MRI-based radiomics for predicting histology in malignant salivary gland tumors: methodology and "proof of principle".
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
30 04 2024
30 04 2024
Historique:
received:
01
12
2023
accepted:
18
04
2024
medline:
1
5
2024
pubmed:
1
5
2024
entrez:
30
4
2024
Statut:
epublish
Résumé
Defining the exact histological features of salivary gland malignancies before treatment remains an unsolved problem that compromises the ability to tailor further therapeutic steps individually. Radiomics, a new methodology to extract quantitative information from medical images, could contribute to characterizing the individual cancer phenotype already before treatment in a fast and non-invasive way. Consequently, the standardization and implementation of radiomic analysis in the clinical routine work to predict histology of salivary gland cancer (SGC) could also provide improvements in clinical decision-making. In this study, we aimed to investigate the potential of radiomic features as imaging biomarker to distinguish between high grade and low-grade salivary gland malignancies. We have also investigated the effect of image and feature level harmonization on the performance of radiomic models. For this study, our dual center cohort consisted of 126 patients, with histologically proven SGC, who underwent curative-intent treatment in two tertiary oncology centers. We extracted and analyzed the radiomics features of 120 pre-therapeutic MRI images with gadolinium (T1 sequences), and correlated those with the definitive post-operative histology. In our study the best radiomic model achieved average AUC of 0.66 and balanced accuracy of 0.63. According to the results, there is significant difference between the performance of models based on MRI intensity normalized images + harmonized features and other models (p value < 0.05) which indicates that in case of dealing with heterogeneous dataset, applying the harmonization methods is beneficial. Among radiomic features minimum intensity from first order, and gray level-variance from texture category were frequently selected during multivariate analysis which indicate the potential of these features as being used as imaging biomarker. The present bicentric study presents for the first time the feasibility of implementing MR-based, handcrafted radiomics, based on T1 contrast-enhanced sequences and the ComBat harmonization method in an effort to predict the formal grading of salivary gland carcinoma with satisfactory performance.
Identifiants
pubmed: 38688932
doi: 10.1038/s41598-024-60200-9
pii: 10.1038/s41598-024-60200-9
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
9945Informations de copyright
© 2024. The Author(s).
Références
Speight, P. M. & Barrett, A. W. Salivary gland tumours: Diagnostic challenges and an update on the latest WHO classification. Diagn. Histopathol. 26(4), 147–158 (2020).
doi: 10.1016/j.mpdhp.2020.01.001
Barnes, L., et al. (eds). Pathology and genetics of head and neck tumours. In World Health Organization Classification of Tumours (series eds. by Kleihues, P. & Sobin, L. H.) (IARC Press, Lyon, France, 2005).
Guzzo, M. et al. Major and minor salivary gland tumors. Crit. Rev. Oncol. Hematol. 74, 134–148 (2010).
pubmed: 19939701
doi: 10.1016/j.critrevonc.2009.10.004
Winkelmann, R. et al. Panagiotis Balermpas Patterns of care, toxicity and outcome in the treatment of salivary gland carcinomas: Long-term experience from a tertiary cancer center. Eur. Arch. Otorhinolaryngol. 278(11), 4411–4421 (2021).
pubmed: 33760953
pmcid: 8486723
doi: 10.1007/s00405-021-06652-5
Sood, S., McGurk, M. & Vaz, F. Management of salivary gland tumours: United Kingdom national multidisciplinary guidelines. J. Laryngol. Otol. 130(Suppl. S2), S142–S149 (2016).
pubmed: 27841127
pmcid: 4873929
doi: 10.1017/S0022215116000566
Walvekar, R. R. et al. Clinicopathologic features as stronger prognostic factors than histology or grade in risk stratification of primary parotid malignancies. Head Neck 33, 225–231 (2011).
pubmed: 21298822
pmcid: 4164959
doi: 10.1002/hed.21433
Kim, B. Y. et al. Diagnostic accuracy of fine needle aspiration cytology for high-grade salivary gland tumors. Ann. Surg. Oncol. 20(7), 2380 (2013).
pubmed: 23440550
doi: 10.1245/s10434-013-2903-z
Geiger, J. L. et al. Management of salivary gland malignancy: ASCO guideline. J. Clin. Oncol. 39(17), 1909–1941 (2021).
pubmed: 33900808
doi: 10.1200/JCO.21.00449
Eytan, D. F. et al. Utility of preoperative fine needle aspiration in parotid lesions. Laryngoscope 128(2), 398–402 (2018).
pubmed: 28782105
doi: 10.1002/lary.26776
Jalaly, J. B. & Baloch, Z. W. Salivary gland neoplasms in small biopsies and fine needle aspirations. Semin. Diagn. Pathol. 40(5), 340–348 (2023).
pubmed: 37085434
doi: 10.1053/j.semdp.2023.04.010
Lee, Y. Y. P., Wong, K. T., King, A. D. & Ahuja, A. T. Imaging of salivary gland tumours. Eur. J. Radiol. 66(3), 419–436 (2008).
pubmed: 18337041
doi: 10.1016/j.ejrad.2008.01.027
Johnson, D. N. et al. Cytologic grading of primary malignant salivary gland tumors: A blinded review by an international panel. Cancer Cytopathol. 128(6), 392–402 (2020).
pubmed: 32267606
pmcid: 7413070
doi: 10.1002/cncy.22271
Van Timmeren, J. E., Cester, D., Tanadini-Lang, S., Alkadhi, H. & Baessler, B. Radiomics in medical imaging—“how to” guide and critical reflection. Insight Imaging 11, 91. https://doi.org/10.1186/s13244-020-00887-2 (2020).
doi: 10.1186/s13244-020-00887-2
Kuo, M. D. & Jamshidi, N. Behind the numbers: Decoding molecular phenotypes with radiogenomics—guiding principles and technical considerations. Radiology 270, 320–325 (2014).
pubmed: 24471381
doi: 10.1148/radiol.13132195
Gevaert, O. et al. Non-small cell lung cancer : Identifying prognostic imaging biomarkers by leveraging public gene expression microarray data—methods and preliminary results. Radiology 264, 387–396 (2012).
pubmed: 22723499
pmcid: 3401348
doi: 10.1148/radiol.12111607
Mazurowski, M. A. Radiogenomics: What it is and why it is important. J. Am. Coll. Radiol. 12, 862–866 (2015).
pubmed: 26250979
doi: 10.1016/j.jacr.2015.04.019
Tanadini-Lang, S. et al. Marta Bogowicz Radiomic biomarkers for head and neck squamous cell carcinoma. Strahlenther. Onkol. 196(10), 868–878 (2020).
pubmed: 32495038
doi: 10.1007/s00066-020-01638-4
Zheng, Y.-M. et al. MRI-based radiomics nomogram for differentiation of benign and malignant lesions of the parotid gland. Eur. Radiol. 31(6), 4042–4052 (2021).
pubmed: 33211145
doi: 10.1007/s00330-020-07483-4
El-Naggar, A. K. et al. (eds) WHO Classification of Head and Neck Tumours 4th edn. (IARC, Lyon, 2017).
Zwanenburg, A. et al. The image biomarker standardization initiative: Standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 295(2), 328–338 (2020).
pubmed: 32154773
doi: 10.1148/radiol.2020191145
Tustison, N. J. et al. N4ITK: improved N3 bias correction. IEEE Trans. Med. Imaging 29(6), 1310–1320 (2010).
pubmed: 20378467
pmcid: 3071855
doi: 10.1109/TMI.2010.2046908
Shinohara, R. T. et al. Statistical normalization techniques for magnetic resonance imaging.". NeuroImage Clin. 6, 9–19 (2014).
pubmed: 25379412
pmcid: 4215426
doi: 10.1016/j.nicl.2014.08.008
Van Griethuysen, J. J. M. et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 77(21), e104–e107 (2017).
pubmed: 29092951
pmcid: 5672828
doi: 10.1158/0008-5472.CAN-17-0339
Sreedhar Kumar, S., Madheswaran, M., Vinutha, B. A., Manjunatha Singh, H. & Charan, K. V. A brief survey of unsupervised agglomerative hierarchical clustering schemes. Int. J. Eng. Technol. (UAE) 8(1), 29–37 (2019).
Shahapure, K. R. & Nicholas, C. Cluster quality analysis using silhouette score. In 2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA), 747–748 (IEEE, 2020).
Orlhac, F. et al. A guide to ComBat harmonization of imaging biomarkers in multicenter studies. J. Nucl. Med. 63(2), 172–179 (2022).
pubmed: 34531263
pmcid: 8805779
doi: 10.2967/jnumed.121.262464
Kumar, V. & Minz, S. Feature selection: A literature review. SmartCR 4(3), 211–229 (2014).
doi: 10.6029/smartcr.2014.03.007
van Herpen, C. et al. ESMO-European Reference Network on Rare Adult Solid Cancers (EURACAN) clinical practice guideline for diagnosis, treatment and follow-up. ESMO Open Salivary Gland Cancer 7(6), 100602 (2022).
doi: 10.1016/j.esmoop.2022.100602
Karimian, S. et al. Potential role of hybrid positron emission tomography in pre-operative assessment of primary salivary gland carcinomas. J. Laryngol. Otol. 137(5), 551–555 (2023).
pubmed: 35729688
doi: 10.1017/S0022215122001475
Reerds, S. T. H. et al. Results of histopathological revisions of major salivary gland neoplasms in routine clinical practice. J. Clin. Pathol. 76(6), 374–378 (2023).
pubmed: 35042756
doi: 10.1136/jclinpath-2021-208072
Jering, M. et al. Diagnostic accuracy and post-procedural complications associated with ultrasound-guided core needle biopsy in the preoperative evaluation of parotid tumors. Head Neck Pathol. 16(3), 651–656 (2022).
pubmed: 34919166
doi: 10.1007/s12105-021-01401-w
van Dijk, L. V. et al. Parotid gland fat related magnetic resonance image biomarkers improve prediction of late radiation-induced xerostomia. Radiother. Oncol. 128(3), 459–466 (2018).
pubmed: 29958772
pmcid: 6625348
doi: 10.1016/j.radonc.2018.06.012
Sheikh, K. et al. Predicting acute radiation induced xerostomia in head and neck cancer using MR and CT radiomics of parotid and submandibular glands. Radiat. Oncol. 14(1), 131 (2019).
pubmed: 31358029
pmcid: 6664784
doi: 10.1186/s13014-019-1339-4
Ikushima, K., Arimura, H., Yasumatsu, R., Kamezawa, H. & Ninomiya, K. Topology-based radiomic features for prediction of parotid gland cancer malignancy grade in magnetic resonance images. MAGMA 36(5), 767–777 (2023).
pubmed: 37079154
doi: 10.1007/s10334-023-01084-0
Kamezawa, H., Arimura, H., Yasumatsu, R., Ninomiya, K. & Haseai, S. Preoperative and non-invasive approach for radiomic biomarker-based prediction of malignancy grades in patients with parotid gland cancer in magnetic resonance images. Med. Imaging Inf. Sci. 37(4), 66–74 (2020).
Friedman, E., Cai, Y. & Chen, B. Imaging of major salivary gland lesions and disease. Oral Maxillofac. Surg. Clin. N. Am. 35(3), 435–449 (2023).
doi: 10.1016/j.coms.2023.02.007
Okahara, M. et al. Parotid tumors: MR imaging with pathological correlation. Eur. Radiol. 13, L25–L33 (2003).
pubmed: 15018162
doi: 10.1007/s00330-003-1999-0
Whybra, P. et al. The image biomarker standardization initiative: Standardized convolutional filters for reproducible radiomics and enhanced clinical insights. Radiology 310(2), e231319 (2024).
pubmed: 38319168
doi: 10.1148/radiol.231319
Grira, N., Crucianu, M. & Boujemaa, N. Unsupervised and semi-supervised clustering: a brief survey. In A Review of Machine Learning Techniques for Processing Multimedia Content Vol. 1 9–16 (2004).
Cios, K. J. et al. Unsupervised learning: Clustering. Data Min. A Knowl. Discov. Approach 15, 257–288 (2007).
Khodabakhshi, Z. et al. Dual-centre harmonised multimodal positron emission tomography/computed tomography image radiomic features and machine learning algorithms for non-small cell lung cancer histopathological subtype phenotype decoding. Clin. Oncol. 35(11), 713–725 (2023).
doi: 10.1016/j.clon.2023.08.003
Orlhac, F. et al. How can we combat multicenter variability in MR radiomics? Validation of a correction procedure. Eur. Radiol. 31, 2272–2280 (2021).
pubmed: 32975661
doi: 10.1007/s00330-020-07284-9
Shiri, I. et al. Impact of feature harmonization on radiogenomics analysis: Prediction of EGFR and KRAS mutations from non-small cell lung cancer PET/CT images. Comput. Biol. Med. 142, 105230 (2022).
pubmed: 35051856
doi: 10.1016/j.compbiomed.2022.105230
Orlhac, F. et al. A postreconstruction harmonization method for multicenter radiomic studies in PET. J. Nucl. Med. 59(8), 1321–1328 (2018).
pubmed: 29301932
doi: 10.2967/jnumed.117.199935
Mahon, R. N., Ghita, M., Hugo, G. D. & Weiss, E. ComBat harmonization for radiomic features in independent phantom and lung cancer patient computed tomography datasets. Phys. Med. Biol. 65(1), 015010 (2020).
pubmed: 31835261
doi: 10.1088/1361-6560/ab6177
Leithner, D. et al. ComBat harmonization for MRI radiomics: Impact on nonbinary tissue classification by machine learning. Invest. Radiol. 15, 10–1097 (2023).
Baba, A. et al. Pre-treatment MRI predictor of high-grade malignant parotid gland cancer. Oral Radiol. 37, 611–616 (2021).
pubmed: 33389599
doi: 10.1007/s11282-020-00498-z
Shah, M. et al. Evaluating intensity normalization on MRIs of human brain with multiple sclerosis. Med. Image Anal. 15(2), 267–282 (2011).
pubmed: 21233004
doi: 10.1016/j.media.2010.12.003
Ganganwar, V. An overview of classification algorithms for imbalanced datasets. Int. J. Emerg. Technol. Adv. Eng. 2(4), 42–47 (2012).
Kotsiantis, S., Kanellopoulos, D. & Pintelas, P. Handling imbalanced datasets: A review. GESTS Int. Trans. Comput. Sci. Eng. 30(1), 25–36 (2006).
Horng, H. et al. Generalized ComBat harmonization methods for radiomic features with multi-modal distributions and multiple batch effects. Sci. Rep. 12(1), 4493 (2022).
pubmed: 35296726
pmcid: 8927332
doi: 10.1038/s41598-022-08412-9