Prediction of Tumor Size in Patients with Invasive Ductal Carcinoma Using FT-IR Spectroscopy Combined with Chemometrics: a Preliminary Study

Overview

Journal Anal Bioanal Chem

Specialty Chemistry

Date 2021 Mar 22

PMID 33751160

Authors

Zhimin Zhu

Cheng Chen

Chen Chen

Ziwei Yan

Fangfang Chen

Bo Yang

Huiting Zhang

Huijie Han

Xiaoyi Lv

Affiliations

Soon will be listed here.

Abstract

Precise detection of tumor size is essential for early diagnosis, treatment, and evaluation of the prognosis of breast cancer. However, there are some errors between the tumor size of breast cancer measured by conventional imaging methods and the pathological tumor size. Invasive ductal carcinoma (IDC) is a common pathological type of breast cancer. In this study, serum Fourier transform infrared spectroscopy (FT-IR) combined with chemometric methods was used to predict the maximum diameter and maximum vertical diameter of tumors in IDC patients. Three models were evaluated based on the pathological tumor size measured after surgery and included grid search support vector machine regression (GS-SVR), back propagation neural network optimized by genetic algorithm (GA-BP-ANN), and back propagation neural network optimized by particle swarm optimization (PSO-BP-ANN). The results show that three models can accurately predict tumor size. The GA-BP-ANN model provided the best fitting quality of the largest tumor diameter with the determination coefficients of 0.984 in test set. And the GS-SVR model provided the best fitting quality of the largest vertical tumor diameter with the determination coefficients of 0.982 in test set. The GS-SVR model had the highest prediction efficiency and the lowest time complexity of the models. The results indicate that serum FT-IR spectroscopy combined with chemometric methods can predict tumor size in IDC patients. In addition, compared with traditional imaging methods, we found that the experimental results of the three models are better than traditional imaging methods in terms of correlation and fitting degree. And the average fitting error of PSO-BP-ANN and GA-BP-ANN models was less than 0.3 mm. The minimally invasive detection method is expected to be developed into a new clinical diagnostic method for tumor size estimation to reduce the diagnostic trauma of patients and provide new diagnostic experience for patients. Graphical Abstract.

References

Haraldsdottir K, Jonsson B, Halldorsdottir A, Tranberg K, Asgeirsson K . Tumor Size of Invasive Breast Cancer on Magnetic Resonance Imaging and Conventional Imaging (Mammogram/Ultrasound): Comparison with Pathological Size and Clinical Implications. Scand J Surg. 2016; 106(1):68-73. DOI: 10.1177/1457496916631855. View

Dummin L, Cox M, Plant L . Prediction of breast tumor size by mammography and sonography--A breast screen experience. Breast. 2006; 16(1):38-46. DOI: 10.1016/j.breast.2006.04.003. View

Gonzalez-Sistal A, Baltasar Sanchez A, Del Rio M, Arias J, Herranz M, Ruibal A . Association between tumor size and immunohistochemical expression of Ki-67, p53 and BCL2 in a node-negative breast cancer population selected from a breast cancer screening program. Anticancer Res. 2014; 34(1):269-73. View

Bunaciu A, Dang Hoang V, Aboul-Enein H . Applications of FT-IR spectrophotometry in cancer diagnostics. Crit Rev Anal Chem. 2015; 45(2):156-65. DOI: 10.1080/10408347.2014.904733. View

Kochan K, Maslak E, Chlopicki S, Baranska M . FT-IR imaging for quantitative determination of liver fat content in non-alcoholic fatty liver. Analyst. 2015; 140(15):4997-5002. DOI: 10.1039/c5an00737b. View

Freitas D, Camara I, Silva P, Wanderley N, Alves M, Morais C . Spectrochemical analysis of liquid biopsy harnessed to multivariate analysis towards breast cancer screening. Sci Rep. 2020; 10(1):12818. PMC: 7393361. DOI: 10.1038/s41598-020-69800-7. View

Morais C, Lima K, Singh M, Martin F . Tutorial: multivariate classification for vibrational spectroscopy in biological samples. Nat Protoc. 2020; 15(7):2143-2162. DOI: 10.1038/s41596-020-0322-8. View

Saif F, Yaseen S, Alameen A, Mane S, Undre P . Identification and characterization of Aspergillus species of fruit rot fungi using microscopy, FT-IR, Raman and UV-Vis spectroscopy. Spectrochim Acta A Mol Biomol Spectrosc. 2020; 246:119010. DOI: 10.1016/j.saa.2020.119010. View

Morais C, Santos M, Lima K, Martin F . Improving data splitting for classification applications in spectrochemical analyses employing a random-mutation Kennard-Stone algorithm approach. Bioinformatics. 2019; 35(24):5257-5263. PMC: 6954661. DOI: 10.1093/bioinformatics/btz421. View

10.

Luypaert J, Heuerding S, Massart D, Vander Heyden Y . Direct orthogonal signal correction as data pretreatment in the classification of clinical lots of creams from near infrared spectroscopy data. Anal Chim Acta. 2007; 582(1):181-9. DOI: 10.1016/j.aca.2006.09.029. View

11.

Martin F, German M, Wit E, Fearn T, Ragavan N, Pollock H . Identifying variables responsible for clustering in discriminant analysis of data from infrared microspectroscopy of a biological sample. J Comput Biol. 2007; 14(9):1176-84. DOI: 10.1089/cmb.2007.0057. View

12.

Luparia A, Mariscotti G, Durando M, Ciatto S, Bosco D, Campanino P . Accuracy of tumour size assessment in the preoperative staging of breast cancer: comparison of digital mammography, tomosynthesis, ultrasound and MRI. Radiol Med. 2013; 118(7):1119-36. DOI: 10.1007/s11547-013-0941-z. View

13.

Cortadellas T, Argacha P, Acosta J, Rabasa J, Peiro R, Gomez M . Estimation of tumor size in breast cancer comparing clinical examination, mammography, ultrasound and MRI-correlation with the pathological analysis of the surgical specimen. Gland Surg. 2017; 6(4):330-335. PMC: 5566672. DOI: 10.21037/gs.2017.03.09. View

14.

Streng M, Ignatov A, Reinisch M, Costa S, Eggemann H . A comparison of tumour size measurements with palpation, ultrasound and mammography in male breast cancer: first results of the prospective register study. J Cancer Res Clin Oncol. 2017; 144(2):381-387. DOI: 10.1007/s00432-017-2554-8. View

15.

Borden J, Man A, Scott D, Liu K . Tobacco-induced alterations to the Fourier-transform infrared spectrum of serum. J Mol Med (Berl). 2003; 81(12):788-94. DOI: 10.1007/s00109-003-0490-3. View

16.

Asseryanis E, Ruecklinger E, Hellan M, Kubista E, Singer C . Breast cancer size in postmenopausal women is correlated with body mass index and androgen serum levels. Gynecol Endocrinol. 2004; 18(1):29-36. DOI: 10.1080/09513590310001651759. View

17.

Sitnikova V, Kotkova M, Nosenko T, Kotkova T, Martynova D, Uspenskaya M . Breast cancer detection by ATR-FTIR spectroscopy of blood serum and multivariate data-analysis. Talanta. 2020; 214:120857. DOI: 10.1016/j.talanta.2020.120857. View