Contextual convolutional neural networks for lung nodule classification using Gaussian-weighted average image patches

Lee, Haeil; Lee, Hansang; Park, Min-Seok; Kim, Junmo

doi:10.1117/12.2253978

Cited by 14 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…%). According to the experimental results in Table 7, the 2D CNN-based method, proposed by Lee et al [39], only utilizes the local information of the nodule, and the final score CPM is only 54.8% which is not efficient. The methods, proposed by Roth et al [36] and Setio et al [40], feed multiple slices of different views and different angles together into the network for training, which enables the network to see more spatial information.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…In the neural network method based on 2D convolution, high-level semantic features automatically extracted by convolutional neural networks (CNN) are used to replace artificially designed features such as shape and texture features [34]- [38]. For example, in order to map 3D contextual information of lung nodules into a 2D space, Haeil et al use averaging multiple slice of candidate nodules according to the Gaussian distribution to produce a 2D image patch for training [39]. To further mine more 3D information in a 2D convolution, Setio et al designed the input to include not only the axial, coronal, and sagittal views of the lung nodules, but also six views of diagonals.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Branch Ensemble Learning Architecture Based on 3D CNN for False Positive Reduction in Lung Nodule Detection

Cao

Liu

et al. 2019

IEEE Access

View full text Add to dashboard Cite

It is critical to have accurate detection of lung nodules in CT images for the early diagnosis of lung cancer. In order to achieve this, it is necessary to reduce the false positive rate of detection. Due to the heterogeneity of lung nodules and their similarity to the background, it is difficult to distinguish true lung nodules from numerous candidate nodules. In this paper, in order to solve this challenging problem, we propose a Multi-Branch Ensemble Learning architecture based on the three-dimensional (3D) convolutional neural networks (MBEL-3D-CNN). The method combines three key ideas: 1) constructing a 3D-CNN to make the maximum utilization of spatial information of lung nodules in the 3D space; 2) embedding a multi-branch network architecture in the 3D-CNN that is well adapted to the heterogeneity of lung nodules, and; 3) using ensemble learning to effectively improve the generalization performance of the 3D-CNN model. In addition, we use offline hard mining operations to make the network capable of handling those indistinguishable positive and negative samples. The proposed method was tested on the dataset LUNA16 in our experiments. The experimental results show that MBEL-3D-CNN architecture can achieve better screening results.INDEX TERMS Computer-aided diagnosis, ensemble learning, false positive reduction, offline hard mining, 3D CNN.

show abstract

Section: Comparison With Other Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Multi-Branch Ensemble Learning Architecture Based on 3D CNN for False Positive Reduction in Lung Nodule Detection

Cao

Liu

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…To the best of our knowledge, there are two main types of methods for the automatic classification of lung nodule currently, namely, traditional methods [2]- [6] and methods of classification using convolutional neural networks and deep learning [7]- [17].…”

Section: Related Workmentioning

confidence: 99%

“…To avoid the above mentioned situation, 2D CNN methods are often used in nodules classification tasks [11]- [17], [34], [35], [41]. Among these 2D CNN methods, Li et al [14] proposed a 7-layer convolutional neural network based on AlexNet structure [18] to classify lung nodules, and Kumar et al [15] proposed a 5-layer auto-encoder to extract deep features for lung nodules classification.…”

Section: Related Workmentioning

confidence: 99%

Multi-Resolution CNN and Knowledge Transfer for Candidate Classification in Lung Nodule Detection

Wang

Zhou

et al. 2019

IEEE Access

View full text Add to dashboard Cite

The automatic lung nodule detection system can facilitate the early screening of lung cancer and timely medical interventions. However, there still exist multiple nodule candidates produced by initial rough detection in this system, and how to determine authenticity is a key problem. As this work is often challenged by the radiological heterogeneity of the computed tomography scans and the variable sizes of lung nodules, we put forward a multi-resolution convolutional neural network (CNN) to extract features of various levels and resolutions from different depth layers in the network for classification of lung nodule candidates. Through the use of knowledge transfer, the method can be divided into three steps. First, we transfer knowledge from the source CNN model which has been applied to edge detection and improve the model to a new multi-resolution model which is suitable for the image classification task. Then, the knowledge is transformed from source training progress so that all of the side-output branches in the model will be considered in the calculation. Moreover, the loss function and objective equation are improved to be imagewise calculation rather than pixel-wise. Finally, samples production and data enhancement are performed to train and test a classifier tailored for classification of lung nodule candidates. The experimental results on the LUNA16 data set show that our method gets an accuracy of 0.9733, a precision of 0.9673, and an AUC of 0.9954 while being used for lung nodule candidate classification, which is higher than the scores obtained by most of the state-of-the-art approach. In addition, when the test samples with three different sizes of 26 * 26, 36 * 36, and 48 * 48 are used to test the multi-resolution CNN, the accuracy rate of all three experiments exceed 92.81%, which demonstrates that the proposed model is insensitive to input scales. INDEX TERMS Convolutional neural network, lung nodule candidate classification, multi-resolution model, knowledge transfer.

show abstract

“…Another example is the method proposed by Lee et al to train 2D convolutional neural network by using weighted image blocks. 19 This method makes use of the spatial correlation of adjacent CT slices to conduct weighted preprocessing of samples before training a 2D network. By means of average weighting or Gaussian weighting, multiple slices are superimposed to form one slice as the input.…”

Section: Related Workmentioning

confidence: 99%

Automatic classification of lung nodule candidates based on a novel 3D convolution network and knowledge transferred from a 2D network

Wang

Zhou²,

He³

et al. 2019

Medical Physics

View full text Add to dashboard Cite

Objective In the automatic lung nodule detection system, the authenticity of a large number of nodule candidates needs to be judged, which is a classification task. However, the variable shapes and sizes of the lung nodules have posed a great challenge to the classification of candidates. To solve this problem, we propose a method for classifying nodule candidates through three‐dimensional (3D) convolution neural network (ConvNet) model which is trained by transferring knowledge from a multiresolution two‐dimensional (2D) ConvNet model. Methods In this scheme, a novel 3D ConvNet model is preweighted with the weights of the trained 2D ConvNet model, and then the 3D ConvNet model is trained with 3D image volumes. In this way, the knowledge transfer method can make 3D network easier to converge and make full use of the spatial information of nodules with different sizes and shapes to improve the classification accuracy. Results The experimental results on 551 065 pulmonary nodule candidates in the LUNA16 dataset show that our method gains a competitive average score in the false‐positive reduction track in lung nodule detection, with the sensitivities of 0.619 and 0.642 at 0.125 and 0.25 FPs per scan, respectively. Conclusions The proposed method can maintain satisfactory classification accuracy even when the false‐positive rate is extremely small in the face of nodules of different sizes and shapes. Moreover, as a transfer learning idea, the method to transfer knowledge from 2D ConvNet to 3D ConvNet is the first attempt to carry out full migration of parameters of various layers including convolution layers, full connection layers, and classifier between different dimensional models, which is more conducive to utilizing the existing 2D ConvNet resources and generalizing transfer learning schemes.

show abstract

Contextual convolutional neural networks for lung nodule classification using Gaussian-weighted average image patches

Cited by 14 publications

References 8 publications

Multi-Branch Ensemble Learning Architecture Based on 3D CNN for False Positive Reduction in Lung Nodule Detection

Multi-Branch Ensemble Learning Architecture Based on 3D CNN for False Positive Reduction in Lung Nodule Detection

Multi-Resolution CNN and Knowledge Transfer for Candidate Classification in Lung Nodule Detection

Automatic classification of lung nodule candidates based on a novel 3D convolution network and knowledge transferred from a 2D network

Contact Info

Product

Resources

About