Multi-scale Convolutional Neural Networks for Lung Nodule Classification

By Wei Shen, Mu Zhou, Feng Yang, Caiyun Yang, Jie Tian. Information Processing in Medical Imaging, 2015

617 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Pulmonary and Respiratory Medicine, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/fb815f5d5cee6cd88513f8526a61ad3989b24e91

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Le Lu
2. B. van Ginneken
3. Xiaohui S. Xie
4. Wentao Zhu
5. Francesco Ciompi
6. Ronald M. Summers
7. Lin F. Yang
8. J. A. van der Laak

In Pulmonary and Respiratory Medicine

1. B. van Ginneken
2. Ronald M. Summers
3. Le Lu
4. Weidong (Tom) Cai
5. Dinggang Shen
6. Gustavo Carneiro
7. D. Feng
8. Xiaohui S. Xie

In Radiology, Nuclear Medicine and Imaging

1. B. van Ginneken
2. Ronald M. Summers
3. Le Lu
4. Dinggang Shen
5. Xiaohui S. Xie
6. Wentao Zhu
7. Holger R. Roth
8. Francesco Ciompi

Citations in the corpus

• Deep Feature Learning for Medical Image Analysis with Convolutional Autoencoder Neural Network (2017, background): “In [7] [22] [23], and evolved convolution networks are proposed to classify the lung nodules through supervised feature learning from medical images.”
• Fifty years of computer analysis in chest imaging: rule-based, machine learning, deep learning (2017, background): “Of course, a step further would be to forget about a model based on a small set of classical features and use deep learning directly to estimate the probability of malignancy, such as was done, e.g., by Shen et al. [60].”
• Deep Learning Applications in Medical Image Analysis (2018, methodology): “[50] used CNNs combined with Support Vector Machine (SVM) and Random Forest (RF) classifiers to classify lung nodules into benign or malignant, based on 1010 labelled CT lung scans from the Lung Image Database Consortium (LIDC-IDRI) dataset.”
• Deep learning and medical image processing for coronavirus (COVID-19) pandemic: A survey (2020, positive): “In Shen, Zhou, Yang, Yang, and Tian (2015), the author ’ s used multi-scale DL approaches to identify lung nodules in CT images.”
• Detecting Cardiovascular Disease from Mammograms with Deep Learning (2017, positive): “For example, in [39] a deep learning architecture was applied to each pixel to address problems of membrane segmentation in electron microscopy images; in [40] a deep convolutional neural network (CNN) was used as the 2nd tier in a twotiered, coarse-to-fine cascade framework, to refine the candidate”
• Deep Learning in Medical Image Analysis (2017, methodology): “To this end, research groups have devised various strategies, such as (i) to take image patches either 2D or 3D as input (25, 35, 36, 37, 38, 39, 40, 41), rather than the full-sized images, to reduce the input dimensionality, thus the number of model parameters; (ii) to expand their dataset by…”
• Secure and Robust Machine Learning for Healthcare: A Survey (2020, methodology): “In another study, a CNN model is trained for the classification of lung nodules [4].”
• Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology (2017, methodology): “84% accuracy on classification with automatic nodule detection and segmentation [43].”
• Deep Learning and Convolutional Neural Networks for Medical Image Computing (2017, methodology): “Alternatively, instead of sampling a 3D patch, we can sample on three orthogonal planes [15] or even a 2D patch with a random”
• Using Deep Learning for Classification of Lung Nodules on Computed Tomography Images (2017, methodology): “[11] diagnosed lung cancer on the LIDC database using a multiscale two-layer CNN and the reported accuracy was 86.”
• Knowledge-based Collaborative Deep Learning for Benign-Malignant Lung Nodule Classification on Chest CT (2019, background): “[59] proposed a multi-scale CNN that captures lung nodule heterogeneity via extracting discriminative features from alternatingly stacked layers.”
• A survey on deep learning in medical image analysis (2017, methodology): “Shen et al. (2015b) used three CNNs, each of which takes a nodule patch at a di ff erent scale as input.”
• Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation (2017, positive): “The multi-scale patch strategy enables the model to learn multi-scale features without involving multiple networks (Shen et al., 2015) (Section 2.1.2).”