Idioma:

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

Shin, Hoo-Chang ; Roth, Holger R. ; Gao, Mingchen ; Lu, Le ; Xu, Ziyue ; Nogues, Isabella ; Yao, Jianhua ; Mollura, Daniel ; Summers, Ronald M.

IEEE transactions on medical imaging, 2016-05, Vol.35 (5), p.1285-1298

United States: IEEE

Texto completo disponível

Citações Citado por

Enviar para

Título:
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
Autor: Shin, Hoo-Chang ; Roth, Holger R. ; Gao, Mingchen ; Lu, Le ; Xu, Ziyue ; Nogues, Isabella ; Yao, Jianhua ; Mollura, Daniel ; Summers, Ronald M.
Assuntos: Biomedical imaging ; Classification ; Computational modeling ; Computed tomography ; computer aided diagnosis ; Databases, Factual ; Datasets ; Diagnosis, Computer-Assisted - methods ; Diseases ; Humans ; image analysis ; Image Interpretation, Computer-Assisted ; Lung Diseases, Interstitial - diagnostic imaging ; Lungs ; Lymph nodes ; Lymph Nodes - diagnostic imaging ; machine learning ; Medical imaging ; Neural networks ; Neural Networks, Computer ; Reproducibility of Results ; Solid modeling
É parte de: IEEE transactions on medical imaging, 2016-05, Vol.35 (5), p.1285-1298
Notas: ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Descrição: Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.
Editor: United States: IEEE
Idioma: Inglês

Links

View this record in MEDLINE/PubMed

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

Shin, Hoo-Chang ; Roth, Holger R. ; Gao, Mingchen ; Lu, Le ; Xu, Ziyue ; Nogues, Isabella ; Yao, Jianhua ; Mollura, Daniel ; Summers, Ronald M.

United States: IEEE

Buscando em bases de dados remotas. Favor aguardar.