Breast Cancer Histopathology Image Classification Using an Ensemble of Deep Learning Models
Open accessThe DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Abstract
Breast cancer is one of the major public health issues and is considered a leading cause of cancer-related deaths among women worldwide. Its early diagnosis can effectively help in increasing the chances of survival rate. To this end, biopsy is usually followed as a gold standard approach in which tissues are collected for microscopic analysis. However, the histopathological analysis of breast cancer is non-trivial, labor-intensive, and may lead to a high degree of disagreement among pathologists. Therefore, an automatic diagnostic system could assist pathologists to improve the effectiveness of diagnostic processes. This paper presents an ensemble deep learning approach for the definite classification of non-carcinoma and carcinoma breast cancer histopathology images using our collected dataset. We trained four different models based on pre-trained VGG16 and VGG19 architectures. Initially, we followed 5-fold cross-validation operations on all the individual models, namely, fully-trained VGG16, fine-tuned VGG16, fully-trained VGG19, and fine-tuned VGG19 models. Then, we followed an ensemble strategy by taking the average of predicted probabilities and found that the ensemble of fine-tuned VGG16 and fine-tuned VGG19 performed competitive classification performance, especially on the carcinoma class. The ensemble of fine-tuned VGG16 and VGG19 models offered sensitivity of 97.73% for carcinoma class and overall accuracy of 95.29%. Also, it offered an F1 score of 95.29%. These experimental results demonstrated that our proposed deep learning approach is effective for the automatic classification of complex-natured histopathology images of breast cancer, more specifically for carcinoma images.
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
Figures
![Figure 1 The complete process of biopsy is depicted in Figure. Steps 01 and 02 are taken from [7] whereas steps 03 and 04 are retrieved from our own dataset.](https://figures.cochat.ai/paper-figures/892b31ad19624a368cfad475524c3872/breast-cancer-histopathology-image-classification-using-an-ensemble-of-deep-figure-1.jpg)

![Figure 3 Representation of fine-tuned VGG16 architecture [20]. In fine-tuned VGG16 and VGG19 models, the first block (comprising two convolutional layers and one max-pooling layer) is frozen whereas the rest of layers are trainable. However, in fully-trained VGG16 and VGG19 models, all the five blocks are trainable.](https://figures.cochat.ai/paper-figures/a64c3d4189ba43fb9d12a3d805af5248/breast-cancer-histopathology-image-classification-using-an-ensemble-of-deep-figure-3.jpg)





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.
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?
The cited source says what the claim attributes to it.
In the citing paper
“Thus, the FS method helps to enhance the performance of the model.”
From Variational Quantum Classifier for Binary Classification: Real vs Synthetic Dataset (2022) · cites this paper as [33]
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 1×
“The intuition of multiple stacked smaller convolutional filters can provide an effective receptive field and is also used in recently proposed pretrained models, including Inception Network [21] and residual neural network (ResNet) [22].”
MethodVery 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 13×
“Of note, we used the convolutional filters, pooling filters, strides, and padding with their default values mentioned in the original VGG16 and VGG19 architectures [20].”
BackgroundMethodInfluentialImageNet 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 5×
“72) when using fine-tuned AlexNet [19] on BreakHis dataset for 200× magnification.”
MethodInfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Bray, F., Ferlay, J., Soerjomataram, I., Siegel, R. L., Torre, L. A., & Jemal, A. (2018) · CA: A Cancer Journal for Clinicians · doi:10.3322/caac.21492 · Cited by 84,109 · cited 1×
“Specifically, breast cancer is the most common malignancy and the leading cause of cancer-related mortalities among women worldwide [1,2].”
BackgroundGradient-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 1×
“Especially convolutional neural networks (CNNs) [18] are widely used in image-related tasks due to their abilities to effectively share parameters across various layers within a deep learning model.”
BackgroundGoing 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
(2014) · Cited by 33,419
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472 · cited 1×
“Also, these methodologies mainly rely on feature extraction methods like scale-invariant feature transform [11], speed robust features [12] and local binary patterns [13] which all are based on supervised information and can be prone to biased results during the classification of breast cancer histopathology images [1…”
MethodMultiresolution gray-scale and rotation invariant texture classification with local binary patterns
Ojala, T., Pietikainen, M., & Maenpaa, T. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2002.1017623 · Cited by 15,398 · cited 1×
“…mainly rely on feature extraction methods like scale-invariant feature transform [11], speed robust features [12] and local binary patterns [13] which all are based on supervised information and can be prone to biased results during the classification of breast cancer histopathology images…”
MethodA 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
SURF: Speeded Up Robust Features
Bay, H., Tuytelaars, T., & Van Gool, L. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744023_32 · Cited by 14,955
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · cited 2×
“In contrast to the traditional machine learning approaches based on hand-crafted features, deep learning models have the ability to yield complicated and high-level features from images automatically [26].”
BackgroundResultQuPath: Open source software for digital pathology image analysis
Bankhead, P., Loughrey, M. B., Fernández, J. A., Dombrowski, Y., McArt, D. G., Dunne, P. D., McQuaid, S., Gray, R. T., Murray, L. J., Coleman, H. G., et al. (2017) · Scientific Reports · doi:10.1038/s41598-017-17204-5 · Cited by 8,908
Global Burden of Disease Cancer Collaboration, Fitzmaurice, C., Allen, C., Barber, R. M., Barregard, L., Bhutta, Z. A., Brenner, H., Dicker, D. J., Chimed-Orchir, O., Dandona, R., et al. (2017) · JAMA Oncology · doi:10.1001/jamaoncol.2016.5688 · Cited by 6,215
Global Burden of Disease Cancer Collaboration, Fitzmaurice, C., Abate, D., Abbasi, N., Abbastabar, H., Abd-Allah, F., Abdel-Rahman, O., Abdelalim, A., Abdoli, A., Abdollahpour, I., et al. (2019) · JAMA Oncology · doi:10.1001/jamaoncol.2019.2996 · Cited by 2,501 · cited 3×
“These statistics indicate that cancer incidence expanded by 33% between 2007 and 2017 worldwide [1].”
BackgroundMethodInfluentialA Dataset for Breast Cancer Histopathological Image Classification
Spanhol, F. A., Oliveira, L. S., Petitjean, C., & Heutte, L. (2016) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2015.2496264 · Cited by 1,832 · cited 5×
“For instance, Spanhol et al. [28] employed CNN for the classification of breast cancer histopathology images and achieved 4 to 6 percentage points higher accuracy on BreakHis dataset [27] when using a variation of AlexNet [19].”
MethodResultInfluentialA method for normalizing histology slides for quantitative analysis
Macenko, M., Niethammer, M., Marron, J. S., Borland, D., Woosley, J. T., Guan, X., Schmitt, C., & Thomas, N. E. (2009) · 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro · doi:10.1109/isbi.2009.5193250 · Cited by 1,482 · cited 1×
“paper, we followed the recent studies [30,31] and employed the approach proposed by [33] for colour normalization.”
MethodClassification of breast cancer histology images using Convolutional Neural Networks
Araújo, T., Aresta, G., Castro, E., Rouco, J., Aguiar, P., Eloy, C., Polónia, A., & Campilho, A. (2017) · PLOS ONE · doi:10.1371/journal.pone.0177544 · Cited by 1,013 · cited 2×
“However, our dataset contains only non-carcinoma and carcinoma classes, unlike [30,31] which have four classes”
BackgroundMethodBreast cancer histopathological image classification using Convolutional Neural Networks
Spanhol, F. A., Oliveira, L. S., Petitjean, C., & Heutte, L. (2016) · 2016 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727519 · Cited by 942 · cited 3×
“[28] employed a variant of AlexNet [19] for the classification of benign and malignant images of BreakHis dataset [27].”
MethodResultDiagnostic Concordance Among Pathologists Interpreting Breast Biopsy Specimens
Elmore, J. G., Longton, G. M., Carney, P. A., Geller, B. M., Onega, T., Tosteson, A. N. A., Nelson, H. D., Pepe, M. S., Allison, K. H., Schnitt, S. J., et al. (2015) · JAMA · doi:10.1001/jama.2015.1405 · Cited by 751 · cited 1×
“Also, the morphological criteria used in the classification of these images are somehow subjective, which leads to the result that an average diagnostic concordance among the pathologists is approximately 75% [8].”
BackgroundBreast Cancer Histopathology Image Analysis: A Review
Veta, M., Pluim, J. P. W., van Diest, P. J., & Viergever, M. A. (2014) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2014.2303852 · Cited by 696 · cited 4×
“The process of biopsy includes the collection of tissue samples, mounting them on microscopic glass slides, and staining these slides for better visualization of nuclei and cytoplasm [6].”
BackgroundMethodInfluentialBreast Cancer Multi-classification from Histopathological Images with Structured Deep Learning Model
Han, Z., Wei, B., Zheng, Y., Yin, Y., Li, K., & Li, S. (2017) · Scientific Reports · doi:10.1038/s41598-017-04075-z · Cited by 683
Histological types of breast cancer: How special are they?
Weigelt, B., Geyer, F. C., & Reis-Filho, J. S. (2010) · Molecular Oncology · doi:10.1016/j.molonc.2010.04.004 · Cited by 572 · cited 2×
“This malignancy erupts from the growth of abnormal breast cells and might invade the adjacent healthy tissues [3].”
BackgroundEarly Diagnosis of Breast Cancer
Wang, L. (2017) · Sensors · doi:10.3390/s17071572 · Cited by 549 · cited 1×
“Its clinical screening is Sensors 2020 , 20 , 4373 initially performed by utilizing radiology images, for instance, mammography, ultrasound imaging, and Magnetic Resonance Imaging (MRI) [4,5].”
MethodDeep learning for magnification independent breast cancer histopathology image classification
Bayramoglu, N., Kannala, J., & Heikkila, J. (2016) · 2016 23rd International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr.2016.7900002 · Cited by 437 · cited 4×
“[29] proposed a magnification independent approach for BreakHis dataset.”
MethodResultInfluentialClassification of Breast Cancer Based on Histology Images Using Convolutional Neural Networks
Bardou, D., Zhang, K., & Ahmad, S. M. (2018) · IEEE Access · doi:10.1109/access.2018.2831280 · Cited by 414 · cited 1×
“00001) and three different batch sizes (16, 32, and 64) while keeping in mind the values used in the recently published study [39,40].”
MethodTransfer learning based histopathologic image classification for breast cancer detection
Deniz, E., Şengür, A., Kadiroğlu, Z., Guo, Y., Bajaj, V., & Budak, Ü. (2018) · Health Information Science and Systems · doi:10.1007/s13755-018-0057-x · Cited by 360
Breast cancer histopathological image classification using a hybrid deep neural network
Yan, R., Ren, F., Wang, Z., Wang, L., Zhang, T., Liu, Y., Rao, X., Zheng, C., & Zhang, F. (2020) · Methods · doi:10.1016/j.ymeth.2019.06.014 · Cited by 350 · cited 4×
“However, our dataset contains only non-carcinoma and carcinoma classes, unlike [30,31] which have four classes”
BackgroundMethodInfluentialDeep Learning for Whole Slide Image Analysis: An Overview
Dimitriou, N., Arandjelović, O., & Caie, P. D. (2019) · Frontiers in Medicine · doi:10.3389/fmed.2019.00264 · Cited by 332
Deep Learning Based Analysis of Histopathological Images of Breast Cancer
Xie, J., Liu, R., Luttrell, J., & Zhang, C. (2019) · Frontiers in Genetics · doi:10.3389/fgene.2019.00080 · Cited by 302
Robertson, S., Azizpour, H., Smith, K., & Hartman, J. (2018) · Translational Research · doi:10.1016/j.trsl.2017.10.010 · Cited by 295 · cited 2×
“Also, these methodologies mainly rely on feature extraction methods like scale-invariant feature transform [11], speed robust features [12] and local binary patterns [13] which all are based on supervised information and can be prone to biased results during the classification of breast cancer histopathology images [1…”
BackgroundMethodComputer-aided diagnosis of breast cancer based on fine needle biopsy microscopic images
Kowal, M., Filipczuk, P., Obuchowicz, A., Korbicz, J., & Monczak, R. (2013) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2013.08.003 · Cited by 274 · cited 2×
“[23] focused on the nuclei segmentation and extracted forty-two morphological, topological and texture features from the segmented nuclei of 500 fine-needle biopsy images of breast cancer.”
BackgroundFilipczuk, P., Fevens, T., Krzyzak, A., & Monczak, R. (2013) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2013.2275151 · Cited by 228
Nahid, A.-A., Mehrabi, M. A., & Kong, Y. (2018) · BioMed Research International · doi:10.1155/2018/2362108 · Cited by 197 · cited 1×
“[43] first used clustering algorithm in order to retrieve the statistical and geometrical clusters hidden in the histopathology images.”
MethodBreakHis based breast cancer automatic diagnosis using deep learning: Taxonomy, survey and insights
Benhammou, Y., Achchab, B., Herrera, F., & Tabik, S. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.09.044 · Cited by 170
Detection of breast cancer on digital histopathology images: Present status and future possibilities
Aswathy, M. A., & Jagannath, M. (2017) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2016.11.001 · Cited by 167 · cited 1×
“Therefore, the computer-assisted diagnosis [4,6,9] plays a significant role to assist pathologists in analyzing the histopathology images.”
BackgroundComputed-aided diagnosis (CAD) in the detection of breast cancer
Dromain, C., Boyer, B., Ferré, R., Canale, S., Delaloge, S., & Balleyguier, C. (2012) · European Journal of Radiology · doi:10.1016/j.ejrad.2012.03.005 · Cited by 155 · cited 2×
“Therefore, the computer-assisted diagnosis [4,6,9] plays a significant role to assist pathologists in analyzing the histopathology images.”
BackgroundMethodYao, H., Zhang, X., Zhou, X., & Liu, S. (2019) · Cancers · doi:10.3390/cancers11121901 · Cited by 144 · cited 1×
“Following [35], we used 5-fold cross-validation on training images which means that 540 images were used for training and 135 images for validation purpose.”
MethodBreast cancer diagnosis from biopsy images with highly reliable random subspace classifier ensembles
Zhang, Y., Zhang, B., Coenen, F., & Lu, W. (2012) · Machine Vision and Applications · doi:10.1007/s00138-012-0459-8 · Cited by 100 · cited 1×
“[25] combined local binary patterns, statistics from the gray level co-occurrence matrix and the curvelet transform, and designed a cascade random space ensemble scheme (with rejection options) for an efficient classification of the microscopic biopsy images of breast cancer.”
BackgroundZahia, S., Garcia Zapirain, M. B., Sevillano, X., González, A., Kim, P. J., & Elmaghraby, A. (2020) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2019.101742 · Cited by 84
Self-citation[Early diagnosis of breast cancer].
González-Larriba, J. L. (1991) · PubMed · Cited by 30
Aurelien, B., Castillo-Olea, C., García-Zapirain, B., & Zahia, S. (2019) · IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) · doi:10.1109/isspit47144.2019.9001816 · Cited by 27
Self-citationEvaluation of Colour Pre-processing on Patch-Based Classification of H&E-Stained Images
Bianconi, F., Kather, J. N., & Reyes‐Aldasoro, C. C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-23937-4_7 · Cited by 20 · cited 1×
“However, the classification performance of our proposed model deteriorated upon using the normalized images, which is also comprehensively explained in [34].”
Research works printed but not linked: 2
- Goodfellow, I., Bengio, Y., and Courville, A. (2017). Deep Learning, The MIT Press.
- Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
Cited by
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00444-8 · Cited by 7,906
McGenity, C., Clarke, E. L., Jennings, C., Matthews, G., Cartlidge, C., Freduah-Agyemang, H., Stocken, D. D., & Treanor, D. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01106-8 · Cited by 290
Aljuaid, H., Alturki, N., Alsubaie, N., Cavallaro, L., & Liotta, A. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.106951 · Cited by 248
A generalized deep learning framework for whole-slide image segmentation and analysis
Khened, M., Kori, A., Rajkumar, H., Krishnamurthi, G., & Srinivasan, B. (2021) · Scientific Reports · doi:10.1038/s41598-021-90444-8 · Cited by 239
Kourou, K., Exarchos, K. P., Papaloukas, C., Sakaloglou, P., Exarchos, T., & Fotiadis, D. I. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.10.006 · Cited by 165
“Similar approaches were proposed by Benhammou et al. [43], Sha et al. [44], Kumar et al. [45], Krithiga et al. [46], Hameed et al. [47], and Li et al. [48] towards assessing the diagnostic capability of deep CNN architectures by analyzing imaging slides.”
Metadata
- Authors
- Hameed, Z., Zahia, S., Garcia-Zapirain, B., Javier Aguirre, J., & María Vanegas, A.
- Affiliations
- Universidad de Deusto (ES)
- eVida Research Group, University of Deusto, 48007 Bilbao, Spain
- Biokeralty Reseach Institute, 01510 Vitoria, Spain
- Clinica Colsanitas, Bogotá 110221, Colombia
- Corresponding author
- Hameed, Zabit
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2020-08-05
- Volume
- 20
- Issue
- 16
- Pages
- 4373
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC7472736
- OpenAlex
- W3047083963
- Cited by
- 277
- References
- 44
- Citations by year
- 2026: 28 · 2025: 45 · 2024: 69 · 2023: 68 · 2022: 37 · 2021: 27 · 2020: 3
- FWCI
- 13.26
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DeustoTeka (submittedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Government of the Basque Country, Spain (MIFLUDAN Project)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Imaging for Blood Diseases
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- breast cancer, histopathological image classification, ensemble deep learning, VGG16, VGG19, fine-tuning, automated diagnosis, breast biopsy
- MeSH terms
- Deep Learning, Breast Neoplasms, Female, Humans, Neural Networks, Computer
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.