The impact of scan number and its preprocessing in micro-FTIR imaging when applying machine learning for breast cancer subtypes classification

Increasing evidence suggests that AnxA2 contributes to invasion and metastasis of breast cancer. However, the clinical significance of AnxA2 expression in breast cancer has not been reported. The expression of AnxA2 in cell lines, tumor tissues, and serum samples of breast cancer patients were analyzed by immunoblotting, immunohistochemistry, and enzyme-linked immunosorbent assay, respectively. We found that AnxA2 was significantly upregulated in tumor tissues and serum samples of breast cancer patients compared with normal controls. The high expression of serum AnxA2 was significantly associated with tumor grades and poor survival of the breast cancer patients. Based on molecular subtypes, AnxA2 expression was significantly elevated in tumor tissues and serum samples of triple-negative breast cancer (TNBC) patients compared with other breast cancer subtypes. Our analyses on breast cancer cell lines demonstrated that secretion of AnxA2 is associated with its tyrosine 23 (Tyr23) phosphorylation in cells. The expression of non-phosphomimetic mutant of AnxA2 in HCC1395 cells inhibits its secretion from cells compared to wild-type AnxA2, which further suggest that Tyr23 phosphorylation is a critical step for AnxA2 secretion from TNBC cells. Our analysis of AnxA2 phosphorylation in clinical samples further confirmed that the phosphorylation of AnxA2 at Tyr23 was high in tumor tissues of TNBC patients compared to matched adjacent non-tumorigenic breast tissues. Furthermore, we observed that the diagnostic value of serum AnxA2 was significantly high in TNBC compared with other breast cancer subtypes. These findings suggest that serum AnxA2 concentration could be a potential diagnostic biomarker for TNBC patients.

Download Full-text

A Review of Computer-Aided Expert Systems for Breast Cancer Diagnosis

Cancers ◽

10.3390/cancers13112764 ◽

2021 ◽

Vol 13 (11) ◽

pp. 2764

Author(s):

Xin Yu Liew ◽

Nazia Hameed ◽

Jeremie Clos

Keyword(s):

Breast Cancer ◽

Machine Learning ◽

Deep Learning ◽

Main Process ◽

Learning Approaches ◽

Learning Methods ◽

Advantages And Disadvantages ◽

Computer Aided ◽

Conventional Methods ◽

The Impact

A computer-aided diagnosis (CAD) expert system is a powerful tool to efficiently assist a pathologist in achieving an early diagnosis of breast cancer. This process identifies the presence of cancer in breast tissue samples and the distinct type of cancer stages. In a standard CAD system, the main process involves image pre-processing, segmentation, feature extraction, feature selection, classification, and performance evaluation. In this review paper, we reviewed the existing state-of-the-art machine learning approaches applied at each stage involving conventional methods and deep learning methods, the comparisons within methods, and we provide technical details with advantages and disadvantages. The aims are to investigate the impact of CAD systems using histopathology images, investigate deep learning methods that outperform conventional methods, and provide a summary for future researchers to analyse and improve the existing techniques used. Lastly, we will discuss the research gaps of existing machine learning approaches for implementation and propose future direction guidelines for upcoming researchers.

Download Full-text