Fine-Grained Breast Cancer Classification With Bilinear Convolutional Neural Networks (BCNNs)

Liu, Weihuang; Juhas, Mario; Zhang, Yang

doi:10.3389/fgene.2020.547327

Cited by 21 publications

(13 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we demonstrated universal encoding of diverse cancer histology images using DTRs and its usefulness in three clinically important applications. A small number of previous researchers applied B-CNN to histopathology images, but they were limited to the supervised classification of histological images into predefined classes (Wang et al, 2017;Liu et al, 2020). In this study, we have revealed that the features extracted by the universal process using pretrained B-CNN from optimized combinations of network models and layers well express complex pan-cancer histology and are practical in clinical settings beyond the classification of a certain cancer type.…”

Section: Discussionmentioning

confidence: 89%

Universal encoding of pan-cancer histology by deep texture representations

et al. 2022

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 89%

Universal encoding of pan-cancer histology by deep texture representations

et al. 2022

View full text Add to dashboard Cite

“…Table 7 is a comparison between the method in this paper and the state-of-the-art methods. Works [ 45 , 46 ] divided the dataset according to the protocol of [ 3 ], works [ 31 , 47 ] divided the dataset according to the patients, the author in [ 48 ] divided the dataset according to the images in the image-level classification, the authors in [ 39 , 40 ] divided the dataset according to the images, and works [ 49 – 51 ] did not mention whether to divide the dataset according to the patients or the images.…”

Section: Resultsmentioning

confidence: 99%

“…Yari et al [ 39 ] constructed 6 deep models with different parameter settings based on ResNet50 and DenseNet161, the highest accuracy of the MIB classification was 99.26%. Liu et al [ 40 ] introduced Bilinear Convolutional Neural Networks (BCNNs) and compared with several other deep learning methods. The accuracy of the MIB classification is 99.24%.…”

Section: Introductionmentioning

confidence: 99%

Breast cancer histopathological images classification based on deep semantic features and gray level co-occurrence matrix

Zhang

Qiao

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

Breast cancer is regarded as the leading killer of women today. The early diagnosis and treatment of breast cancer is the key to improving the survival rate of patients. A method of breast cancer histopathological images recognition based on deep semantic features and gray level co-occurrence matrix (GLCM) features is proposed in this paper. Taking the pre-trained DenseNet201 as the basic model, part of the convolutional layer features of the last dense block are extracted as the deep semantic features, which are then fused with the three-channel GLCM features, and the support vector machine (SVM) is used for classification. For the BreaKHis dataset, we explore the classification problems of magnification specific binary (MSB) classification and magnification independent binary (MIB) classification, and compared the performance with the seven baseline models of AlexNet, VGG16, ResNet50, GoogLeNet, DenseNet201, SqueezeNet and Inception-ResNet-V2. The experimental results show that the method proposed in this paper performs better than the pre-trained baseline models in MSB and MIB classification problems. The highest image-level recognition accuracy of 40×, 100×, 200×, 400× is 96.75%, 95.21%, 96.57%, and 93.15%, respectively. And the highest patient-level recognition accuracy of the four magnifications is 96.33%, 95.26%, 96.09%, and 92.99%, respectively. The image-level and patient-level recognition accuracy for MIB classification is 95.56% and 95.54%, respectively. In addition, the recognition accuracy of the method in this paper is comparable to some state-of-the-art methods.

show abstract

“…One of the most needs for automatic disease diagnosis is to distinguish different tissue components (tumour epithelium, stroma, necrosis, tumour-infiltrating lymphocytes, etc.) in H&E-stained WSIs [11][12][13]. Therefore, an initial step in automatic diagnosis is to develop a robust automatic tissue segmentation algorithm.…”

Section: Introductionmentioning

confidence: 99%

Histopathological Tissue Segmentation of Lung Cancer with Bilinear CNN and Soft Attention

Wang

Liu

et al. 2022

BioMed Research International

View full text Add to dashboard Cite

Automatic tissue segmentation in whole-slide images (WSIs) is a critical task in hematoxylin and eosin- (H&E-) stained histopathological images for accurate diagnosis and risk stratification of lung cancer. Patch classification and stitching the classification results can fast conduct tissue segmentation of WSIs. However, due to the tumour heterogeneity, large intraclass variability and small interclass variability make the classification task challenging. In this paper, we propose a novel bilinear convolutional neural network- (Bilinear-CNN-) based model with a bilinear convolutional module and a soft attention module to tackle this problem. This method investigates the intraclass semantic correspondence and focuses on the more distinguishable features that make feature output variations relatively large between interclass. The performance of the Bilinear-CNN-based model is compared with other state-of-the-art methods on the histopathological classification dataset, which consists of 107.7 k patches of lung cancer. We further evaluate our proposed algorithm on an additional dataset from colorectal cancer. Extensive experiments show that the performance of our proposed method is superior to that of previous state-of-the-art ones and the interpretability of our proposed method is demonstrated by Grad-CAM.

show abstract

Fine-Grained Breast Cancer Classification With Bilinear Convolutional Neural Networks (BCNNs)

Cited by 21 publications

References 46 publications

Universal encoding of pan-cancer histology by deep texture representations

Universal encoding of pan-cancer histology by deep texture representations

Breast cancer histopathological images classification based on deep semantic features and gray level co-occurrence matrix

Histopathological Tissue Segmentation of Lung Cancer with Bilinear CNN and Soft Attention

Contact Info

Product

Resources

About