Classifying Breast Cancer Tissue by Raman Spectroscopy with One-dimensional Convolutional Neural Network

Author(s):  
Danying Ma ◽  
Linwei Shang ◽  
Jinlan Tang ◽  
Yilin Bao ◽  
Juanjuan Fu ◽  
...  
2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Siti Norbaini Sabtu ◽  
S. F. Abdul Sani ◽  
L. M. Looi ◽  
S. F. Chiew ◽  
Dharini Pathmanathan ◽  
...  

AbstractThe epithelial-mesenchymal transition (EMT) is a crucial process in cancer progression and metastasis. Study of metabolic changes during the EMT process is important in seeking to understand the biochemical changes associated with cancer progression, not least in scoping for therapeutic strategies aimed at targeting EMT. Due to the potential for high sensitivity and specificity, Raman spectroscopy was used here to study the metabolic changes associated with EMT in human breast cancer tissue. For Raman spectroscopy measurements, tissue from 23 patients were collected, comprising non-lesional, EMT and non-EMT formalin-fixed and paraffin embedded breast cancer samples. Analysis was made in the fingerprint Raman spectra region (600–1800 cm−1) best associated with cancer progression biochemical changes in lipid, protein and nucleic acids. The ANOVA test followed by the Tukey’s multiple comparisons test were conducted to see if there existed differences between non-lesional, EMT and non-EMT breast tissue for Raman spectroscopy measurements. Results revealed that significant differences were evident in terms of intensity between the non-lesional and EMT samples, as well as the EMT and non-EMT samples. Multivariate analysis involving independent component analysis, Principal component analysis and non-negative least square were used to analyse the Raman spectra data. The results show significant differences between EMT and non-EMT cancers in lipid, protein, and nucleic acids. This study demonstrated the capability of Raman spectroscopy supported by multivariate analysis in analysing metabolic changes in EMT breast cancer tissue.


2015 ◽  
Vol 48 (6) ◽  
pp. 393-402
Author(s):  
L. Rocha-Osornio ◽  
J. L. Pichardo-Molina ◽  
G. Barbosa-Sabanero ◽  
J. M. de la Roca ◽  
C. Frausto-Reyes ◽  
...  

2020 ◽  
Vol 14 ◽  
Author(s):  
Lahari Tipirneni ◽  
Rizwan Patan

Abstract:: Millions of deaths all over the world are caused by breast cancer every year. It has become the most common type of cancer in women. Early detection will help in better prognosis and increases the chance of survival. Automating the classification using Computer-Aided Diagnosis (CAD) systems can make the diagnosis less prone to errors. Multi class classification and Binary classification of breast cancer is a challenging problem. Convolutional neural network architectures extract specific feature descriptors from images, which cannot represent different types of breast cancer. This leads to false positives in classification, which is undesirable in disease diagnosis. The current paper presents an ensemble Convolutional neural network for multi class classification and Binary classification of breast cancer. The feature descriptors from each network are combined to produce the final classification. In this paper, histopathological images are taken from publicly available BreakHis dataset and classified between 8 classes. The proposed ensemble model can perform better when compared to the methods proposed in the literature. The results showed that the proposed model could be a viable approach for breast cancer classification.


Sign in / Sign up

Export Citation Format

Share Document