Robust automatic breast cancer staging using a combination of functional genomics and image-omics

Breast Cancer Pathological Image Classification Based on the Multiscale CNN Squeeze Model

The use of an automatic histopathological image identification system is essential for expediting diagnoses and lowering mistake rates. Although it is of enormous clinical importance, computerized breast cancer multiclassification using histological pictures has rarely been investigated. A deep learning-based classification strategy is suggested to solve the challenge of automated categorization of breast cancer pathology pictures. The attention model that acts on the feature channel is the channel refinement model. The learned channel weight may be used to reduce superfluous features when implementing the feature channel. To increase classification accuracy, calibration is necessary. To increase the accuracy of channel recalibration findings, a multiscale channel recalibration model is provided, and the msSE-ResNet convolutional neural network is built. The multiscale properties flow through the network's highest pooling layer. The channel weights obtained at different scales are delivered into line fusion and used as input to the next channel recalibration model, which may improve the results of channel recalibration. The experimental findings reveal that the spatial recalibration model fares poorly on the job of classifying breast cancer pathology pictures when applied to the semantic segmentation of brain MRI images. The public BreakHis dataset is used to conduct the experiment. The network performs benign/malignant breast pathology picture classification collected at various magnifications with a classification accuracy of 88.87 percent, according to experimental data. The diseased images are also more resilient. Experiments on pathological pictures at various magnifications show that msSE-ResNet34 is capable of performing well when used to classify pathological images at various magnifications.

Correlation of breast cancer microcirculation construction with tumor stem cells (CSCs) and epithelial-mesenchymal transition (EMT) based on contrast-enhanced ultrasound (CEUS)

Objective

This study is to explore the correlation between the contrast-enhanced ultrasound (CEUS) characteristics of breast cancer and the epithelial-mesenchyme transformation (EMT).

Methods

Totally 119 patients of breast cancer underwent CEUS. Tissues in the active area were collected and subjected to the immunohistochemical detection, PT-PCR and Western blot. Correlation analysis was conducted between the clinical pathological parameters and the CEUS indicators.

Results

The expression levels of CD44, N-cadherin, and β-catenin in breast cancer tissues were higher than those in adjacent tissues (P<0.05). However, the expression levels of CD24 and E-cadherin in breast cancer tissues were lower than those in adjacent tissues (P<0.05). There was no significant difference in E-cadherin mRNA and Vimentin levels between cancer and adjacent tissues (P>0.05). The expressions were up-regulated in the CSCs, with higher histological grade, lymph node metastasis, and negative estrogen receptor (ER) expression. Smaller breast tumors, with no lymph node metastasis, lower clinical stage, and positive ER expression, tended to exhibit the up-regulated epithelial phenotype. Breast tumors, with high histological grade, lymph node metastasis, high clinical staging grade, and negative ER expression, tended to exhibit the up-regulated interstitial phenotype. The peak intensity of the time-intensity curve (TIC) for the CEUS was positively correlated with the CSC marker CD44 and the interstitial phenotype marker N-cadherin. The starting time of enhancement was negatively correlated with the N-cadherin. Area under the curve was positively correlated with the expression of CD44 and N-cadherin, while negatively correlated with the epithelial phenotype marker β-catenin. The time to peak was negatively correlated with the interstitial phenotypes Vimentin and N-cadherin, with no correlation with the E-cadherin or β-catenin.

Conclusion

Breast cancers show the enlarged lesions after enlargement and perfusion defect for the CEUS. The fast-in pattern, high enhancement, and high perfusion in the TIC are correlated with the CSCs and EMT expressions, suggesting poor disease prognosis.

Relationship of shear wave elastography anisotropy with tumor stem cells and epithelial-mesenchymal transition in breast cancer

Background

This study is to examine the feasibility of shear wave elastography (SWE) anisotropy in assessing the prognosis of breast cancer.

Methods

We enrolled 119 breast cancer patients from January 2017 to October 2019. SWE was performed before operation. Emax (maximum elasticity value), Emean (average elasticity value), Esd (standard deviation of the lesion elasticity value), Eratio (elasticity value of adipose tissue), anisotropy coefficient and difference were recorded. After operation, we collected clinical pathological data, and performed immunohistochemistry and real-time PCR tests on CD44, CD24, E-cadherin, β-catenin, vimentin and N-cadherin. Finally, we analyzed the correlation among parameters of SWE, anisotropy and clinicopathology, and markers of CSCs (cancer stem cells) and EMT (epithelial-mesenchymal transition).

Results

Emax, Emean and Esd of the cross section were higher than those of the longitudinal section. Breast cancer with a higher elastic modulus was often accompanied by a hyperechoic halo, which was manifested as mixed echo and post-echo attenuation, and was accompanied by a higher BI-RADS (breast imaging reporting and data system) classification. When breast cancer had hyperechoic halo and weakened posterior echo, SWE of the lesion showed more obvious anisotropy. In addition, larger diameter of the longitudinal section indicated higher stiffness of the cross section. Correlation analysis showed that E-cadherin was negatively correlated with SWE in longitudinal section. CD44, N-cadherin, β-catenin were positively correlated with SWE in longitudinal and cross sections. Vimentin and CD24 had no correlation with SWE parameters.

Conclusion

SWE of breast cancer is anisotropic. The cross-sectional SWE is better than the longitudinal SWE, Emax is better than Emean, the anisotropy of SWE is better than SWE, and the anisotropy factor is better than the anisotropy difference.

Review of Statistical Learning Methods in Integrated Omics Studies (An Integrated Information Science)

Integrated omics is becoming a new channel for investigating the complex molecular system in modern biological science and sets a foundation for systematic learning for precision medicine. The statistical/machine learning methods that have emerged in the past decade for integrated omics are not only innovative but also multidisciplinary with integrated knowledge in biology, medicine, statistics, machine learning, and artificial intelligence. Here, we review the nontrivial classes of learning methods from the statistical aspects and streamline these learning methods within the statistical learning framework. The intriguing findings from the review are that the methods used are generalizable to other disciplines with complex systematic structure, and the integrated omics is part of an integrated information science which has collated and integrated different types of information for inferences and decision making. We review the statistical learning methods of exploratory and supervised learning from 42 publications. We also discuss the strengths and limitations of the extended principal component analysis, cluster analysis, network analysis, and regression methods. Statistical techniques such as penalization for sparsity induction when there are fewer observations than the number of features and using Bayesian approach when there are prior knowledge to be integrated are also included in the commentary. For the completeness of the review, a table of currently available software and packages from 23 publications for omics are summarized in the appendix.

An Assessment of Imaging Informatics for Precision Medicine in Cancer

Objectives: Precision medicine requires the measurement, quantification, and cataloging of medical characteristics to identify the most effective medical intervention. However, the amount of available data exceeds our current capacity to extract meaningful information. We examine the informatics needs to achieve precision medicine from the perspective of quantitative imaging and oncology. Methods: The National Cancer Institute (NCI) organized several workshops on the topic of medical imaging and precision medicine. The observations and recommendations are summarized herein. Results: Recommendations include: use of standards in data collection and clinical correlates to promote interoperability; data sharing and validation of imaging tools; clinician's feedback in all phases of research and development; use of open-source architecture to encourage reproducibility and reusability; use of challenges which simulate real-world situations to incentivize innovation; partnership with industry to facilitate commercialization; and education in academic communities regarding the challenges involved with translation of technology from the research domain to clinical utility and the benefits of doing so. Conclusions: This article provides a survey of the role and priorities for imaging informatics to help advance quantitative imaging in the era of precision medicine. While these recommendations were drawn from oncology, they are relevant and applicable to other clinical domains where imaging aids precision medicine.