Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

@article{Shin2016DeepCN,
  title={Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning},
  author={Hoo-Chang Shin and Holger R. Roth and Mingchen Gao and Le Lu and Ziyue Xu and Isabella Nogues and Jianhua Yao and Daniel J. Mollura and Ronald M. Summers},
  journal={IEEE Transactions on Medical Imaging},
  year={2016},
  volume={35},
  pages={1285-1298}
}
Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs. [...] Key Method There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning.Expand
Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation
TLDR
This paper proposes a novel deep neural network architecture based on transfer learning for microscopic image classification that produces significant performance gains comparing to the neural network structure that uses only features extracted from single CNN and several traditional classification methods. Expand
Convolutional neural networks based transfer learning for diabetic retinopathy fundus image classification
TLDR
Experimental results show that convolutional neural networks based transfer learning can achieve better classification results in the authors' task with small datasets, by taking advantage of knowledge learned from other related tasks with larger datasets (source domain). Expand
On Evaluating CNN Representations for Low Resource Medical Image Classification
TLDR
Not only is the superiority of the CNN based transfer learning approach against an assembly of knowledge driven features demonstrated, but the proposed metric also carries an 87% correlation with the test set performances as obtained using various CNN representations. Expand
DeTrac: Transfer Learning of Class Decomposed Medical Images in Convolutional Neural Networks
TLDR
The paper presents Decompose, Transfer, and Compose (DeTraC) approach, a novel CNN architecture based on class decomposition to improve the performance of medical image classification using transfer learning andclass decomposition approach. Expand
Convolutional neural networks for histopathology image classification: Training vs. Using pre-trained networks
TLDR
The result shows that pre-trained networks are quite competitive against training from scratch, and fine-tuning does not seem to add any tangible improvement for VGG16 to justify additional training. Expand
A survey of the recent architectures of deep convolutional neural networks
TLDR
This survey focuses on the intrinsic taxonomy present in the recently reported deep CNN architectures and classifies the recent innovations in CNN architectures into seven different categories, based on spatial exploitation, depth, multi-path, width, feature-map exploitation, channel boosting, and attention. Expand
Hierarchical Transfer Convolutional Neural Networks for Image Classification
TLDR
A novel hierarchical transfer CNN framework is proposed, which consists of a group of shallow CNNs and a cloud CNN, which will boost the generalization performance of the cloud CNN significantly, especially during the early stage of training. Expand
Unsupervised Domain Adaptation to Classify Medical Images Using Zero-Bias Convolutional Auto-Encoders and Context-Based Feature Augmentation
TLDR
This work uses a new hierarchical unsupervised feature extractor that constrains the transformation of generic features from a pre-trained CNN to non-redundant and locally relevant features for the medical image data and proposes a context-based feature augmentation scheme to improve the discriminative power of the feature representation. Expand
Transfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data
TLDR
This work proposes a transfer learning based method, making knowledge learned from sufficient unlabeled SAR scene images transferrable to labeled SAR target data, and designs an assembled CNN architecture consisting of a classification pathway and a reconstruction pathway, together with a feedback bypass additionally. Expand
Deep convolutional neural networks with transfer learning for automated brain image classification
TLDR
The prime objective of the present work is to explore the capability of different pre-trained DCNN models with transfer learning for pathological brain image classification and proposes a more generic method that can achieve an accuracy value of 100%, 94%, and 95.92% for three datasets. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 86 REFERENCES
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
TLDR
This work designs a method to reuse layers trained on the ImageNet dataset to compute mid-level image representation for images in the PASCAL VOC dataset, and shows that despite differences in image statistics and tasks in the two datasets, the transferred representation leads to significantly improved results for object and action classification. Expand
Off-the-shelf convolutional neural network features for pulmonary nodule detection in computed tomography scans
TLDR
This work uses the features from one such network, OverFeat, trained for object detection in natural images, for nodule detection in computed tomography scans and concludes that CNN features have great potential to be used for detection tasks in volumetric medical data. Expand
Chest pathology detection using deep learning with non-medical training
TLDR
This first-of-its-kind experiment shows that Deep learning with ImageNet, a large scale non-medical image database may be a good substitute to domain specific representations, which are yet to be available, for general medical image recognition tasks. Expand
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. Expand
Region-Based Convolutional Networks for Accurate Object Detection and Segmentation
TLDR
A simple and scalable detection algorithm that improves mean average precision (mAP) by more than 50 percent relative to the previous best result on VOC 2012-achieving a mAP of 62.4 percent. Expand
Unregistered Multiview Mammogram Analysis with Pre-trained Deep Learning Models
TLDR
This work trains a separate CNN model for each view and each segmentation map using an Imagenet pre-trained model, which estimates the patient’s risk of developing breast cancer using the Breast Imaging-Reporting and Data System (BI-RADS) score. Expand
Segmentation label propagation using deep convolutional neural networks and dense conditional random field
TLDR
A segmentation based label propagation method to a publicly available dataset on interstitial lung disease to address the missing annotation challenge and combines the cues from the initial annotations, deep convolutional neural networks and a dense fully-connected Conditional Random Field that achieves high quantitative accuracy levels. Expand
Learning Deep Features for Scene Recognition using Places Database
TLDR
A new scene-centric database called Places with over 7 million labeled pictures of scenes is introduced with new methods to compare the density and diversity of image datasets and it is shown that Places is as dense as other scene datasets and has more diversity. Expand
Analyzing the Performance of Multilayer Neural Networks for Object Recognition
TLDR
This paper experimentally probes several aspects of CNN feature learning in an attempt to help practitioners gain useful, evidence-backed intuitions about how to apply CNNs to computer vision problems. Expand
Return of the Devil in the Details: Delving Deep into Convolutional Nets
TLDR
It is shown that the data augmentation techniques commonly applied to CNN-based methods can also be applied to shallow methods, and result in an analogous performance boost, and it is identified that the dimensionality of the CNN output layer can be reduced significantly without having an adverse effect on performance. Expand
...
1
2
3
4
5
...