DuaLAnet: Dual Lesion Attention Network for Thoracic Disease Classification in Chest X-Rays

Autor(es)

Teixeira, Vinicius ; Braz, Leodecio ; Pedrini, Helio ; Dias, Zanoni ; Paiva, AC ; Conci, A ; Braz, G ; Almeida, JDS ; Fernandes, LAF

• Tipo de documento: Artigo Científico
• Fonte: PROCEEDINGS OF THE 2020 INTERNATIONAL CONFERENCE ON SYSTEMS, SIGNALS AND IMAGE PROCESSING (IWSSIP), 27TH EDITION; v. N/A, p. 6-pg., 2020-01-01.

Resumo

The chest radiography is one of the most accessible radiological examinations for diagnosis of lung and heart diseases. Deep learning techniques have been increasingly used to provide more accurate detection of thorax lesions on Chest X-Ray (CXR) images. However, we observe that we can use the complementarity of dual asymmetric deep convolutional neural networks (DCNNs) to improve the ability of CXR image classification compared to the single network. In this paper, we propose a novel dual lesion attention network named DuaLAnet for the classification of 14 thorax diseases on chest radiography. The DuaLAnet consists of two asymmetric attention networks, DenseNet-169 and ResNet-152, to integrate the advantages into a wider architecture, thus extracting more discriminative features of different abnormalities from the raw CXRs. Moreover, a training strategy is designed to integrate the loss contribution of the involved classifiers into a unified loss. The proposed DuaLAnet has been evaluated against eight deep learning models using the patient-wise official split of the ChestX-ray14 dataset [1]. Our results show that DuaLAnet achieves and average per-class AUC of 0.820 in the experiments, which clearly substantiate the effectiveness of DuaLAnet when compared to the state-of-the-art baselines. (AU)

• Processo FAPESP: 17/16246-0 - Análise de mídias sensíveis usando arquiteturas de aprendizado profundo
• Beneficiário: Sandra Eliza Fontes de Avila
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 19/20875-8 - Classificação de imagens de radiografias de tórax utilizando redes neurais profundas
• Beneficiário: Vinicius Teixeira de Melo
• Modalidade de apoio: Bolsas no Brasil - Mestrado
• Processo FAPESP: 17/12646-3 - Déjà vu: coerência temporal, espacial e de caracterização de dados heterogêneos para análise e interpretação de integridade
• Beneficiário: Anderson de Rezende Rocha
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 15/11937-9 - Investigação de problemas difíceis do ponto de vista algorítmico e estrutural
• Beneficiário: Flávio Keidi Miyazawa
• Modalidade de apoio: Auxílio à Pesquisa - Temático