Computer assisted recognition of breast cancer in biopsy images via fusion of nucleus-guided deep convolutional features

George, Kalpana; Sankaran, Praveen; K, Paul Joseph

doi:10.1016/j.cmpb.2020.105531

Cited by 27 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 8 shows that the method proposed in this paper is superior to many state-of-the-art methods in benign and malignant tumor recognition, both for the image level and the patient level. It is worth mentioning that works (35)(36)(37)(38)(39)(40)(41)(42)(43) did not split training and test set according to the protocol of (9), works (44,45) adopted the existed protocol, and works (46,47) randomly divided training set (70%) and test set (30%), but they did not mention whether it was the same as the protocol. Although the recognition accuracy of the works (37, 39, 41-43, 46, 47) is significantly higher than that of our method, they all use deep learning model, which requires a large number of labeled training samples and consumes longer training time.…”

Section: Experiments Resultsmentioning

confidence: 99%

Breast Cancer Histopathological Images Recognition Based on Low Dimensional Three-Channel Features

Qiao

Zhang

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

Breast cancer (BC) is the primary threat to women’s health, and early diagnosis of breast cancer is imperative. Although there are many ways to diagnose breast cancer, the gold standard is still pathological examination. In this paper, a low dimensional three-channel features based breast cancer histopathological images recognition method is proposed to achieve fast and accurate breast cancer benign and malignant recognition. Three-channel features of 10 descriptors were extracted, which are gray level co-occurrence matrix on one direction (GLCM1), gray level co-occurrence matrix on four directions (GLCM4), average pixel value of each channel (APVEC), Hu invariant moment (HIM), wavelet features, Tamura, completed local binary pattern (CLBP), local binary pattern (LBP), Gabor, histogram of oriented gradient (Hog), respectively. Then support vector machine (SVM) was used to assess their performance. Experiments on BreaKHis dataset show that GLCM1, GLCM4 and APVEC achieved the recognition accuracy of 90.2%-94.97% at the image level and 89.18%-94.24% at the patient level, which is better than many state-of-the-art methods, including many deep learning frameworks. The experimental results show that the breast cancer recognition based on high dimensional features will increase the recognition time, but the recognition accuracy is not greatly improved. Three-channel features will enhance the recognizability of the image, so as to achieve higher recognition accuracy than gray-level features.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Breast Cancer Histopathological Images Recognition Based on Low Dimensional Three-Channel Features

Qiao

Zhang

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…Instead of examining all patches, the authors of [18] proposed to focus on selected nuclei patches, which are extracted using Laplacian blob detector algorithm. The features are extracted using CNN and image-wise classification is performed using patch probability decision method and patch feature fusion.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning Models Combining for Breast Cancer Histopathology Image Classification

Elmannai¹,

Hamdi²,

Algarni³

2021

IJCIS

View full text Add to dashboard Cite

Breast cancer is one of the foremost reasons of death among women in the world. It has the largest mortality rate compared to the types of cancer accounting for 1.9 million per year in 2020. An early diagnosis may increase the survival rates. To this end, automating the analysis and the diagnosis allows to improve the accuracy and to reduce processing time. However, analyzing breast imagery's is non-trivial and may lead to experts' disagreements. In this research, we focus on breast cancer histopathological images acquired using the microscopic scan of breast tissues. We present combined two deep convolutional neural networks (DCNNs) to extract distinguished image features using transfer learning. The pre-trained Inception and the Xceptions models are used in parallel. Then, the feature maps are combined and reduced by dropout before being fed to the last fully connected layers for classification. We follow a sub-image classification then a whole image classification based on majority vote and maximum probability rules. Four tissue malignancy levels are considered: normal, benign, in situ carcinoma, and invasive carcinoma. The experimentations are performed to the Breast Cancer Histology (BACH) dataset. The overall accuracy for the sub-image classification is 97.29% and for the carcinoma cases the sensitivity achieved 99.58%. The whole image classification overall accuracy reaches 100% by majority vote and 95% by maximum probability fusion decision. The numerical results showed that our proposed approach outperforms the previous methods in terms of accuracy and sensitivity. The proposed design allows an extension to whole-slide histology images classification.

show abstract

“…where, are the strides which are parameters of neural network that changes the movement of images, 1 , 2 , and 3 are the filter of feature maps, the other layers like ReLU and FC are explained in Eqs. (5,6).…”

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

“…The CAD serves as the basis for counting the cells and for the study of subcellular morphology such as the investigation of shape, texture, and size of the cellular components. The detection of cell nuclei is difficult during the analysis of histopathological images such as target cells that are in various states [6]. The smaller cells will be surrounded by the background clutters made up of histopathological structures such as collagen, capillaries, etc., along with the irrelevant visual aspects and artefacts which occur during the acquisition of images [7].…”

Section: Introductionmentioning

confidence: 99%

Multi-Objective Feature Selection Method by Using ACO with PSO Algorithm for Breast Cancer Detection

Saturi¹,

Premchand²

2021

IJIES

View full text Add to dashboard Cite

Breast cancer is the second most cause of cancer deaths in women after lung cancer, and the treatment and diagnosis of breast cancer at an earlier stage is an important requirement for the reduction of the mortality rate. The detection of cell nuclei is the core operation involved in Computer-Aided Diagnosis (CAD) that is used in breast cancer detection. The existing deep learning methods used contour information for accurate detection. But, the existing cancer detection method extracted only the semantic information from the former layer and was not provided the details about the semantic shallow layers in detecting cancer. To solve such an issue, a multi-objective feature selection method was proposed by using Ant Colony Optimization (ACO) with Particle Swarm Optimization (PSO) for the detection of breast cancer. The proposed method utilized the BreakHis dataset and data augmentation was applied to analyze the internal morphological features of the images. The features were extracted by using Convolutional Neural Network (CNN), Histogram of Gradients (HoG) and Local Ternary Pattern (LTP). Then, the features are selected by the proposed multi-objective feature selection method by using ACO with PSO. The selected features are forwarded to the Long Short Term Memory (LSTM) network for the process of classification. The proposed multi-objective feature selection method has the advantage of minimizing the features and reduces the rate of error classification, through a selection of optimal features to increase the rate of breast cancer detection. The proposed multi-objective feature selection method achieved a higher accuracy rate of 95.72% in the detection of breast cancer. Whereas, the existing method showed an accuracy of 93.68% in the detection of breast cancer.

show abstract

Computer assisted recognition of breast cancer in biopsy images via fusion of nucleus-guided deep convolutional features

Cited by 27 publications

References 27 publications

Breast Cancer Histopathological Images Recognition Based on Low Dimensional Three-Channel Features

Breast Cancer Histopathological Images Recognition Based on Low Dimensional Three-Channel Features

Deep Learning Models Combining for Breast Cancer Histopathology Image Classification

Multi-Objective Feature Selection Method by Using ACO with PSO Algorithm for Breast Cancer Detection

Contact Info

Product

Resources

About