Deep Learning for Breast Cancer Diagnosis from Mammograms—A Comparative Study
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Deep convolutional neural networks (CNNs) are investigated in the context of computer-aided diagnosis (CADx) of breast cancer. State-of-the-art CNNs are trained and evaluated on two mammographic datasets, consisting of ROIs depicting benign or malignant mass lesions. The performance evaluation of each examined network is addressed in two training scenarios: the first involves initializing the network with pre-trained weights, while for the second the networks are initialized in a random fashion. Extensive experimental results show the superior performance achieved in the case of fine-tuning a pretrained network compared to training from scratch.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“The implementation of a “residual block”, as described in [19], is straightforward: for every few convolutional layers a “shortcut connection” is added that runs parallel to these layers and implements the identity mapping.”
BackgroundVery 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 1×
“In [16] authors investigated the effect of network depth while keeping the convolution filters very small.”
BackgroundImageNet 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 11×
“AlexNet AlexNet [9] was the first convolutional neural network (CNN) that exhibited performance beyond the state-of-the-art in the task of object detection and classification.”
BackgroundMethodInfluentialImageNet: 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 1×
“For the fine-tuning experiments the networks were initialized with the pre-trained weights from the ImageNet dataset [25].”
MethodGoing 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
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 · cited 1×
“This coincides with the results reported in ILSVCR competition [27] as well.”
ResultBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 2×
“In subsequent publications [18], a revised version of the Inception module have been proposed, along with slightly modified network architectures.”
BackgroundMethodBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
(2010) · Cited by 14,134
Siegel, R. L., Miller, K. D., & Jemal, A. (2015) · CA: A Cancer Journal for Clinicians · doi:10.3322/caac.21254 · Cited by 11,853 · cited 1×
“Recent studies have shown that breast cancer is the most common type of cancer among women [1], accounting for about one third of newly diagnosed cancers in the US [2].”
BackgroundImproving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382 · cited 1×
“A particularly important aspect of training was the use of dropout [15] (with probability of 0.”
BackgroundOeffinger, K. C., Fontham, E. T. H., Etzioni, R., Herzig, A., Michaelson, J. S., Shih, Y.-C. T., Walter, L. C., Church, T. R., Flowers, C. R., LaMonte, S. J., et al. (2015) · JAMA · doi:10.1001/jama.2015.12783 · Cited by 1,653
One weird trick for parallelizing convolutional neural networks
Krizhevsky, A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1404.5997 · Cited by 919 · cited 1×
“While LRN was adopted and incorporated into various other network architectures, it was removed from AlexNet in a subsequent publication [14].”
MethodA curated mammography data set for use in computer-aided detection and diagnosis research
Lee, R. S., Gimenez, F., Hoogi, A., Miyake, K. K., Gorovoy, M., & Rubin, D. L. (2017) · Scientific Data · doi:10.1038/sdata.2017.177 · Cited by 859 · cited 1×
“The Curated Breast Imaging Subset of DDSM (CBIS-DDSM) [23] is an updated and standardized version of DDSM.”
MethodCurrent Status of the Digital Database for Screening Mammography
Heath, M., Bowyer, K., Kopans, D., Kegelmeyer, P., Moore, R., Chang, K., & Munishkumaran, S. (1998) · Computational Imaging and Vision · doi:10.1007/978-94-011-5318-8_75 · Cited by 787 · cited 1×
“This dataset consists of 400 mass ROIs extracted from the Digital Database for Screening Mammography (DDSM) [20] that was developed and used in our previous work [21].”
MethodHuynh, B. Q., Li, H., & Giger, M. L. (2016) · Journal of Medical Imaging · doi:10.1117/1.jmi.3.3.034501 · Cited by 539
Arevalo, J., González, F. A., Ramos-Pollán, R., Oliveira, J. L., & Guevara Lopez, M. A. (2016) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2015.12.014 · Cited by 476 · cited 1×
“[6] tested various CNNs and compared them with two hand-crafted descriptors for the task of mass diagnosis.”
MethodConvolutional neural network improvement for breast cancer classification
Ting, F. F., Tan, Y. J., & Sim, K. S. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.11.008 · Cited by 449 · cited 1×
“[12] created and trained from scratch their network for breast mass classification.”
BackgroundBenign and malignant breast tumors classification based on region growing and CNN segmentation
Rouhi, R., Shahbazzadeh, M. J., Kasaei, S., & Keshavarzian, P. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2014.09.020 · Cited by 431
Hubbard, R. A., Kerlikowske, K., Flowers, C. I., Yankaskas, B. C., Zhu, W., & Miglioretti, D. L. (2011) · Annals of Internal Medicine · doi:10.7326/0003-4819-155-8-201110180-00004 · Cited by 414
A deep feature based framework for breast masses classification
Jiao, Z., Gao, X., Wang, Y., & Li, J. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.02.060 · Cited by 304 · cited 1×
“[10] proposed a scheme in which a pre-trained CNN was fine-tuned on a subset of DDSM database.”
MethodDeep learning in mammography and breast histology, an overview and future trends
Hamidinekoo, A., Denton, E., Rampun, A., Honnor, K., & Zwiggelaar, R. (2018) · Medical Image Analysis · doi:10.1016/j.media.2018.03.006 · Cited by 273 · cited 1×
“Since the emergence of deep learning, various works have been published exploiting deep architectures [5].”
BackgroundUnregistered Multiview Mammogram Analysis with Pre-trained Deep Learning Models
Carneiro, G., Nascimento, J., & Bradley, A. P. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-24574-4_78 · Cited by 235 · cited 1×
“[7] used a pre-trained CNN that was fine-tuned using unregistered mammograms and segmented microcalcification and masses.”
MethodBreast mass classification in digital mammography based on extreme learning machine
Xie, W., Li, Y., & Ma, Y. (2016) · Neurocomputing · doi:10.1016/j.neucom.2015.08.048 · Cited by 167
Tsochatzidis, L., Zagoris, K., Arikidis, N. S., Karahaliou, A. N., Costaridou, L. I., & Pratikakis, I. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.05.023 · Cited by 106
Self-citationBreast Mass Classification in Mammograms using Ensemble Convolutional Neural Networks
Rampun, A., Scotney, B. W., Morrow, P., et al. (2018) · IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/healthcom.2018.8531154 · Cited by 58 · cited 1×
“[13] used an ensemble of a slightly modified version of AlexNet pre-trained and fine-tuned on CBIS-DDSM.”
Method
Metadata
- Authors
- Tsochatzidis, L., Costaridou, L., & Pratikakis, I.
- Venue
- Journal of Imaging
- Publisher
- MDPI AG
- Published
- 2019-03-13
- Volume
- 5
- Issue
- 3
- Pages
- 37
- ISSN
- 2313-433X (ISSN-L)
- OpenAlex
- W2921877691
- Cited by
- 196
- References
- 26
- FWCI
- 11.17
- Type
- journal article
- Language
- en
- Open access
- gold
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.