Differentiation of Benign From Malignant Sinonasal Masses Using Diffusion Weighted Imaging and Dynamic Contrast Enhanced Magnetic Resonance Imaging

Imaging of chronic rhinosinusitis with nasal polyps in the era of biological therapies

PURPOSE OF REVIEW

Chronic rhinosinusitis (CRS) is a chronic inflammatory disorder of the sinonasal cavities classified into two major phenotypes: CRS with nasal polyps (CRSwNP) and without nasal polyps (CRSsNP). The diagnosis of CRS is based on clinical symptoms associated with imaging and/or nasal endoscopy findings of mucosal inflammation.

RECENT FINDINGS

Recently, novel biological therapies have emerged as therapeutic options for CRSwNP. Imaging is helpful in deciding whether surgery is likely to be beneficial and in guiding surgery. It can also help demonstrate a clinical response to medical therapy. However, specific guidelines concerning the role of imaging in CRwNP are lacking.

SUMMARY

This article provides a comprehensive and critical multidisciplinary review of the role of conventional radiology, computed tomography (CT), and magnetic resonance imaging (MRI) in the diagnosis and characterization of CRSwNP. Since the complete characterization of nasal polyps on CT or MR images is very challenging, we provide a critical review of the best imaging methods and essential reporting elements used to assess nasal polyps.

Development and validation of apparent diffusion coefficient histogram-based nomogram for predicting malignant transformation of sinonasal inverted papilloma

OBJECTIVES

To develop and validate a nomogram based on whole-tumour histograms of apparent diffusion coefficient (ADC) maps for predicting malignant transformation (MT) in sinonasal inverted papilloma (IP).

METHODS

This retrospective study included 209 sinonasal IPs with and without MT, which were assigned into a primary cohort (n = 140) and a validation cohort (n = 69). Eight ADC histogram features were extracted from the whole-tumour region of interest. Morphological MRI features and ADC histogram parameters were compared between the two groups (with and without MT). Stepwise logistic regression was used to identify independent predictors and to construct models. The predictive performances of variables and models were assessed using the area under the curve (AUC). The optimal model was presented as a nomogram, and its calibration was assessed.

RESULTS

Four morphological features and seven ADC histogram parameters showed significant differences between the two groups in both cohorts (all p < 0.05). Maximum diameter, loss of convoluted cerebriform pattern, ADC10th and ADCSkewness were identified as independent predictors to construct the nomogram. The nomogram showed significantly better performance than the morphological model in both the primary (AUC, 0.96 vs 0.88; p = 0.006) and validation (AUC, 0.96 vs 0.88; p = 0.015) cohorts. The nomogram showed good calibration in both cohorts. Decision curve analysis demonstrated that the nomogram is clinically useful.

CONCLUSIONS

The developed nomogram, which incorporates morphological MRI features and ADC histogram parameters, can be conveniently used to facilitate the pre-operative prediction of MT in IPs.

MRI features of sinonasal tract angiofibroma/juvenile nasopharyngeal angiofibroma: Case series and systematic review

BACKGROUND AND PURPOSE

To comprehensively summarize the radiological characteristics of sinonasal tract angiofibroma (STA) (commonly known as juvenile nasopharyngeal angiofibroma).

METHODS

Forty-four lesions from 41 cases provided by 33 study articles identified through a systematic review and 13 lesions from 13 cases from our institution associated with patients with STA who underwent MRI were included in the review study, carried out by two board-certified experienced radiologists.

RESULTS

The study participants were all male patients with a mean age of 15.6 years at the time of diagnosis. All of them presented with nasal cavity lesions (100%), predominantly in the nasopharynx (98.2%). The sphenopalatine foramen/pterygopalatine fossa was involved in 76.0%, and compressive shift of the posterolateral wall of the maxillary sinus was present in more than half (57.9%). T2-weighted imaging signal intensity was heterogeneous with mixed high and iso intensities as compared to skeletal muscle (100%). T1-weighted imaging showed partial high signal intensity in 61.1% of the cases. Flow void and intense enhancement were present in almost all cases. Cystic/nonenhancement changes on contrast-enhanced MRI were relatively common (40.8%). The mean apparent diffusion coefficient value (2.07 × 10-3  mm2 /second) and some quantitative dynamic contrast-enhanced MRI parameters were high. There was a significant difference in the frequency of residual/recurrent lesions based on the presence of MRI findings of skull base invasion (p = .017) and intracranial extension (p = .003).

CONCLUSIONS

We summarized the MRI findings of STA that can facilitate timely diagnosis and appropriate management.

Machine learning to differentiate small round cell malignant tumors and non-small round cell malignant tumors of the nasal and paranasal sinuses using apparent diffusion coefficient values

OBJECTIVE

We used radiomics feature-based machine learning classifiers of apparent diffusion coefficient (ADC) maps to differentiate small round cell malignant tumors (SRCMTs) and non-SRCMTs of the nasal and paranasal sinuses.

MATERIALS

A total of 267 features were extracted from each region of interest (ROI). Datasets were randomized into two sets, a training set (∼70%) and a test set (∼30%). We performed dimensional reductions using the Pearson correlation coefficient and feature selection analyses (analysis of variance [ANOVA], relief, recursive feature elimination [RFE]) and classifications using 10 machine learning classifiers. Results were evaluated with a leave-one-out cross-validation analysis.

RESULTS

We compared the AUC for all the pipelines in the validation dataset using FeAture Explorer (FAE) software. The pipeline using RFE feature selection and Gaussian process classifier yielded the highest AUCs with ten features. When the "one-standard error" rule was used, FAE produced a simpler model with eight features, including Perc.01%, Perc.10%, Perc.90%, Perc.99%, S(1,0) SumAverg, S(5,5) AngScMom, S(5,5) Correlat, and WavEnLH_s-2. The AUCs of the training, validation, and test datasets achieved 0.995, 0.902, and 0.710, respectively. For ANOVA, the pipeline with the auto-encoder classifier yielded the highest AUC using only one feature, Perc.10% (training/validation/test datasets: 0.886/0.895/0.809, respectively). For the relief, the AUCs of the training, validation, and test datasets that used the LRLasso classifier using five features (Perc.01%, Perc.10%, S(4,4) Correlat, S(5,0) SumAverg, S(5,0) Contrast) were 0.892, 0.886, and 0.787, respectively. Compared with the RFE and relief, the results of all algorithms of ANOVA feature selection were more stable with the AUC values higher than 0.800.

CONCLUSIONS

We demonstrated the feasibility of combining artificial intelligence with the radiomics from ADC values in the differential diagnosis of SRCMTs and non-SRCMTs and the potential of this non-invasive approach for clinical applications.

KEY POINTS

• The parameter with the best diagnostic performance in differentiating SRCMTs from non-SRCMTs was the Perc.10% ADC value. • Results of all the algorithms of ANOVA feature selection were more stable and the AUCs were higher than 0.800, as compared with RFE and relief. • The pipeline using RFE feature selection and Gaussian process classifier yielded the highest AUC.