashkin. "High-Resolution CT Scan Findings in Patients With Symptomatic Scleroderma-Related Interstitial Lung Disease". Chest 2008; 134(2):358–367.
Goodfellow, I, Bengio, Y, Courville, A. Deep Learning. MIT Press; 2016.
Alexander Selvikvåg Lundervold, Arvid Lundervold. "An overview of deep learning in medical imaging focusing on MRI". Zeitschrift für Medizinische Physik 2019; 29(2):102-127
Montagnon, A. "Deep learning workflow in radiology: a primer". Insights into Imaging 2020; 11(1):22.
Prastyo Eko Susanto, Arrie Kurniawardhan, Dhomas Hatta Fudholi, Ridho Rahmadi. "A Mobile Deep Learning Model on Covid-19 CT-Scan Classification". International Journal of Artificial Intelligence Research 2022; 6(2).
TÜRK V, ÇATAL REİS H, KAYA S. Derin öğrenme mimarilerini kullanarak göğüs BT görüntülerinden otomatik Covid-19 tahmini. Gümüşhane Üniversitesi Fen Bilimleri Enstitüsü Dergisi. Gumushane University Journal of Science and Technology Institute; 2022. Disponível em: http://doi.org/10.17714/gumusfenbil.1002738
Almeida, A, Bilbao, A, Ruby, L, Rominger, M, López-De-Ipiña, D, Dahl, J, ElKaffas, A, Sanabria, SLung ultrasound for point-of-care COVID-19 pneumonia stratification: computer-aided diagnostics in a smartphone. First experiences classifying semiology from public datasets. In 2020 IEEE International Ultrasonics Symposium (IUS) 2020 (pp. 1-4).
Torrey L, Shavlik J. Transfer Learning. Handbook of Research on Machine Learning Applications and Trends. IGI Global; 2010. p. 242–64. Disponível em: http://doi.org/10.4018/978-1-60566-766-9.ch011
Yu X, Wang J, Hong QQ, Teku R, Wang SH, Zhang YD. Transfer learning for medical images analyses: A survey. Vol. 489, Neurocomputing. Elsevier BV; 2022. p. 230–54. Disponível em: http://doi.org/10.1016/j.neucom.2021.08.159
Zhang X, Zhou J, Sun W, Kumar Jha S. A Lightweight CNN Based on Transfer Learning for COVID-19 Diagnosis. Vol. 72, Computers, Materials & Continua. Computers, Materials and Continua (Tech Science Press); 2022. p. 1123–37. Disponível em: http://doi.org/10.32604/cmc.2022.02458
Hilmizen N, Bustamam A, Sarwinda D. The Multimodal Deep Learning for Diagnosing COVID-19 Pneumonia from Chest CT-Scan and X-Ray Images. 2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI). IEEE; 2020. Disponível em: http://doi.org/10.1109/ISRITI51436.2020.9315478
Martins JVG, Gregório MP, Baffa M de FO, Coelho AM. Classificação da COVID-19 em Radiografias do Tórax Utilizando Redes Neurais Profundas e Padrões Binários Locais. J Health Inform. 15º de março de 2021 [citado 29º de abril de 2024];12. Disponível em: https://jhi.sbis.org.br/index.php/jhi-sbis/article/view/843
Trombetta GBW, Fröhlich W da R, Rigo SJ, Rodrigues CA. Aplicação de Deep Learning para Diagnóstico de Pneumonia Causada por COVID -19 a partir de Imagens de Raio X. J Health Inform. 15º de março de 2021 [citado 29º de abril de 2024];12. Disponível em: https://jhi.sbis.org.br/index.php/jhi-sbis/article/view/828
Mikołajczyk, A, Grochowski, MData augmentation for improving deep learning in image classification problem. In 2018 International Interdisciplinary PhD Workshop (IIPhDW) 2018 (pp. 117-122).
Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen. MobileNetV2: Inverted Residuals and Linear Bottlenecks.
Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv; 2014. Disponível em: https://arxiv.org/abs/1409.1556
He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. arXiv; 2015. Disponível em: https://arxiv.org/abs/1512.03385
Tan M, Le QV. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv. 2019; Disponível em: https://arxiv.org/abs/1905.11946
Kingma DP, Ba J. Adam: A Method for Stochastic Optimization. arXiv; 2014. Disponível em: https://arxiv.org/abs/1412.6980
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
