Idioma:

3D multi-view convolutional neural networks for lung nodule classification

Kang, Guixia ; Liu, Kui ; Hou, Beibei ; Zhang, Ningbo Deng, Yong

PloS one, 2017-11, Vol.12 (11), p.e0188290-e0188290 [Periódico revisado por pares]

United States: Public Library of Science

Texto completo disponível

Citações Citado por

Enviar para

Título:
3D multi-view convolutional neural networks for lung nodule classification
Autor: Kang, Guixia ; Liu, Kui ; Hou, Beibei ; Zhang, Ningbo
Deng, Yong
Assuntos: Accuracy ; Algorithms ; Architectural engineering ; Architecture ; Artificial neural networks ; Automation ; Benign ; Biology and Life Sciences ; Care and treatment ; Chains ; Classification ; Communication ; Communications networks ; Computed tomography ; Computer and Information Sciences ; Consortia ; Diagnosis ; Engineering ; Humans ; Image classification ; Image databases ; International conferences ; Lung cancer ; Lung diseases ; Lung Neoplasms - diagnostic imaging ; Lung nodules ; Medical diagnosis ; Medical imaging ; Medicine and Health Sciences ; Metastases ; Neural networks ; Neural Networks (Computer) ; Nodules ; Pattern recognition ; People and Places ; Research and Analysis Methods ; Solitary Pulmonary Nodule - diagnostic imaging ; Strategy ; Tomography, X-Ray Computed
É parte de: PloS one, 2017-11, Vol.12 (11), p.e0188290-e0188290
Notas: ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Competing Interests: Guixia Kang is employed by Beijing Ciji Network Technology Co., Ltd. There are no further patents, products in development or marketed products to declare. This does not alter our adherence to all the PLOS ONE policies on sharing data and materials.
Descrição: The 3D convolutional neural network (CNN) is able to make full use of the spatial 3D context information of lung nodules, and the multi-view strategy has been shown to be useful for improving the performance of 2D CNN in classifying lung nodules. In this paper, we explore the classification of lung nodules using the 3D multi-view convolutional neural networks (MV-CNN) with both chain architecture and directed acyclic graph architecture, including 3D Inception and 3D Inception-ResNet. All networks employ the multi-view-one-network strategy. We conduct a binary classification (benign and malignant) and a ternary classification (benign, primary malignant and metastatic malignant) on Computed Tomography (CT) images from Lung Image Database Consortium and Image Database Resource Initiative database (LIDC-IDRI). All results are obtained via 10-fold cross validation. As regards the MV-CNN with chain architecture, results show that the performance of 3D MV-CNN surpasses that of 2D MV-CNN by a significant margin. Finally, a 3D Inception network achieved an error rate of 4.59% for the binary classification and 7.70% for the ternary classification, both of which represent superior results for the corresponding task. We compare the multi-view-one-network strategy with the one-view-one-network strategy. The results reveal that the multi-view-one-network strategy can achieve a lower error rate than the one-view-one-network strategy.
Editor: United States: Public Library of Science
Idioma: Inglês

Links

View this record in MEDLINE/PubMed

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

3D multi-view convolutional neural networks for lung nodule classification

Kang, Guixia ; Liu, Kui ; Hou, Beibei ; Zhang, Ningbo Deng, Yong

United States: Public Library of Science

Buscando em bases de dados remotas. Favor aguardar.