Texture analysis in the characterization of parotid salivary gland lesions: A study on MR diffusion weighted imaging

Imaging of human papilloma virus (HPV) related oropharynx tumour: what we know to date

The tumours of head and neck district are around 3% of all malignancies and squamous cell carcinoma is the most frequent histotype, with rapid increase during the last two decades because of the increment of the infection due to human papilloma virus (HPV). Even if the gold standard for the diagnosis is histological examination, including the detection of viral DNA and transcription products, imaging plays a fundamental role in the detection and staging of HPV + tumours, in order to assess the primary tumour, to establish the extent of disease and for follow-up. The main diagnostic tools are Computed Tomography (CT), Positron Emission Tomography-Computed Tomography (PET-CT) and Magnetic Resonance Imaging (MRI), but also Ultrasound (US) and the use of innovative techniques such as Radiomics have an important role. Aim of our review is to illustrate the main imaging features of HPV + tumours of the oropharynx, in US, CT and MRI imaging. In particular, we will outline the main limitations and strengths of the various imaging techniques, the main uses in the diagnosis, staging and follow-up of disease and the fundamental differential diagnoses of this type of tumour. Finally, we will focus on the innovative technique of texture analysis, which is increasingly gaining importance as a diagnostic tool in aid of the radiologist.

Magnetic resonance imaging in naso-oropharyngeal carcinoma: role of texture analysis in the assessment of response to radiochemotherapy, a preliminary study

OBJECTIVE

Identifying MRI texture parameters able to distinguish inflammation, fibrosis, and residual cancer in patients with naso-oropharynx carcinoma after radiochemotherapy (RT-CHT).

MATERIAL AND METHODS

In this single-centre, observational, retrospective study, texture analysis was performed on ADC maps and post-gadolinium T1 images of patients with histological diagnosis of naso-oropharyngeal carcinoma treated with RT-CHT. An initial cohort of 99 patients was selected; 57 of them were later excluded. The final cohort of 42 patients was divided into 3 groups (inflammation, fibrosis, and residual cancer) according to MRI, 18F-FDG-PET/CT performed 3-4 months after RT-CHT, and biopsy. Pre-RT-CHT lesions and the corresponding anatomic area post-RT-CHT were segmented with 3D slicer software from which 107 textural features were derived. T-Student and Wilcoxon signed-rank tests were performed, and features with p-value < 0.01 were considered statistically significant. Cut-off values-obtained by ROC curves-to discriminate post-RT-CHT non-tumoural changes from residual cancer were calculated for the parameters statistically associated to the diseased status at follow-up.

RESULTS

Two features-Energy and Grey Level Non-Uniformity-were statistically significant on T1 images in the comparison between 'positive' (residual cancer) and 'negative' patients (inflammation and fibrosis). Energy was also found to be statistically significant in both patients with fibrosis and residual cancer. Grey Level Non-Uniformity was significant in the differentiation between residual cancer and inflammation. Five features were statistically significant on ADC maps in the differentiation between 'positive' and 'negative' patients. The reduction in values of such features between pre- and post-RT-CHT was correlated with a good response to therapy.

CONCLUSIONS

Texture analysis on post-gadolinium T1 images and ADC maps can differentiate residual cancer from fibrosis and inflammation in early follow-up of naso-oropharyngeal carcinoma treated with RT-CHT.

Current status of diffusion-weighted imaging in differentiating parotid tumors

Recently, diffusion-weighted imaging (DWI) is an essential magnetic resonance imaging (MRI) protocol for head and neck imaging in clinical practice as it plays an important role in lesion detection, tumor extension evaluation, differential diagnosis, therapeutic effect prediction, therapy evaluation, and recurrence diagnosis. Especially in the parotid gland, several studies have already attempted to achieve accurate differentiation between benign and malignant tumors using DWI. A conventional single-shot echo-planar-based DWI is widely used for head and neck imaging, whereas advanced DWI sequences, such as intravoxel incoherent motion, diffusion kurtosis imaging, periodically rotated overlapping parallel lines with enhanced reconstruction, and readout-segmented echo-planar imaging (readout segmentation of long variable echo-trains), have been used to characterize parotid tumors. The mean apparent diffusion coefficient values are easily measured and useful for assessing cellularity and histological characteristics, whereas advanced image analyses, such as histogram analysis, texture analysis, and machine and deep learning, have been rapidly developed. Furthermore, a combination of DWI and other MRI protocols has reportedly improved the diagnostic accuracy of parotid tumors. This review article summarizes the current state of DWI in differentiating parotid tumors.

A Deep Learning Model for Classification of Parotid Neoplasms Based on Multimodal Magnetic Resonance Image Sequences

OBJECTIVE

To design a deep learning model based on multimodal magnetic resonance image (MRI) sequences for automatic parotid neoplasm classification, and to improve the diagnostic decision-making in clinical settings.

METHODS

First, multimodal MRI sequences were collected from 266 patients with parotid neoplasms, and an artificial intelligence (AI)-based deep learning model was designed from scratch, combining the image classification network of Resnet and the Transformer network of Natural language processing. Second, the effectiveness of the deep learning model was improved through the multi-modality fusion of MRI sequences, and the fusion strategy of various MRI sequences was optimized. In addition, we compared the effectiveness of the model in the parotid neoplasm classification with experienced radiologists.

RESULTS

The deep learning model delivered reliable outcomes in differentiating benign and malignant parotid neoplasms. The model, which was trained by the fusion of T2-weighted, postcontrast T1-weighted, and diffusion-weighted imaging (b = 1000 s/mm² ), produced the best result, with an accuracy score of 0.85, an area under the receiver operator characteristic (ROC) curve of 0.96, a sensitivity score of 0.90, and a specificity score of 0.84. In addition, the multi-modal paradigm exhibited reliable outcomes in diagnosing the pleomorphic adenoma and the Warthin tumor, but not in the identification of the basal cell adenoma.

CONCLUSION

An accurate and efficient AI based classification model was produced to classify parotid neoplasms, resulting from the fusion of multimodal MRI sequences. The effectiveness certainly outperformed the model with single MRI images or single MRI sequences as input, and potentially, experienced radiologists.

LEVEL OF EVIDENCE

3 Laryngoscope, 133:327-335, 2023.

Reproducibility of CT radiomic features in lung neuroendocrine tumours (NETs) patients: analysis in a heterogeneous population

BACKGROUND

The aim is to find a correlation between texture features extracted from neuroendocrine (NET) lung cancer subtypes, both Ki-67 index and the presence of lymph-nodal mediastinal metastases detected while using different computer tomography (CT) scanners.

METHODS

Sixty patients with a confirmed pulmonary NET histological diagnosis, a known Ki-67 status and metastases, were included. After subdivision of primary lesions in baseline acquisition and venous phase, 107 radiomic features of first and higher orders were extracted. Spearman's correlation matrix with Ward's hierarchical clustering was applied to confirm the absence of bias due to the database heterogeneity. Nonparametric tests were conducted to identify statistically significant features in the distinction between patient groups (Ki-67 < 3-Group 1; 3 ≤ Ki-67 ≤ 20-Group 2; and Ki-67 > 20-Group 3, and presence of metastases).

RESULTS

No bias arising from sample heterogeneity was found. Regarding Ki-67 groups statistical tests, seven statistically significant features (p value < 0.05) were found in post-contrast enhanced CT; three in baseline acquisitions. In metastasis classes distinction, three features (first-order class) were statistically significant in post-contrast acquisitions and 15 features (second-order class) in baseline acquisitions, including the three features distinguishing between Ki-67 groups in baseline images (MCC, ClusterProminence and Strength).

CONCLUSIONS

Some radiomic features can be used as a valid and reproducible tool for predicting Ki-67 class and hence the subtype of lung NET in baseline and post-contrast enhanced CT images. In particular, in baseline examination three features can establish both tumour class and aggressiveness.

Texture analysis of conventional magnetic resonance imaging and diffusion-weighted imaging for distinguishing sinonasal non-Hodgkin's lymphoma from squamous cell carcinoma

PURPOSE

To evaluate the value of texture analysis (TA) of conventional magnetic resonance imaging (MRI) and diffusion-weighted imaging (DWI) in the differential diagnosis between sinonasal non-Hodgkin's lymphoma (NHL) and squamous cell carcinoma (SCC).

METHODS

Forty-two patients with sinonasal SCC and 30 patients with NHL were retrospectively enrolled. TAs were performed on T2-weighted image (T2WI), apparent diffusion coefficient (ADC) and contrast-enhanced T1-weighted image (T1WI). Texture parameters, including mean value, skewness, kurtosis, entropy and uniformity were obtained and compared between sinonasal SCC and NHL groups. Receiver-operating characteristic (ROC) curves and logistic regression analyses were used to evaluate the diagnostic value and identify the independent TA parameters.

RESULTS

The mean value and entropy of ADC, and mean value of contrast-enhanced T1WI were significantly lower in the sinonasal NHL group than those in the SCC group (all P < 0.05). ROC analysis indicated that the entropy of ADC had the best diagnostic performance (AUC 0.832; Sensitivity 0.95; Specificity 0.67; Cutoff value 6.522). Logistic regression analysis showed that the entropy of ADC (P = 0.002, OR = 26.990) was the independent parameter for differentiating sinonasal NHL from SCC.

CONCLUSION

TA parameters of conventional MRI and DWI, particularly the entropy value of ADC, might be useful in the differentiating diagnosis between sinonasal NHL and SCC.

Frequency and imaging features of the adjacent osseous changes of salivary gland carcinomas in the head and neck region

PURPOSE

The association between salivary gland carcinomas and adjacent osseous changes in the head and neck region is not clear. We evaluated the frequency and imaging features of such changes and investigated the specific characteristics of salivary gland carcinomas associated with them.

METHODS

A total of 118 patients with histologically proven salivary gland carcinomas were retrospectively reviewed. The imaging characteristics of osseous changes were sorted into three categories based on computed tomography images: sclerotic change, erosive change, and lytic change. The frequency of all these osseous changes and any one of them was compared between different pathologies using Fisher's exact test. Odds ratios were calculated to evaluate the association between these changes and perineural spread.

RESULTS

Osseous changes were found in 21 (18%) of 118 cases. Among these, seven (6%) cases were with sclerotic, nine (8%) with erosive, and nine (8%) with lytic changes (four with mixed change). Adenoid cystic carcinoma showed a significantly higher frequency of sclerotic and erosive changes, and either osseous change, than the other salivary gland carcinomas (p < 0.001 for each). Sclerotic changes were only present in the adenoid cystic carcinomas. Perineural spread was a significant factor in showing higher osseous change frequencies (odds ratio = 3.98, p = 0.006).

CONCLUSION

Among salivary gland carcinomas in the head and neck region, adenoid cystic carcinomas had a significantly higher frequency of adjacent osseous changes, especially sclerotic changes, than other salivary gland carcinomas.

Machine learning-based radiomics for histological classification of parotid tumors using morphological MRI: a comparative study

OBJECTIVES

To evaluate the effectiveness of machine learning models based on morphological magnetic resonance imaging (MRI) radiomics in the classification of parotid tumors.

METHODS

In total, 298 patients with parotid tumors were randomly assigned to a training and test set at a ratio of 7:3. Radiomics features were extracted from the morphological MRI images and screened using the Select K Best and LASSO algorithm. Three-step machine learning models with XGBoost, SVM, and DT algorithms were developed to classify the parotid neoplasms into four subtypes. The ROC curve was used to measure the performance in each step. Diagnostic confusion matrices of these models were calculated for the test cohort and compared with those of the radiologists.

RESULTS

Six, twelve, and eight optimal features were selected in each step of the three-step process, respectively. XGBoost produced the highest area under the curve (AUC) for all three steps in the training cohort (0.857, 0.882, and 0.908, respectively), and for the first step in the test cohort (0.826), but produced slightly lower AUCs than SVM in the latter two steps in the test cohort (0.817 vs. 0.833, and 0.789 vs. 0.821, respectively). The total accuracies of XGBoost and SVM in the confusion matrices (70.8% and 59.6%) outperformed those of DT and the radiologist (46.1% and 49.2%).

CONCLUSION

This study demonstrated that machine learning models based on morphological MRI radiomics might be an assistive tool for parotid tumor classification, especially for preliminary screening in absence of more advanced scanning sequences, such as DWI.

KEY POINTS

• Machine learning algorithms combined with morphological MRI radiomics could be useful in the preliminary classification of parotid tumors. • XGBoost algorithm performed better than SVM and DT in subtype differentiation of parotid tumors, while DT seemed to have a poor validation performance. • Using morphological MRI only, the XGBoost and SVM algorithms outperformed radiologists in the four-type classification task for parotid tumors, thus making these models a useful assistant diagnostic tool in clinical practice.

Apparent Diffusion Coefficient Map–Based Radiomics Features for Differential Diagnosis of Pleomorphic Adenomas and Warthin Tumors From Malignant Tumors

Purpose

The magnetic resonance imaging (MRI) findings may overlap due to the complex content of parotid gland tumors and the differentiation level of malignant tumor (MT); consequently, patients may undergo diagnostic lobectomy. This study assessed whether radiomics features could noninvasively stratify parotid gland tumors accurately based on apparent diffusion coefficient (ADC) maps.

Methods

This study examined diffusion-weighted imaging (DWI) obtained with echo planar imaging sequences. Eighty-eight benign tumors (BTs) [54 pleomorphic adenomas (PAs) and 34 Warthin tumors (WTs)] and 42 MTs of the parotid gland were enrolled. Each case was randomly divided into training and testing cohorts at a ratio of 7:3 and then was compared with each other, respectively. ADC maps were digitally transferred to ITK SNAP (www.itksnap.org). The region of interest (ROI) was manually drawn around the whole tumor margin on each slice of ADC maps. After feature extraction, the Synthetic Minority Oversampling TEchnique (SMOTE) was used to remove the unbalance of the training dataset. Then, we applied the normalization process to the feature matrix. To reduce the similarity of each feature pair, we calculated the Pearson correlation coefficient (PCC) value of each feature pair and eliminated one of them if the PCC value was larger than 0.95. Then, recursive feature elimination (RFE) was used to process feature selection. After that, we used linear discriminant analysis (LDA) as the classifier. Receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic performance of the ADC.

Results

The LDA model based on 13, 8, 3, and 1 features can get the highest area under the ROC curve (AUC) in differentiating BT from MT, PA from WT, PA from MT, and WT from MT on the validation dataset, respectively. Accordingly, the AUC and the accuracy of the model on the testing set achieve 0.7637 and 73.17%, 0.925 and 92.31%, 0.8077 and 75.86%, and 0.5923 and 65.22%, respectively.

Conclusion

The ADC-based radiomics features may be used to assist clinicians for differential diagnosis of PA and WT from MTs.

Role of Texture Analysis in Oropharyngeal Carcinoma: A Systematic Review of the Literature

Simple Summary

The incidence of squamous cell carcinomas of the oropharynx has rapidly increased in the last two decades due to human papilloma virus infection (HPV). HPV-positive and HPV-negative squamous cell tumours differ in radiological imaging, treatment, and prognosis; therefore, differential diagnosis is mandatory. Radiomics with texture analysis is an innovative technique that has been used increasingly in recent years to characterise the tissue heterogeneity of certain structures such as neoplasms or organs by measuring the spatial distribution of pixel values on radiological imaging. This review delineates the application of texture analysis in oropharyngeal tumours and explores how radiomics may potentially improve clinical decision-making.

Abstract

Human papilloma virus infection (HPV) is associated with the development of lingual and palatine tonsil carcinomas. Diagnosing, differentiating HPV-positive from HPV-negative cancers, and assessing the presence of lymph node metastases or recurrences by the visual interpretation of images is not easy. Texture analysis can provide structural information not perceptible to human eyes. A systematic literature search was performed on 16 February 2022 for studies with a focus on texture analysis in oropharyngeal cancers. We conducted the research on PubMed, Scopus, and Web of Science platforms. Studies were screened for inclusion according to the preferred reporting items for systematic reviews. Twenty-six studies were included in our review. Nineteen articles related specifically to the oropharynx and seven articles analysed the head and neck area with sections dedicated to the oropharynx. Six, thirteen, and seven articles used MRI, CT, and PET, respectively, as the imaging techniques by which texture analysis was performed. Regarding oropharyngeal tumours, this review delineates the applications of texture analysis in (1) the diagnosis, prognosis, and assessment of disease recurrence or persistence after therapy, (2) early differentiation of HPV-positive versus HPV-negative cancers, (3) the detection of cancers not visualised by imaging alone, and (4) the assessment of lymph node metastases from unknown primary carcinomas.

Techniques, Tricks, and Stratagems of Oral Cavity Computed Tomography and Magnetic Resonance Imaging

The oral cavity constitutes a complex anatomical area that can be affected by many developmental, inflammatory, and tumoural diseases. MultiSlice Computed Tomography (MSCT) and Magnetic Resonance Imaging (MRI) currently represent the essential and complementary imaging techniques for detecting oral cavity abnormalities. Advanced MRI with diffusion-weighted imaging (DWI) and dynamic contrast-enhanced perfusion-weighted imaging (DCE-PWI) has recently increased the ability to characterise oral lesions and distinguish disease recurrences from post therapy changes. The analysis of the oral cavity area via imaging techniques is also complicated both by mutual close appositions of different mucosal surfaces and metal artifacts from dental materials. Nevertheless, an exact identification of oral lesions is made possible thanks to dynamic manoeuvres and specific stratagems applicable on MSCT and MRI acquisitions. This study summarises the currently available imaging techniques for oral diseases, with particular attention to the role of DWI, DCE-PWI, and dynamic manoeuvres. We also propose MSCT and MRI acquisition protocols for an accurate study of the oral cavity area.

Two-Dimensional EspEn: A New Approach to Analyze Image Texture by Irregularity

Image processing has played a relevant role in various industries, where the main challenge is to extract specific features from images. Specifically, texture characterizes the phenomenon of the occurrence of a pattern along the spatial distribution, taking into account the intensities of the pixels for which it has been applied in classification and segmentation tasks. Therefore, several feature extraction methods have been proposed in recent decades, but few of them rely on entropy, which is a measure of uncertainty. Moreover, entropy algorithms have been little explored in bidimensional data. Nevertheless, there is a growing interest in developing algorithms to solve current limits, since Shannon Entropy does not consider spatial information, and SampEn2D generates unreliable values in small sizes. We introduce a proposed algorithm, EspEn (Espinosa Entropy), to measure the irregularity present in two-dimensional data, where the calculation requires setting the parameters as follows: m (length of square window), r (tolerance threshold), and ρ (percentage of similarity). Three experiments were performed; the first two were on simulated images contaminated with different noise levels. The last experiment was with grayscale images from the Normalized Brodatz Texture database (NBT). First, we compared the performance of EspEn against the entropy of Shannon and SampEn2D. Second, we evaluated the dependence of EspEn on variations of the values of the parameters m, r, and ρ. Third, we evaluated the EspEn algorithm on NBT images. The results revealed that EspEn could discriminate images with different size and degrees of noise. Finally, EspEn provides an alternative algorithm to quantify the irregularity in 2D data; the recommended parameters for better performance are m = 3, r = 20, and ρ = 0.7.

Magnetic resonance imaging of salivary gland tumours: Key findings for imaging characterisation

Salivary gland tumours are rare, representing only 3% of all head and neck neoplasms, with the parotid gland being the most common site (80 %). The risk of malignancy is inversely proportional to the size of the gland: lesions arising in the sublingual or minor salivary glands are more likely to be malignant, whereas parotid gland neoplasms are mostly benign. Fine needle aspiration cytology and core needle biopsy are considered the most accurate modalities for the diagnosis of a salivary gland neoplasm; however, they are not always conclusive due to procedural sampling errors and for the presence of a cytological / histological overlap between benign and malignant tumours. Moreover, they cannot be easily performed for parotid deep portion localisation. The role of magnetic resonance imaging (MRI) is growing and advanced techniques (diffusion-weighted and dynamic contrast-enhanced perfusion-weighted imaging) can provide useful additional information for the assessment of salivary gland neoplasms. The aim of this review is to present the main MRI and clinical features of salivary gland tumours to improve their comprehensive evaluation and characterisation.