CoChat
Sign Up
Cited by 755AI in cancer detectionRadiomics and Machine Learning in Medical ImagingMedical Image Segmentation Techniques

The DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.

Computer-Aided Diagnosis with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans

Open access
Cheng, Jie-Zhi, Ni, Dong, Chou, Yi-Hong, Qin, Jing, Tiu, Chui-Mei, Chang, Yeun-Chung, Huang, Chiun-Sheng, Shen, Dinggang, Chen, Chung-Ming·2016·Scientific Reports
DOI 10.1038/srep24454PMC PMC4832199
Open this paper in CoChat — free accountOpen PDF

Abstract

This paper performs a comprehensive study on the deep-learning-based computer-aided diagnosis (CADx) for the differential diagnosis of benign and malignant nodules/lesions by avoiding the potential errors caused by inaccurate image processing results (e.g., boundary segmentation), as well as the classification bias resulting from a less robust feature set, as involved in most conventional CADx algorithms. Specifically, the stacked denoising auto-encoder (SDAE) is exploited on the two CADx applications for the differentiation of breast ultrasound lesions and lung CT nodules. The SDAE architecture is well equipped with the automatic feature exploration mechanism and noise tolerance advantage, and hence may be suitable to deal with the intrinsically noisy property of medical image data from various imaging modalities. To show the outperformance of SDAE-based CADx over the conventional scheme, two latest conventional CADx algorithms are implemented for comparison. 10 times of 10-fold cross-validations are conducted to illustrate the efficacy of the SDAE-based CADx algorithm. The experimental results show the significant performance boost by the SDAE-based CADx algorithm over the two conventional methods, suggesting that deep learning techniques can potentially change the design paradigm of the CADx systems without the need of explicit design and selection of problem-oriented features.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/srep24454

Cites

48 of 48 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Exhibition of breast lesions and lung nodules in US and CT images.
Figure 1 Exhibition of breast lesions and lung nodules in US and CT images.CC BY · PubMed Central
Figure 2 Examples of constructed patterns in the first and second hidden layers at the pre-training step: (a,b) patterns of the first and second hidden layers for pulmonary nodules; (c,d) patterns of the first and second hidden layers for breast lesions. SDAE architecture with two hidden layers is used in this study for the differentiation of pulmonary nodules and breast lesions. It is worth noting that the patterns of the second hidden layers are constructed as the weighted sums from all patterns in the first layer. In the reconstruction, the first layer neurons are simply all assumed activated. The neuron activation can be more complicated with the feed-in of real image data. In (b,d) the example patterns enclosed by the yellow rectangles hold the positive weightings to the RN nodule and benignant lesion classes in the supervised training step, whereas the patterns in blue regions are connected to the RM nodule and malignant lesion classes with positive weightings. It can be observed from (b,d) that the second hidden layer patterns appear fuzzier due to the effect of weighted sum. All patterns are normalized for clearer presentation.
Figure 2 Examples of constructed patterns in the first and second hidden layers at the pre-training step: (a,b) patterns of the first and second hidden layers for pulmonary nodules; (c,d) patterns of the first and second hidden layers for breast lesions. SDAE architecture with two hidden layers is used in this study for the differentiation of pulmonary nodules and breast lesions. It is worth noting that the patterns of the second hidden layers are constructed as the weighted sums from all patterns in the first layer. In the reconstruction, the first layer neurons are simply all assumed activated. The neuron activation can be more complicated with the feed-in of real image data. In (b,d) the example patterns enclosed by the yellow rectangles hold the positive weightings to the RN nodule and benignant lesion classes in the supervised training step, whereas the patterns in blue regions are connected to the RM nodule and malignant lesion classes with positive weightings. It can be observed from (b,d) that the second hidden layer patterns appear fuzzier due to the effect of weighted sum. All patterns are normalized for clearer presentation.CC BY · PubMed Central
Figure 3 ACC Bland and Altman plots for six algorithm comparing pairs of “SDAE-CURVE”, “SDAE-RANK” , “SDAE-MORPH”, “CURVE-RANK”, “CURVE-MORPH”, and “RANK-MORPH” on the lung CT dataset. The comparing pairs with ending tag “ALL” are the results with the strategy of using all member slices of a nodule for the training and testing of the three algorithms. The pairs with tag “SINGLE” compare the computerized results with the slice selection strategy of using middle slice.
Figure 3 ACC Bland and Altman plots for six algorithm comparing pairs of “SDAE-CURVE”, “SDAE-RANK” , “SDAE-MORPH”, “CURVE-RANK”, “CURVE-MORPH”, and “RANK-MORPH” on the lung CT dataset. The comparing pairs with ending tag “ALL” are the results with the strategy of using all member slices of a nodule for the training and testing of the three algorithms. The pairs with tag “SINGLE” compare the computerized results with the slice selection strategy of using middle slice.CC BY · PubMed Central
Figure 4 ACC Bland and Altman plots for performance comparison of the pairs “SDAE-CURVE”, “SDAE-RANK”, “SDAE-MORPH”, “CURVE-RANK”, “CURVE-MORPH”, and “RANK-MORPH” on the breast dataset.
Figure 4 ACC Bland and Altman plots for performance comparison of the pairs “SDAE-CURVE”, “SDAE-RANK”, “SDAE-MORPH”, “CURVE-RANK”, “CURVE-MORPH”, and “RANK-MORPH” on the breast dataset.CC BY · PubMed Central
Figure 5 Box plots for performance for the lung and breast datasets with respect to the ACC and AUC metrics.
Figure 5 Box plots for performance for the lung and breast datasets with respect to the ACC and AUC metrics.CC BY · PubMed Central
Figure 6 Flow-chart of our deep-learning-based CADx training framework. The pixels of resized ROIs are fed into the network architecture at the pre-training step. The pre-trained network is then refined with the supervised training by adding three neurons carrying aspect ratio of the original ROI and also the resizing factors at the input layer. The final identification result can be made with the softmax classification.
Figure 6 Flow-chart of our deep-learning-based CADx training framework. The pixels of resized ROIs are fed into the network architecture at the pre-training step. The pre-trained network is then refined with the supervised training by adding three neurons carrying aspect ratio of the original ROI and also the resizing factors at the input layer. The final identification result can be made with the softmax classification.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 1

  1. Vezhnevets, V. & Konouchine, V. GrowCut: Interactive multi-label ND image segmentation by cellular automata. Proc. of Graphicon. 1, 150–156 (2005).

Cited by

Sorted by citations

  • A survey on deep learning in medical image analysis

    Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332

    “Janowczyk et al. (2016a) used SAEs to normalize H&E-stained histopathology images whereas Benou et al. (2016) used CNNs to perform de-noising in DCE-MRI time-series.”
    BackgroundMethodInfluential

  • A guide to deep learning in healthcare

    Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., & Dean, J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0316-z · Cited by 5,312

    “Many studies have demonstrated promising results in complex diagnostics spanning dermatology 9,10 , radiology 11–14 , ophthalmology 15–17 , and pathology 18–21 (Fig.”
    Background

  • Deep learning in medical image analysis

    Shen, D., Wu, G., & Suk, H.-I. (2017) · Annual Review of Biomedical Engineering · doi:10.1146/annurev-bioeng-071516-044442 · Cited by 4,968

    “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…”
    Method

  • Artificial intelligence in radiology

    Hosny, A., Parmar, C., Quackenbush, J., Schwartz, L. H., & Aerts, H. J. W. L. (2018) · Nature Reviews Cancer · doi:10.1038/s41568-018-0016-5 · Cited by 3,803

    “Such performance gain is assessed using multiple metrics, including the area under receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity, to name a few 35 .”

  • Deep learning for healthcare: review, opportunities and challenges

    Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018) · Briefings in Bioinformatics · doi:10.1093/bib/bbx044 · Cited by 3,076

See all 755

Related

See all

Metadata

Authors
Cheng, J.-Z., Ni, D., Chou, Y.-H., Qin, J., Tiu, C.-M., Chang, Y.-C., Huang, C.-S., Shen, D., & Chen, C.-M.
Affiliations
  • Shenzhen University (CN)
  • Taipei Veterans General Hospital (TW)
  • National Taiwan University (TW)
  • University of North Carolina at Chapel Hill (US)
Corresponding author
  • Chou, Yi-Hong
  • Shen, Dinggang
  • Chen, Chung-Ming
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2016-04-15
Volume
6
Issue
1
Pages
24454-24454
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/srep24454
PMC
PMC4832199
OpenAlex
W2341106171
Cited by
755
References
48
Citations by year
2026: 9 · 2025: 32 · 2024: 78 · 2023: 59 · 2022: 100 · 2021: 120 · 2020: 103 · 2019: 110 · 2018: 87 · 2017: 45 · 2016: 11
FWCI
68.59
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Carolina Digital Repository (University of North Carolina at Chapel Hill) (submittedVersion)
  • UNC Libraries
Funders
  • National Science Council (NSC 100)
  • Shenzhen Fundamental Research Program (JCYJ20130329105033277, JCYJ20150525092940982, 81571758, JCYJ20140509172609164, JSE201109150013A)
  • National Cancer Institute (R01CA206100)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
Keywords
computer-aided diagnosis, stacked denoising autoencoder, pulmonary nodules, benign versus malignant differentiation, medical image denoising, feature extraction, noise immunity, differential diagnosis
MeSH terms
Machine Learning, Algorithms, Breast, Solitary Pulmonary Nodule, Diagnosis, Computer-Assisted, Female, Humans, Tomography, X-Ray Computed, Ultrasonography, Reproducibility of Results, Datasets as Topic

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.

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