Breast cancer cell nuclei classification in histopathology images using deep neural networks

Feng, Yangqin; Zhang, Lei; Zhang, Yi

doi:10.1007/s11548-017-1663-9

Cited by 64 publications

(31 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…MLP is a supervised classification system that consists of at least three layers of nodes: the first layer is the input layer, the middle layer is the hidden layer, and the last layer is the output layer. Input and output layers are used to feed in data and obtain the output results, respectively [23][24][25][26]. However, the hidden layer can be modified to increase the complexity of the model.…”

Section: Mlp Classificationmentioning

confidence: 99%

Multi-Features Classification of Prostate Carcinoma Observed in Histological Sections: Analysis of Wavelet-Based Texture and Colour Features

Bhattacharjee

Kim

Park

et al. 2019

Cancers

View full text Add to dashboard Cite

Microscopic biopsy images are coloured in nature because pathologists use the haematoxylin and eosin chemical colour dyes for biopsy examinations. In this study, biopsy images are used for histological grading and the analysis of benign and malignant prostate tissues. The following PCa grades are analysed in the present study: benign, grade 3, grade 4, and grade 5. Biopsy imaging has become increasingly important for the clinical assessment of PCa. In order to analyse and classify the histological grades of prostate carcinomas, pixel-based colour moment descriptor (PCMD) and gray-level co-occurrence matrix (GLCM) methods were used to extract the most significant features for multilayer perceptron (MLP) neural network classification. Haar wavelet transformation was carried out to extract GLCM texture features, and colour features were extracted from RGB (red/green/blue) colour images of prostate tissues. The MANOVA statistical test was performed to select significant features based on F-values and P-values using the R programming language. We obtained an average highest accuracy of 92.7% using level-1 wavelet texture and colour features. The MLP classifier performed well, and our study shows promising results based on multi-feature classification of histological sections of prostate carcinomas.

show abstract

Section: Mlp Classificationmentioning

confidence: 99%

Multi-Features Classification of Prostate Carcinoma Observed in Histological Sections: Analysis of Wavelet-Based Texture and Colour Features

Bhattacharjee

Kim

Park

et al. 2019

Cancers

View full text Add to dashboard Cite

show abstract

“…Ren et al (19) proposed a novel manifold regularized classification DNN to enhance CT image-based lung nodule classification. Feng et al (20) developed an end-to-end DNN model that can achieve promising performance in breast cancer cell nuclei classification.…”

Section: Introductionmentioning

confidence: 99%

“…Feng et al. ( 20 ) developed an end-to-end DNN model that can achieve promising performance in breast cancer cell nuclei classification. Considering the fact that deep learning requires a larger sample size than radiomics, we were interested to find out how these machine and deep learning algorithms performed to identify benign and malignant sacral tumors based on our relatively large sample size.…”

Section: Introductionmentioning

confidence: 99%

Machine and Deep Learning Based Radiomics Models for Preoperative Prediction of Benign and Malignant Sacral Tumors

et al. 2020

View full text Add to dashboard Cite

Purpose: To assess the performance of deep neural network (DNN) and machine learning based radiomics on 3D computed tomography (CT) and clinical characteristics to predict benign or malignant sacral tumors. Materials and methods: This single-center retrospective analysis included 459 patients with pathologically proven sacral tumors. After semi-automatic segmentation, 1,316 hand-crafted radiomics features of each patient were extracted. All models were built on training set (321 patients) and tested on validation set (138 patients). A DNN model and four machine learning classifiers (logistic regression [LR], random forest [RF], support vector machine [SVM] and k-nearest neighbor [KNN]) based on CT features and clinical characteristics were built, respectively. The area under the receiver operating characteristic curve (AUC) and accuracy (ACC) were used to evaluate different models. Results: In total, 459 patients (255 males, 204 females; mean age of 42.1 ± 17.8 years, range 4-82 years) were enrolled in this study, including 206 cases of benign tumor and 253 cases of malignant tumor. The sex, age and tumor size had significant differences between the benign tumors and malignant tumors (c 2 sex = 10.854, Z age = −6.616, Z size = 2.843, P < 0.05). The radscore, sex, and age were important indicators for differentiating benign and malignant sacral tumors (odds ratio [OR]1 = 2.492, OR2 = 2.236, OR3 = 1.037, P < 0.01). Among the four clinical-radiomics models (RMs), clinical-LR had the best performance in the validation set (AUC = 0.84, ACC = 0.81). The clinical-DNN model also achieved a high performance (an AUC of 0.83 and an ACC of 0.76 in the validation set) in identifying benign and malignant sacral tumors. Conclusions: Both the clinical-LR and clinical-DNN models would have a high impact on assisting radiologists in their clinical diagnosis of sacral tumors.

show abstract

“…This systematic review aimed to evaluate the accuracy of computer image processing for performing the diagnosis of odontogenic cysts in comparison to the diagnosis previously determined by histopathologists using both histological and clinical information from the respective patients. In recent years, many attempts have been made to use automated machine vision systems for the analysis of medical images ( 27 ), including breast cancer ( 28 ) and colorectal cancer ( 29 ), which affect a large number of people around the world. However, each study considers a specific method depending on the characteristics of the disease of interest.…”

Section: Discussionmentioning

confidence: 99%

Accuracy of computer-aided image analysis in the diagnosis of odontogenic cysts: A systematic review

Bittencourt

Mafra²,

Julia³

et al. 2021

Med Oral

View full text Add to dashboard Cite

Background This study aimed to search for scientific evidence concerning the accuracy of computer-assisted analysis for diagnosing odontogenic cysts. Material and Methods A systematic review was conducted according to the PRISMA statements and considering eleven databases, including the grey literature. Protocol was registered in PROSPERO (CRD 42020189349). The PECO strategy was used to define the eligibility criteria and only studies involving diagnostic accuracy were included. Their risk of bias was investigated using the Joanna Briggs Institute Critical Appraisal tool. Results Out of 437 identified citations, five papers, published between 2006 and 2019, fulfilled the criteria and were included in this systematic review. A total of 5,264 images from 508 lesions, classified as radicular cyst, odontogenic keratocyst, lateral periodontal cyst, glandular odontogenic cyst, or dentigerous cyst, were analyzed. All selected articles scored low risk of bias. In three studies, the best performances were achieved when the two subtypes of odontogenic keratocysts (solitary or syndromic) were pooled together, the case-wise analysis showing a success rate of 100% for odontogenic keratocysts and radicular cysts, in one of them. In two studies, the dentigerous cyst was associated with the majority of misclassifications, and its omission from the dataset improved significantly the classification rates. Conclusions The overall evaluation showed all studies presented high accuracy rates of computer-aided systems in classifying odontogenic cysts in digital images of histological tissue sections. However, due to the heterogeneity of the studies, a meta-analysis evaluating the outcomes of interest was not performed and a pragmatic recommendation about their use is not possible. Key words: Computer-assisted diagnosis, computer-assisted image analysis, computer-assisted image processing, odontogenic cysts, keratocysts, radicular cysts.

show abstract

Breast cancer cell nuclei classification in histopathology images using deep neural networks

Abstract: We propose an end-to-end DNN model for cell nuclei and non-nuclei classification of histopathology images. It demonstrates that the proposed method can achieve promising performance in cell nuclei classification, and the proposed method is suitable for the cell nuclei classification task.

Cited by 64 publications

References 29 publications

Multi-Features Classification of Prostate Carcinoma Observed in Histological Sections: Analysis of Wavelet-Based Texture and Colour Features

Multi-Features Classification of Prostate Carcinoma Observed in Histological Sections: Analysis of Wavelet-Based Texture and Colour Features

Machine and Deep Learning Based Radiomics Models for Preoperative Prediction of Benign and Malignant Sacral Tumors

Accuracy of computer-aided image analysis in the diagnosis of odontogenic cysts: A systematic review

Contact Info

Product

Resources

About