Zeiser FA, Santos IG, Bohn HC, da Costa CA, de Oliveira Ramos G, da Rosa Righi R, Maier A, Andrade JRM, Bacelar A (2023)
Publication Type: Conference contribution
Publication year: 2023
Publisher: Science and Technology Publications, Lda
Pages Range: 399-405
Conference Proceedings Title: International Conference on Web Information Systems and Technologies, WEBIST - Proceedings
Event location: Hybrid, Rome, ITA
ISBN: 9789897586729
Diagnosing pleural effusion is important to recognize the disease's etiology and reduce the length of hospital stay for patients after fluid content analysis. In this context, machine learning techniques have been increasingly used to help physicians identify radiological findings. In this work, we propose using contrastive learning to classify chest X-rays with and without pleural effusion. A model based on contrastive learning is trained to extract discriminative features from the images and reports to maximize the similarity between the correct image and text pairs. Preliminary results show that the proposed approach is promising, achieving an AUC of 0.900, an accuracy of 86.28%, and a sensitivity of 88.54% for classifying pleural effusion on chest X-rays. These results demonstrate that the proposed method achieves comparable or superior to state of the art results. Using contrastive learning can be a promising alternative to improve the accuracy of medical image classification models, contributing to a more accurate and effective diagnosis.
APA:
Zeiser, F.A., Santos, I.G., Bohn, H.C., da Costa, C.A., de Oliveira Ramos, G., da Rosa Righi, R.,... Bacelar, A. (2023). Pleural Effusion Classification on Chest X-Ray Images with Contrastive Learning. In Francisco Garcia Penalvo, Massimo Marchiori (Eds.), International Conference on Web Information Systems and Technologies, WEBIST - Proceedings (pp. 399-405). Hybrid, Rome, ITA: Science and Technology Publications, Lda.
MLA:
Zeiser, Felipe André, et al. "Pleural Effusion Classification on Chest X-Ray Images with Contrastive Learning." Proceedings of the 19th International Conference on Web Information Systems and Technologies, WEBIST 2023, Hybrid, Rome, ITA Ed. Francisco Garcia Penalvo, Massimo Marchiori, Science and Technology Publications, Lda, 2023. 399-405.
BibTeX: Download