Deep learning-based breast cancer classification through medical imaging modalities: state of the art and research challenges

Ghulam Murtaza, Liyana Shuib, Ainuddin Wahid Abdul Wahab, Ghulam Mujtaba, Ghulam Mujtaba, Henry Friday Nweke, Mohammed Ali Al-garadi, Fariha Zulfiqar, Ghulam Raza, Nor Aniza Azmi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Breast cancer is a common and fatal disease among women worldwide. Therefore, the early and precise diagnosis of breast cancer plays a pivotal role to improve the prognosis of patients with this disease. Several studies have developed automated techniques using different medical imaging modalities to predict breast cancer development. However, few review studies are available to recapitulate the existing literature on breast cancer classification. These studies provide an overview of the classification, segmentation, or grading of many cancer types, including breast cancer, by using traditional machine learning approaches through hand-engineered features. This review focuses on breast cancer classification by using medical imaging multimodalities through state-of-the-art artificial deep neural network approaches. It is anticipated to maximize the procedural decision analysis in five aspects, such as types of imaging modalities, datasets and their categories, pre-processing techniques, types of deep neural network, and performance metrics used for breast cancer classification. Forty-nine journal and conference publications from eight academic repositories were methodically selected and carefully reviewed from the perspective of the five aforementioned aspects. In addition, this study provided quantitative, qualitative, and critical analyses of the five aspects. This review showed that mammograms and histopathologic images were mostly used to classify breast cancer. Moreover, about 55% of the selected studies used public datasets, and the remaining used exclusive datasets. Several studies employed augmentation, scaling, and image normalization pre-processing techniques to minimize inconsistencies in breast cancer images. Several types of shallow and deep neural network architecture were employed to classify breast cancer using images. The convolutional neural network was utilized frequently to construct an effective breast cancer classification model. Some of the selected studies employed a pre-trained network or developed new deep neural networks to classify breast cancer. Most of the selected studies used accuracy and area-under-the-curve metrics followed by sensitivity, precision, and F-measure metrics to evaluate the performance of the developed breast cancer classification models. Finally, this review presented 10 open research challenges for future scholars who are interested to develop breast cancer classification models through various imaging modalities. This review could serve as a valuable resource for beginners on medical image classification and for advanced scientists focusing on deep learning-based breast cancer classification through different medical imaging modalities.

Original languageEnglish
JournalArtificial Intelligence Review
DOIs
Publication statusAccepted/In press - 1 Jan 2019
Externally publishedYes

Fingerprint

Medical imaging
cancer
learning
neural network
Imaging techniques
Deep learning
Modality
Breast Cancer
Medical Imaging
Decision theory
Image classification
Processing
Network architecture
Learning systems
Disease
Neural networks
multimodality
Deep neural networks
grading
normalization

Keywords

  • Breast cancer classification
  • Convolutional neural network
  • Deep learning
  • Medical imaging modalities

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language
  • Artificial Intelligence

Cite this

Deep learning-based breast cancer classification through medical imaging modalities : state of the art and research challenges. / Murtaza, Ghulam; Shuib, Liyana; Abdul Wahab, Ainuddin Wahid; Mujtaba, Ghulam; Mujtaba, Ghulam; Nweke, Henry Friday; Al-garadi, Mohammed Ali; Zulfiqar, Fariha; Raza, Ghulam; Azmi, Nor Aniza.

In: Artificial Intelligence Review, 01.01.2019.

Research output: Contribution to journalArticle

Murtaza, Ghulam ; Shuib, Liyana ; Abdul Wahab, Ainuddin Wahid ; Mujtaba, Ghulam ; Mujtaba, Ghulam ; Nweke, Henry Friday ; Al-garadi, Mohammed Ali ; Zulfiqar, Fariha ; Raza, Ghulam ; Azmi, Nor Aniza. / Deep learning-based breast cancer classification through medical imaging modalities : state of the art and research challenges. In: Artificial Intelligence Review. 2019.
@article{4e82b78e617b49bb972a100d7aa055f3,
title = "Deep learning-based breast cancer classification through medical imaging modalities: state of the art and research challenges",
abstract = "Breast cancer is a common and fatal disease among women worldwide. Therefore, the early and precise diagnosis of breast cancer plays a pivotal role to improve the prognosis of patients with this disease. Several studies have developed automated techniques using different medical imaging modalities to predict breast cancer development. However, few review studies are available to recapitulate the existing literature on breast cancer classification. These studies provide an overview of the classification, segmentation, or grading of many cancer types, including breast cancer, by using traditional machine learning approaches through hand-engineered features. This review focuses on breast cancer classification by using medical imaging multimodalities through state-of-the-art artificial deep neural network approaches. It is anticipated to maximize the procedural decision analysis in five aspects, such as types of imaging modalities, datasets and their categories, pre-processing techniques, types of deep neural network, and performance metrics used for breast cancer classification. Forty-nine journal and conference publications from eight academic repositories were methodically selected and carefully reviewed from the perspective of the five aforementioned aspects. In addition, this study provided quantitative, qualitative, and critical analyses of the five aspects. This review showed that mammograms and histopathologic images were mostly used to classify breast cancer. Moreover, about 55{\%} of the selected studies used public datasets, and the remaining used exclusive datasets. Several studies employed augmentation, scaling, and image normalization pre-processing techniques to minimize inconsistencies in breast cancer images. Several types of shallow and deep neural network architecture were employed to classify breast cancer using images. The convolutional neural network was utilized frequently to construct an effective breast cancer classification model. Some of the selected studies employed a pre-trained network or developed new deep neural networks to classify breast cancer. Most of the selected studies used accuracy and area-under-the-curve metrics followed by sensitivity, precision, and F-measure metrics to evaluate the performance of the developed breast cancer classification models. Finally, this review presented 10 open research challenges for future scholars who are interested to develop breast cancer classification models through various imaging modalities. This review could serve as a valuable resource for beginners on medical image classification and for advanced scientists focusing on deep learning-based breast cancer classification through different medical imaging modalities.",
keywords = "Breast cancer classification, Convolutional neural network, Deep learning, Medical imaging modalities",
author = "Ghulam Murtaza and Liyana Shuib and {Abdul Wahab}, {Ainuddin Wahid} and Ghulam Mujtaba and Ghulam Mujtaba and Nweke, {Henry Friday} and Al-garadi, {Mohammed Ali} and Fariha Zulfiqar and Ghulam Raza and Azmi, {Nor Aniza}",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/s10462-019-09716-5",
language = "English",
journal = "Artificial Intelligence Review",
issn = "0269-2821",
publisher = "Springer Netherlands",

}

TY - JOUR

T1 - Deep learning-based breast cancer classification through medical imaging modalities

T2 - state of the art and research challenges

AU - Murtaza, Ghulam

AU - Shuib, Liyana

AU - Abdul Wahab, Ainuddin Wahid

AU - Mujtaba, Ghulam

AU - Mujtaba, Ghulam

AU - Nweke, Henry Friday

AU - Al-garadi, Mohammed Ali

AU - Zulfiqar, Fariha

AU - Raza, Ghulam

AU - Azmi, Nor Aniza

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Breast cancer is a common and fatal disease among women worldwide. Therefore, the early and precise diagnosis of breast cancer plays a pivotal role to improve the prognosis of patients with this disease. Several studies have developed automated techniques using different medical imaging modalities to predict breast cancer development. However, few review studies are available to recapitulate the existing literature on breast cancer classification. These studies provide an overview of the classification, segmentation, or grading of many cancer types, including breast cancer, by using traditional machine learning approaches through hand-engineered features. This review focuses on breast cancer classification by using medical imaging multimodalities through state-of-the-art artificial deep neural network approaches. It is anticipated to maximize the procedural decision analysis in five aspects, such as types of imaging modalities, datasets and their categories, pre-processing techniques, types of deep neural network, and performance metrics used for breast cancer classification. Forty-nine journal and conference publications from eight academic repositories were methodically selected and carefully reviewed from the perspective of the five aforementioned aspects. In addition, this study provided quantitative, qualitative, and critical analyses of the five aspects. This review showed that mammograms and histopathologic images were mostly used to classify breast cancer. Moreover, about 55% of the selected studies used public datasets, and the remaining used exclusive datasets. Several studies employed augmentation, scaling, and image normalization pre-processing techniques to minimize inconsistencies in breast cancer images. Several types of shallow and deep neural network architecture were employed to classify breast cancer using images. The convolutional neural network was utilized frequently to construct an effective breast cancer classification model. Some of the selected studies employed a pre-trained network or developed new deep neural networks to classify breast cancer. Most of the selected studies used accuracy and area-under-the-curve metrics followed by sensitivity, precision, and F-measure metrics to evaluate the performance of the developed breast cancer classification models. Finally, this review presented 10 open research challenges for future scholars who are interested to develop breast cancer classification models through various imaging modalities. This review could serve as a valuable resource for beginners on medical image classification and for advanced scientists focusing on deep learning-based breast cancer classification through different medical imaging modalities.

AB - Breast cancer is a common and fatal disease among women worldwide. Therefore, the early and precise diagnosis of breast cancer plays a pivotal role to improve the prognosis of patients with this disease. Several studies have developed automated techniques using different medical imaging modalities to predict breast cancer development. However, few review studies are available to recapitulate the existing literature on breast cancer classification. These studies provide an overview of the classification, segmentation, or grading of many cancer types, including breast cancer, by using traditional machine learning approaches through hand-engineered features. This review focuses on breast cancer classification by using medical imaging multimodalities through state-of-the-art artificial deep neural network approaches. It is anticipated to maximize the procedural decision analysis in five aspects, such as types of imaging modalities, datasets and their categories, pre-processing techniques, types of deep neural network, and performance metrics used for breast cancer classification. Forty-nine journal and conference publications from eight academic repositories were methodically selected and carefully reviewed from the perspective of the five aforementioned aspects. In addition, this study provided quantitative, qualitative, and critical analyses of the five aspects. This review showed that mammograms and histopathologic images were mostly used to classify breast cancer. Moreover, about 55% of the selected studies used public datasets, and the remaining used exclusive datasets. Several studies employed augmentation, scaling, and image normalization pre-processing techniques to minimize inconsistencies in breast cancer images. Several types of shallow and deep neural network architecture were employed to classify breast cancer using images. The convolutional neural network was utilized frequently to construct an effective breast cancer classification model. Some of the selected studies employed a pre-trained network or developed new deep neural networks to classify breast cancer. Most of the selected studies used accuracy and area-under-the-curve metrics followed by sensitivity, precision, and F-measure metrics to evaluate the performance of the developed breast cancer classification models. Finally, this review presented 10 open research challenges for future scholars who are interested to develop breast cancer classification models through various imaging modalities. This review could serve as a valuable resource for beginners on medical image classification and for advanced scientists focusing on deep learning-based breast cancer classification through different medical imaging modalities.

KW - Breast cancer classification

KW - Convolutional neural network

KW - Deep learning

KW - Medical imaging modalities

UR - http://www.scopus.com/inward/record.url?scp=85067701488&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067701488&partnerID=8YFLogxK

U2 - 10.1007/s10462-019-09716-5

DO - 10.1007/s10462-019-09716-5

M3 - Article

AN - SCOPUS:85067701488

JO - Artificial Intelligence Review

JF - Artificial Intelligence Review

SN - 0269-2821

ER -