AF-SENet: Classification of Cancer in Cervical Tissue Pathological Images Based on Fusing Deep Convolution Features

Huang, Pan; Tan, Xiaoheng; Chen, Chen; Li, Yongming

doi:10.3390/s21010122

Cited by 38 publications

(17 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They showed that the accuracy of normal-cancer classification was high (99.64%), but the accuracy of the LSIL-HSIL classification was 76.34%. A recent study that classified cervical tissue pathological images based on fusing deep convolution features has been published [ 37 ]. The researchers analyzed the dataset comprising small-sized images cropped from 468 WSIs, including those of normal tissues, LSIL, HSIL, and cancer.…”

Section: Discussionmentioning

confidence: 99%

Automated Diagnosis of Cervical Intraepithelial Neoplasia in Histology Images via Deep Learning

et al. 2022

View full text Add to dashboard Cite

Artificial intelligence has enabled the automated diagnosis of several cancer types. We aimed to develop and validate deep learning models that automatically classify cervical intraepithelial neoplasia (CIN) based on histological images. Microscopic images of CIN3, CIN2, CIN1, and non-neoplasm were obtained. The performances of two pre-trained convolutional neural network (CNN) models adopting DenseNet-161 and EfficientNet-B7 architectures were evaluated and compared with those of pathologists. The dataset comprised 1106 images from 588 patients; images of 10% of patients were included in the test dataset. The mean accuracies for the four-class classification were 88.5% (95% confidence interval [CI], 86.3–90.6%) by DenseNet-161 and 89.5% (95% CI, 83.3–95.7%) by EfficientNet-B7, which were similar to human performance (93.2% and 89.7%). The mean per-class area under the receiver operating characteristic curve values by EfficientNet-B7 were 0.996, 0.990, 0.971, and 0.956 in the non-neoplasm, CIN3, CIN1, and CIN2 groups, respectively. The class activation map detected the diagnostic area for CIN lesions. In the three-class classification of CIN2 and CIN3 as one group, the mean accuracies of DenseNet-161 and EfficientNet-B7 increased to 91.4% (95% CI, 88.8–94.0%), and 92.6% (95% CI, 90.4–94.9%), respectively. CNN-based deep learning is a promising tool for diagnosing CIN lesions on digital histological images.

show abstract

Section: Discussionmentioning

confidence: 99%

Automated Diagnosis of Cervical Intraepithelial Neoplasia in Histology Images via Deep Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Thus we decided to do exploratory research with the following different fusion strategies: (1) On the basis of different pre-training models, we use all convolutional layers to realize feature extraction and fusion, as shown in Fig. 6 , fusion strategy 1 [ 48 ]. (2) On the basis of the aforementioned strategy, we abandon InceptionRensENetV2 as the feature extractor, and use the partial convolutional layers of the other three pre-training models to extract and fuse features, as shown in Fig.…”

Section: Methodsmentioning

confidence: 99%

“…To better evaluate the reliability and generalization ability of models, in this paper, we use the receiver operating characteristic (ROC) curve to judge the performance of our built classification models and the area under ROC curve (AUC) to verify the generalization ability of the models in a more intuitive way [ 12 , 48 ].…”

Section: Methodsmentioning

confidence: 99%

Fusing pre-trained convolutional neural networks features for multi-differentiated subtypes of liver cancer on histopathological images

Dong

Zhou

et al. 2022

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Liver cancer is a malignant tumor with high morbidity and mortality, which has a tremendous negative impact on human survival. However, it is a challenging task to recognize tens of thousands of histopathological images of liver cancer by naked eye, which poses numerous challenges to inexperienced clinicians. In addition, factors such as long time-consuming, tedious work and huge number of images impose a great burden on clinical diagnosis. Therefore, our study combines convolutional neural networks with histopathology images and adopts a feature fusion approach to help clinicians efficiently discriminate the differentiation types of primary hepatocellular carcinoma histopathology images, thus improving their diagnostic efficiency and relieving their work pressure. In this study, for the first time, 73 patients with different differentiation types of primary liver cancer tumors were classified. We performed an adequate classification evaluation of liver cancer differentiation types using four pre-trained deep convolutional neural networks and nine different machine learning (ML) classifiers on a dataset of liver cancer histopathology images with multiple differentiation types. And the test set accuracy, validation set accuracy, running time with different strategies, precision, recall and F1 value were used for adequate comparative evaluation. Proved by experimental results, fusion networks (FuNet) structure is a good choice, which covers both channel attention and spatial attention, and suppresses channel interference with less information. Meanwhile, it can clarify the importance of each spatial location by learning the weights of different locations in space, then apply it to the study of classification of multi-differentiated types of liver cancer. In addition, in most cases, the Stacking-based integrated learning classifier outperforms other ML classifiers in the classification task of multi-differentiation types of liver cancer with the FuNet fusion strategy after dimensionality reduction of the fused features by principle component analysis (PCA) features, and a satisfactory result of 72.46% is achieved in the test set, which has certain practicality.

show abstract

“…In another study, Huang et al [ 23 ] suggest extracting deep convolutional features by fine-tuning pre-trained deep network models, including ResNet-50V2, DenseNet-121, InceptionV3, VGG19 Net, and Inception ResNet, and then local binary patterns and a histogram of the oriented gradient are used to extract traditional image features. The serial fusion effect of the deep features extracted by ResNet-50V2 and DenseNet-121 (C5) is the best, with the average classification accuracy reaching 95.33%, which is 1.07% higher than ResNet-50V2 and 1.05% higher than DenseNet-121.…”

Section: Review Of Studymentioning

confidence: 99%

“…Furthermore, the recognition ability is significantly improved to 90.89%, which is 2.88% higher than ResNet-50V2 and 2.1% higher than DenseNet-121. Thus, this method significantly improves the accuracy and generalisation ability of pathological cervical whole slice image (WSI) recognition by fusing deep features [ 23 ]. Mulmule and Kanphade [ 24 ] proposed method that employs adaptive fuzzy k-means clustering to separate cell from the unwanted background of the pathological Pap smear image.…”

Section: Review Of Studymentioning

confidence: 99%

Cervical Net: A Novel Cervical Cancer Classification Using Feature Fusion

et al. 2022

View full text Add to dashboard Cite

Cervical cancer, a common chronic disease, is one of the most prevalent and curable cancers among women. Pap smear images are a popular technique for screening cervical cancer. This study proposes a computer-aided diagnosis for cervical cancer utilising the novel Cervical Net deep learning (DL) structures and feature fusion with Shuffle Net structural features. Image acquisition and enhancement, feature extraction and selection, as well as classification are the main steps in our cervical cancer screening system. Automated features are extracted using pre-trained convolutional neural networks (CNN) fused with a novel Cervical Net structure in which 544 resultant features are obtained. To minimise dimensionality and select the most important features, principal component analysis (PCA) is used as well as canonical correlation analysis (CCA) to obtain the best discriminant features for five classes of Pap smear images. Here, five different machine learning (ML) algorithms are fed into these features. The proposed strategy achieved the best accuracy ever obtained using a support vector machine (SVM), in which in which fused features between Cervical Net and Shuffle Net is 99.1% for all classes.

show abstract

AF-SENet: Classification of Cancer in Cervical Tissue Pathological Images Based on Fusing Deep Convolution Features

Cited by 38 publications

References 41 publications

Automated Diagnosis of Cervical Intraepithelial Neoplasia in Histology Images via Deep Learning

Automated Diagnosis of Cervical Intraepithelial Neoplasia in Histology Images via Deep Learning

Fusing pre-trained convolutional neural networks features for multi-differentiated subtypes of liver cancer on histopathological images

Cervical Net: A Novel Cervical Cancer Classification Using Feature Fusion

Contact Info

Product

Resources

About