Lung nodule classification by the combination of fusion classifier and cascaded convolutional neural networks

  title={Lung nodule classification by the combination of fusion classifier and cascaded convolutional neural networks},
  author={Masaharu Sakamoto and Hiroki Nakano and Kun Zhao and Taro Sekiyama},
  journal={2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)},
Lung nodule classification is a class imbalance problem, as nodules are found with much lower frequency than non-nodules. In the class imbalance problem, conventional classifiers tend to be overwhelmed by the majority class and ignore the minority class. We showed that cascaded convolutional neural networks can classify the nodule candidates precisely for a class imbalanced nodule candidate data set in our previous study. In this paper, we propose Fusion classifier in conjunction with the… Expand
Multi-model Ensemble Learning Architecture Based on 3D CNN for Lung Nodule Malignancy Suspiciousness Classification
A multi-model ensemble learning architecture based on 3D convolutional neural network (MMEL-3DCNN) is proposed to improve the robustness of the nodule classification model and has been experimentally verified on the public dataset, LIDC-IDRI. Expand
A serialized classification method for pulmonary nodules based on lightweight cascaded convolutional neural network‐long short‐term memory
This work analysis 3D volumes as serialized 2D slices and presents a new neural network structure lightweight convolutional neural network (CNN)‐long short‐term memory (LSTM) for lung nodule classification and analyzes the feasibility of migrating this framework to mobile devices. Expand
Semi-supervised adversarial model for benign-malignant lung nodule classification on chest CT
A semi-supervised adversarial classification (SSAC) model that can be trained by using both labeled and unlabeled data for benign-malignant lung nodule classification is proposed and achieves superior performance on the benchmark LIDC-IDRI dataset. Expand
A survey of pulmonary nodule detection, segmentation and classification in computed tomography with deep learning techniques
A survey reviews some recent works on detection, segmentation and classification for pulmonary nodule in CT scans with deep learning techniques for lung cancer detection and diagnosis. Expand
Research progress of computer aided diagnosis system for pulmonary nodules in CT images.
Recent CAD techniques for pulmonary nodule detection and diagnosis in CT Images are reviewed, finding that deep learning based CAD is the mainstream of current research. Expand
An artificial-intelligence lung imaging analysis system (ALIAS) for population-based nodule computing in CT scans
An artificial-intelligence lung image analysis system (ALIAS) for nodule detection and segmentation and after segmenting the nodules, the locations, sizes, as well as imaging features are computed at the population level for studying the differences between benign and malignant nodules. Expand
Two-Stream Compare and Contrast Network for Vertebral Compression Fracture Diagnosis
This paper proposes a novel Two-Stream Compare and Contrast Network (TSCCN) which consists of two streams, a recognition stream which learns to identify VCFs through comparing and contrasting between adjacent vertebrae, and a classification stream which compares and contrasts between intra-class and inter-class to learn features for fine-grained classification. Expand


Multi-stage Neural Networks with Single-Sided Classifiers for False Positive Reduction and Its Evaluation Using Lung X-Ray CT Images
This work proposes cascaded convolutional neural networks to cope with the class imbalanced problem of lung nodule classification, and achieves the sensitivity of 92.4% and 94.5% at 4 and 8 false positives per scan in Free Receiver Operating Characteristics (FROC) curve analysis. Expand
Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks
It was showed that the proposed multi-view ConvNets is highly suited to be used for false positive reduction of a CAD system. Expand
Multilevel Contextual 3-D CNNs for False Positive Reduction in Pulmonary Nodule Detection
A novel method employing three-dimensional convolutional neural networks for false positive reduction in automated pulmonary nodule detection from volumetric computed tomography (CT) scans and a simple yet effective strategy to encode multilevel contextual information to meet the challenges coming with the large variations and hard mimics of pulmonary nodules. Expand
Mitosis Detection in Breast Cancer Histology Images via Deep Cascaded Networks
This work proposes a fast and accurate method to detect mitosis by designing a novel deep cascaded convolutional neural network, which is composed of two components: a coarse retrieval model to identify and locate the candidates of mitosis while preserving a high sensitivity and a fine discrimination model utilizing knowledge transferred from cross-domain. Expand
Joint Training of Cascaded CNN for Face Detection
It is shown that the back propagation algorithm used in training CNN can be naturally used inTraining CNN cascade, and how jointly training can be conducted on naive CNN cascade and more sophisticated region proposal network (RPN) and fast R-CNN. Expand
ImageNet classification with deep convolutional neural networks
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
A convolutional neural network cascade for face detection
This work proposes a cascade architecture built on convolutional neural networks (CNNs) with very powerful discriminative capability, while maintaining high performance, and introduces a CNN-based calibration stage after each of the detection stages in the cascade. Expand
Addressing the Class Imbalance Problem in Medical Datasets
This paper examines the performance of over-sampled and under-sampling techniques to balance cardiovascular data and proposes an improved under sampling technique that displays significant better performance than the existing methods. Expand
SMOTE: Synthetic Minority Over-sampling Technique
A combination of the method of oversampling the minority (abnormal) class and under-sampling the majority class can achieve better classifier performance (in ROC space) and a combination of these methods and the area under the Receiver Operating Characteristic curve (AUC) and the ROC convex hull strategy is evaluated. Expand
Classification of Imbalanced Data: a Review
This paper provides a review of the classification of imbalanced data regarding the application domains, the nature of the problem, the learning difficulties with standard classifier learning algorithms; the learning objectives and evaluation measures; the reported research solutions; and the class imbalance problem in the presence of multiple classes. Expand