Computed tomography-based radiomic markers are independent prognosticators of survival in advanced laryngeal cancer: a pilot study

Abstract

Objective: Advanced laryngeal cancers are clinically complex; there is a paucity of modern decision-making models to guide tumour-specific management. This pilot study aims to identify computed tomography-based radiomic features that may predict survival and enhance prognostication.

Methods: Pre-biopsy, contrast-enhanced computed tomography scans were assembled from a retrospective cohort (n = 72) with advanced laryngeal cancers (T3 and T4). The LIFEx software was used for radiomic feature extraction. Two features: shape compacity (irregularity of tumour volume) and grey-level zone length matrix - grey-level non-uniformity (tumour heterogeneity) were selected via least absolute shrinkage and selection operator-based Cox regression and explored for prognostic potential.

Results: A greater shape compacity (hazard ratio 2.89) and grey-level zone length matrix - grey-level non-uniformity (hazard ratio 1.64) were significantly associated with worse 5-year disease-specific survival (p < 0.05). Cox regression models yielded a superior C-index when incorporating radiomic features (0.759) versus clinicopathological variables alone (0.655).

Conclusions: Two radiomic features were identified as independent prognostic biomarkers. A multi-centre prospective study is necessary for further exploration. Integrated radiomic models may refine the treatment of advanced laryngeal cancers.

Keywords: Laryngeal neoplasms; biomarkers; prognosis.

Figure 1.

Flowchart demonstrating patients included in the study: This flowchart illustrates the patients included in the study (n = 72). Additional detail is provided on the number of patients excluded (n = 59) and the relevant rationale.

Figure 2.

Delineation of the region of interest on the LIFEx platform: This figure illustrates axial, coronal and sagittal views of a CT scan from a patient with laryngeal cancer on the LIFEx software platform. Two blinded radiologists outlined the tumour (highlighted in pink) on each individual CT slice to obtain 3D segmentation including the whole tumor volume. This area (region of interest or volume of interest) would undergo radiomic analysis.

Figure 3.

Radiomics texture feature selection using LASSO Cox regression: The ten-fold cross-validation method was used to select the model tuning parameter (λ). The log of λ was plotted against partial likelihood deviance, where a lower value suggested better model performance. The selected λ was used for co-efficient shrinkage and is depicted by the dotted line. In this figure, each individual line represents a radiomic marker. As λ increases only two radiomic markers remain (shape compacity and grey-level zone length matrix grey-level non-uniformity). LASSO = least absolute shrinkage and selection operator.

Figure 4.

Kaplan-Meier survival curves stratified based on radiomic values: Two radiomics features were selected via the least absolute shrinkage and selection operator-based Cox regression model and assessed for prognostic significance: (a)shape compacity and (b)GLZLM-GLNU. Patients were stratified via radiomic values into upper, middle and lower terciles. The relevant Kaplan-Meier survival curves are demonstrated in this figure. GLZLM – GLNU: grey-level zone length matrix – grey-level non-uniformity