CT-derived radiomic features to discriminate histologic characteristics of pancreatic neuroendocrine tumors

Abstract

Purpose

To assess the ability of radiomic features (RF) extracted from contrast-enhanced CT images (ceCT) and non-contrast-enhanced (non-ceCT) in discriminating histopathologic characteristics of pancreatic neuroendocrine tumors (panNET).

Methods

panNET contours were delineated on pre-surgical ceCT and non-ceCT. First- second- and higher-order RF (adjusted to eliminate redundancy) were extracted and correlated with histological panNET grade (G1 vs G2/G3), metastasis, lymph node invasion, microscopic vascular infiltration. Mann–Whitney with Bonferroni corrected p values assessed differences. Discriminative power of significant RF was calculated for each of the end-points. The performance of conventional-imaged-based-parameters was also compared to RF.

Results

Thirty-nine patients were included (mean age 55-years-old; 24 male). Mean diameters of the lesions were 24 × 27 mm. Sixty-nine RF were considered. Sphericity could discriminate high grade tumors (AUC = 0.79, p = 0.002). Tumor volume (AUC = 0.79, p = 0.003) and several non-ceCT and ceCT RF were able to identify microscopic vascular infiltration: voxel-alignment, neighborhood intensity-difference and intensity-size-zone families (AUC ≥ 0.75, p < 0.001); voxel-alignment, intensity-size-zone and co-occurrence families (AUC ≥ 0.78, p ≤ 0.002), respectively). Non-ceCT neighborhood-intensity-difference (AUC = 0.75, p = 0.009) and ceCT intensity-size-zone (AUC = 0.73, p = 0.014) identified lymph nodal invasion; several non-ceCT and ceCT voxel-alignment family features were discriminative for metastasis (p < 0.01, AUC = 0.80–0.85). Conventional CT ‘necrosis’ could discriminate for microscopic vascular invasion (AUC = 0.76, p = 0.004) and ‘arterial vascular invasion’ for microscopic metastasis (AUC = 0.86, p = 0.001). No conventional-imaged-based-parameter was significantly associated with grade and lymph node invasion.

Conclusions

Radiomic features can discriminate histopathology of panNET, suggesting a role of radiomics as a non-invasive tool for tumor characterization.

Trial registration number: NCT03967951, 30/05/2019

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Data availability

Prior study cited at relevant place in the text as Ref [17].

References

  1. 1.

    Maxwell JE, Howe JR (2015) Imaging in neuroendocrine tumors: an update for the clinician. Int J Endocr Oncol 2(2):159–168

    CAS  Article  Google Scholar 

  2. 2.

    Lewis RB, Lattin GE, Paal E (2010) Pancreatic endocrine tumors: radiologic clinicopathologic correlation. Radiographics 30(6):1445–1464

    Article  Google Scholar 

  3. 3.

    Klimstra DS (2016) Pathologic classification of neuroendocrine neoplasms. Hematol Oncol Clin North Am 30(1):1–19

    Article  Google Scholar 

  4. 4.

    Pasaoglu E, Dursun N, Ozyalvacli G, Hacihasanoglu E, Behzatoglu K, Calay O (2015) Comparison of World Health Organization 2000/2004 and World Health Organization 2010 classifications for gastrointestinal and pancreatic neuroendocrine tumors. Ann Diagn Pathol 19(2):81–87

    Article  Google Scholar 

  5. 5.

    Kim JY, Hong SM, Ro JY (2017) Recent updates on grading and classification of neuroendocrine tumors. Ann Diagn Pathol 29:11–16. https://doi.org/10.1016/j.anndiagpath.2017.04.005

    Article  PubMed  Google Scholar 

  6. 6.

    Rebours V, Cordova J, Couvelard A, Fabre M, Palazzo L, Vullierme MP, Hentic O, Sauvanet A, Aubert A, Bedossa P, Ruszniewski P (2015) Can pancreatic neuroendocrine tumour biopsy accurately determine pathological characteristics? Dig Liver Dis 47(11):973–977. https://doi.org/10.1016/j.dld.2015.06.005

    Article  PubMed  Google Scholar 

  7. 7.

    Tamm EP, Bhosale P, Lee JH, Rohren EM (2016) State-of-the-art Imaging of pancreatic neuroendocrine tumors. Surg Oncol Clin N Am 25(2):375–400. https://doi.org/10.1016/j.soc.2015.11.007

    Article  PubMed  PubMed Central  Google Scholar 

  8. 8.

    Choi TW, Kim JH, Yu MH, Park SJ, Han JK (2018) Pancreatic neuroendocrine tumor: prediction of the tumor grade using CT findings and computerized texture analysis. Acta Radiol 59(4):383–392. https://doi.org/10.1177/0284185117725367

    CAS  Article  PubMed  Google Scholar 

  9. 9.

    Bartolini I, Bencini L, Risaliti M, Ringressi MN, Moraldi L, Taddei A (2018) Current management of pancreatic neuroendocrine tumors: from demolitive surgery to observation. Gastroenterol Res Pract. https://doi.org/10.1155/2018/9647247

    Article  PubMed  PubMed Central  Google Scholar 

  10. 10.

    Rinke A, Gress TM (2017) Neuroendocrine cancer, therapeutic strategies in G3 cancers. Digestion 95(2):109–114

    CAS  Article  Google Scholar 

  11. 11.

    Lambin P, Rios-Velazquez E, Leijenaar R et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48(4):441–446

    Article  Google Scholar 

  12. 12.

    Wilson R, Devaraj A (2017) Radiomics of pulmonary nodules and lung cancer. Transl Lung Cancer Res 6(1):86–91. https://doi.org/10.21037/tlcr.2017.01.04

    Article  PubMed  PubMed Central  Google Scholar 

  13. 13.

    Nazari M, Shiri I, Hajianfar G et al (2020) Noninvasive Fuhrman grading of clear cell renal cell carcinoma using computed tomography radiomic features and machine learning. Radiol Med 125(8):754–762. https://doi.org/10.1007/s11547-020-01169-z

    Article  PubMed  Google Scholar 

  14. 14.

    Kirienko M, Ninatti G, Cozzi L et al (2020) Computed tomography (CT)-derived radiomic features differentiate prevascular mediastinum masses as thymic neoplasms versus lymphomas. Radiol med. https://doi.org/10.1007/s11547-020-01188-w

    Article  PubMed  Google Scholar 

  15. 15.

    Giganti F, Marra P, Ambrosi A et al (2017) Pre-treatment MDCT-based texture analysis for therapy response prediction in gastric cancer: Comparison with tumour regression grade at final histology. Eur J Radiol 90:129–137. https://doi.org/10.1016/j.ejrad.2017.02.043

    Article  PubMed  Google Scholar 

  16. 16.

    Desseroit MC, 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(3):406–411

    CAS  Article  Google Scholar 

  17. 17.

    Mori M, Benedetti G, Partelli S 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 

  18. 18.

    Fang YHD, Lin CY, Shih MJ et al (2014) Development and evaluation of an open-source software package “CGITA” for quantifying tumor heterogeneity with molecular images. Biomed Res Int 5:248505–248509

    Google Scholar 

  19. 19.

    Rindi G, Kloppel G, Alhman H et al (2006) TNM staging of foregut (neuro)endocrine tumors: a consensus proposal including a grading system. Virchows Arch 449:395–401. https://doi.org/10.1007/s00428-006-0250-1

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  20. 20.

    Ohike N, Adsay NV, La Rosa S, Volante M, Zamboni G (2017) Mixed neuroendocrine-non-neuroendocrine neoplasms. In: Lloyd RV, Osamura RY, Kloppel G, Rosai J (eds) WHO classification of tumours of endocrine organs. IARC Press, Lyon, pp 238–239

    Google Scholar 

  21. 21.

    Belli ML, Mori M, Broggi S, Cattaneo GM et al (2018) Quantifying the robustness of [18F] FDG-PET/CT radiomic features with respect to tumor delineation in head and neck and pancreatic cancer patients. Phys Med 49:105–111

    Article  Google Scholar 

  22. 22.

    Canellas R, Burk KS, Parakh A, Sahani DV (2018) Prediction of pancreatic neuroendocrine tumor grade based on CT features and texture analysis. AJR Am J Roentgenol 210(2):341–346. https://doi.org/10.2214/AJR.17.18417

    Article  PubMed  Google Scholar 

  23. 23.

    Yang G, Ji M, Chen J et al (2017) Surgery management for sporadic small (≤2 cm), non- functioning pancreatic neuroendocrine tumors: a consensus statement by the Chinese Study Group for Neuroendocrine Tumors (CSNET). Int J Oncol 50:567–574

    Article  Google Scholar 

  24. 24.

    Smith JK, Ng SC, Hill JS et al (2010) Complications after pancreatectomy for neuroendocrine tumors: a national study. J Surg Res 163:63–68

    Article  Google Scholar 

  25. 25.

    Falconi M, Eriksson B, Kaltsas G et al (2016) Vienna consensus conference participants. ENETS consensus guidelines update for the management of patients with functional pancreatic neuroendocrine tumors and non-functional pancreatic neuroendocrine tumors. Neuroendocrinology 103(2):153–171

    CAS  Article  Google Scholar 

  26. 26.

    Bian Y, Jiang H, Ma C et al (2020) CT-Based radiomics score for distinguishing between grade 1 and grade 2 nonfunctioning pancreatic neuroendocrine tumors. AJR Am J Roentgenol 215(4):852–863. https://doi.org/10.2214/AJR.19.22123

    Article  PubMed  Google Scholar 

  27. 27.

    Gu D, Hu Y, Ding H et al (2019) CT radiomics may predict the grade of pancreatic neuroendocrine tumors: a multicenter study. Eur Radiol 29(12):6880–6890. https://doi.org/10.1007/s00330-019-06176-x

    Article  PubMed  Google Scholar 

  28. 28.

    Liang W, Yang P, Huang R et al (2019) A combined nomogram model to preoperatively predict histologic grade in pancreatic neuroendocrine tumors. Clin Cancer Res 25(2):584–594. https://doi.org/10.1158/1078-0432.CCR-18-1305

    Article  PubMed  Google Scholar 

  29. 29.

    Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278(2):563–577. https://doi.org/10.1148/radiol.2015151169

    Article  PubMed  Google Scholar 

Download references

Funding

The study was supported by an AIRC grant (IG18965); the PI is professor Massimo Falconi. PhD Scholarship of Dr Valentina Andreasi and Research Fellowship of Dr. Francesca Muffatti were supported by Gioja Bianca Costanza Fund.

Author information

Affiliations

Authors

Contributions

All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Giulia Benedetti, Martina Mori, Marta Maria Panzeri, Maurizio Barbera and Francesca Muffatti. The first draft of the manuscript was written by Giulia Benedetti and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Francesco De Cobelli.

Ethics declarations

Ethics approval research involves human participants

This study was performed in line with the principles of the Declaration of Helsinki. Approval was granted by the Ethics Committee of IRCCS Ospedale San Raffaele (19/INT/ 2019). The study is registered at ClinicalTrial.gov (registration number NCT03967951, 31/05/2019).

Consent to participate

Informed consent was obtained from all individual participants included in the study.

Consent to publish

Patients signed informed consent regarding publishing their data and photographs.

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

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

Download citation

Keywords

  • Pancreatic neoplasms
  • Neuroendocrine tumors
  • Radiomic features
  • Area under the curve (AUC)
  • Computed tomography