Reproducibility of CT radiomic features in lung neuroendocrine tumours (NETs) patients: analysis in a heterogeneous population.
Computed tomography
Ki-67
Lung cancer
Lung carcinoids
Radiomics
Journal
La Radiologia medica
ISSN: 1826-6983
Titre abrégé: Radiol Med
Pays: Italy
ID NLM: 0177625
Informations de publication
Date de publication:
Feb 2023
Feb 2023
Historique:
received:
30
09
2022
accepted:
04
01
2023
pubmed:
14
1
2023
medline:
25
2
2023
entrez:
13
1
2023
Statut:
ppublish
Résumé
The aim is to find a correlation between texture features extracted from neuroendocrine (NET) lung cancer subtypes, both Ki-67 index and the presence of lymph-nodal mediastinal metastases detected while using different computer tomography (CT) scanners. Sixty patients with a confirmed pulmonary NET histological diagnosis, a known Ki-67 status and metastases, were included. After subdivision of primary lesions in baseline acquisition and venous phase, 107 radiomic features of first and higher orders were extracted. Spearman's correlation matrix with Ward's hierarchical clustering was applied to confirm the absence of bias due to the database heterogeneity. Nonparametric tests were conducted to identify statistically significant features in the distinction between patient groups (Ki-67 < 3-Group 1; 3 ≤ Ki-67 ≤ 20-Group 2; and Ki-67 > 20-Group 3, and presence of metastases). No bias arising from sample heterogeneity was found. Regarding Ki-67 groups statistical tests, seven statistically significant features (p value < 0.05) were found in post-contrast enhanced CT; three in baseline acquisitions. In metastasis classes distinction, three features (first-order class) were statistically significant in post-contrast acquisitions and 15 features (second-order class) in baseline acquisitions, including the three features distinguishing between Ki-67 groups in baseline images (MCC, ClusterProminence and Strength). Some radiomic features can be used as a valid and reproducible tool for predicting Ki-67 class and hence the subtype of lung NET in baseline and post-contrast enhanced CT images. In particular, in baseline examination three features can establish both tumour class and aggressiveness.
Sections du résumé
BACKGROUND
BACKGROUND
The aim is to find a correlation between texture features extracted from neuroendocrine (NET) lung cancer subtypes, both Ki-67 index and the presence of lymph-nodal mediastinal metastases detected while using different computer tomography (CT) scanners.
METHODS
METHODS
Sixty patients with a confirmed pulmonary NET histological diagnosis, a known Ki-67 status and metastases, were included. After subdivision of primary lesions in baseline acquisition and venous phase, 107 radiomic features of first and higher orders were extracted. Spearman's correlation matrix with Ward's hierarchical clustering was applied to confirm the absence of bias due to the database heterogeneity. Nonparametric tests were conducted to identify statistically significant features in the distinction between patient groups (Ki-67 < 3-Group 1; 3 ≤ Ki-67 ≤ 20-Group 2; and Ki-67 > 20-Group 3, and presence of metastases).
RESULTS
RESULTS
No bias arising from sample heterogeneity was found. Regarding Ki-67 groups statistical tests, seven statistically significant features (p value < 0.05) were found in post-contrast enhanced CT; three in baseline acquisitions. In metastasis classes distinction, three features (first-order class) were statistically significant in post-contrast acquisitions and 15 features (second-order class) in baseline acquisitions, including the three features distinguishing between Ki-67 groups in baseline images (MCC, ClusterProminence and Strength).
CONCLUSIONS
CONCLUSIONS
Some radiomic features can be used as a valid and reproducible tool for predicting Ki-67 class and hence the subtype of lung NET in baseline and post-contrast enhanced CT images. In particular, in baseline examination three features can establish both tumour class and aggressiveness.
Identifiants
pubmed: 36637739
doi: 10.1007/s11547-023-01592-y
pii: 10.1007/s11547-023-01592-y
pmc: PMC9938819
doi:
Substances chimiques
Ki-67 Antigen
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
203-211Informations de copyright
© 2023. The Author(s).
Références
Beasley MB, Thunnissen FB, Hasleton PhS et al (2004) Carcinoid tumour. In: Travis WD, Brambilla E, Muller-Harmelink HK et al (eds) Pathology and genetics of tumours of the lung, pleura, thymus and heart. IARC Press, Lyon, pp 59–62
Capella C, Heitz PU, Hofer H et al (1994) Revised classification of neuroendocrine tumours of the lung, pancreas and gut. Digestion 55(3):11–23
doi: 10.1159/000201197
pubmed: 7698533
Travis WD, Brambilla E, Burke A et al (2015) Introduction to the 2015 World Health Organization classification of tumors of the lung, pleura, thymus and heart. J Thorac Oncol 10(9):1240–1242
doi: 10.1097/JTO.0000000000000663
pubmed: 26291007
Klimstra DS (2016) Pathologic classification of neuroendocrine neoplasms. Hematol Oncol Clin North Am 30:1–19
doi: 10.1016/j.hoc.2015.08.005
pubmed: 26614366
Klöppel G (2017) Neuroendocrine neoplasms: dichotomy, origin and classification. Visc Med 33(5):324–330
doi: 10.1159/000481390
pubmed: 29177160
pmcid: 5697503
Devesa SS, Bray F, Vizcaino AP, Parkin DM (2005) International lung cancer trends by histologic type: male: female differences diminishing and adenocarcinoma rates rising. Int J Cancer 117:294–299
doi: 10.1002/ijc.21183
pubmed: 15900604
Crocetti E, Paci E (2003) Malignant carcinoids in the USA, SEER 1992–1999. An epidemiological study with 6830 cases. Eur J Cancer Prev 12(3):191–194
Chong S, Lee KS, Chung MJ et al (2006) Neuroendocrine tumors of the lung: clinical, pathologic, and imaging findings. Radiographics 26:41–57
doi: 10.1148/rg.261055057
pubmed: 16418242
Danti G, Berti V, Abenavoli E et al (2020) Diagnostic imaging of typical lung carcinoids: relationship between MDCT, (111)In-Octreoscan and (18)F-FDG-PET imaging features with Ki-67 index. Radiol Med 125:715–729. https://doi.org/10.1007/s11547-020-01172-4
doi: 10.1007/s11547-020-01172-4
pubmed: 32189174
Jeung MY, Gasser B, Gangi A et al (2002) Bronchial carcinoid tumors of the thorax: spectrum of radiologic fndings. Radiographics 22(2):351–365
doi: 10.1148/radiographics.22.2.g02mr01351
pubmed: 11896225
Nessi R, Basso Ricci P, Basso Ricci S et al (1991) Bronchial carcinoid tumors: radiologic observations in 49 cases. J Thorac Imaging 6:47–53
doi: 10.1097/00005382-199104000-00011
pubmed: 1649924
Malla S, Kumar P, Madhusudhan KS (2020) Radiology of the neuroendocrine neoplasms of the gastrointestinal tract: a comprehensive review. Abdom Radiol. https://doi.org/10.1007/s00261-020-02773-3
doi: 10.1007/s00261-020-02773-3
Skov BG, Krasnik M, Lantuejoul S et al (2008) Reclassification of neuroendocrine tumors improves the separation of carcinoids and the prediction of survival. J Thorac Oncol 3(12):1410–1415
doi: 10.1097/JTO.0b013e31818e0dd4
pubmed: 19057265
Scapicchio C, Gabelloni M, Barucci A (2021) A deep look into radiomics. Radiol Med 126(10):1296–1311. https://doi.org/10.1007/s11547-021-01389-x
doi: 10.1007/s11547-021-01389-x
pubmed: 34213702
pmcid: 8520512
Karmazanovsky G, Gruzdev I, Tikhonova V et al (2021) Computed tomography-based radiomics approach in pancreatic tumors characterization. Radiol Med 126:1388–1395
doi: 10.1007/s11547-021-01405-0
Palatresi D, Fedeli F, Danti G et al (2022) Correlation of CT radiomic features for GISTs with pathological classification and molecular subtypes: Preliminary and monocentric experience. Radiol Med 127:117–128
doi: 10.1007/s11547-021-01446-5
pubmed: 35022956
Granata V, Fusco R, De Muzio F et al (2022) Radiomics textural features by MR imaging to assess clinical outcomes following liver resection in colorectal liver metastases. Radiol Med 127(5):461–470
doi: 10.1007/s11547-022-01477-6
pubmed: 35347583
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
doi: 10.1007/s11547-021-01333-z
pubmed: 33523367
Neri E, Coppola F, Miele V (2020) Artificial intelligence: Who is responsible for the diagnosis? Radiol Med 125(6):517–521. https://doi.org/10.1007/s11547-020-01135-9
doi: 10.1007/s11547-020-01135-9
pubmed: 32006241
Coppola F, Faggioni L, Regge D et al (2021) Artificial intelligence: radiologists’ expectations and opinions gleaned from a nationwide online survey. Radiol Med 126(1):63–71. https://doi.org/10.1007/s11547-020-01205-y
doi: 10.1007/s11547-020-01205-y
pubmed: 32350797
Rinaldi L, De Angelis SP, Raimondi S et al (2022) Reproducibility of radiomic features in CT images of NSCLC patients: an integrative analysis on the impact of acquisition and reconstruction parameters. Eur Radiol Experimental. https://doi.org/10.1186/s41747-021-00258-6
doi: 10.1186/s41747-021-00258-6
Zhang L, Kang L, Li G et al (2020) Computed tomography-based radiomics model for discriminating the risk stratification of gastrointestinal stromal tumors. Radiol Med 125:465–473
doi: 10.1007/s11547-020-01138-6
pubmed: 32048155
Nardi C, Tomei M, Pietragalla M et al (2021) Texture analysis in the characterization of parotid salivary gland lesions: A study on MR diffusion weighted imaging. Eur J Radiol 136:109529
doi: 10.1016/j.ejrad.2021.109529
pubmed: 33453571
Mungai F, Verrone GB, Pietragalla M et al (2019) CT assessment of tumor heterogeneity and the potential for the prediction of human papillomavirus status in oropharyngeal squamous cell carcinoma. Radiol Med 124:804–811
doi: 10.1007/s11547-019-01028-6
pubmed: 30911988
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 125:951–960
doi: 10.1007/s11547-020-01188-w
pubmed: 32306201
Santone A, Brunese MC, Donnarumma F et al (2021) Radiomic features for prostate cancer grade detection through formal verification. Radiol Med 126:688–697
doi: 10.1007/s11547-020-01314-8
pubmed: 33394366
Cozzi D, Bicci E, Cavigli E (2022) Radiomics in pulmonary neuroendocrine tumours (NETs). Radiol Med. https://doi.org/10.1007/s11547-022-01494-5
doi: 10.1007/s11547-022-01494-5
pubmed: 35538389
pmcid: 9130162
Agazzi GM, Ravanelli M, Roca E et al (2021) CT texture analysis for prediction of EGFR mutational status and ALK rearrangement in patients with non-small cell lung cancer. Radiol Med 126:786–794. https://doi.org/10.1007/s11547-020-01323-7
doi: 10.1007/s11547-020-01323-7
pubmed: 33512651
Mackin D, Fave X, Zhang L et al (2015) Measuring computed tomography scanner variability of radiomics features. Invest Radiol 50(11):757–765. https://doi.org/10.1097/RLI.0000000000000180
doi: 10.1097/RLI.0000000000000180
pubmed: 26115366
pmcid: 4598251
Meyer M, Ronald J, Vernuccio F, Nelson RC (2019) Reproducibility of CT radiomic features within the same patient: influence of radiation dose and CT reconstruction settings. Radiology 293(3):583–591. https://doi.org/10.1148/radiol.2019190928
doi: 10.1148/radiol.2019190928
pubmed: 31573400
Ganeshan B, Goh V, Mandeville HC et al (2013) Non-small cell lung cancer: histopathologic correlates for texture parameters at CT. Radiology 266:326–336
doi: 10.1148/radiol.12112428
pubmed: 23169792
Grazzini G, Danti G, Cozzi D et al (2019) Diagnostic imaging of gastrointestinal neuroendocrine tumours (GI-NETs): relationship between MDCT features and 2010 WHO classification. Radiol Med 124:94–102
doi: 10.1007/s11547-018-0946-8
pubmed: 30255371
Abenavoli E, Linguanti F, Briganti V et al (2020) Typical lung carcinoids: review of classification, radiological signs and nuclear imaging findings. Clin Translat Imaging. https://doi.org/10.1007/s40336-020-00364-2
doi: 10.1007/s40336-020-00364-2
Chetan MR, Gleeson FV (2021) Radiomics in predicting treatment response in non-small-cell lung cancer: current status, challenges and future perspectives. Eur Radiol 31(1049):1058
Hassani C, Varghese BA, Nieva J, Duddalwar V (2019) Radiomics in pulmonary lesion imaging. Am J Roentgenol AJR 212(3):497–504
doi: 10.2214/AJR.18.20623
Botta F, Raimondi S, Rinaldi L et al (2020) Association of a CT-based clinical and radiomics score of non-small cell lung cancer (NSCLC) with lymph node status and overall survival. Cancers 12(6):1432. https://doi.org/10.3390/cancers12061432
doi: 10.3390/cancers12061432
pubmed: 32486453
pmcid: 7352293
Fusco R, Granata V, Mazzei MA et al (2021) Quantitative imaging decision support (QDIS™) tool consistency evaluation and radiomic analysis by means of 594 metrics in lung carcinoma on chest CT scan. Cancer Control. https://doi.org/10.1177/1073274820985786
doi: 10.1177/1073274820985786
pubmed: 34620004
pmcid: 8506147
Granata V, Fusco R, Costa M et al (2021) Preliminary report on computed tomography radiomics features as biomarkers to immunotherapy selection in lung adenocarcinoma patients. Cancers (Basel) 7;13(16):3992 https://doi.org/10.3390/cancers13163992