CoChat
Sign Up
Cited by 314AI in cancer detectionRadiomics and Machine Learning in Medical ImagingArtificial Intelligence in Healthcare

The DOI matches its Crossref record; 64 of the 65 references it cites were found in a registry or an index.

Breast Cancer Classification from Ultrasound Images Using Probability-Based Optimal Deep Learning Feature Fusion

Open access
Jabeen, Kiran, Khan, Muhammad Attique, Alhaisoni, Majed, Tariq, Usman, Zhang, Yu-Dong, Hamza, Ameer, Mickus, Artūras, Damaševičius, Robertas·2022·Sensors
DOI 10.3390/s22030807PMC PMC8840464
Open this paper in CoChat — free account

Abstract

After lung cancer, breast cancer is the second leading cause of death in women. If breast cancer is detected early, mortality rates in women can be reduced. Because manual breast cancer diagnosis takes a long time, an automated system is required for early cancer detection. This paper proposes a new framework for breast cancer classification from ultrasound images that employs deep learning and the fusion of the best selected features. The proposed framework is divided into five major steps: (i) data augmentation is performed to increase the size of the original dataset for better learning of Convolutional Neural Network (CNN) models; (ii) a pre-trained DarkNet-53 model is considered and the output layer is modified based on the augmented dataset classes; (iii) the modified model is trained using transfer learning and features are extracted from the global average pooling layer; (iv) the best features are selected using two improved optimization algorithms known as reformed differential evaluation (RDE) and reformed gray wolf (RGW); and (v) the best selected features are fused using a new probability-based serial approach and classified using machine learning algorithms. The experiment was conducted on an augmented Breast Ultrasound Images (BUSI) dataset, and the best accuracy was 99.1%. When compared with recent techniques, the proposed framework outperforms them.

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 · 10.3390/s22030807

Cites

64 of 64 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 The proposed framework for breast cancer classification using Ultrasound Images.
Figure 1 The proposed framework for breast cancer classification using Ultrasound Images.CC BY · PubMed Central
Figure 2 Sample ultrasound images of the BUSI dataset [59].
Figure 2 Sample ultrasound images of the BUSI dataset [59].CC BY · PubMed Central
Figure 3 Structure of Modified DarkNet-53 deep model.
Figure 3 Structure of Modified DarkNet-53 deep model.CC BY · PubMed Central
Figure 4 The layer wise architecture of Modified DarkNet-53 deep model.
Figure 4 The layer wise architecture of Modified DarkNet-53 deep model.CC BY · PubMed Central
Figure 5 Transfer learning-based training of modified model and extract features.
Figure 5 Transfer learning-based training of modified model and extract features.CC BY · PubMed Central
Figure 6 Confusion matrix of Cubic SVM for training/testing ratio of 50:50.
Figure 6 Confusion matrix of Cubic SVM for training/testing ratio of 50:50.CC BY · PubMed Central
Figure 7 Confusion matrix of Cubic SVM for training/testing ratio of 70:30.
Figure 7 Confusion matrix of Cubic SVM for training/testing ratio of 70:30.CC BY · PubMed Central
Figure 8 Confusion matrix of Cubic SVM for the training/testing ratio of 60:40.
Figure 8 Confusion matrix of Cubic SVM for the training/testing ratio of 60:40.CC BY · PubMed Central
Figure 9 Summary of DarkNet53 classification accuracy using different training/testing ratios.
Figure 9 Summary of DarkNet53 classification accuracy using different training/testing ratios.CC BY · PubMed Central
Figure 10 Confusion matrix of Cubic SVM for the features selected using DE and the train/test ratio of 50:50.
Figure 10 Confusion matrix of Cubic SVM for the features selected using DE and the train/test ratio of 50:50.CC BY · PubMed Central
Figure 11 Confusion matrix of Cubic SVM for BGWO-based best feature selection.
Figure 11 Confusion matrix of Cubic SVM for BGWO-based best feature selection.CC BY · PubMed Central
Figure 12 Confusion matrix of Cubic SVM after the proposed feature fusion approach.
Figure 12 Confusion matrix of Cubic SVM after the proposed feature fusion approach.CC BY · PubMed Central
Figure 13 Computational time-based comparison of each step using the proposed framework.
Figure 13 Computational time-based comparison of each step using the proposed framework.CC BY · PubMed Central
Figure 14 Critical difference diagram from the Nemenyi test: a comparison of classifiers (α = 0.05).
Figure 14 Critical difference diagram from the Nemenyi test: a comparison of classifiers (α = 0.05).CC BY · PubMed Central
Figure 15 Critical difference diagram from the Nemenyi test: a comparison of feature selection methods (α = 0.05).
Figure 15 Critical difference diagram from the Nemenyi test: a comparison of feature selection methods (α = 0.05).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

1 retracted

Show all 65 references

Research works printed but not linked: 2

  1. Hussain, 2021, Intelligent Deep Learning and Improved Whale Optimization Algorithm Based Framework for Object Recognition, Hum. Cent. Comput. Inf. Sci., 11, 34
  2. Xiangmin, H., Jun, W., Weijun, Z., Cai, C., Shihui, Y., and Jun, S. (2020). Deep Doubly Supervised Transfer Network for Diagnosis of Breast Cancer with Imbalanced Ultrasound Imaging Modalities. arXiv.

Cited by

Sorted by citations

Related

See all

Metadata

Authors
Jabeen, K., Khan, M. A., Alhaisoni, M., Tariq, U., Zhang, Y.-D., Hamza, A., Mickus, A., & Damaševičius, R.
Affiliations
  • HITEC University (PK)
  • University of Ha'il (SA)
  • Prince Sattam Bin Abdulaziz University (SA)
  • Department of Informatics, University of Leicester, Leicester LE1 7RH, UK
  • Vytautas Magnus University (LT)
Corresponding author
Damaševičius, Robertas
ORCID
Venue
Sensors
Publisher
MDPI AG
Published
2022-01-21
Volume
22
Issue
3
Pages
807
ISSN
1424-8220 (ISSN-L)
DOI
10.3390/s22030807
PMC
PMC8840464
OpenAlex
W4207017358
Cited by
314
References
65
Citations by year
2026: 47 · 2025: 66 · 2024: 76 · 2023: 82 · 2022: 43
FWCI
21.97
Type
journal article
Language
en
Open access
Licence
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Vytautas Magnus University (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
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
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
breast cancer classification, breast ultrasound images, feature fusion, feature selection, transfer learning, Darknet-53, data augmentation, BUSI dataset, early cancer detection
MeSH terms
Deep Learning, Breast, Breast Neoplasms, Female, Humans, Probability, Ultrasonography, Mammary

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