CT-based radiomics features in the prediction of thyroid cartilage invasion from laryngeal and hypopharyngeal squamous cell carcinoma

Cancer Imaging - Tập 20 - Trang 1-11 - 2020
Ran Guo1,2, Jian Guo1, Lichen Zhang1, Xiaoxia Qu1, Shuangfeng Dai3, Ruchen Peng2, Vincent F. H. Chong4, Junfang Xian1
1Department of Radiology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
2Department of Radiology, Beijing Luhe Hospital, Capital Medical University, Beijing, China
3Huiying Medical Technology Co., Ltd, Beijing, China
4Department of Diagnostic Imaging, National University Health System, Singapore, Singapore

Tóm tắt

Laryngeal and hypopharyngeal squamous cell carcinoma (LHSCC) with thyroid cartilage invasion are considered T4 and need total laryngectomy. However, the accuracy of preoperative diagnosis of thyroid cartilage invasion remains lower. Therefore, the purpose of this study was to assess the potential of computed tomography (CT)-based radiomics features in the prediction of thyroid cartilage invasion from LHSCC. A total of 265 patients with pathologically proven LHSCC were enrolled in this retrospective study (86 with thyroid cartilage invasion and 179 without invasion). Two head and neck radiologists evaluated the thyroid cartilage invasion on CT images. Radiomics features were extracted from venous phase contrast-enhanced CT images. The least absolute shrinkage and selection operator (LASSO) and logistic regression (LR) method were used for dimension reduction and model construction. In addition, the support vector machine-based synthetic minority oversampling (SVMSMOTE) algorithm was adopted to balance the dataset and a new LR-SVMSMOTE model was constructed. The performance of the radiologist and the two models were evaluated with receiver operating characteristic (ROC) curves and compared using the DeLong test. The areas under the ROC curves (AUCs) in the prediction of thyroid cartilage invasion from LHSCC for the LR-SVMSMOTE model, LR model, and radiologist were 0.905 [95% confidence interval (CI): 0.863 to 0.937)], 0.876 (95%CI: 0.830 to 0.913), and 0.721 (95%CI: 0.663–0.774), respectively. The AUCs of both models were higher than that of the radiologist assessment (all P < 0.001). There was no significant difference in predictive performance between the LR-SVMSMOTE and LR models (P = 0.05). Models based on CT radiomic features can improve the accuracy of predicting thyroid cartilage invasion from LHSCC and provide a new potentially noninvasive method for preoperative prediction of thyroid cartilage invasion from LHSCC.

Tài liệu tham khảo

Steuer CE, El-Deiry M, Parks JR, et al. An update on larynx cancer. CA Cancer J Clin. 2017;67(1):31–50.

Preda L, Conte G, Bonello L, et al. Diagnostic accuracy of surface coil MRI in assessing cartilaginous invasion in laryngeal tumours: do we need contrast-agent administration? Eur Radiol. 2017;27(11):4690–8.

Bray F, Ferlay J, Soerjomataram I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2018;68(6):394–424.

Do L, Puthawala A, Syed N, et al. Treatment outcomes of T4 locally advanced head and neck cancers with soft tissue invasion or bone and cartilage invasion. Am J Clin Oncol. 2009;32(5):477–82.

Choi YS, Park SG, Song E-K, et al. Comparison of the therapeutic effects of total laryngectomy and a larynx-preservation approach in patients with T4a laryngeal cancer and thyroid cartilage invasion: a multicenter retrospective review. Head Neck. 2016;38(8):1271–7.

Li B, Bobinski M, Gandour-Edwards R, et al. Overstaging of cartilage invasion by multidetector CT scan for laryngeal cancer and its potential effect on the use of organ preservation with chemoradiation. Br J Radiol. 2011;84(997):64–9.

Vaupel P, Mayer A. Hypoxia in cancer: significance and impact on clinical outcome. Cancer Metastasis Rev. 2007;26(2):225–39.

Forastiere AA, Ismaila N, Lewin JS, et al. Use of larynx-preservation strategies in the treatment of laryngeal cancer: American society of clinical oncology clinical practice guideline update. J Clin Oncol. 2018;36(11):1143–69.

Beitler JJ, Muller S, Grist WJ, et al. Prognostic accuracy of computed tomography findings for patients with laryngeal cancer undergoing laryngectomy. J Clin Oncol. 2010;28(14):2318–22.

Kuno H, Sakamaki K, Fujii S, et al. Comparison of MR imaging and dual-energy CT for the evaluation of cartilage invasion by laryngeal and hypopharyngeal squamous cell carcinoma. AJNR Am J Neuroradiol. 2018;39(3):524–31.

Castelijns JA, Becker M, Hermans R. Impact of cartilage invasion on treatment and prognosis of laryngeal cancer. Eur Radiol. 1996;6(2):156–69.

Kuno H, Onaya H, Iwata R, et al. Evaluation of cartilage invasion by laryngeal and hypopharyngeal squamous cell carcinoma with dual-energy CT. Radiology. 2012;265(2):488–96.

Becker M, Zbären P, Casselman JW, et al. Neoplastic invasion of laryngeal cartilage: reassessment of criteria for diagnosis at MR imaging. Radiology. 2008;249(2):551–9.

Atula T, Markkola A, Leivo I, et al. Cartilage invasion of laryngeal cancer detected by magnetic resonance imaging. Eur Arch Otorhinolaryngol. 2001;258(6):272–5.

Kumar V, Gu Y, Basu S, et al. Radiomics: the process and the challenges. Magn Reson Imaging. 2012;30(9):1234–48.

Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012;48(4):441–6.

Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology. 2016;278(2):563–77.

Chen L, Wang H, Zeng H, et al. Evaluation of CT-based radiomics signature and nomogram as prognostic markers in patients with laryngeal squamous cell carcinoma. Cancer Imaging. 2020;20(1):28.

Xu Y, Hosny A, Zeleznik R, et al. Deep learning predicts lung cancer treatment response from serial medical imaging. Clin Cancer Res. 2019;25(11):3266–75.

Shu J, Tang Y, Cui J, et al. Clear cell renal cell carcinoma: CT-based radiomics features for the prediction of fuhrman grade. Eur J Radiol. 2018;109:8–12.

Liu Z, Zhang X-Y, Shi Y-J, et al. Radiomics analysis for evaluation of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer. Clin Cancer Res. 2017;23(23):7253–62.

Feng Z, Rong P, Cao P, et al. Machine learning-based quantitative texture analysis of CT images of small renal masses: differentiation of angiomyolipoma without visible fat from renal cell carcinoma. Eur Radiol. 2018;28(4):1625–33.

Kocak B, Durmaz ES, Ates E, et al. Unenhanced CT texture analysis of clear cell renal cell carcinoma: a machine learning–based study for predicting histopathologic nuclear grade. AJR Am J Roentgenol. 2019;212:W1–8.

Chawla NV, Bowyer KW, Hall LO, et al. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002;16(1):321–57.

Sun Y, Wong A, Kamel SM. Classification of imbalanced data: a review. sInt J Pattern Recognit Artif Intell. 2009;23(4):687–719.

Cateni S, Colla V, Vannucci M. A method for resampling imbalanced datasets in binary classification tasks for real-world problems. Neurocomputing. 2014;135(5):32–41.

Nguyen HM, Cooper EW, Kamei K. Borderline over-sampling for imbalanced data classification. Int J Knowl Eng Soft Data Paradig. 2011;3(1):4–21.

Becker M, Zbären P, Delavelle J, et al. Neoplastic invasion of the laryngeal cartilage: reassessment of criteria for diagnosis at CT. Radiology. 1997;203(2):521–32.

Zwanenburg A, Leger S, Vallières M et al. Image biomarker standardisation initiative-Feature definitions. arXiv:161207003 [cs, cv]. 2016.

Liang M, Cai Z, Zhang H, et al. Machine learning-based analysis of rectal cancer MRI radiomics for prediction of metachronous liver metastasis. Acad Radiol. 2019;26(11):1495–504.

Theodorsson-Norheim E. Kruskal-Wallis test: BASIC computer program to perform nonparametric one-way analysis of variance and multiple comparisons on ranks of several independent samples. Comput Methods Prog Biomed. 1986;23(1):57–62.

Friedman J, Hastie T, Tibshirani R. Regularization paths for generalized linear models via coordinate descent. J Stat Softw. 2010;33(1):1–22.

DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44(3):837–45.

Dadfar N, Seyyedi M, Forghani R, et al. Computed tomography appearance of normal nonossified thyroid cartilage: implication for tumor invasion diagnosis. J Comput Assist Tomogr. 2015;39(2):240–3.

Dankbaar JW, Oosterbroek J, Jager EA, et al. Detection of cartilage invasion in laryngeal carcinoma with dynamic contrast-enhanced CT. Laryngoscope Investig Otolaryngol. 2017;2(6):373–9.

Lambin P, Leijenaar RTH, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 2017;14(12):749–62.

Avanzo M, Stancanello J, El Naqa I. Beyond imaging: the promise of radiomics. Phys Med. 2017;38:122–39.

Nie P, Yang G, Wang Z, et al. A CT-based radiomics nomogram for differentiation of renal angiomyolipoma without visible fat from homogeneous clear cell renal cell carcinoma. Eur Radiol. 2019;30(2):1274–84.

Zhu X, Dong D, Chen Z, et al. Radiomic signature as a predictive factor for histologic subtype classification of non-small cell lung cancer. Eur Radiol. 2018;28(7):2772–8.

Rios Velazquez E, Aerts HJWL, Gu Y, et al. A semiautomatic CT-based ensemble segmentation of lung tumors: comparison with oncologists’ delineations and with the surgical specimen. Radiother Oncol. 2012;105(2):167–73.

Ermiş E, Jungo A, Poel R, et al. Fully automated brain resection cavity delineation for radiation target volume definition in glioblastoma patients using deep learning. Radiat Oncol. 2020;15(1):100.

Thông tin
Thông tin xuất bản

Cancer Imaging

Tập 20

1-11

Thông tin tác giả