Skip to main content

Advertisement

SpringerLink
Log in

Limited impact of discretization/interpolation parameters on the predictive power of CT radiomic features in a surgical cohort of pancreatic cancer patients

  • Abdominal Radiology
  • Published:
La radiologia medica Aims and scope Submit manuscript

Abstract

Purpose

To explore the variation of the discriminative power of CT (Computed Tomography) radiomic features (RF) against image discretization/interpolation in predicting early distant relapses (EDR) after upfront surgery.

Materials and methods

Data of 144 patients with pre-surgical high contrast CT were processed consistently with IBSI (Image Biomarker Standardization Initiative) guidelines. Image interpolation/discretization parameters were intentionally changed, including cubic voxel size (0.21–27 mm3) and binning (32–128 grey levels) in a 15 parameter’s sets. After excluding RF with poor inter-observer delineation agreement (ICC < 0.80) and not negligible inter-scanner variability, the variation of 80 RF against discretization/interpolation was first quantified. Then, their ability in classifying patients with early distant relapses (EDR, < 10 months, previously assessed at the first quartile value of time-to-relapse) was investigated in terms of AUC (Area Under Curve) variation for those RF significantly associated to EDR.

Results

Despite RF variability against discretization/interpolation parameters was large and only 30/80 RF showed %COV < 20 (%COV = 100*STDEV/MEAN), AUC changes were relatively limited: for 30 RF significantly associated with EDR (AUC values around 0.60–0.70), the mean values of SD of AUC variability and AUC range were 0.02 and 0.05 respectively. AUC ranges were between 0.00 and 0.11, with values ≤ 0.05 in 16/30 RF. These variations were further reduced when excluding the extreme values of 32 and 128 for grey levels (Average AUC range 0.04, with values between 0.00 and 0.08).

Conclusions

The discriminative power of CT RF in the prediction of EDR after upfront surgery for pancreatic cancer is relatively invariant against image interpolation/discretization within a large range of voxel sizes and binning.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. NCCN (2019) NCCN clinical practice guidelines in oncology. Pancreatic adenocarcinoma; Version 1. J Nat Compr Cancer Netw JNCCN 5(10):998–1033. https://doi.org/10.6004/jnccn.2007.0085

    Article  Google Scholar 

  2. Petrelli F, Inno A, Barni S et al (2017) Borderline resectable pancreatic cancer: more than an anatomical concept. Dig Liver Dis 49(2):223–226. https://doi.org/10.1016/j.dld.2016.11.010

    Article  PubMed  Google Scholar 

  3. Matsumoto I, Murakami Y, Shinzeki M et al (2015) Proposed preoperative risk factors for early recurrence in patients with resectable pancreatic ductal adenocarcinoma after surgical resection: a multi-center retrospective study. Pancreatology 15(6):674–680. https://doi.org/10.1016/j.pan.2015.09.008

    Article  PubMed  Google Scholar 

  4. Lee Y, Lee J, Yang S et al (2019) Neoadjuvant therapy versus upfront surgery in resectable pancreatic cancer according to intention-to-treat and per-protocol analysis: a systematic review and meta-analysis. Sci Rep 9:15662. https://doi.org/10.1038/s41598-019-52167-9

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  5. Barugola G, Partelli S, Marcucci S et al (2009) Resectable pancreatic cancer: who really benefits from resection? Ann Surg Oncol 16:3316–3322. https://doi.org/10.1245/s10434-009-0670-7

    Article  PubMed  Google Scholar 

  6. Bergquist JR, Puig CA, Shubert CR et al (2016) Carbohydrate antigen 19–9 elevation in anatomically resectable, early stage pancreatic cancer is independently associated with decreased overall survival and an indication for neoadjuvant therapy: a national cancer database study. J Am Coll Surg 223:52–65. https://doi.org/10.1016/j.jamcollsurg.2016.02.009

    Article  PubMed  Google Scholar 

  7. Nakamura T, Asano T, Okamura K et al (2019) A preoperative prognostic scoring system to predict prognosis for resectable pancreatic cancer: who will benefit from upfront surgery? J Gastrointest Surg 23(5):990–996. https://doi.org/10.1007/s11605-018-3972-x

    Article  PubMed  Google Scholar 

  8. Groot V, Rezaee N, Wu W et al (2018) Patterns, timing, and predictors of recurrence following pancreatectomy for pancreatic ductal adenocarcinoma. Ann Surg 267(5):936–945. https://doi.org/10.1097/SLA.0000000000002234

    Article  PubMed  Google Scholar 

  9. Barugola G, Frulloni L, Salvia R et al (2009) Is CA 19–9 a screening marker? Dig Liver Dis 41:325–327. https://doi.org/10.1016/j.dld.2009.02.009

    Article  CAS  PubMed  Google Scholar 

  10. Ballehaninna UK, Chamberlain RS (2012) The clinical utility of serum CA 19–9 in the diagnosis, prognosis and management of pancreatic adenocarcinoma: an evidence based appraisal. J Gastrointest Oncol 3:105–119. https://doi.org/10.3978/j.issn.2078-6891.2011.021

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Crippa S, Pergolini I, Javed A et al (2020) Implications of perineural invasion on disease recurrence and survival after pancreatectomy for pancreatic head ductal adenocarcinoma. Ann Surg 276(2):378–385. https://doi.org/10.1097/SLA.0000000000004464

    Article  PubMed  Google Scholar 

  12. Karmazanovsky G, Gruzdev I, Tikhonova V et al (2021) Computed tomography-based radiomics approach in pancreatic tumors characterization. Radiol Med 126(11):1388–1395. https://doi.org/10.1007/s11547-021-01405-0

    Article  Google Scholar 

  13. Marti-Bonmati L, Cerdá-Alberich L, Pérez-Girbés A et al (2022) Pancreatic cancer, radiomics and artificial intelligence. Br J Radiol 95(1137):20220072. https://doi.org/10.1259/bjr.20220072

    Article  PubMed  Google Scholar 

  14. Palumbo D, Mori M, Prato F et al (2021) Prediction of early distant recurrence in upfront resectable pancreatic adenocarcinoma: a multidisciplinary. Mach Learn-Based Approach Cancers 13(19):4938. https://doi.org/10.3390/cancers13194938

    Article  Google Scholar 

  15. Mori M, Passoni P, Incerti E et al (2020) Training and validation of a robust PET radiomic-based index to predict distant-relapse-free-survival after radio chemotherapy for locally advanced pancreatic cancer. Radiother Oncol 153:258–264. https://doi.org/10.1016/j.radonc.2020.07.003

    Article  CAS  PubMed  Google Scholar 

  16. Chen X, Oshima K, Schott D et al (2017) Assessment of treatment response during chemoradiation therapy for pancreatic cancer based on quantitative radiomic analysis of daily CTs: an exploratory study. PLoS ONE. https://doi.org/10.1371/journal.pone.0178961

    Article  PubMed  PubMed Central  Google Scholar 

  17. Desseroit M, Tixier F, Weber WA et al (2017) 18F- Reliability of PET/CT shape and heterogeneity features in functional and morphological components of non-small cell lung cancer tumors: a repeatability analysis in a prospective multi-center cohort. J Nucl Med 58:406–411. https://doi.org/10.2967/jnumed.116.180919

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. Zhao B (2021) Understanding sources of variation to improve the reproducibility of radiomics. Front Oncol 11:633176. https://doi.org/10.3389/fonc.2021.633176

    Article  PubMed  PubMed Central  Google Scholar 

  19. Mori M, Cattaneo GM, Muffatti F et al (2019) CT radiomic features of pancreatic neuroendocrine neoplasms (panNEN) are robust against delineation uncertainty. Physica Med 57:41–46. https://doi.org/10.1016/j.ejmp.2018.12.005

    Article  Google Scholar 

  20. Van Velden FH, Kramer GM, Frings V et al (2016) Repeatability of radiomic features in non-small-cell lung cancer [18F]FDG-PET/ CT studies: impact of reconstruction and delineation. Mol Imaging Biol 18(5):788–795. https://doi.org/10.1007/s11307-016-0940-2

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  21. Lu L, Ehmke RC, Schwartz LH et al (2016) Assessing agreement between radiomic features computed for multiple CT imaging settings. PLOS ONE 11(12):e0166550. https://doi.org/10.1371/journal.pone.0166550

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  22. Linsalata S, Borgheresi R, Marfisi D et al (2022) Radiomics of patients with locally advanced rectal cancer: effect of preprocessing on features estimation from computed tomography imaging. Biomed Res Int 2022:2003286. https://doi.org/10.1155/2022/2003286

    Article  PubMed  PubMed Central  Google Scholar 

  23. Hosseini S, Shiri I, Hajianfar G et al (2021) The impact of preprocessing on the PET-CT radiomics features in non-small cell lung cancer. Front Biomed Technol 8(4):261–272. https://doi.org/10.18502/fbt.v8i4.7754

    Article  Google Scholar 

  24. Hu P, Wang J, Zhong H et al (2016) Reproducibility with repeat CT in radiomics study for rectal cancer. Oncotarget 7(44):71440–71446. https://doi.org/10.18632/oncotarget.12199

    Article  PubMed  PubMed Central  Google Scholar 

  25. Oliver JA, Budzevich M, Zhang GG et al (2015) Variability of image features computed from conventional and respiratory-gated PET/CT images of lung cancer. Trans Oncol 8(6):524–534. https://doi.org/10.1016/j.tranon.2015.11.013

    Article  Google Scholar 

  26. Sedlaczek O, Kleesiek J, Gallagher F et al (2022) Quantification and reduction of cross-vendor variation in multicenter DWI MR imaging: results of the cancer core Europe imaging task force. Eur Radiol 32:8617–8628. https://doi.org/10.1007/s00330-022-08880-7

    Article  PubMed  PubMed Central  Google Scholar 

  27. Ibrahim A, Refaee T, Primakov S et al (2021) The effects of in-plane spatial resolution on ct-based radiomic features’ stability with and without combat harmonization. Cancers 13(8):1848. https://doi.org/10.3390/cancers13081848

    Article  PubMed  PubMed Central  Google Scholar 

  28. He L, Huang Y, Ma Z et al (2016) Effects of contrast-enhancement, reconstruction slice thickness and convolution kernel on the diagnostic performance of radiomics signature in solitary pulmonary nodule. Nat Sci Rep 6:34921. https://doi.org/10.1038/srep34921

    Article  CAS  Google Scholar 

  29. Larue RTHM, Van De Voorde L, Van Timmeren JE et al (2017) 4DCT imaging to assess radiomics feature stability: an investigation for thoracic cancers. Radiother Oncol 125(1):147–153. https://doi.org/10.1016/j.radonc.2017.07.023

    Article  PubMed  Google Scholar 

  30. Loi S, Mori M, Benedetti G et al (2020) Robustness of CT radiomic features against image discretization and interpolation in characterizing pancreatic neuroendocrine neoplasms. Physica Med 76:125–133. https://doi.org/10.1016/j.ejmp.2020.06.025

    Article  Google Scholar 

  31. Zwanenburg A, Vallieres M, Abdalah M et al (2020) The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput imagebased phenotyping. Radiology 95(2):328–338. https://doi.org/10.1148/radiol.2020191145

    Article  Google Scholar 

  32. Scalco E, Mori M, Palumbo D, et al. (2022) Limited impact of scanner variability on CT radiomic features in predicting outcome for pancreatic cancer patients. ECR meeting, Vienna

  33. Mim Software Inc. (MIM Software Inc. Cleveland OH). https://www.mimsoftware.com/solutions/radiation-oncology

  34. Tixier F, Le Rest CC, Hatt M et al (2011) Intratumor heterogeneity characterized by textural features on baseline 18F-FDG PET images predicts response to concomitant radiochemotherapy in esophageal cancer. J. Nucl. Med. 52(3):369–78. https://doi.org/10.2967/jnumed.110.082404

    Article  PubMed  Google Scholar 

  35. Whybra P, Parkinson C, Foley K et al (2019) Assessing radiomic feature robustness to interpolation in 18F-FDG PET imaging. Sci. Rep. 9(1):9649

    Article  PubMed  PubMed Central  Google Scholar 

  36. Deasy JO, Blanco AI, Clark VH (2003) CERR: a computational environment for radiotherapy research. Med Phys 30(5):979–85. https://doi.org/10.1118/1.1568978

    Article  PubMed  Google Scholar 

  37. Traverso A, Wee L, Dekker A et al (2018) Repeatability and reproducibility of radiomic features: a systematic review. Int J Radiat Oncol Biol Phys 102(4):1143–1158. https://doi.org/10.1016/j.ijrobp.2018.05.053

    Article  PubMed  PubMed Central  Google Scholar 

  38. Qiu Q, Duan J, Duan Z et al (2019) Reproducibility and non-redundancy of radiomic features extracted from arterial phase CT scans in hepatocellular carcinoma patients: impact of tumor segmentation variability. Quant Imaging Med Surg 9(3):453–464. https://doi.org/10.21037/qims.2019.03.02

    Article  PubMed  PubMed Central  Google Scholar 

  39. Lv W, Yuan Q, Wang Q et al (2018) Robustness versus disease differentiation when varying parameter settings in radiomics features: application to nasopharyngeal PET/CT. Eur Radiol 28(8):3245–3254. https://doi.org/10.1007/s00330-018-5343-0

    Article  PubMed  Google Scholar 

  40. Benedetti G, Mori M, Panzeri MM et al (2021) CT-derived radiomic features to discriminate histologic characteristics of pancreatic neuroendocrine tumors. Radiol Med 126:745–760. https://doi.org/10.1007/s11547-021-01333-z

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

Martina Mori was supported by AIRC (Italian Association for Cancer Research, IG23150).

Author information

Authors and Affiliations

  1. Medical Physics, San Raffaele Scientific Institute, Via Olgettina 690, 20132, Milan, Italy

    Sara Loi, Martina Mori, Gabriele Palazzo, Antonella Del Vecchio & Claudio Fiorino

  2. San Raffaele Scientific Institute, Milan, Italy

    Diego Palumbo & Francesco De Cobelli

  3. Pancreatic Surgery Unit, Pancreas Translational and Clinical Research Center, San Raffaele Scientific Institute, Milan, Italy

    Stefano Crippa & Massimo Falconi

  4. Università Vita-Salute, Milan, Italy

    Stefano Crippa, Massimo Falconi & Francesco De Cobelli

  5. School of Engineering, Cardiff University, Cardiff, Wales, UK

    Emiliano Spezi

Authors
  1. Sara Loi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Martina Mori
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Diego Palumbo
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Stefano Crippa
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Gabriele Palazzo
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Emiliano Spezi
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Antonella Del Vecchio
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Massimo Falconi
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Francesco De Cobelli
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Claudio Fiorino
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Sara Loi, Diego Palumbo, Martina Mori, Gabriele Palazzo, Claudio Fiorino and Stefano Crippa. The first draft of the manuscript was written by Sara Loi and Claudio Fiorino and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Claudio Fiorino.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

The content of this study was approved by ethics committee and have therefore been performed in accordance with the ethical standards laid down in the 1964 Declaration of Helsinki and its later amendments. A specific informed consent was signed by the patients whose data are analyzed in the study.

Consent to participate

A specific informed consent was signed by the patients whose data are analyzed in the study.

Additional information

Publisher's Note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 28 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Loi, S., Mori, M., Palumbo, D. et al. Limited impact of discretization/interpolation parameters on the predictive power of CT radiomic features in a surgical cohort of pancreatic cancer patients. Radiol med 128, 799–807 (2023). https://doi.org/10.1007/s11547-023-01649-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11547-023-01649-y

Keywords

Search

Navigation