CoChat

Breast Cancer Histopathology Image Classification Using an Ensemble of Deep Learning Models

Open access
Hameed, Zabit, Zahia, Sofia, Garcia-Zapirain, Begonya, Javier Aguirre, José, María Vanegas, Ana · 2020 · Sensors

The 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.

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

Integrity signals

Registry

Crossref · 10.3390/s20164373

Cites

44 of 44 references verified0 citation errors · 0 not checkable

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.
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.CC BY · PubMed Central
Figure 2 The examples of original (A,C) and normalized (B,D) images of carcinoma and non-carcinoma cases.
Figure 2 The examples of original (A,C) and normalized (B,D) images of carcinoma and non-carcinoma cases.CC BY · PubMed Central
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.
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.CC BY · PubMed Central
Figure 4 The proposed ensemble architecture using the fine-tuned VGG16 and VGG19 models along with 5-fold cross-validation approach.
Figure 4 The proposed ensemble architecture using the fine-tuned VGG16 and VGG19 models along with 5-fold cross-validation approach.CC BY · PubMed Central
Figure 5 The training and validation accuracy curves of fully-trained and fine-tuned VGG16 models.
Figure 5 The training and validation accuracy curves of fully-trained and fine-tuned VGG16 models.CC BY · PubMed Central
Figure 6 The training and validation loss curves of fully-trained and fine-tuned VGG16 models.
Figure 6 The training and validation loss curves of fully-trained and fine-tuned VGG16 models.CC BY · PubMed Central
Figure 7 The training and validation accuracy curves of fully-trained and fine-tuned VGG19 models.
Figure 7 The training and validation accuracy curves of fully-trained and fine-tuned VGG19 models.CC BY · PubMed Central
Figure 8 The training and validation loss curves of fully-trained and fine-tuned VGG19 models.
Figure 8 The training and validation loss curves of fully-trained and fine-tuned VGG19 models.CC BY · PubMed Central

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.

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: 2

  1. Goodfellow, I., Bengio, Y., and Courville, A. (2017). Deep Learning, The MIT Press.
  2. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.

Cited by

See all 309

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)
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
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.