Pre‐trained convolutional neural networks as feature extractors for diagnosis of breast cancer using histopathology

Saxena, Shweta; Shukla, Sanyam; Gyanchandani, Manasi

doi:10.1002/ima.22399

Cited by 79 publications

(41 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In deep ANNs, transfer learning strategies are applied more frequently in the classification of breast histopathological images in recent four years. The papers involved in this article are [56], [57], [64], [65], [78], [82], [85], [86], [100], [106], [108], [112], [121], [125], [126], [129], [137], [155]. Transfer learning is a method used to transfer knowledge acquired from one task to resolve another [157].…”

Section: B Analysis Of Deep Ann Methodsmentioning

confidence: 99%

“…(2) Using a pre-trained network as a feature extractor, and then using these features to train a new classifier (e.g. [56], [64], [78], [82], [85], [86], [106], [108], [112], [126], [137], [155]). In the transfer learning, the VGG16 [158], VGG19, and ResNet50 [159] are very popular pre-trained CNN models due to their more in-depth architectures [64].…”

Section: B Analysis Of Deep Ann Methodsmentioning

confidence: 99%

“…In [86], a novel feature extraction method is proposed for the classification of breast histopathological images. First, the images are divided into small pieces that are not overlapped.…”

Section: Related Work Of Breakhis In 2020mentioning

confidence: 99%

See 2 more Smart Citations

A Comprehensive Review for Breast Histopathology Image Analysis Using Classical and Deep Neural Networks

et al. 2020

View full text Add to dashboard Cite

Breast cancer is one of the most common and deadliest cancers among women. Since histopathological images contain sufficient phenotypic information, they play an indispensable role in the diagnosis and treatment of breast cancers. To improve the accuracy and objectivity of Breast Histopathological Image Analysis (BHIA), Artificial Neural Network (ANN) approaches are widely used in the segmentation and classification tasks of breast histopathological images. In this review, we present a comprehensive overview of the BHIA techniques based on ANNs. First of all, we categorize the BHIA systems into classical and deep neural networks for in-depth investigation. Then, the relevant studies based on BHIA systems are presented. After that, we analyze the existing models to discover the most suitable algorithms. Finally, publicly accessible datasets, along with their download links, are provided for the convenience of future researchers.

show abstract

Section: B Analysis Of Deep Ann Methodsmentioning

confidence: 99%

Section: B Analysis Of Deep Ann Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Review for Breast Histopathology Image Analysis Using Classical and Deep Neural Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The proposed strategy is divided into three steps: patch‐generation, feature extraction, and classification, as shown by Figure 1. For the BreakHis dataset, the patch‐generation and feature extraction methods are the same as our recent work 26 . For the BisQue dataset, the original image size of breast cancer histopathology under consideration is 896 × 768 × 3 pixels.…”

Section: Proposed Methodsologymentioning

confidence: 99%

Breast cancer histopathology image classification using kernelized weighted extreme learning machine

Saxena

Shukla

Gyanchandani

2020

Int J Imaging Syst Tech

Self Cite

View full text Add to dashboard Cite

Histopathology is considered as the gold standard for diagnosing breast cancer. Traditional machine learning (ML) algorithm provides a promising performance for cancer diagnosis if the training dataset is balanced. Nevertheless, if the training dataset is imbalanced the performance of the ML model is skewed toward the majority class. It may pose a problem for the pathologist because if the benign sample is misclassified as malignant, then a pathologist could make a misjudgment about the diagnosis. A limited investigation has been done in literature for solving the class imbalance problem in computer‐aided diagnosis (CAD) of breast cancer using histopathology. This work proposes a hybrid ML model to solve the class imbalance problem. The proposed model employs pretrained ResNet50 and the kernelized weighted extreme learning machine for CAD of breast cancer using histopathology. The breast cancer histopathological images are obtained from publicly available BreakHis and BisQue datasets. The proposed method achieved a reasonable performance for the classification of the minority as well as the majority class instances. In comparison, the proposed approach outperforms the state‐of‐the‐art ML models implemented in previous studies using the same training‐testing folds of the publicly accessible BreakHis dataset.

show abstract

“…Shwetha et al had developed a deep learning model for the diagnosis of breast cancer using histopathology. They had used pretrained CNNs as feature extractors 13 . They have used the pretrained models such as ResNet50‐SVM, ResNet101‐SVM, and AlexNet‐SVM.…”

Section: Introductionmentioning

confidence: 99%

Development of automatic glioma brain tumor detection system using deep convolutional neural networks

Kalaiselvi

Padmapriya

Sriramakrishnan

et al. 2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

We have developed six convolutional neural network (CNN) models for finding optimal brain tumor detection system on high‐grade glioma and low‐grade glioma lesions from voluminous magnetic resonance imaging human brain scans. Glioma is the most common form of brain tumor. The models are constructed based on the different combinations and settings of hyperparameters with conventional CNN architecture. The six models are two layers with five epochs, five layers with dropout, five layers with stopping criteria (FLSC), FLSC and dropout (FLSCD), FLSC and batch normalization (FLSCBN), and FLSCBN and dropout. The models were trained and tested with BraTS2013 and whole brain atlas data sets. Among them, FLSCBN model yielded the best classification results for brain tumor detection. Experimental results revealed that our deep learning approach was better than the conventional state‐of‐art methods.

show abstract

Pre‐trained convolutional neural networks as feature extractors for diagnosis of breast cancer using histopathology

Cited by 79 publications

References 45 publications

A Comprehensive Review for Breast Histopathology Image Analysis Using Classical and Deep Neural Networks

A Comprehensive Review for Breast Histopathology Image Analysis Using Classical and Deep Neural Networks

Breast cancer histopathology image classification using kernelized weighted extreme learning machine

Development of automatic glioma brain tumor detection system using deep convolutional neural networks

Contact Info

Product

Resources

About