Non-Invasive Procedure in Differential Diagnosis of Sarcoidosis and Tuberculosis Lymph Nodes:  Radiomic Model of 18F-FDG PET-CT

##plugins.themes.themeTen.article.main##

Damla Serçe Unat https://orcid.org/0000-0003-4743-5469

Keywords

: Sarcoidosis, Tuberculosis, 18F-FDG PET-CT, Radiomic analysis

Abstract

Background and aim: Clinical and pathological features of two granulomatous diseases tuberculosis (TB) and sarcoidosis lymphadenopathy share similar properties. 18-F FDG Positron-Emission Tomography-Computed Tomography (18F-FDG PET-CT) is performed to discriminate two diseases. Even biopsy and culture via Endobronchial Ultrasonography (EBUS) sometimes did not get definite diagnosis. Radiomics can defined as high-throughput mining of radiological images. We aimed to investigate the role of radiomic analysis of these 18F-FDG PET/CT images in discrimination of TB and sarcoidosis


Methods: All patients with mediastinal LAP who underwent EBUS biopsy were screened for inclusion. Among these patients, patients who were diagnosed with TB or sarcoidosis by pathological and microbiological methods were included in the study. Radiomic model and clinicoradiomic models were formed AUC, sensitivity and specificity values of models obtained by logistic regression results were calculated.


Results: 54 tuberculosis and 163 sarcoidosis lymph nodes were analyzed. Gender, GLCM_Correlation and GLCM_Energy features were found to be important prognostic factors in distinguishing between sarcoidosis and tuberculosis (p: 0.012, OR: 2.423 (1.215-4.830, 95% CI); p<0.001, OR: 5.400 (2.108-13.830, 95%) CI); p<0.001, OR: 3.335 (1.693-6.571, 95% CI; respectively). The p, AUC, sensitivity, and specificity values of the obtained clinicoradiomic model were calculated as <0.001, 0.762 (0.651-0.798, 95% CI), 59.5% and 81.5%, respectively.


Conclusions: The model created with radiomics methods and clinical features gave significant results in distinguishing tuberculosis and sarcoidosis. This is promising for radiomic models that could replace invasive methods. It is expected that radiomic models will be used more in daily life in the future.

Abstract 0 |

References

1. Global tuberculosis report 2022. Geneva: World Health organization; 2022. licence: cc bY-Nc-sa 3.0 iGo.
2. Visca D, Ong CWM, Tiberi S et al. Tuberculosis and COVID-19 interaction: A review of biological, clinical and public health effects. Pulmonology. 2021 Mar;27(2):151–65.
3. Jonas DE, Riley SR, Lee LC et al. Screening for Latent Tuberculosis Infection in Adults: Updated Evidence Report and Systematic Review for the US Preventive Services Task Force. JAMA. 2023 May;329(17):1495–509.
4. Keijsers RGM, Grutters JC. In Which Patients with Sarcoidosis Is FDG PET/CT Indicated? J Clin Med 2020, Vol 9, Page 890. 2020 Mar;9(3):890.
5. Belperio JA, Shaikh F, Abtin FG et al. Diagnosis and Treatment of Pulmonary Sarcoidosis: A Review. JAMA. 2022 Mar;327(9):856–67.
6. Calandriello L, D’abronzo R, Pasciuto G et al. Novelties in Imaging of Thoracic Sarcoidosis. J Clin Med 2021, Vol 10, Page 2222. 2021 May;10(11):2222.
7. Lee CU, Chong S, Choi HW, Choi JC. Quantitative image analysis using chest computed tomography in the evaluation of lymph node involvement in pulmonary sarcoidosis and tuberculosis. PLoS One. 2018 Nov;13(11).
8. Mondoni M, Saderi L, Puci MV, et al. Xpert MTB/RIF in the Diagnosis of Mediastinal Tuberculous Lymphadenitis by Endoscopic Ultrasound-Guided Needle Aspiration Techniques: A Systematic Review and Meta-Analysis. Respiration. 2023 Mar;102(3):237–46.
9. Dubaniewicz A. Mycobacterial Heat Shock Proteins in Sarcoidosis and Tuberculosis. Int J Mol Sci 2023, Vol 24, Page 5084. 2023 Mar;24(6):5084.
10. Typiak M, Rękawiecki B, Rębała K, Dubaniewicz A. Comparative Analysis of FCGR Gene Polymorphism in Pulmonary Sarcoidosis and Tuberculosis. Cells. 2023 May;12(9):1221.
11. Obi ON, Saketkoo LA, Russell AM, Baughman RP. Sarcoidosis: Updates on therapeutic drug trials and novel treatment approaches. Front Med. 2022 Oct;9:991783.
12. Papiris SA, Georgakopoulos A, Papaioannou AI et al. Emerging phenotypes of sarcoidosis based on 18F-FDG PET/CT: a hierarchical cluster analysis. https://doi.org/101080/1747634820201684902. 2019 Feb;14(2):229–38.
13. Özütemiz C, Koksel Y, Froelich JW et al. Comparison of the Effect of Three Different Dietary Modifications on Myocardial Suppression in 18F-FDG PET/CT Evaluation of Patients for Suspected Cardiac Sarcoidosis. J Nucl Med. 2021 Dec;62(12):1759–67.
14. Ryan SM, Fingerlin TE et al. Radiomic measures from chest high-resolution computed tomography associated with lung function in sarcoidosis. Eur Respir J. 2019 Aug;54(2).
15. Boellaard R, Delgado-Bolton R, Oyen WJG et al. FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0. Eur J Nucl Med Mol Imaging [Internet]. 2015 Feb 1 [cited 2024 Feb 12];42(2):328–54. Available from: https://pubmed.ncbi.nlm.nih.gov/25452219/
16. Nioche C, Orlhac F, Boughdad S et al. LIFEx: A Freeware for Radiomic Feature Calculation in Multimodality Imaging to Accelerate Advances in the Characterization of Tumor Heterogeneity. Cancer Res [Internet]. 2018 Aug 15 [cited 2024 Feb 12];78(16):4786–9. Available from: https://pubmed.ncbi.nlm.nih.gov/29959149/
17. Fritscher-Ravens A, Ghanbari A, Topalidis T et al. Granulomatous mediastinal adenopathy: can endoscopic ultrasound-guided fine-needle aspiration differentiate between tuberculosis and sarcoidosis? Endoscopy. 2011 Nov;43(11):955-61. doi: 10.1055/s-0031-1271110. Epub 2011 Aug 10. PMID: 21833904.
18. Kerget B, Afşin DE, Aksakal A. The role of systemic immune-inflammation index (SII) in the differential diagnosis of granulomatous and reactive LAP diagnosed by endobronchial ultrasonography: Evaluation of the systemic immune-inflammation index in sarcoidosis, tuberculosis and reactive lymphadenitis. Sarcoidosis Vasc Diffuse Lung Dis [Internet]. 2023 Sep. 13 [cited 2024 Nov. 29];40(3):e2023038. Available from: https://mattioli1885journals.com/index.php/sarcoidosis/article/view/14743
19. Du X, Zhang Y, Chen L, et al. Comparing the Differential Diagnostic Values of 18F-Alfatide II PET/CT between Tuberculosis and Lung Cancer Patients. Contrast Media Mol Imaging. 2018 Feb 19;2018:8194678. doi: 10.1155/2018/8194678. PMID: 29670497; PMCID: PMC5836463.
20. Kung BT, Seraj SM, Zadeh MZ, t al. An update on the role of 18F-FDG-PET/CT in major infectious and inflammatory diseases. Am J Nucl Med Mol Imaging [Internet]. 2019 [cited 2024 Feb 12];9(6):255. Available from: /pmc/articles/PMC6971480/
21. Vaidyanathan S, Patel CN, Scarsbrook AF, Chowdhury FU. FDG PET/CT in infection and inflammation--current and emerging clinical applications. Clin Radiol [Internet]. 2015 Jul 1 [cited 2024 Feb 12];70(7):787–800. Available from: https://pubmed.ncbi.nlm.nih.gov/25917543/
22. Xu B, Guan Z, Liu C et al. Can multimodality imaging using 18F-FDG/18F-FLT PET/CT benefit the diagnosis and management of patients with pulmonary lesions? Eur J Nucl Med Mol Imaging [Internet]. 2011 Feb [cited 2024 Feb 12];38(2):285–92. Available from: https://pubmed.ncbi.nlm.nih.gov/20936411/
23. Ma X, Xia L, Chen J, Wan W, Zhou W. Development and validation of a deep learning signature for predicting lymph node metastasis in lung adenocarcinoma: comparison with radiomics signature and clinical-semantic model. Eur Radiol. 2023 Mar;33(3):1949-1962. doi: 10.1007/s00330-022-09153-z. Epub 2022 Sep 28. PMID: 36169691.
24. Nakajo M, Hirahara D, Jinguji M, et al. Machine learning approach using 18F-FDG-PET-radiomic features and the visibility of right ventricle 18F-FDG uptake for predicting clinical events in patients with cardiac sarcoidosis. Jpn J Radiol. 2024 Jul;42(7):744-752. doi: 10.1007/s11604-024-01546-y. Epub 2024 Mar 16. PMID: 38491333; PMCID: PMC11217075.
25. Lovinfosse P, Ferreira M, Withofs N, et al. Distinction of Lymphoma from Sarcoidosis on 18F-FDG PET/CT: Evaluation of Radiomics-Feature-Guided Machine Learning Versus Human Reader Performance. J Nucl Med. 2022 Dec;63(12):1933-1940. doi: 10.2967/jnumed.121.263598. Epub 2022 May 19. PMID: 35589406; PMCID: PMC9730930.
26. Zhao W, Xiong Z, Jiang Y et al. Radiomics based on enhanced CT for differentiating between pulmonary tuberculosis and pulmonary adenocarcinoma presenting as solid nodules or masses. J Cancer Res Clin Oncol. 2023 Jul;149(7):3395-3408. doi: 10.1007/s00432-022-04256-y. Epub 2022 Aug 8. PMID: 35939114.
27. Zhang J, Hao L, Qi M et al. Radiomics nomogram for preoperative differentiation of pulmonary mucinous adenocarcinoma from tuberculoma in solitary pulmonary solid nodules. BMC Cancer. 2023 Mar 21;23(1):261. doi: 10.1186/s12885-023-10734-4. PMID: 36944978; PMCID: PMC10029225.
28. Yang X, Li C, Hou J et al. Differentiating Peripherally Located Pulmonary Noncalcified Hamartoma From Carcinoid Using CT Radiomics Approaches. J Comput Assist Tomogr. 2023 May-Jun 01;47(3):402-411. doi: 10.1097/RCT.0000000000001414. Epub 2023 Jan 17. PMID: 37185003.
29. Zhou J, Wen Y, Ding R et al. Radiomics signature based on robust features derived from diffusion data for differentiation between benign and malignant solitary pulmonary lesions. Cancer Imaging. 2024 Jan 22;24(1):14. doi: 10.1186/s40644-024-00660-4. PMID: 38246984; PMCID: PMC10802010.
30. Shang H, Li J, Jiao T et al. Differentiation of Lung Metastases Originated From Different Primary Tumors Using Radiomics Features Based on CT Imaging. Acad Radiol. 2023 Jan;30(1):40-46. doi: 10.1016/j.acra.2022.04.008. Epub 2022 May 14. PMID: 35577699.
31. Zhang R, Wei Y, Shi F et al. The diagnostic and prognostic value of radiomics and deep learning technologies for patients with solid pulmonary nodules in chest CT images. BMC Cancer. 2022 Nov 1;22(1):1118. doi: 10.1186/s12885-022-10224-z. PMID: 36319968; PMCID: PMC9628173.
32. Li Y, Yu Y, Liu Q et al. A CT-based radiomics nomogram for the differentiation of pulmonary cystic echinococcosis from pulmonary abscess. Parasitol Res. 2022 Dec;121(12):3393-3401. doi: 10.1007/s00436-022-07663-9. Epub 2022 Oct 1. PMID: 36181541; PMCID: PMC9525946.