Multi-scale Convolutional Neural Networks for Lung Nodule Classification

@article{Shen2015MultiscaleCN,
  title={Multi-scale Convolutional Neural Networks for Lung Nodule Classification},
  author={Wei Shen and Mu Zhou and Feng Yang and Caiyun Yang and Jie Tian},
  journal={Information processing in medical imaging : proceedings of the ... conference},
  year={2015},
  volume={24},
  pages={
          588-99
        }
}
  • Wei Shen, Mu Zhou, +2 authors Jie Tian
  • Published 28 June 2015
  • Computer Science
  • Information processing in medical imaging : proceedings of the ... conference
We investigate the problem of diagnostic lung nodule classification using thoracic Computed Tomography (CT) screening. [] Key Method In particular, to sufficiently quantify nodule characteristics, our framework utilizes multi-scale nodule patches to learn a set of class-specific features simultaneously by concatenating response neuron activations obtained at the last layer from each input scale. We evaluate the proposed method on CT images from Lung Image Database Consortium and Image Database Resource…
View on PubMed
or.nsfc.gov.cn
430 Citations
Highly Influential Citations
27
Background Citations
109
Methods Citations
116
Results Citations
5

430 Citations

Citation Type

Citation Type

Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification
Lung nodule malignancy prediction using multi-task convolutional neural network
TLDR
Experiments show that the proposed method could predict the lung nodule malignancy likelihood effectively and outperforms the state-of-the-art methods, and demonstrated the possibility of the method facilitating the radiologists for nodule staging assessment and individual therapeutic planning.
A multi-view deep convolutional neural networks for lung nodule segmentation
  • Shuo Wang, Mu Zhou, +4 authors Jie Tian
  • Computer Science
    2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
  • 2017
TLDR
It is shown that MV-CNN demonstrated encouraging performance for segmenting various type of nodules including juxta-pleural, cavitary, and non-solid nodules, achieving an average dice similarity coefficient (DSC) of 77.67% and average surface distance (ASD) of 0.24, outperforming conventional image segmentation approaches.
Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation
A Lightweight Multi-Section CNN for Lung Nodule Classification and Malignancy Estimation
TLDR
A lightweight, multiple view sampling based multi-section CNN architecture that encodes a nodule's volumetric information into a compact representation by aggregating information from its different cross sections via a view pooling layer and works directly on the cross sections generated from volume enclosing the nodule.
Multiview convolutional neural networks for lung nodule classification
TLDR
The results reveal that the deep features learned by the model proposed in this article have a higher separability than features from the image space and the multiview strategies; therefore, researchers can get better representation.
Efficient Lung Nodule Classification Using Transferable Texture Convolutional Neural Network
TLDR
This work proposed transferable texture Convolutional Neural Networks (CNN) to improve the classification performance of pulmonary nodules in CT scans, which has been evaluated on publicly available LIDC-IDRI and the LUNGx Challenge database through different evaluation matrices.
Joint learning for pulmonary nodule segmentation, attributes and malignancy prediction
TLDR
An interpretable and multi-task learning CNN — Joint learning for Pulmonary Nodule Segmentation Attributes and Malignancy Prediction (PN-SAMP), able to not only accurately predict the malignancy of lung nodules, but also provide semantic high-level attributes as well as the areas of detected nodules.
Using Multi-level Convolutional Neural Network for Classification of Lung Nodules on CT images
  • Juan Lyu, S. Ling
  • Computer Science
    2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
  • 2018
TLDR
A multi-level convolutional neural network (ML-CNN) is developed to investigate the problem of lung nodule malignancy classification and it is indicated that the model achieves the best result in ternary classification.
Lung Nodule Malignancy Classification Based ON NLSTx Data
TLDR
This paper proposes a dataset of difficult-to-diagnose lung nodules based on data from the National Lung Screening Trial (NLST), which it refers to as NLSTx, and proposes a novel deep convolutional neural network (CNN) / recurrent neural network framework that allows for use of pre-trained 2-D Convolutional feature extractors, similar to those developed in the ImageNet challenge.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 19 REFERENCES
A New 2.5D Representation for Lymph Node Detection Using Random Sets of Deep Convolutional Neural Network Observations
TLDR
This work operates a preliminary candidate generation stage, towards -100% sensitivity at the cost of high FP levels (-40 per patient), to harvest volumes of interest (VOI), and decomposes any 3D VOI by resampling 2D reformatted orthogonal views N times, via scale, random translations, and rotations with respect to the VOI centroid coordinates.
Computer-aided diagnosis of pulmonary nodules on CT scans: segmentation and classification using 3D active contours.
TLDR
Preliminary results indicate that use of the 3D AC model and the3D texture features surrounding the nodule is a promising approach to the segmentation and classification of lung nodules with CAD.
Computer-aided diagnostic scheme for distinction between benign and malignant nodules in thoracic low-dose CT by use of massive training artificial neural network
TLDR
A computer-aided diagnostic (CAD) scheme for distinction between benign and malignant nodules in LDCT scans by use of a massive training artificial neural network (MTANN) is developed, which may be useful in assisting radiologists in the diagnosis of lung nodulesIn LDCT.
A texture feature analysis for diagnosis of pulmonary nodules using LIDC-IDRI database
TLDR
This paper evaluated the performance of two-dimensional and 3D texture features from CT images on pulmonary nodules diagnosis using the large database LIDC-IDRI and found that the distinguishing results on the nodule malignancy based on the 3D Haralick texture features is noticeably more consistent with the expert observer ratings.
The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans.
TLDR
The goal of this process was to identify as completely as possible all lung nodules in each CT scan without requiring forced consensus and is expected to provide an essential medical imaging research resource to spur CAD development, validation, and dissemination in clinical practice.
3D shape analysis for early diagnosis of malignant lung nodules.
TLDR
Preliminary experiments on 327 lung nodules resulted in the 93.6% correct classification (for the 95% confidence interval), showing that the proposed method is a promising supplement to current technologies for the early diagnosis of lung cancer.
Learning Hierarchical Features for Scene Labeling
TLDR
A method that uses a multiscale convolutional network trained from raw pixels to extract dense feature vectors that encode regions of multiple sizes centered on each pixel, alleviates the need for engineered features, and produces a powerful representation that captures texture, shape, and contextual information.
ImageNet classification with deep convolutional neural networks
TLDR
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.
Deeply-Supervised Nets
TLDR
The proposed deeply-supervised nets (DSN) method simultaneously minimizes classification error while making the learning process of hidden layers direct and transparent, and extends techniques from stochastic gradient methods to analyze the algorithm.
Co-occurrence of Local Anisotropic Gradient Orientations (CoLlAGe): Distinguishing Tumor Confounders and Molecular Subtypes on MRI
TLDR
The utility of CoLIAGe in distinguishing two subtly different types of pathologies on MRI in the context of brain tumors and breast cancer is demonstrated and CoLlAGe was found to have significantly improved classification performance, as compared to the traditional texture features.
...
1
2
...