Minkowski functionals: An MRI texture analysis tool for determination of the aggressiveness of breast cancer - PubMed (original) (raw)
doi: 10.1002/jmri.25057. Epub 2015 Oct 10.
Affiliations
- PMID: 26453892
- DOI: 10.1002/jmri.25057
Minkowski functionals: An MRI texture analysis tool for determination of the aggressiveness of breast cancer
Michael J Fox et al. J Magn Reson Imaging. 2016 Apr.
Abstract
Background: This work aims to see whether Minkowski Functionals can be used to distinguish between cancer types before chemotherapy treatment has begun, and whether a response to treatment can be predicted by an initial scan alone.
Methods: Fat-nulled T1w 3T DCE-MRI scans were taken of 100 cases of biopsy confirmed breast cancer and a series of binary images created on lesion containing slices. Minkowski Functionals were calculated for each binary image and the change in these values as the binary threshold was raised was described using 6(th) order polynomials. These polynomials were used to compare between patient subgroups, for triple negative breast cancer (TNBC) status, chemotherapy response, biopsy grade, nodal status, and lymphovascular invasion status.
Results: When using Minkowski Functionals statistically significant (P < 0.05) differences were found between TNBC status, biopsy grade, and lymphovascular invasion status subgroups for all methodologies. The analysis performance did not appear to be affected by the number of threshold steps used. Most notably, very strong differences (P ≤ 0.01) were found between TNBC and other intrinsic subtype patients. When analyzed with a binary logistic regression model, an area under the curve value of 0.917 (0.846-0.987, 95% confidence interval) for TNBC classification was found.
Conclusion: The method of texture analysis presented here provides a novel way to characterize tumors, and demonstrates clear differences between cancer groups which are detectable before treatment begins, and can help with treatment planning as a valuable prognosis tool.
Keywords: Minkowski functionals; breast cancer; contrast enhanced MRI; image processing; texture analysis.
© 2015 Wiley Periodicals, Inc.
Similar articles
- Evaluation with 3.0-T MR imaging: predicting the pathological response of triple-negative breast cancer treated with anthracycline and taxane neoadjuvant chemotherapy.
Kim MJ, Kim EK, Park S, Moon HJ, Kim SI, Park BW. Kim MJ, et al. Acta Radiol. 2015 Sep;56(9):1069-77. doi: 10.1177/0284185114548507. Epub 2014 Sep 16. Acta Radiol. 2015. PMID: 25228161 - Texture analysis in assessment and prediction of chemotherapy response in breast cancer.
Ahmed A, Gibbs P, Pickles M, Turnbull L. Ahmed A, et al. J Magn Reson Imaging. 2013 Jul;38(1):89-101. doi: 10.1002/jmri.23971. Epub 2012 Dec 13. J Magn Reson Imaging. 2013. PMID: 23238914 - Primary human breast adenocarcinoma: imaging and histologic correlates of intrinsic susceptibility-weighted MR imaging before and during chemotherapy.
Li SP, Taylor NJ, Makris A, Ah-See ML, Beresford MJ, Stirling JJ, d'Arcy JA, Collins DJ, Padhani AR. Li SP, et al. Radiology. 2010 Dec;257(3):643-52. doi: 10.1148/radiol.10100421. Epub 2010 Sep 21. Radiology. 2010. PMID: 20858850 - Current strategy for triple-negative breast cancer: appropriate combination of surgery, radiation, and chemotherapy.
Yagata H, Kajiura Y, Yamauchi H. Yagata H, et al. Breast Cancer. 2011 Jul;18(3):165-73. doi: 10.1007/s12282-011-0254-9. Epub 2011 Feb 3. Breast Cancer. 2011. PMID: 21290263 Review. - Tumor necrosis by pretreatment breast MRI: association with neoadjuvant systemic therapy (NAST) response in triple-negative breast cancer (TNBC).
Abdelhafez AH, Musall BC, Adrada BE, Hess K, Son JB, Hwang KP, Candelaria RP, Santiago L, Whitman GJ, Le-Petross HT, Moseley TW, Arribas E, Lane DL, Scoggins ME, Leung JWT, Mahmoud HS, White JB, Ravenberg EE, Litton JK, Valero V, Wei P, Thompson AM, Moulder SL, Pagel MD, Ma J, Yang WT, Rauch GM. Abdelhafez AH, et al. Breast Cancer Res Treat. 2021 Jan;185(1):1-12. doi: 10.1007/s10549-020-05917-7. Epub 2020 Sep 13. Breast Cancer Res Treat. 2021. PMID: 32920733 Free PMC article. Review.
Cited by
- CT-based radiomics for predicting breast cancer radiotherapy side effects.
Llorián-Salvador Ó, Windeler N, Martin N, Etzel L, Andrade-Navarro MA, Bernhardt D, Rost B, Borm KJ, Combs SE, Duma MN, Peeken JC. Llorián-Salvador Ó, et al. Sci Rep. 2024 Aug 29;14(1):20051. doi: 10.1038/s41598-024-70723-w. Sci Rep. 2024. PMID: 39209947 Free PMC article. - Contrast computed tomography-based radiomics is correlation with COG risk stratification of neuroblastoma.
Zhang Y, Yang Y, Ning G, Wu X, Yang G, Li Y. Zhang Y, et al. Abdom Radiol (NY). 2023 Jun;48(6):2111-2121. doi: 10.1007/s00261-023-03875-4. Epub 2023 Mar 23. Abdom Radiol (NY). 2023. PMID: 36951989 - Ipsilateral Recurrence of DCIS in Relation to Radiomics Features on Contrast Enhanced Breast MRI.
Park GE, Kim SH, Lee EB, Nam Y, Sung W. Park GE, et al. Tomography. 2022 Mar 1;8(2):596-606. doi: 10.3390/tomography8020049. Tomography. 2022. PMID: 35314626 Free PMC article. - CT-based radiomics scores predict response to neoadjuvant chemotherapy and survival in patients with gastric cancer.
Sun KY, Hu HT, Chen SL, Ye JN, Li GH, Chen LD, Peng JJ, Feng ST, Yuan YJ, Hou X, Wu H, Li X, Wu TF, Wang W, Xu JB. Sun KY, et al. BMC Cancer. 2020 May 25;20(1):468. doi: 10.1186/s12885-020-06970-7. BMC Cancer. 2020. PMID: 32450841 Free PMC article. - Implementation of machine learning into clinical breast MRI: Potential for objective and accurate decision-making in suspicious breast masses.
Ellmann S, Wenkel E, Dietzel M, Bielowski C, Vesal S, Maier A, Hammon M, Janka R, Fasching PA, Beckmann MW, Schulz Wendtland R, Uder M, Bäuerle T. Ellmann S, et al. PLoS One. 2020 Jan 30;15(1):e0228446. doi: 10.1371/journal.pone.0228446. eCollection 2020. PLoS One. 2020. PMID: 31999755 Free PMC article.
Publication types
MeSH terms
Substances
LinkOut - more resources
Full Text Sources
Medical