Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
- PMID: 26886976
- PMCID: PMC4890616
- DOI: 10.1109/TMI.2016.2528162
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
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.
Figures
![Fig. 1.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7176472/bin/7404017-fig-1-source.gif)
![Fig. 2.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7176472/bin/7404017-fig-2-source.gif)
![Fig. 3.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7176472/bin/7404017-fig-3-source.gif)
![Fig. 4.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7176472/bin/7404017-fig-4-source.gif)
![Fig. 5.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7176472/bin/7404017-fig-5-source.gif)
![Fig. 6.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7176472/bin/7404017-fig-6-source.gif)
![Fig. 7.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7176472/bin/7404017-fig-7-source.gif)
![Fig. 8.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7176472/bin/7404017-fig-8-source.gif)
![Fig. 9.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7176472/bin/7404017-fig-9-source.gif)
![Fig. 10.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7176472/bin/7404017-fig-10-source.gif)
![Fig. 11.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7176472/bin/7404017-fig-11-source.gif)
![Fig. 12.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7176472/bin/7404017-fig-12-source.gif)
![Fig. 13.](https://cdn.statically.io/img/www.ncbi.nlm.nih.gov/pmc/articles/instance/7176472/bin/7404017-fig-13-source.gif)
Similar articles
-
Seeking an optimal approach for Computer-aided Diagnosis of Pulmonary Embolism.Med Image Anal. 2024 Jan;91:102988. doi: 10.1016/j.media.2023.102988. Epub 2023 Oct 13. Med Image Anal. 2024. PMID: 37924750
-
MABAL: a Novel Deep-Learning Architecture for Machine-Assisted Bone Age Labeling.J Digit Imaging. 2018 Aug;31(4):513-519. doi: 10.1007/s10278-018-0053-3. J Digit Imaging. 2018. PMID: 29404850 Free PMC article.
-
A deep convolutional neural network architecture for interstitial lung disease pattern classification.Med Biol Eng Comput. 2020 Apr;58(4):725-737. doi: 10.1007/s11517-019-02111-w. Epub 2020 Jan 22. Med Biol Eng Comput. 2020. PMID: 31965407
-
Convolutional neural networks for computer-aided detection or diagnosis in medical image analysis: An overview.Math Biosci Eng. 2019 Jul 15;16(6):6536-6561. doi: 10.3934/mbe.2019326. Math Biosci Eng. 2019. PMID: 31698575 Review.
-
Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review.Artif Intell Med. 2019 Apr;95:64-81. doi: 10.1016/j.artmed.2018.08.008. Epub 2018 Sep 6. Artif Intell Med. 2019. PMID: 30195984 Review.
Cited by
-
The Role and Applications of Artificial Intelligence in the Treatment of Chronic Pain.Curr Pain Headache Rep. 2024 Jun 1. doi: 10.1007/s11916-024-01264-0. Online ahead of print. Curr Pain Headache Rep. 2024. PMID: 38822995 Review.
-
Predicting mortality after transcatheter aortic valve replacement using preprocedural CT.Sci Rep. 2024 May 31;14(1):12526. doi: 10.1038/s41598-024-63022-x. Sci Rep. 2024. PMID: 38822074 Free PMC article.
-
Development and external validation of a transfer learning-based system for the pathological diagnosis of colorectal cancer: a large emulated prospective study.Front Oncol. 2024 Apr 25;14:1365364. doi: 10.3389/fonc.2024.1365364. eCollection 2024. Front Oncol. 2024. PMID: 38725622 Free PMC article.
-
Application of convolutional neural networks in medical images: a bibliometric analysis.Quant Imaging Med Surg. 2024 May 1;14(5):3501-3518. doi: 10.21037/qims-23-1600. Epub 2024 Apr 11. Quant Imaging Med Surg. 2024. PMID: 38720828 Free PMC article.
-
Ultrasound deep learning radiomics and clinical machine learning models to predict low nuclear grade, ER, PR, and HER2 receptor status in pure ductal carcinoma in situ.Gland Surg. 2024 Apr 29;13(4):512-527. doi: 10.21037/gs-23-417. Epub 2024 Apr 11. Gland Surg. 2024. PMID: 38720675 Free PMC article.
References
-
- Deng J., et al. , “ImageNet: A large-scale hierarchical image database,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2009, pp. 248–255.
-
- Russakovsky O., et al. , “ImageNet large scale visual recognition challenge,” ArXiv:1409.0575, 2014.
-
- LeCun Y., Bottou L., Bengio Y., and Haffner P., “Gradient-based learning applied to document recognition,” Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, Nov. 1998.
-
- Krizhevsky A., Sutskever I., and Hinton G. E., “ImageNet classification with deep convolutional neural networks,” Proc. NIPS, pp. 1097–1105, 2012.
-
- Krizhevsky A., Learning multiple layers of features from tiny images, M.S. thesisDept. Comp. Sci.Univ. Toronto, Toronto, Canada: 2009.
MeSH terms
Grants and funding
LinkOut - more resources
Full Text Sources
Other Literature Sources
Miscellaneous