MRI-based radiomic prognostic signature for locally advanced oral cavity squamous cell carcinoma: development, testing and comparison with genomic prognostic signatures

Abstract

Background . At present, the prognostic prediction in advanced oral cavity squamous cell carcinoma (OCSCC) is based on the tumor-node-metastasis (TNM) staging system, and the most used imaging modality in these patients is magnetic resonance image (MRI). With the aim to improve the prediction, we developed an MRI-based radiomic signature as a prognostic marker for overall survival (OS) in OCSCC patients and compared it with published gene expression signatures for prognosis of OS in head and neck cancer patients, replicated herein on our OCSCC dataset. Methods For each patient, 1072 radiomic features were extracted from T1 and T2-weighted MRI (T1w and T2w). Features selection was performed, and an optimal set of five of them was used to fit a Cox proportional hazard regression model for OS. The radiomic signature was developed on a multi-centric locally advanced OCSCC retrospective dataset (n = 123) and validated on a prospective cohort (n = 108). Results The performance of the signature was evaluated in terms of C-index (0.68 (IQR 0.66–0.70)), hazard ratio (HR 2.64 (95% CI 1.62–4.31)), and high/low risk group stratification (log-rank p < 0.001, Kaplan-Meier curves). When tested on a multi-centric prospective cohort (n = 108), the signature had a C-index of 0.62 (IQR 0.58–0.64) and outperformed the clinical and pathologic TNM stage and six out of seven gene expression prognostic signatures. In addition, the significant difference of the radiomic signature between stages III and IVa/b in patients receiving surgery suggests a potential association of MRI features with the pathologic stage. Conclusions Overall, the present study suggests that MRI signatures, containing non-invasive and cost-effective remarkable information, could be exploited as prognostic tools.

MRI radiomics in head and neck cancer from reproducibility to combined approaches

“…From the literature survey, 7 reproducible MRI-based radiomic signatures for HNSCC patients were identified 18 , 19 , 29 – 33 as those which satisfy the minimum requirements for reproducibility. They are reported in Table 2 , along with their constitutive features in Table 3 .…”

“… Ref. Image pre-processing Features Feature normalization Signature threshold R1 Bos 2021 29 (iii); (iv); (v) 10 (T1wCont) Z-score (no details) NA R2 Chen 2022 30 NA 6 (T1wCont) NA NA R3 Alfieri 2022 31 (i); (ii); (iii); (iv); (v) 3 (T1w, T1wCont, T2w) Z-score (µ and σ provided) NA R4 Siow 2022 32 (ii); (iii); (iv); (v) 4 (T1wCont) NA 0.5 R5 Mossinelli 2023 33 NA 2 (T2w) Unspecified standardization NA R6 Bologna 2023 19 (i); (ii); (iii); (iv); (v) 4 (T1w, T2w) Z-score (µ and σ provided) NA R7 Corti 2023 18 (iii); (iv); (v) 5 (T2w) Z-score (µ and σ provided) 0.082 (i) denoising, through a 3D Gaussian filter with a 3 × 3x3 voxel kernel and σ = 0.5; (ii) intensity non-uniformities correction, through the N4ITK algorithm; (iii) intensity standardization, using Z-score; (iv) voxel size resampling to a specific isotropic resolution, through B-spline interpolation, and (v) fixed-bin histogram discretization, with a specific number of bins. µ: media value for Z-score standardization σ: standard deviation for Z-score sta...…”

“…In the present study, a subset of HNSCC patients of the BD2Decide project (NCT02832102) presenting with pre-contrast T1-weighted (T1w) and T2-weighted (T2w) and post-contrast T1w (T1wCont) MR image sequence (acquired with 1.5 T scanner and with a 3 mm slice thickness) was considered 17 . To avoid overlap with the training dataset of previously developed signatures 18 , 19 , only prospective patients were included, leading to a subset of n = 58 patients. Table 1 summarizes the baseline clinical information of the selected patients included in the study.…”

Identification of CT-based non-invasive radiomic biomarkers for overall survival prediction in oral cavity squamous cell carcinoma

“…Recent investigations also hint at the potential role of PET imaging in identifying cancer-associated genetic mutations 30 and the prospective use of radiomics-based imaging biomarkers for outcome predictions in head and neck cancer 31 . To the best of our knowledge, only a few studies 32 – 35 have identified MRI radiomics features that could be exploited as prognostic tools for overall survival in OSCC. Study 36 found a significant association between Rad-score (linear combination of three PET-based radiomics features) and overall survival.…”

Magnetic resonance imaging-based prediction models for tumor stage and cervical lymph node metastasis of tongue squamous cell carcinoma

“…This approach can extract many quantitative non-invasive tumor biomarkers with important potential implication for precision medicine across different cancer types including OTSCC [16] , [17] , [18] . Intra-tumor heterogeneity can be captured by first-order and higher-order textural features and may reflect the microstructural tissue characteristics and help clinicians to better stratify patients [19] .…”