Cited by 5,759AI in cancer detectionAdvanced Neural Network ApplicationsRadiomics and Machine Learning in Medical Imaging

The DOI matches its Crossref record; 78 of the 104 references it cites were found in a registry or an index; none of the 71 sources its claims cite is checked for support yet.

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

Open access

Shin, Hoo-Chang, Roth, Holger R., Gao, Mingchen, Lu, Le, Xu, Ziyue, Nogues, Isabella, Yao, Jianhua, Mollura, Daniel, Summers, Ronald M.·2016·IEEE Transactions on Medical Imaging

DOI 10.1109/tmi.2016.2528162PMC PMC4890616

Open this paper in CoChat — free account

Abstract

Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. 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. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.

AI snapshot

Written from the paper’s full text.

TL;DR

This paper empirically evaluates CNN architectures, dataset characteristics, and ImageNet transfer learning for two computer-aided detection tasks: thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. It reports state-of-the-art mediastinal LN detection and the first five-fold cross-validation ILD slice classification results, finding that transfer learning and end-to-end training generally outperform off-the-shelf CNN features.

Key findings

For mediastinal LN detection, GoogLeNet-RI-L achieved AUC = 0.95 and 0.85 TPR/3FP, surpassing prior results of AUC = 0.92 and 0.70 TPR/3FP [22] and 0.78 TPR/3FP [36].
Transfer learning from ImageNet consistently improved performance: GoogLeNet-TL-H versus GoogLeNet-RI-H gave 0.81 versus 0.61 TPR/3FP in mediastinum and 0.70 versus 0.48 TPR/3FP in abdomen; AlexNet-TL-H versus AlexNet-RI-H gave 0.81 versus 0.79 TPR/3FP in mediastinum and 0.69 versus 0.67 TPR/3FP in abdomen.
For ILD slice-level five-fold CV, GoogLeNet-TL reached 0.57 accuracy versus GoogLeNet-RI 0.41, and AlexNet-TL reached 0.46 versus AlexNet-RI 0.44; patch-level ILD classification was less challenging, with five deep models in the range [0.74, 0.76] and an averaged model at 0.79.
CNNs trained from scratch or fine-tuned from ImageNet consistently outperformed CNNs using only off-the-shelf CNN features in both LN and ILD problems.

Methods

The study evaluated CifarNet, AlexNet, and GoogLeNet architectures (later also OverFeat and VGGNet) on two CADe tasks: thoraco-abdominal LN detection using 388 mediastinal LNs in 90 patient CT scans and 595 abdominal LNs in 86 patient CT scans, and ILD classification using 905 annotated image slices from 120 patients with six ILD labels.
LN detection used randomly sampled 2.5D views with fields-of-view spanning 35–128 mm, rescaled to 64×64 pixels, and three-fold cross-validation with FROC AUC and TPR/3FP metrics; ILD classification used slice-level and patch-level tasks under patient-level five-fold cross-validation, with CT windowing encoded into RGB channels and data augmentation.
Training used the Caffe framework and NVidia K40 GPUs; models trained from scratch used random Gaussian initialization for 30 epochs with mini-batch size 50, while transfer learning fine-tuned all layers except the last at a learning rate 10 times smaller than default, with the last fully connected layer randomly initialized and trained at 0.01.

Limitations

The paper states that the ILD dataset is partially labeled, with very few CT slices labeled as normal or healthy, and that this is one of its main limitations; it also states that the dataset’s limited patient population of 120 patients may not adequately represent ILD disease CT lung imaging patterns.
The paper states that slice-level CNN learning is restricted to only 905 CT image slices, that no existing work has reached performance requirements for a realistic clinical setting, and that the most critical bottlenecks for ILD classification are cross-dataset learning and limited patient population size.
Evident from the reported results: ILD slice-level CV5 accuracies were low (0.41–0.57), and LOO validation produced much higher accuracies than CV5 (e.g., AlexNet-TL 0.867 versus 0.46; GoogLeNet-TL 0.902 versus 0.57), indicating sensitivity to evaluation protocol; also, for abdominal LN detection the best reported CNN result (0.70 TPR/3FP) did not surpass the prior [22] result of 0.83 TPR/3FP.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1109/tmi.2016.2528162

Cites

78 of 78 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 71 cited sources checked · 0 supported · 0 flagged

A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories.”
- Also stated in: § Introduction · plain
  “For the first time, ILD classification results under the patient-level five-fold cross-validation protocol (CV5) are investigated and reported.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Abstract
Load-bearingStrength:plain· not yet calibratedn = 120
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
None of the sources cited for this claim have been checked yet.
In the paper
“CNN training learns to ignore them by setting very small filter weights around the corresponding regions (Fig. 13).”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Datasets and Related Work > Interstitial Lung Disease Dataset
Strength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes
- Rests on an assumption: Some areas outside the lung appear in both healthy or diseased images.
In the paper
“ILD [37] is a partially labeled database; this is one of its main limitations.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Datasets and Related Work > Interstitial Lung Disease Dataset
What the sources say
- Not checked yetcites [37] Depeursinge A., “ Building a reference multimedia database for interstitial lung diseases,” Comput. Med. Imaging and. Grap., vol. 36, no. 3, pp. 227– 238, 2012. 21803548
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes

Show all 72 claims

It may state two separate claims as one. 32
Probably not a substantial claim. 28
The quote only partly states this claim. 3
Borderline: one of the tests for a substantial claim is unclear. 1

None of the sources cited for this claim have been checked yet.
In the paper
“We obtain 86% sensitivity on 3 false positives (FP) per patient, versus the prior state-of-art sensitivities of 78% [36] (stacked shallow learning) and 70% [22] (CNN), as prior state-of-the-art.”
- Also stated in: § Abstract · plain
  “We achieve the state-of-the-art performance on the mediastinal LN detection”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Introduction
What the sources say
- Not checked yetcites [36] Seff A., Lu L., Barbu A., Roth H., Shin H.-C., and Summers R. M., “ Leveraging mid-level semantic boundary cues for computer-aided lymph node detection,” Proc. MICCAI, 2015. source
- Not checked yetcites [22] Roth H., “ Improving computer-aided detection using convolutional neural networks and random view aggregation,” IEEE Trans. Med. Imag.. PMC7340334 26441412 source
Load-bearingStrength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“GoogLeNet-RI-L | 0.95 | 0.85 | 0.91 | 0.69”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Thoracoabdominal Lymph Node Detection
What the sources say
- Not checked yetcites [36] Seff A., Lu L., Barbu A., Roth H., Shin H.-C., and Summers R. M., “ Leveraging mid-level semantic boundary cues for computer-aided lymph node detection,” Proc. MICCAI, 2015. source
- Not checked yetcites [22] Roth H., “ Improving computer-aided detection using convolutional neural networks and random view aggregation,” IEEE Trans. Med. Imag.. PMC7340334 26441412 source
Load-bearingStrength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
It may state two separate claims as one. The quote only partly states this claim.
In the paper
“Patch-CV5 yields higher F-scores than [54] and classifies the extra consolidation (CD) class.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Interstitial Lung Disease Classification
What the sources say
- Not checked yetcites [54] Li Q., “ Medical image classification with convolutional neural network,” Proc. 13th Int. Conf. Control Automat. Robot. Vis., pp. 844– 848, 2014.
Load-bearingStrength:plain· not yet calibratedn = 120
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“There are currently three major techniques that successfully employ CNNs to medical image classification: 1) training the “CNN from scratch” [13]–[17]; 2) using “off-the-shelf CNN” features (without retraining the CNN) as complementary information channels to existing hand-crafted image features, for chest X-rays [10] and CT lung nodule identification [9], [12]; and 3) performing unsupervised pre-”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Introduction
What the sources say
- Not checked yetcites [13]–[17]
- Not checked yetcites [9], [12]
- Not checked yetcites [18]–[21]
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes
It may state two separate claims as one.
In the paper
“ImageNet is currently the largest image dataset among other standard datasets for visual recognition.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Methods > Imagenet: Large Scale Annotated Natural Image Dataset
What the sources say
- Not matched
  Couldn’t be matched to a paper in Crossref, so it can’t be checked.
  cites [1] Deng J., “ ImageNet: A large-scale hierarchical image database,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2009, pp. 248– 255.
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“More importantly, it also introduces a new module called “Inception”, which concatenates filters of different sizes and dimensions into a single new filter (refer to Fig. 6).”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Methods > Convolutional Neural Network Architectures
What the sources say
- Not checked yetcites [33] Szegedy C., “ Going deeper with convolutions,” in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 2015, pp. 1– 9. source
Strength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Evaluation protocols and details are critical to deriving significant empirical findings [34].”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Introduction
What the sources say
- Not checked yetcites [34] Chatfield K., Simonyan K., Vedaldi A., and Zisserman A., “ Return of the devil in the details: Delving deep into convolutional nets,” Br. Mach. Vis. Conf., 2014. source
Strength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✗ Checkable: fails✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. It may be too vague to check against evidence. The paper’s conclusions may not depend on it.
In the paper
“The AlexNet architecture was published in [4], achieved significantly improved performance over the other non-deep learning methods for ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2012.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Methods > Convolutional Neural Network Architectures
What the sources say
- Not checked yetcites [4] Krizhevsky A., Sutskever I., and Hinton G. E., “ ImageNet classification with deep convolutional neural networks,” Proc. NIPS, pp. 1097– 1105, 2012. source
Strength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“The ImageNet dataset is publicly available, and the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) has become the standard benchmark for large-scale object recognition.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Methods > Imagenet: Large Scale Annotated Natural Image Dataset
What the sources say
- Not matched
  Couldn’t be matched to a paper in Crossref, so it can’t be checked.
  cites [1] Deng J., “ ImageNet: A large-scale hierarchical image database,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2009, pp. 248– 255.
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“AlexNet can be fine-tuned on the PASCAL dataset to surpass the performance of the ImageNet pre-trained AlexNet, although the difference is not as significant as that between the CNN and non-CNN methods.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Methods > Training Protocols and Transfer Learning
What the sources say
- Not checked yetcites [6] Girshick R., Donahue J., Darrell T., and Malik J., “ Region-based convolutional networks for accurate object detection and semantic segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 38, no. 1, pp. 142– 158, Jan. 2016. 26656583 source
Strength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes
It may state two separate claims as one.
In the paper
“GoogLeNet is the current state-of-the-art CNN architecture for the ILSVRC challenge, where it achieved 5.5% top-5 classification error on the ImageNet challenge, compared to AlexNet's 15.3% top-5 classification error.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Methods > Convolutional Neural Network Architectures
What the sources say
- Not checked yetcites [33] Szegedy C., “ Going deeper with convolutions,” in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 2015, pp. 1– 9. source
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“On the other hand, the mainstream deep CNN architectures (e.g., AlexNet and GoogLeNet) contain tens of millions of free parameters to train, and thus require sufficiently large numbers of labeled medical images.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Methods > Training Protocols and Transfer Learning
Load-bearingStrength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes? Based: unclear
It may state two separate claims as one.
- Rests on an assumption: Collecting and annotating large numbers of medical images still poses significant challenges.
In the paper
“ImageNet [1] has more than 1.2 million 256×256 images categorized under 1000 object class categories.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Methods > Imagenet: Large Scale Annotated Natural Image Dataset
What the sources say
- Not matched
  Couldn’t be matched to a paper in Crossref, so it can’t be checked.
  cites [1] Deng J., “ ImageNet: A large-scale hierarchical image database,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2009, pp. 248– 255.
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“The experimental results in [40] are conducted with a patient-level hard split of 100 (training) and 20 (testing).”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Interstitial Lung Disease Classification
What the sources say
- Not checked yetcites [40] Gao M., “ Holistic classification of CT attenuation patterns for interstitial lung diseases via deep convolutional neural networks,” in Proc. MICCAI First Workshop Deep Learn. Med. Image Anal., 2015. PMC5881940 29623248
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“This difference lies in the fact that annotated lymph node segmentation masks are required to learn a mid-level semantic boundary detector [36], whereas CNN approaches only need LN locations for training [22].”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Thoracoabdominal Lymph Node Detection
What the sources say
- Not checked yetcites [36] Seff A., Lu L., Barbu A., Roth H., Shin H.-C., and Summers R. M., “ Leveraging mid-level semantic boundary cues for computer-aided lymph node detection,” Proc. MICCAI, 2015. source
- Not checked yetcites [22] Roth H., “ Improving computer-aided detection using convolutional neural networks and random view aggregation,” IEEE Trans. Med. Imag.. PMC7340334 26441412 source
Load-bearingStrength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“Both [38] and [39] use the evaluation protocol of “leave-one-patient-out” (LOO), which is arguably much easier and not directly comparable to 10-fold CV [54] or our Patch-CV5.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Interstitial Lung Disease Classification
What the sources say
- Not checked yetcites [38] Song Y., Cai W., Zhou Y., and Feng D. D., “ Feature-based image patch approximation for lung tissue classification,” IEEE Trans. Med. Imag., vol. 32, no. 4, pp. 797– 808, Apr. 2013. 23340591 source
- Not checked yetcites [39] Song Y., “ Large margin local estimate with applications to medical image classification,” IEEE Trans. Med. Imag., vol. 34, no. 6, pp. 1362– 1377, Jun. 2015. 25616009 source
- Not checked yetcites [54] Li Q., “ Medical image classification with convolutional neural network,” Proc. 13th Int. Conf. Control Automat. Robot. Vis., pp. 844– 848, 2014. source
Load-bearingStrength:hedged· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
It may state two separate claims as one.
None of the sources cited for this claim have been checked yet.
In the paper
“GoogLeNet is the state-of-the-art deep model, which has outperformed other notable models, such as AlexNet, OverFeat, and VGGNet [67], [68] in various computer vision benchmarks.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Evaluation of Five CNN Models Using ILD Classification
What the sources say
- Not checked yetcites [67] Sermanet P., “ Overfeat: Integrated recognition, localization and detection using convolutional networks,” Proc. ICLR, 2014. source
- Not checked yetcites [68] Simonyan K. and Zisserman A., “ Very deep convolutional networks for large-scale image recognition,” Proc. ICLR, 2014. source
Load-bearingStrength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
It may state two separate claims as one.
In the paper
“This image sampling scheme contributes to our best reported performance results in both mediastinal LN detection (in this paper) and automated pancreas segmentation [45].”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Thoracoabdominal Lymph Node Detection
What the sources say
- Not checked yetcites [45] Roth H., “ DeepOrgan: Multi-level deep convolutional networks for automated pancreas segmentation,” Proc. MICCAI, 2015. source
Load-bearingStrength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
It may state two separate claims as one.
In the paper
“The overall reported LN detection results are clinically significant, as indicated in [63].”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Thoracoabdominal Lymph Node Detection
What the sources say
- Not matched
  Couldn’t be matched to a paper in Crossref, so it can’t be checked.
  cites [63] Kim L., “ Performance assessment of retroperitoneal lymph node computer-assisted detection using random forest and deep convolutional neural network learning algorithms in tandem,” in 102nd Annu. Meet. Radiol. Soc. N. Am., 2014.
Strength:hedged· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“In general, patch-level ILD classification is less challenging than slice-level classification, as far more data samples can be sampled from the manually annotated ROIs (up to 100 image patches per ROI), available from [37].”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Interstitial Lung Disease Classification
What the sources say
- Not checked yetcites [37] Depeursinge A., “ Building a reference multimedia database for interstitial lung diseases,” Comput. Med. Imaging and. Grap., vol. 36, no. 3, pp. 227– 238, 2012. 21803548
Strength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes
It may state two separate claims as one.
In the paper
“Recently, Gao et al. [40] have argued that a new CADe protocol on holistic classification of ILD diseases directly, using axial CT slice attenuation patterns and CNN, may be more realistic for clinical applications.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Interstitial Lung Disease Classification
What the sources say
- Not checked yetcites [40] Gao M., “ Holistic classification of CT attenuation patterns for interstitial lung diseases via deep convolutional neural networks,” in Proc. MICCAI First Workshop Deep Learn. Med. Image Anal., 2015. PMC5881940 29623248
Strength:hedged· not yet calibratedCausal:conditional· not yet calibrated
Tests✗ Asserted: fails✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The authors may not put it forward as true. The paper’s conclusions may not depend on it.
In the paper
“OverFeat is described in [67] as an integrated framework for using CNN for classification, localization and detection.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Evaluation of Five CNN Models Using ILD Classification
What the sources say
- Not checked yetcites [67] Sermanet P., “ Overfeat: Integrated recognition, localization and detection using convolutional networks,” Proc. ICLR, 2014.
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“The main difference between our dataset preparation protocol and that from [22] is a more aggressive extraction of random views within a much larger range of FOVs.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Thoracoabdominal Lymph Node Detection
What the sources say
- Not checked yetcites [22] Roth H., “ Improving computer-aided detection using convolutional neural networks and random view aggregation,” IEEE Trans. Med. Imag.. PMC7340334 26441412
Load-bearingStrength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
Probably not a substantial claim.
In the paper
“In abdominal LN detection, [22] obtains the best trade-off between its CNN model complexity and sampled data configuration.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Thoracoabdominal Lymph Node Detection
What the sources say
- Not checked yetcites [22] Roth H., “ Improving computer-aided detection using convolutional neural networks and random view aggregation,” IEEE Trans. Med. Imag.. PMC7340334 26441412
Strength:plain· not yet calibratedCausal:correlational· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“Although the ILD [37] and LTRC datasets [64] (used in [19]) were generated and annotated separately, they contain many common disease labels. For instance, the ILD disease classes emphysema (EM), ground glass (GG), fibrosis (FB), and micronodules (MN) belong to both datasets, and thus can be jointly trained/tested to form a larger and unified dataset.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Interstitial Lung Disease Classification
What the sources say
- Not checked yetcites [37] Depeursinge A., “ Building a reference multimedia database for interstitial lung diseases,” Comput. Med. Imaging and. Grap., vol. 36, no. 3, pp. 227– 238, 2012. 21803548 source
- Not matched
  Couldn’t be matched to a paper in Crossref, so it can’t be checked.
  cites [64] Holmes III D., Bartholmai B., Karwoski R., Zavaletta V., and Robb R., “ The lung tissue research consortium: An extensive open database containing histological, clinical, and radiological data to study chronic lung disease,” in MICCAI Open Sci. Workshop, 2006.
Load-bearingStrength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
It may state two separate claims as one.
In the paper
“A segmentation label propagation method was recently proposed [47] to provide full pixel-wise labeling of the ILD data images.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Interstitial Lung Disease Classification
What the sources say
- Not checked yetcites [47] Gao M., Lu L., Nogues I., Summers M. R., and Mollura D., “ Segmentation label propagation using deep convolutional neural networks and dense conditional random field,” Proc. IEEE Int. Conf. Comput. Vis., pp. 1377– 1385, 2015. source
Strength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“Overfeat is the winning model of the ILSVRC 2013 in detection and classification tasks.”
§ Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning > Evaluations and Discussions > Evaluation of Five CNN Models Using ILD Classification
What the sources say
- Not checked yetcites [67] Sermanet P., “ Overfeat: Integrated recognition, localization and detection using convolutional networks,” Proc. ICLR, 2014.
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.

54 of 54

The paper relies on this without support.
Fine-tuning an ImageNet pre-trained CNN model on medical image datasets had not yet been exploited at the time of the study.
“However, the fine-tuning of an ImageNet pre-trained CNN model on medical image datasets has not yet been exploited.”
The paper relies on this without support.
Obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge.
“However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge.”
The paper relies on this without support.
Some areas outside the lung appear in both healthy or diseased images.
“Some areas outside of the lung appear in both healthy or diseased images.”
The paper relies on this without support.
The low-attenuation CT window is useful for visualizing certain texture patterns of lung diseases, especially emphysema.
“The low-attenuation CT window is useful for visualizing certain texture patterns of lung diseases (especially emphysema).”
The paper relies on this without support.
Collecting and annotating large numbers of medical images still poses significant challenges.
“Collecting and annotating large numbers of medical images still poses significant challenges.”
The authors state this as an assumption.
OverFeat and VGGNet may generate quantitative performance results ranked between AlexNet's and GoogLeNet's.
“Likewise, a reasonable assumption is that OverFeat and VGGNet may generate quantitative performance results ranked between AlexNet's and GoogLeNet's.”
The authors state this as an assumption.
OverFeat's and VGGNet's performance levels fall between AlexNet's and GoogLeNet's.
“The reported results validate our assumption that OverFeat's and VGGNet's performance levels fall between AlexNet's and GoogLeNet's (this observation is consistent with the computer vision findings).”
The paper relies on this without support.
Both the ILD and ImageNet datasets use full-size images.
“Indeed, both datasets use full-size images.”
The paper relies on this without support.
CifarNet is designed for images with smaller dimensions (32×32 images), and thus is not catered to classification tasks involving 256×256 images.
“CifarNet is designed for images with smaller dimensions (32×32 images), and thus is not catered to classification tasks involving 256×256 images.”
The paper relies on this without support.
Medical datasets are often biased, in that the number of healthy samples is much larger than the number of diseased instances, or that the numbers of images per class are uneven.
“Medical datasets are often “biased”, in that the number of healthy samples is much larger than the number of diseased instances, or that the numbers of images per class are uneven.”

10 of 10

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

Five-model ensemble lists only four distinct CNNs
Minor
The purported list of five CNNs includes AlexNet-RI-H twice, leaving only four distinct model names.
GoogLeNet pooling-layer counts disagree
Minor
The figure caption says GoogLeNet contains three pooling layers, while the architecture description says it has two pooling layers outside its Inception layers.
Table VIII labels its second task as both LN and ILD
Minor
The table caption calls the second task LN patch-level detection, but the corresponding column header calls it ILD-Patch.
Reported mediastinal sensitivity differs from Table II
Minor
The paper reports 86% sensitivity at three false positives per patient, but Table II's best mediastinal TPR/3FP is 0.85, or 85%.

4 of 4

Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 2×
“GoogLeNet is the state-of-the-art deep model, which has outperformed other notable models, such as AlexNet, OverFeat, and VGGNet [67], [68] in various computer vision benchmarks.”
BackgroundMethod
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 9×
“For datadriven learning, large-scale well-annotated datasets with representative data distribution characteristics are crucial to learning more accurate or generalizable models [5], [4].”
BackgroundMethodInfluential
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 4×
“datasets with representative data distribution characteristics are crucial to learning more accurate or generalizable models [5], [4]. Unlike previous image datasets used in computer vision, ImageNet [1] offers a very comprehensive database of more than 1.2 million categorized natural images of 1000+ classes. The CNN…”
BackgroundMethodInfluential
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 2×
“achieved signiﬁcantly improved performance over the other non-deep learning methods for ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2012. This success has revived the interest in CNNs [3] in computer vision. ImageNet consists of 1.2 million 256 256 images belonging to 1000 categories. At times, the obje…”
BackgroundInfluential
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 2×
“Although natural images and medical images differ significantly, conventional image descriptors developed for object recognition in natural images, such as the scale-invariant feature transform (SIFT) [30] and the histogram of oriented gradients (HOG) [31], have been widely used for object detection and segmentation i…”
Background
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · cited 9×
“AlexNet [4] and GoogLeNet [33] are also modified to evaluate these state-of-the-art CNN architecture from ImageNet classification task [2] to our CADe problems and datasets.”
BackgroundMethodInfluential
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834 · cited 1×
“However, current FCNN approaches [65], [66] lack adequate spatial resolution in their directly output label space.”
Background
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,889

Flagged first, then by citations

Show all 104 references

26 of the 104 references couldn’t be matched to a known paper.

Research works printed but not linked: 3

seff, 2015, Leveraging mid-level semantic boundary cues for computer-aided lymph node detection, Proc MICCAI
kim, 2014, Performance assessment of retroperitoneal lymph node computer-assisted detection using random forest and deep convolutional neural network learning algorithms in tandem, 102nd Annu Meet Radiol Soc N Am
sermanet, 2014, Overfeat: Integrated recognition, localization and detection using convolutional networks, Proc ICLR

Sorted by citations

Items 1,001–1,020 of 1,020

A Deep Learning Network for Right Ventricle Segmentation in Short:Axis MRI
Luo, G., An, R., Wang, K., Dong, S., & Zhang, H. (2016) · Computing in cardiology · doi:10.22489/cinc.2016.139-406 · Cited by 62
Pulmonary nodule classification in lung cancer screening with three-dimensional convolutional neural networks
Liu, S., Xie, Y., Jirapatnakul, A. C., & Reeves, A. P. (2017) · Journal of medical imaging · doi:10.1117/1.jmi.4.4.041308 · Cited by 63
Uncertainty-aware organ classification for surgical data science applications in laparoscopy
Moccia, S., Wirkert, S. J., Kenngott, H., Vemuri, A. S., Apitz, M., Mayer, B., De Momi, E., Mattos, L. S., & Maier-Hein, L. (2018) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2018.2813015 · Cited by 56
A binocular image fusion approach for minimizing false positives in handgun detection with deep learning
Olmos, R., Tabik, S., Lamas, A., Pérez-Hernández, F., & Herrera, F. (2019) · Information Fusion · doi:10.1016/j.inffus.2018.11.015 · Cited by 57
Face Recognition Based on Deep Learning and FPGA for Ethnicity Identification
AlBdairi, A. J. A., Xiao, Z., Alkhayyat, A., Humaidi, A. J., Fadhel, M. A., Taher, B. H., Alzubaidi, L., Santamaría, J., & Al-Shamma, O. (2022) · Applied Sciences · doi:10.3390/app12052605 · Cited by 54
Learning hidden patterns from patient multivariate time series data using convolutional neural networks: A case study of healthcare cost prediction
Morid, M. A., Sheng, O. R. L., Kawamoto, K., & Abdelrahman, S. (2020) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2020.103565 · Cited by 49
Self-supervised transfer learning of physiological representations from free-living wearable data
Spathis, D., Perez-Pozuelo, I., Brage, S., Wareham, N. J., & Mascolo, C. (2021) · Proceedings of the Conference on Health, Inference, and Learning · doi:10.1145/3450439.3451863 · Cited by 40
An electrocardiogram-based AI algorithm for early detection of pulmonary hypertension
DuBrock, H. M., Wagner, T. E., Carlson, K., Carpenter, C. L., Awasthi, S., Attia, Z. I., Frantz, R. P., Friedman, P. A., Kapa, S., Annis, J., et al. (2024) · European Respiratory Journal · doi:10.1183/13993003.00192-2024 · Cited by 38
Toward point-of-care ultrasound estimation of fetal gestational age from the trans-cerebellar diameter using CNN-based ultrasound image analysis
Maraci, M. A., Yaqub, M., Craik, R., Beriwal, S., Self, A., von Dadelszen, P., Papageorghiou, A., & Noble, J. A. (2020) · Journal of medical imaging · doi:10.1117/1.jmi.7.1.014501 · Cited by 36
Deep reinforcement learning and its applications in medical imaging and radiation therapy: a survey
Xu, L., Zhu, S., & Wen, N. (2022) · Physics in Medicine & Biology · doi:10.1088/1361-6560/ac9cb3 · Cited by 35
Evolutionary Programming Based Deep Learning Feature Selection and Network Construction for Visual Data Classification
Tian, H., Chen, S.-C., & Shyu, M.-L. (2020) · Information Systems Frontiers · doi:10.1007/s10796-020-10023-6 · Cited by 34
Advances in Machine Learning Approaches to Heart Failure with Preserved Ejection Fraction
Ahmad, F. S., Luo, Y., Wehbe, R. M., Thomas, J. D., & Shah, S. J. (2022) · Heart Failure Clinics · doi:10.1016/j.hfc.2021.12.002 · Cited by 34
A Pseudo-Siamese Feature Fusion Generative Adversarial Network for Synthesizing High-Quality Fetal Four-Chamber Views
Qiao, S., Pan, S., Luo, G., Pang, S., Chen, T., Singh, A. K., & Lv, Z. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3143319 · Cited by 32
Transfer learning from RF to B-mode temporal enhanced ultrasound features for prostate cancer detection
Azizi, S., Mousavi, P., Yan, P., Tahmasebi, A., Kwak, J. T., Xu, S., Turkbey, B., Choyke, P., Pinto, P., Wood, B., et al. (2017) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-017-1573-x · Cited by 30
Pre-training in Medical Data: A Survey
Qiu, Y., Lin, F., Chen, W., & Xu, M. (2023) · Machine Intelligence Research · doi:10.1007/s11633-022-1382-8 · Cited by 30
Boosting Convolutional Neural Networks Performance Based on FPGA Accelerator
Al-Shamma, O., Fadhel, M. A., Hameed, R. A., Alzubaidi, L., & Zhang, J. (2020) · Advances in Intelligent Systems and Computing · doi:10.1007/978-3-030-16657-1_47 · Cited by 27
TN‐USMA Net: Triple normalization‐based gastrointestinal stromal tumors classification on multicenter EUS images with ultrasound‐specific pretraining and meta attention
Liu, C., Qiao, M., Jiang, F., Guo, Y., Jin, Z., & Wang, Y. (2021) · Medical Physics · doi:10.1002/mp.15172 · Cited by 22
AI Detection of Glottic Neoplasm Using Voice Signals, Demographics, and Structured Medical Records
Wang, C., Chen, T., Lee, N., & Fang, S. (2024) · The Laryngoscope · doi:10.1002/lary.31563 · Cited by 13
Automated segmentation of insect anatomy from micro‐CT images using deep learning
Toulkeridou, E., Gutierrez, C. E., Baum, D., Doya, K., & Economo, E. P. (2023) · Natural Sciences · doi:10.1002/ntls.20230010 · Cited by 13
Artificial intelligence and deep learning in ophthalmology
Ting, D. S. W., Pasquale, L. R., Peng, L., Campbell, J. P., Lee, A. Y., Raman, R., Tan, G. S. W., Schmetterer, L., Keane, P. A., & Wong, T. Y. (2019) · British Journal of Ophthalmology · doi:10.1136/bjophthalmol-2018-313173 · Cited by 1,554

Authors: Shin, H.-C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., & Summers, R. M.
Affiliations: National Institutes of Health (US)
Corresponding author: Shin, Hoo-Chang
ORCID: Roth, Holger R.
Gao, Mingchen
Xu, Ziyue
Yao, Jianhua
Mollura, Daniel
Summers, Ronald M.
Venue: IEEE Transactions on Medical Imaging
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Published: 2016-05
Volume: 35
Issue: 5
Pages: 1285-1298
ISSN: 0278-0062 (ISSN-L)
1558-254X
DOI: 10.1109/tmi.2016.2528162
PMC: PMC4890616
OpenAlex: W2253429366
Cited by: 5,759
References: 104
Citations by year: 2026: 279 · 2025: 480 · 2024: 572 · 2023: 614 · 2022: 725 · 2021: 872 · 2020: 808 · 2019: 712 · 2018: 426 · 2017: 223 · 2016: 44
FWCI: 385.74
Type: journal article
Language: en
Open access: green
www.ncbi.nlm.nih.gov
Licence: cc-by
ieeexplore.ieee.org/Xplorehelp/downloads/license-information/USG.html (vor)
Locations: IEEE Transactions on Medical Imaging (publishedVersion)
PubMed Central (publishedVersion, cc-by)
PubMed (publishedVersion)
arXiv (Cornell University) (submittedVersion)
arXiv (Cornell University)
Funders: National Institutes of Health
NIH Clinical Center (Z01CL040004)
Topics: Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
Keywords: computer-aided detection, deep convolutional neural networks, transfer learning, CNN architecture comparison, medical image classification, ImageNet pre-training, fine-tuning, lymph node detection, interstitial lung disease classification, computed tomography
MeSH terms: Diagnosis, Computer-Assisted, Humans, Image Interpretation, Computer-Assisted, Lymph Nodes, Reproducibility of Results, Databases, Factual, Neural Networks, Computer, Lung Diseases, Interstitial

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

A language model drew the claims from the paper on 2026-10-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-09 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

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

Abstract

Overview

AI snapshot

TL;DR

Key findings

Methods

Limitations

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Self-check

Citations

Cites

Cited by

Related

Metadata

Record

About these checks