Double-Shot Transfer Learning for Breast Cancer Classification from X-Ray Images

Alkhaleefah, Mohammad; Ma, Shang‐Chih; Chang, Yang-Lang; Huang, Bormin; Chittem, Praveen Kumar; Achhannagari, Vishnu Priya

doi:10.3390/app10113999

Cited by 26 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automated nuclei segmentation and classification is a repetitive activity and challenging for pathological images. Due to rapid development in digital pathology, various cancer diagnosis and grading systems have been proposed, including brain image analysis [8][9][10], cervix [11], lungs [12], liver [13] and breast [5,[14][15][16][17][18]. In this regard, we can find more systems in [19][20][21][22].…”

Section: Automated Image Analysis In Histopathologymentioning

confidence: 99%

“…They used CNN as a feature extractor and support vector machine for classification purposes. Although classification accuracy improved, due to the small number of training data, it might experience overfitting [16]. Khan et al, [21] proposed a framework intended to score cancerous tumour tissues based on ER and PR hormone receptors by using image processing techniques.…”

Section: Automated Image Analysis In Histopathologymentioning

confidence: 99%

See 1 more Smart Citation

Automated Grading of Breast Cancer Histopathology Images Using Multilayered Autoencoder

Mehak¹,

Ashraf²,

Zafar³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Breast cancer (BC) is the most widely recognized cancer in women worldwide. By 2018, 627,000 women had died of breast cancer (World Health Organization Report 2018). To diagnose BC, the evaluation of tumours is achieved by analysis of histological specimens. At present, the Nottingham Bloom Richardson framework is the least expensive approach used to grade BC aggressiveness. Pathologists contemplate three elements, 1. mitotic count, 2. gland formation, and 3. nuclear atypia, which is a laborious process that witness's variations in expert's opinions. Recently, some algorithms have been proposed for the detection of mitotic cells, but nuclear atypia in breast cancer histopathology has not received much consideration. Nuclear atypia analysis is performed not only to grade BC but also to provide critical information in the discrimination of normal breast, non-invasive breast (usual ductal hyperplasia, atypical ductal hyperplasia) and pre-invasive breast (ductal carcinoma in situ) and invasive breast lesions. We proposed a deep-stacked multi-layer autoencoder ensemble with a softmax layer for the feature extraction and classification process. The classification results show the value of the multilayer autoencoder model in the evaluation of nuclear polymorphisms. The proposed method has indicated promising results, making them more fit in breast cancer grading.

show abstract

Section: Automated Image Analysis In Histopathologymentioning

confidence: 99%

Section: Automated Image Analysis In Histopathologymentioning

confidence: 99%

Automated Grading of Breast Cancer Histopathology Images Using Multilayered Autoencoder

Mehak¹,

Ashraf²,

Zafar³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…First, we find local maxima and minima; we use these to compute the upper and lower envelopes of the signal, denoted u(t) and l(t), respectively. Initializing index k = 1, we compute the mean as (20) We compute the sifted IMF, (21) We use this to update the signal (22) Now we increment k, compute new envelopes of the updated signal, and repeat the calculations in Eqs. (20)- (22) until all IMFs are computed.…”

Section: Empirical Mode Decompositionmentioning

confidence: 99%

“…Such studies employed a pre-trained network or developed new deep neural networks to classify breast cancer [12,[18][19][20]. In related work that been done in this paper and in order to be able to differentiate between benign and malignant breast cancer, many researchers have developed many machine learning techniques to classify such breast cancer images using various pre-trained networks such as visual geometry group, , and which can be applied and used on breast cancer data sets [21][22][23][24].…”

Section: Related Workmentioning

confidence: 99%

A Two-User Variational Mode Decomposition Algorithm for Blind Source Separation of Arbitrary Signals

Sud

2020

American Journal of Science & Engineering

View full text Add to dashboard Cite

Blind source separation (BSS) is a problem wherein two unknown source signals that have been combined in some fashion when collected at a single receiver must be separated. This problem is exacerbated by source signals that are time-varying, i.e. non-stationary, in nature. All commonly used techniques, such as Fourier analysis, wavelet analysis, and adaptive filtering algorithms do not apply. First, there is no training data, the data may not be digital in nature but have a random, time-varying amplitude, and there are not enough samples to estimate the signal due to the non-stationarity. A novel technique known as empirical mode decomposition (EMD) overcomes many of the issues related to non-stationarity, but suffers in noisy channels. More recently, a technique known as variational mode decomposition (VMD) was introduced that overcomes the limitations of the other techniques to reconstruct unknown, non-stationary signals; this is termed the single user (SU) VMD algorithm. In this paper, we describe a two-user VMD algorithm that improves performance over the SU algorithm by up to an order of magnitude for the problem of BSS. The two-user VMD only assumes that an estimate of the power levels of the two users may be obtained. Performance is most improved when the powers of the two signals are close to equal.

show abstract

“…DL has shown promising results in resolving this problem recently. DL efficiency, however, is dependent on training with large, annotated datasets, which unfortunately, public mammography datasets lack [9,10].…”

Section: Introductionmentioning

confidence: 99%

Automated Breast Cancer Detection Models Based on Transfer Learning

Alruwaili

Gouda

2022

Sensors

View full text Add to dashboard Cite

Breast cancer is among the leading causes of mortality for females across the planet. It is essential for the well-being of women to develop early detection and diagnosis techniques. In mammography, focus has contributed to the use of deep learning (DL) models, which have been utilized by radiologists to enhance the needed processes to overcome the shortcomings of human observers. The transfer learning method is being used to distinguish malignant and benign breast cancer by fine-tuning multiple pre-trained models. In this study, we introduce a framework focused on the principle of transfer learning. In addition, a mixture of augmentation strategies were used to prevent overfitting and produce stable outcomes by increasing the number of mammographic images; including several rotation combinations, scaling, and shifting. On the Mammographic Image Analysis Society (MIAS) dataset, the proposed system was evaluated and achieved an accuracy of 89.5% using (residual network-50) ResNet50, and achieved an accuracy of 70% using the Nasnet-Mobile network. The proposed system demonstrated that pre-trained classification networks are significantly more effective and efficient, making them more acceptable for medical imaging, particularly for small training datasets.

show abstract

Double-Shot Transfer Learning for Breast Cancer Classification from X-Ray Images

Cited by 26 publications

References 18 publications

Automated Grading of Breast Cancer Histopathology Images Using Multilayered Autoencoder

Automated Grading of Breast Cancer Histopathology Images Using Multilayered Autoencoder

A Two-User Variational Mode Decomposition Algorithm for Blind Source Separation of Arbitrary Signals

Automated Breast Cancer Detection Models Based on Transfer Learning

Contact Info

Product

Resources

About