Skip to main content

Biological interpretation of prognostic radiomic score by correlating with tumor heterogeneity and microenvironment

To the Editor

We read with great interest the article by Dr. Wang and colleagues entitled “radiomics predicts the prognosis of patients with locally advanced breast cancer by reflecting the heterogeneity of tumor cells and the tumor microenvironment,” which was recently published online in Breast Cancer Research [1]. To our knowledge, this study is the first attempt to predict individual disease-free survival (DFS) in patients with locally advanced breast cancer who received neoadjuvant chemotherapy and postoperative radiotherapy by radiomics. The authors constructed a radiomic score to predict the prognosis of patients and assessed the associations of radiomic score with the tumor microenvironment and immunophenotype, as well as computational histopathology.

Despite the encouraging results, two issues regarding results need to be clarified. First, the multivariate Cox analysis of clinicopathological factors and radiomic score showed that only age and radiomic score were independent predictors for DFS in the training cohort. The nomogram also displays that the contribution of clinicopathological factors except for age was very small, thus most clinicopathological factors can be discarded. In addition, the range of median DFS probability was very narrow, suggesting the clinical usefulness of the nomogram may be limited. The calibration curves indicate the calibration of the nomogram was not good and the Hosmer–Lemeshow test is necessary to determine the goodness of fit of the nomogram. Second, the C-index of the radiomic nomogram in the training and validation cohorts was 0.820 and 0.612, respectively. Similarly, the C-index of radiomic score alone was 0.810 and 0.614 for training and validation cohorts, respectively. The results of the radiomic score and radiomic nomogram in the two cohorts suggested overfitting.

Radiomic features contain abundant information about tumor biology that is governed not only by cancer cells but also by the tumor microenvironment (TME) [2]. Biological validation of radiomic features remains a critically elusive but important issue for clinical translation of radiomic analysis [3]. In this study, radiomics revealed heterogeneity of tumor cells and tumor microenvironment by gene set enrichment analysis and the assessment of tumor immunophenotype. The biological interpretation of radiomics was mainly via bioinformatic analysis, which was short of adequate experimental evidence. Thus, we are looking forward to furthering investigations for validation. In terms of heterogeneity of tumor cells, GSEA showed that DNA repair, G2/M checkpoint, and PI3K/Akt/mTOR pathways were enriched in both the high- and low-score groups. However, there may be some differential pathways in the two groups, which can reflect the biological differences between these groups and the biological underpinnings of the radiomic score. In terms of heterogeneity of TME, tumor immunophenotype was assessed by MHC molecule score, which was involved with tumor escape mechanisms. However, TME comprises various cell types, including immune cells and stromal cells, cellular factors, and molecules [4]. Tumor immunophenotype can be determined by CD8+ cytotoxic T-cell fractions, immune-suppressive regulatory T cells (T), myeloid-derived suppressor cells, and M2 tumor-associated macrophages (TAMs), which are closely related to the prognosis of breast cancer [5,6,7]. Hence, tumor immunophenotype should be assessed by more biomarkers with immunohistochemistry, such as M2 TAM (CD68+, CD163+) [8]. Moreover, given that some genes, such as SLURP1, PAX7, UCP1, and ABCA10, were proven to be associated with the prognosis of LABC, and high-score MHC was significantly correlated with molecule score, these merits can be added to the construction of radiomic model to achieve better predictive performance.

Availability of data and materials

Not applicable.

References

  1. Wang X, Xie T, Luo J, Zhou Z, Yu X, Guo X. Radiomics predicts the prognosis of patients with locally advanced breast cancer by reflecting the heterogeneity of tumor cells and the tumor microenvironment. Breast Cancer Res BCR. 2022;24(1):20.

    CAS  Article  Google Scholar 

  2. Li G, Li L, Li Y, Qian Z, Wu F, He Y, Jiang H, Li R, Wang D, Zhai Y, et al. An MRI radiomics approach to predict survival and tumour-infiltrating macrophages in gliomas. Brain J Neurol. 2022. https://doi.org/10.1093/brain/awab340.

    Article  PubMed  Google Scholar 

  3. Tomaszewski M, Gillies R. The biological meaning of radiomic features. Radiology. 2021;299(2):E256.

    Article  Google Scholar 

  4. Vitale I, Manic G, Coussens L, Kroemer G, Galluzzi L. Macrophages and metabolism in the tumor microenvironment. Cell Metab. 2019;30(1):36–50.

    CAS  Article  Google Scholar 

  5. Tang X. Tumor-associated macrophages as potential diagnostic and prognostic biomarkers in breast cancer. Cancer Lett. 2013;332(1):3–10.

    CAS  Article  Google Scholar 

  6. Blessin N, Li W, Mandelkow T, Jansen H, Yang C, Raedler J, Simon R, Büscheck F, Dum D, Luebke A, et al. Prognostic role of proliferating CD8 cytotoxic Tcells in human cancers. Cell Oncol (Dordr). 2021;44(4):793–803.

    CAS  Article  Google Scholar 

  7. Ahmadvand S, Faghih Z, Montazer M, Safaei A, Mokhtari M, Jafari P, Talei A, Tahmasebi S, Ghaderi A. Importance of CD45RO+ tumor-infiltrating lymphocytes in post-operative survival of breast cancer patients. Cell Oncol (Dordr). 2019;42(3):343–56.

    CAS  Article  Google Scholar 

  8. Qiu S, Waaijer S, Zwager M, de Vries E, van der Vegt B, Schröder C. Tumor-associated macrophages in breast cancer: Innocent bystander or important player? Cancer Treat Rev. 2018;70:178–89.

    CAS  Article  Google Scholar 

Download references

Acknowledgements

Not applicable.

Funding

Not applicable.

Author information

Authors and Affiliations

Authors

Contributions

JLZ and BZ conceived and drafted the letter to the editor. Both authors read and approved the final manuscript.

Corresponding author

Correspondence to Bin Zhang.

Ethics declarations

Ethics approval and consent to participate

Not applicable.

Consent for publication

Not applicable.

Competing interests

The authors have no competing interests to declare.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zheng, J., Zhang, B. Biological interpretation of prognostic radiomic score by correlating with tumor heterogeneity and microenvironment. Breast Cancer Res 24, 32 (2022). https://doi.org/10.1186/s13058-022-01527-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1186/s13058-022-01527-x