• Corpus ID: 245334728

A Deep Learning Based Workflow for Detection of Lung Nodules With Chest Radiograph

  title={A Deep Learning Based Workflow for Detection of Lung Nodules With Chest Radiograph},
  author={Yan Tai and Yupeng Fang and Fang-Yi Su and Jung-Hsien Chiang},
MATERIALS AND METHODS: We collected CXRs from NCKUH database and VBD, an open-source medical image dataset, as our training and validation data. A number of CXRs from the Ministry of Health and Welfare(MOHW) database served as our test data. We built a segmentation model to identify lung areas from CXRs, and sliced them into 16 patches. Physicians labeled the CXRs by clicking the patches. These labeled patches were then used to train and fine-tune a deep neural network(DNN) model, classifying… 

Figures and Tables from this paper



A robust convolutional neural network for lung nodule detection in the presence of foreign bodies

The trained RetinaNet architecture was found to be only slightly prone to foreign bodies in terms of misclassifications: out of 59 additional radiographs containing foreign bodies, false-positives in two radiographs were falsely detected due to foreign body detection.

Lung nodule detection in chest X-rays using synthetic ground-truth data comparing CNN-based diagnosis to human performance.

A method to generate synthetic thorax radiographs with realistic nodules from CT scans, and a perfect ground truth knowledge is presented, which allowed for a detailed evaluation of CAD systems' and radiologists' performance due to the availability of accurate ground-truth labels for nodsules from synthetic data.

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

This paper presents UNet++, a new, more powerful architecture for medical image segmentation where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways, and argues that the optimizer would deal with an easier learning task when the feature maps from the decoder and encoder networks are semantically similar.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Learning Deep Features for Discriminative Localization

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable localization ability

Deep Residual Learning for Image Recognition

This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.

Densely Connected Convolutional Networks

The Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion, and has several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.

The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets

It is shown that the visual interpretability of ROC plots in the context of imbalanced datasets can be deceptive with respect to conclusions about the reliability of classification performance, owing to an intuitive but wrong interpretation of specificity.

Non-small-cell lung cancer

The final author version and the galley proof are versions of the publication after peer review that features the final layout of the paper including the volume, issue and page numbers.

SGDR: Stochastic Gradient Descent with Warm Restarts

This paper proposes a simple warm restart technique for stochastic gradient descent to improve its anytime performance when training deep neural networks and empirically studies its performance on the CIFAR-10 and CIFARS datasets.