Priority radiomic parameters for computed tomography of head and neck malignancies: A systematic review

Abstract

BACKGROUND: Radiomics is the newest and most promising direction in modern radiographic diagnostics. The number of head and neck cancer studies employing radiomics is increasing annually. A systematic review of recent publications (2021–2023) on computed tomography (CT) of head and neck malignancies was performed.

AIM: To present systematized data on parameters for radiomic analysis for head and neck malignancies identified by CT data.

MATERIALS AND METHODS: The literature search was carried out in PubMed. The basic characteristics of the selected articles were extracted, and their quality was assessed using RQS 2.0 and the modified QUADAS-CAD questionnaire. The reproducibility level of radiomic parameters selected for predictive models in different studies was assessed. Eleven articles were selected for the review. In most cases, a high risk of systematic error associated with data imbalance in terms of demographic parameters and level of pathologies was noted.

RESULTS: The range of RQS 2.0 scores for the included articles varied from 19.44% to 50.00% of the maximum possible score. The decreasing research quality was mainly caused by the lack of external result validation (73% of the analyzed articles) and data accessibility and transparency (82%). Inter-study reproducibility of radiomic parameters was low owing to the wide variety of techniques used for image acquisition, image post-processing, extraction, and statistical processing of radiomic parameters.

CONCLUSION: A set of stable radiomic parameters must be successfully introduced into clinical practice. The standardization of radiomics method and creation of an open radiomics database are necessary for this purpose.

Keywords

radiomics / head and neck cancer / radiomic parameters

References

[1] Rizzo S, Botta F, Raimondi S, et al. Radiomics: the facts and the challenges of image analysis. Eur Radiol Exp. 2018;2. doi: 10.1186/s41747-018-0068-z

[2] Rizzo S., Botta F., Raimondi S., et al. Radiomics: the facts and the challenges of image analysis // Eur Radiol Exp. 2018. Vol. 2. doi: 10.1186/s41747-018-0068-z

[3] Lambin P, Leijenaar R, Deist T, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 2017;14:749–762. doi: 10.1038/nrclinonc.2017.141

[4] Lambin P., Leijenaar R., Deist T., et al. Radiomics: the bridge between medical imaging and personalized medicine // Nat Rev Clin Oncol. 2017. Vol. 14. P. 749–762. doi: 10.1038/nrclinonc.2017.141

[5] Mayerhoefer ME, Materka A, Langs G, et al. Introduction to Radiomics. J Nucl Med. 2020;61(4):488–495. doi: 10.2967/jnumed.118.222893

[6] Mayerhoefer M.E., Materka A., Langs G., et al. Introduction to Radiomics // J Nucl Med. 2020. Vol. 61, N 4. P. 488–495. doi: 10.2967/jnumed.118.222893

[7] Wan Y, Yang P, Xu L, et al. Radiomics analysis combining unsupervised learning and handcrafted features: A multiple-disease study. Medical Physics. 2021;48(11):7003–7015. doi: 10.1002/mp.15199

[8] Wan Y., Yang P., Xu L., et al. Radiomics analysis combining unsupervised learning and handcrafted features: A multiple-disease study // Medical Physics. 2021. Vol. 48, N 11. P. 7003–7015. doi: 10.1002/mp.15199

[9] Zwanenburg A, Vallières M, Abdalah MA, et al. The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. Radiology. 2020;295(2). doi: 10.1148/radiol.2020191145

[10] Zwanenburg A., Vallières M., Abdalah M.A., et al. The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping // Radiology. 2020. Vol. 295, N 2. doi: 10.1148/radiol.2020191145

[11] Berenguer R, Pastor-Juan M, Canales-Vázquez J, et al. Radiomics of CT Features May Be Nonreproducible and Redundant: Influence of CT Acquisition Parameters. Radiology. 2018;288(2). doi: 10.1148/radiol.2018172361

[12] Berenguer R., Pastor-Juan M., Canales-Vázquez J., et al. Radiomics of CT Features May Be Nonreproducible and Redundant: Influence of CT Acquisition Parameters // Radiology. 2018. Vol. 288, N 2. doi: 10.1148/radiol.2018172361

[13] Laura QM, Chow MD. Head and Neck Cancer. N Engl J Med. 2020;382:60–72. doi: 10.1056/NEJMra1715715

[14] Laura Q.M., Chow M.D. Head and Neck Cancer // N Engl J Med. 2020. Vol. 382. P. 60–72. doi: 10.1056/NEJMra1715715

[15] Sung H, Ferlay J, Siegel RL, et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. Ca Cancer J Clin. 2021;71(3):209–249. doi: 10.3322/caac.21660

[16] Sung H., Ferlay J., Siegel R.L., et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries // Ca Cancer J Clin. 2021. Vol. 71, N 3. P. 209–249. doi: 10.3322/caac.21660

[17] Bolotina LV, Vladimirova LYu, Den’gina NV, Novik AV, Romanov IS. Practice guidelines for the treatment of malignant tumors of the head and neck. Zlokačestvennye opuholi. 2020;10(3s2-1):93–108. (In Russ). doi: 10.18027/2224-5057-2020-10-3s2-06

[18] Болотина Л.В., Владимирова Л.Ю., Деньгина Н.В., Новик А.В., Романов И.С. Практические рекомендации по лечению злокачественных опухолей головы и шеи // Злокачественные опухоли. 2020. Т. 10, № 3s2-1. С. 93–108. doi: 10.18027/2224-5057-2020-10-3s2-06

[19] Bossi P, Chan AT, Licitra L, et al. Nasopharyngeal carcinoma: ESMO-EURACAN Clinical Practice Guidelines for diagnosis, treatment and follow-up. Annals of oncology. 2021;32(4):452–465. doi: 10.1016/j.annonc.2020.12.007

[20] Bossi P., Chan A.T., Licitra L., et al. Nasopharyngeal carcinoma: ESMO-EURACAN Clinical Practice Guidelines for diagnosis, treatment and follow-up // Annals of oncology. 2021. Vol. 32, N 4. P. 452–465. doi: 10.1016/j.annonc.2020.12.007

[21] Petrovichev VS, Neklyudova MV, Sinitsyn VE, Nikitin IG. Dual-energy computed tomography for head and neck cancer. Digital Diagnostics. 2021;2(3):343–355. doi: 10.17816/DD62572

[22] Петровичев В.С., Неклюдова М.В., Синицын В.Е., Никитин И.Г. Двухэнергетическая компьютерная томография рака головы и шеи // Digital Diagnostics. 2021. Т. 2, № 3. С. 343–355. doi: 10.17816/DD62572

[23] Guha A, Connor S, Anjari M, et al. Radiomic analysis for response assessment in advanced head and neck cancers, a distant dream or an inevitable reality? A systematic review of the current level of evidence. BJR. 2019;93(1106). doi: 10.1259/bjr.20190496

[24] Guha A., Connor S., Anjari M., et al. Radiomic analysis for response assessment in advanced head and neck cancers, a distant dream or an inevitable reality? A systematic review of the current level of evidence // BJR. 2019. Vol. 93, N 1106. doi: 10.1259/bjr.20190496

[25] Giannitto C, Mercante G, Ammirabile A, et al. Radiomics-based machine learning for the diagnosis of lymph node metastases in patients with head and neck cancer: Systematic review. Head & Neck. 2022;45(2):482–491. doi: 10.1002/hed.27239

[26] Giannitto C., Mercante G., Ammirabile A., et al. Radiomics-based machine learning for the diagnosis of lymph node metastases in patients with head and neck cancer: Systematic review // Head & Neck. 2022. Vol. 45, N 2. P. 482–491. doi: 10.1002/hed.27239

[27] Yu Y, Li X, Li W, Wang H, Wang Y. Pretreatment radiomics power in evaluating neoadjuvant chemotherapy response and outcome for patients with head and neck squamous cell carcinoma: a systematic review and meta-analysis. Preprint. 2023. doi: 10.21203/rs.3.rs-2530190/v1

[28] Yu Y., Li X., Li W., Wang H., Wang Y. Pretreatment radiomics power in evaluating neoadjuvant chemotherapy response and outcome for patients with head and neck squamous cell carcinoma: a systematic review and meta-analysis. Preprint. 2023. doi: 10.21203/rs.3.rs-2530190/v1

[29] Page MJ, McKenzie JE, Bossuyt PM, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;372. doi: 10.1136/bmj.n71

[30] Page M.J., McKenzie J.E., Bossuyt P.M., et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews // BMJ. 2021. Vol. 372. doi: 10.1136/bmj.n71

[31] Radiomics Quality Score — RQS 2.0 [Internet]. [cited 1 Jan 2023]. Available from: https://www.radiomics.world/rqs2

[32] Radiomics Quality Score — RQS 2.0. [Internet]. [дата обращения 01.01.2023]. Доступ по ссылке: https://www.radiomics.world/rqs2

[33] Kodenko MR, Vasilev YA, Vladzymyrskyy AV, et al. Diagnostic Accuracy of AI for Opportunistic Screening of Abdominal Aortic Aneurysm in CT: A Systematic Review and Narrative Synthesis. Diagnostics. 2022;12(12):3197. doi: 10.3390/diagnostics12123197

[34] Kodenko M.R., Vasilev Y.A., Vladzymyrskyy A.V., et al. Diagnostic Accuracy of AI for Opportunistic Screening of Abdominal Aortic Aneurysm in CT: A Systematic Review and Narrative Synthesis // Diagnostics. 2022. Vol. 12, N 12. P. 3197. doi: 10.3390/diagnostics12123197

[35] Kodenko MR, Reshetnikov RV, Makarova TA. Modification of quality assessment tool for artificial intelligence diagnostic test accuracy studies (QUADAS-CAD). Digital Diagnostics. 2022;3(S1):4–5. doi: 10.17816/DD105567

[36] Коденко М.Р., Решетников Р.В., Макарова Т.А. Инструмент оценки качества исследований диагностической точности алгоритмов искусственного интеллекта (QUADAS-CAD) // Digital Diagnostics. 2022. Т. 3, № S1. С. 4–5. doi: 10.17816/DD105567

[37] Teng X, Zhang J, Ma Z, et al. Improving radiomic model reliability using robust features from perturbations for head-and-neck carcinoma. Front. Oncol. 2022;12. doi: 10.3389/fonc.2022.974467

[38] Teng X., Zhang J., Ma Z., et al. Improving radiomic model reliability using robust features from perturbations for head-and-neck carcinoma // Front. Oncol. 2022. Vol. 12. doi: 10.3389/fonc.2022.974467

[39] Liu X, Maleki F, Muthukrishnan N, et al. Site-Specific Variation in Radiomic Features of Head and Neck Squamous Cell Carcinoma and Its Impact on Machine Learning Models. Cancers. 2021;13(15). doi: 10.3390/cancers13153723

[40] Liu X., Maleki F., Muthukrishnan N., et al. Site-Specific Variation in Radiomic Features of Head and Neck Squamous Cell Carcinoma and Its Impact on Machine Learning Models // Cancers. 2021. Vol. 13, N 15. doi: 10.3390/cancers13153723

[41] Zhao X, Li W, Zhang J, et al. Radiomics analysis of CT imaging improves preoperative prediction of cervical lymph node metastasis in laryngeal squamous cell carcinoma. European Radiology. 2023;33:1121–1131. doi: 10.1007/s00330-022-09051-4

[42] Zhao X., Li W., Zhang J., et al. Radiomics analysis of CT imaging improves preoperative prediction of cervical lymph node metastasis in laryngeal squamous cell carcinoma // European Radiology. 2023. Vol. 33. P. 1121–1131. doi: 10.1007/s00330-022-09051-4

[43] Zhang W, Peng J, Zhao S, et al. Deep learning combined with radiomics for the classification of enlarged cervical lymph nodes. Journal of Cancer Research and Clinical Oncology. 2022;148:2773–2780. doi: 10.1007/s00432-022-04047-5

[44] Zhang W., Peng J., Zhao S., et al. Deep learning combined with radiomics for the classification of enlarged cervical lymph nodes // Journal of Cancer Research and Clinical Oncology. 2022. Vol. 148. P. 2773–2780. doi: 10.1007/s00432-022-04047-5

[45] Yang G, Yang F, Zhang F, et al. Radiomics Profiling Identifies the Value of CT Features for the Preoperative Evaluation of Lymph Node Metastasis in Papillary Thyroid Carcinoma. Diagnostics. 2022;12(5). doi: 10.3390/diagnostics12051119

[46] Yang G., Yang F., Zhang F., et al. Radiomics Profiling Identifies the Value of CT Features for the Preoperative Evaluation of Lymph Node Metastasis in Papillary Thyroid Carcinoma // Diagnostics. 2022. Vol. 12, N 5. doi: 10.3390/diagnostics12051119

[47] Li J, Wu X, Mao N, et al. Computed Tomography-Based Radiomics Model to Predict Central Cervical Lymph Node Metastases in Papillary Thyroid Carcinoma: A Multicenter Study. Front. Endocrinol. 2021;12. doi: 10.3389/fendo.2021.741698

[48] Li J., Wu X., Mao N., et al. Computed Tomography-Based Radiomics Model to Predict Central Cervical Lymph Node Metastases in Papillary Thyroid Carcinoma: A Multicenter Study // Front. Endocrinol. 2021. Vol. 12. doi: 10.3389/fendo.2021.741698

[49] Franzese C, Lillo S, Cozzi L, et al. Predictive value of clinical and radiomic features for radiation therapy response in patients with lymph node-positive head and neck cancer. Head & Neck. 2023;45(5):1184–1193. doi: 10.1002/hed.27332

[50] Franzese C., Lillo S., Cozzi L., et al. Predictive value of clinical and radiomic features for radiation therapy response in patients with lymph node-positive head and neck cancer // Head & Neck. 2023. Vol. 45, N 5. P. 1184–1193. doi: 10.1002/hed.27332

[51] Gonçalves M, Gsaxner Ch, Ferreira A, et al. Radiomics in Head and Neck Cancer Outcome Predictions. Diagnostics. 2022;12(11). doi: 10.3390/diagnostics12112733

[52] Gonçalves M., Gsaxner Ch., Ferreira A., et al. Radiomics in Head and Neck Cancer Outcome Predictions // Diagnostics. 2022. Vol. 12, N 11. doi: 10.3390/diagnostics12112733

[53] Zhai T, Wesseling F, Langendijk J, et al. External validation of nodal failure prediction models including radiomics in head and neck cancer. Oral Oncology. 2021;112. doi: 10.1016/j.oraloncology.2020.105083

[54] Zhai T., Wesseling F., Langendijk J., et al. External validation of nodal failure prediction models including radiomics in head and neck cancer // Oral Oncology. 2021. Vol. 112. doi: 10.1016/j.oraloncology.2020.105083

[55] Morgan HE, Wang K, Dohopolski M, et al. Exploratory ensemble interpretable model for predicting local failure in head and neck cancer: the additive benefit of CT and intra-treatment cone-beam computed tomography features. Quant Imaging Med Surg. 2021;11(12):4781–4796. doi: 10.21037/qims-21-274

[56] Morgan H.E., Wang K., Dohopolski M., et al. Exploratory ensemble interpretable model for predicting local failure in head and neck cancer: the additive benefit of CT and intra-treatment cone-beam computed tomography features // Quant Imaging Med Surg. 2021. Vol. 11, N 12. P. 4781–4796. doi: 10.21037/qims-21-274

[57] Intarak S, Chongpison Y, Vimolnoch M, et al. Tumor Prognostic Prediction of Nasopharyngeal Carcinoma Using CT-Based Radiomics in Non-Chinese Patients. Front. Oncol. 2022;12. doi: 10.3389/fonc.2022.775248

[58] Intarak S., Chongpison Y., Vimolnoch M., et al. Tumor Prognostic Prediction of Nasopharyngeal Carcinoma Using CT-Based Radiomics in Non-Chinese Patients // Front. Oncol. 2022. Vol. 12. doi: 10.3389/fonc.2022.775248

[59] Zhong J, Lu J, Zhang G, et al. An overview of meta-analyses on radiomics: more evidence is needed to support clinical translation. Insights Imaging. 2023;14. doi: 10.1186/s13244-023-01437-2

[60] Zhong J., Lu J., Zhang G., et al. An overview of meta-analyses on radiomics: more evidence is needed to support clinical translation // Insights Imaging. 2023. Vol. 14. doi: 10.1186/s13244-023-01437-2

[61] Certificate of state registration of the computer program № 2022617324/ 19.04.2022. Morozov SP, Andreichenko AE, Chetverikov SF, et al. Web-based tool for performing ROC analysis of diagnostic test results: № 2022616046. (In Russ).

[62] Свидетельство о государственной регистрации программы для ЭВМ № 2022617324/ 19.04.2022. Морозов С.П., Андрейченко А.Е., Четвериков С.Ф., и др. Веб-инструмент для выполнения ROC анализа результатов диагностических тестов: № 2022616046.

[63] Giraud P, Giraud Ph, Gasnier A, et al. Radiomics and Machine Learning for Radiotherapy in Head and Neck Cancers. Front. Oncol. 2019;9. doi: 10.3389/fonc.2019.00174

[64] Giraud P., Giraud Ph., Gasnier A., et al. Radiomics and Machine Learning for Radiotherapy in Head and Neck Cancers // Front. Oncol. 2019. Vol. 9. doi: 10.3389/fonc.2019.00174

[65] Certificate of state registration of the computer program № 2023619686/ 15.05.2023. Vasilev YuA, Vladzymirskyy AV, Omelyanskaya OV, et al. Web-based tool for quality control of datasets: № 2023617136. (In Russ).

[66] Свидетельство о государственной регистрации программы для ЭВМ № 2023619686/ 15.05.2023. Васильев Ю.А., Владзимирский А.В., Омелянская О.В., и др. Веб-инструмент для контроля качества датасетов: № 2023617136.

[67] Gundersen OE, Kjensmo S. State of the Art: Reproducibility in Artificial Intelligence. Proceedings of the AAAI Conference on Artificial Intelligence. 2018;32(1). doi: 10.1609/aaai.v32i1.11503

[68] Gundersen O.E., Kjensmo S. State of the Art: Reproducibility in Artificial Intelligence // Proceedings of the AAAI Conference on Artificial Intelligence. 2018. Vol. 32, N 1. doi: 10.1609/aaai.v32i1.11503

[69] Tortora M, Gemini L, Scaravilli A, et al. Radiomics Applications in Head and Neck Tumor Imaging: A Narrative Review. Cancers. 2023;15(4). doi: 10.3390/cancers15041174

[70] Tortora M., Gemini L., Scaravilli A., et al. Radiomics Applications in Head and Neck Tumor Imaging: A Narrative Review // Cancers. 2023. Vol. 15, N 4. doi: 10.3390/cancers15041174

[71] Image Biomarker Standardisation Initiative (IBSI) [Internet]. [cited 1 Jan 2023]. Available from: https://theibsi.github.io/

[72] Image Biomarker Standardisation Initiative (IBSI) [Internet]. [дата обращения: 01.01.2023]. Доступ по ссылке: https://theibsi.github.io/

[73] Morozov SP, Vladzymirskyy AV, Klyashtornyi VG, et al. Practice guidelines for the treatment of malignant tumors of the head and neck. Moscow; 2019. (In Russ).

[74] Морозов С.П., Владзимирский А.В., Кляшторный В.Г., и др. Клинические испытания программного обеспечения на основе интеллектуальных технологий (лучевая диагностика). Москва, 2019.

[75] Buvat I, Orlhac F. The Dark Side of Radiomics: On the Paramount Importance of Publishing Negative Results. The Journal of Nuclear Medicine. 2019;60(11):1543–1544. doi: 10.2967/jnumed.119.235325

[76] Buvat I., Orlhac F. The Dark Side of Radiomics: On the Paramount Importance of Publishing Negative Results // The Journal of Nuclear Medicine. 2019. Vol. 60, N 11. P. 1543–1544. doi: 10.2967/jnumed.119.235325

[77] Kocak B, Bulut E, Bayrak ON, et al. NEgatiVE results in Radiomics research (NEVER): A meta-research study of publication bias in leading radiology journals. European Journal of Radiology. 2023;163. doi: 10.1016/j.ejrad.2023.110830

[78] Kocak B., Bulut E., Bayrak O.N., et al. NEgatiVE results in Radiomics research (NEVER): A meta-research study of publication bias in leading radiology journals // European Journal of Radiology. 2023. Vol. 163. doi: 10.1016/j.ejrad.2023.110830

[79] Berenguer R, Pastor-Juan MR, Canales-Vázquez J, et al. Radiomics of CT Features May Be Nonreproducible and Redundant: Influence of CT Acquisition Parameters. Radiology. 2018;288(2). doi: 10.1148/radiol.2018172361

[80] Berenguer R., Pastor-Juan M.R., Canales-Vázquez J., et al. Radiomics of CT Features May Be Nonreproducible and Redundant: Influence of CT Acquisition Parameters // Radiology. 2018. Vol. 288, N 2. doi: 10.1148/radiol.2018172361

[81] Morozov SP, Lindenbraten LD, Gabai PG, et al. Fundamentals of medical imaging management. Morozov SP, editor. Moscow: GEOTAR-Media; 2020. (In Russ). doi: 10.33029/9704-5247-9-MEN-2020-1-424

[82] Морозов С.П., Линденбратен Л.Д., Габай П.Г., и др. Основы менеджмента медицинской визуализации / под ред. С.П. Морозова. Москва : ГЭОТАР-Медиа, 2020. doi: 10.33029/9704-5247-9-MEN-2020-1-424

[83] Khoruzhaya AN, Ahkmad ES, Semenov DS. The role of the quality control system for diagnostics of oncological diseases in radiomics. Digital Diagnostics. 2021;2(2):170–184. doi: 10.17816/DD60393

[84] Хоружая А.Н., Ахмад Е.С., Семенов Д.С. Роль системы контроля качества лучевой диагностики онкологических заболеваний в радиомике // Digital Diagnostics. 2021. Т. 2, № 2. С. 170–184. doi: 10.17816/DD60393

Funding

Правительство Российской ФедерацииGovernment of the Russian Federation(123031500005-2)

RIGHTS & PERMISSIONS

Eco-Vector