Rationale and objectives
Preoperative prediction of the recurrence risk in patients with advanced sinonasal
squamous cell carcinoma (SNSCC) is critical for individualized treatment. To evaluate
the predictive ability of radiomics signature (RS) based on deep learning and multiparametric
MRI for the risk of 2-year recurrence in advanced SNSCC.
Materials and methods
Preoperative MRI datasets were retrospectively collected from 265 SNSCC patients (145
recurrences) who underwent preoperative MRI, including T2-weighted (T2W), contrast-enhanced
T1-weighted (T1c) sequences and diffusion-weighted (DW). All patients were divided
into 165 training cohort and 70 test cohort. A deep learning segmentation model based
on VB-Net was used to segment regions of interest (ROIs) for preoperative MRI and
radiomics features were extracted from automatically segmented ROIs. Least absolute
shrinkage and selection operator (LASSO) and logistic regression (LR) were applied
for feature selection and radiomics score construction. Combined with meaningful clinicopathological
predictors, a nomogram was developed and its performance was evaluated. In addition,
X-title software was used to divide patients into high-risk or low-risk early relapse
(ER) subgroups. Recurrence-free survival probability (RFS) was assessed for each subgroup.
Results
The radiomics score, T stage, histological grade and Ki-67 predictors were independent
predictors. The segmentation models of T2WI, T1c, and apparent diffusion coefficient
(ADC) sequences achieved Dice coefficients of 0.720, 0.727, and 0.756, respectively,
in the test cohort. RS-T2, RS-T1c and RS-ADC were derived from single-parameter MRI.
RS-Combined (combined with T2WI, T1c, and ADC features) was derived from multiparametric
MRI and reached area under curve (AUC) and accuracy of 0.854 (0.749-0.927) and 74.3%
(0.624-0.840), respectively, in the test cohort. The calibration curve and decision
curve analysis (DCA) illustrate its value in clinical practice. Kaplan-Meier analysis
showed that the 2-year RFS rate for low-risk patients was significantly greater than
that for high-risk patients in both the training and testing cohorts (p < 0.001).
Conclusion
Automated nomograms based on multi-sequence MRI help to predict ER in SNSCC patients
preoperatively.
Keywords
Abbreviations:
SNSCC (Sinonasal squamous cell carcinoma), RS (Radiomics signature), T2W (T2-weighted), T1c (Contrast-enhanced T1-weighted), DW (Diffusion-weighted), ROIs (Segment regions of interest), LASSO (Least absolute shrinkage and selection operator), LR (Logistic regression), ER (Early relapse), RFS (Recurrence-free survival probability), DCA (Decision curve analysis), TNM (Tumor-node-metastasis), ADC (Apparent diffusion coefficient), AUC (Area under curve), NER (Nonearly recurrence), GLCM (Gray-level co-occurrence matrix), GLRLM (Gray-level run-length matrix), GLSZM (Gray-level size zone matrix), GLDM (Gray-level dependence matrix), NGTDM (Neighboring gray-tone difference matrix), SVM (Support vector machine characteristic), PPV (Positive predictive value), NPV (Negative predictive value), SD (standard deviation), CI (Confidence interval), OR (Odd ratios)To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Academic RadiologyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
REFERENCES
- Epidemiology of cancer of the nose and paranasal sinuses: current concepts.Head Neck Surg. 1979; 2: 3-11
- Incidence and survival in patients with sinonasal cancer: a historical analysis of population-based data.Head Neck. 2012; 34: 877-885
- Paranasal sinus squamous cell carcinoma incidence and survival based on Surveillance, Epidemiology, and End Results data, 1973 to 2009.Cancer. 2013; 119: 2602-2610
- Preoperative chemotherapy for sinonasal squamous cell carcinoma (SNSCC): time to move closer to a definitive answer.Cancer. 2021; 127: 1734-1735
- Sinonasal squamous cell carcinomas: clinical outcomes and predictive factors.Int J Oral Maxillofac Surg. 2014; 43: 1-6
- NCCN guidelines® insights: head and neck cancers, version 1.2022.J Natl Compr Canc Netw. 2022; 20: 224-234
- Malignant tumors of the nasal cavity and paranasal sinuses.Head Neck. 2002; 24: 821-829
- Prognostic factors in maxillary sinus and nasal cavity carcinoma.Eur J Surg Oncol. 2005; 31: 1206-1212
- A clinical-radiomics nomogram based on the Apparent Diffusion Coefficient (ADC) for individualized prediction of the risk of early relapse in advanced sinonasal squamous cell carcinoma: a 2-year follow-up study.Front Oncol. 2022; 12870935
- Prognostic significance of Ki-67 expression for patients with laryngeal squamous cell carcinoma primarily treated by total laryngectomy.Eur Arch Otorhinolaryngol. 2004; 261: 376-380
- p63 and Ki-67 immunostainings in laryngeal squamous cell carcinoma are related to survival.Eur Arch Otorhinolaryngol. 2014; 271: 1641-1651
- Prediction of the treatment outcome using intravoxel incoherent motion and diffusional kurtosis imaging in nasal or sinonasal squamous cell carcinoma patients.Eur Radiol. 2017; 27: 956-965
- Radiomics: images are more than pictures, they are data.Radiology. 2016; 278: 563-577
- Radiomics: extracting more information from medical images using advanced feature analysis.Eur J Cancer. 2012; 48: 441-446
- An MRI-Based Radiomic Nomogram for Discrimination Between Malignant and Benign Sinonasal Tumors.J Magn Reson Imaging. 2021; 53: 141-151
- Radiomics nomograms based on multi-parametric MRI for preoperative differential diagnosis of malignant and benign sinonasal tumors: a two-centre study.Front Oncol. 2021; 11659905
- Apparent diffusion coefficient-based radiomic nomogram in sinonasal squamous cell carcinoma: a preliminary study on histological grade evaluation.J Comput Assist Tomogr. 2022; 46: 823-829
- Abnormal lung quantification in chest CT images of COVID-19 patients with deep learning and its application to severity prediction.Med Phys. 2021; 48: 1633-1645
- Extensions to decision curve analysis, a novel method for evaluating diagnostic tests, prediction models and molecular markers.BMC Med Inform Decis Mak. 2008; 8: 53
- Clinical outcomes of sinonasal squamous cell carcinomas based on tumor etiology.Int Forum Allergy Rhinol. 2017; 7: 508-513
- Comparison of outcomes between patients with de-novo sinonasal squamous cell carcinoma vs malignant transformations from inverted papillomas.Int Forum Allergy Rhinol. 2020; 10: 762-767
- Breast cancer heterogeneity: mr imaging texture analysis and survival outcomes.Radiology. 2017; 282: 665-675
- Texture Analysis Based on Preoperative Magnetic Resonance Imaging (MRI) and conventional MRI features for predicting the early recurrence of single hepatocellular carcinoma after hepatectomy.Acad Radiol. 2019; 26: 1164-1173
- Pre-treatment magnetic resonance-based texture features as potential imaging biomarkers for predicting event free survival in anal cancer treated by chemoradiotherapy.Eur Radiol. 2018; 28: 2801-2811
- Penalized Cox regression analysis in the high-dimensional and low-sample size settings, with applications to microarray gene expression data.Bioinformatics. 2005; 21: 3001-3008
- Support vector machine for breast cancer classification using diffusion-weighted MRI histogram features: Preliminary study.J Magn Reson Imaging. 2018; 47: 1205-1216
- Retrospective assessment of histogram-based diffusion metrics for differentiating benign and malignant endometrial lesions.J Comput Assist Tomogr. 2016; 40: 723-729
- ADC-derived spatial features can accurately classify adnexal lesions.J Magn Reson Imaging. 2018; 47: 1061-1071
- MRI radiomics for assessment of molecular subtype, pathological complete response, and residual cancer burden in breast cancer patients treated with neoadjuvant chemotherapy.Acad Radiol. 2022; 29 (Suppl): S145-Ss54
- A radiomics model for preoperative prediction of brain invasion in meningioma non-invasively based on MRI: a multicentre study.EBioMedicine. 2020; 58102933
- Discriminating pseudoprogression and true progression in diffuse infiltrating glioma using multi-parametric MRI data through deep learning.Sci Rep. 2020; 10: 20331
- Survival outcomes in sinonasal poorly differentiated squamous cell carcinoma.Laryngoscope. 2021; 131: E1040-E10e8
- Development and validation of a nomogram for prognosis of sinonasal squamous cell carcinoma.Int Forum Allergy Rhinol. 2019; 9: 1030-1040
Sylvester MJ, Fenberg R, Mckean EL, Vankoevering KK. Treatment of Sinonasal Squamous Cell Carcinoma: The Experience at a Single Tertiary Care Facility Over 32 Years. 30th Annual Meeting North American Skull Base Society2020.
- Survival outcomes and prognostic factors of squamous cell carcinomas arising from sinonasal inverted papillomas: a retrospective analysis of 120 patients.Int Forum Allergy Rhinol. 2019; 9: 1367-1373
- Computed tomography-based radiomics nomogram: potential to predict local recurrence of gastric cancer after radical resection.Front Oncol. 2021; 11638362
- Clinical and biological prognostic factors in 179 cases with sinonasal carcinoma treated in the Italian Piedmont region.Oncology. 2009; 76: 262-269
- Ki67 antigen as a predictive factor for prognosis of sinonasal mucosal melanoma.Clin Exp Otorhinolaryngol. 2008; 1: 206-210
- Prediction of high-risk cytogenetic status in multiple myeloma based on magnetic resonance imaging: utility of radiomics and comparison of machine learning methods.J Magn Reson Imaging. 2021; 54: 1303-1311
- Classification of pulmonary lesion based on multiparametric MRI: utility of radiomics and comparison of machine learning methods.Eur Radiol. 2020; 30: 4595-4605
Article info
Publication history
Published online: March 14, 2023
Accepted:
November 13,
2022
Received in revised form:
November 12,
2022
Received:
October 13,
2022
Publication stage
In Press Corrected ProofIdentification
Copyright
© 2023 Published by Elsevier Inc. on behalf of The Association of University Radiologists.
