MRI-based texture analysis to differentiate the most common parotid tumours

Assessment of chemotherapy resistance changes in human colorectal cancer xenografts in rats based on MRI histogram features

Purpose

We investigated the value of magnetic resonance imaging (MRI) histogram features, a non-invasive method, in assessing the changes in chemoresistance of colorectal cancer xenografts in rats.

Methods

A total of 50 tumor-bearing mice with colorectal cancer were randomly divided into two groups: control group and 5-fluorouracil (5-FU) group. The MRI histogram characteristics and the expression levels of p53 protein and MRP1 were obtained at 24 h, 48 h, 72 h, 120 h, and 168 h after treatment.

Results

Sixty highly repeatable MRI histogram features were obtained. There were 16 MRI histogram parameters and MRP1 resistance protein differences between groups. At 24 h after treatment, the MRI histogram texture parameters of T2-weighted imaging (T2WI) images (10%, 90%, median, energy, and RootMeanSquared) and D images (10% and Range) were positively correlated with MRP1 (r = 0.925, p = 0.005). At 48 h after treatment, histogram texture parameters of apparent diffusion coefficient (ADC) images (Energy) were positively correlated with the presence of MRP1 resistance protein (r = 0.900, p = 0.037). There was no statistically significant difference between MRI histogram features and p53 protein expression level.

Conclusions

MRI histogram texture parameters based on T2WI, D, and ADC maps can help to predict the change of 5-FU resistance in colorectal cancer in the early stage and provide important reference significance for clinical treatment.

Improved Cervical Lymph Node Characterization among Patients with Head and Neck Squamous Cell Carcinoma Using MR Texture Analysis Compared to Traditional FDG-PET/MR Features Alone

Accurate differentiation of benign and malignant cervical lymph nodes is important for prognosis and treatment planning in patients with head and neck squamous cell carcinoma. We evaluated the diagnostic performance of magnetic resonance image (MRI) texture analysis and traditional 18F-deoxyglucose positron emission tomography (FDG-PET) features. This retrospective study included 21 patients with head and neck squamous cell carcinoma. We used texture analysis of MRI and FDG-PET features to evaluate 109 histologically confirmed cervical lymph nodes (41 metastatic, 68 benign). Predictive models were evaluated using area under the curve (AUC). Significant differences were observed between benign and malignant cervical lymph nodes for 36 of 41 texture features (p < 0.05). A combination of 22 MRI texture features discriminated benign and malignant nodal disease with AUC, sensitivity, and specificity of 0.952, 92.7%, and 86.7%, which was comparable to maximum short-axis diameter, lymph node morphology, and maximum standard uptake value (SUVmax). The addition of MRI texture features to traditional FDG-PET features differentiated these groups with the greatest AUC, sensitivity, and specificity (0.989, 97.5%, and 94.1%). The addition of the MRI texture feature to lymph node morphology improved nodal assessment specificity from 70.6% to 88.2% among FDG-PET indeterminate lymph nodes. Texture features are useful for differentiating benign and malignant cervical lymph nodes in patients with head and neck squamous cell carcinoma. Lymph node morphology and SUVmax remain accurate tools. Specificity is improved by the addition of MRI texture features among FDG-PET indeterminate lymph nodes. This approach is useful for differentiating benign and malignant cervical lymph nodes.

Efficacy of texture analysis of ultrasonographic images in the differentiation of metastatic and non-metastatic cervical lymph nodes in patients with squamous cell carcinoma of the tongue

OBJECTIVE

We investigated the efficacy of using texture analysis of ultrasonographic images of the cervical lymph nodes of patients with squamous cell carcinoma of the tongue to differentiate between metastatic and non-metastatic lymph nodes.

STUDY DESIGN

We analyzed 32 metastatic and 28 non-metastatic lymph nodes diagnosed by histopathologic examination on presurgical US images. Using the LIFEx texture analysis program, we extracted 36 texture features from the images and calculated the statistical significance of differences in texture features between metastatic and non-metastatic lymph nodes using the t test. To assess the diagnostic ability of the significantly different texture features to discriminate between metastatic and non-metastatic nodes, we performed receiver operating characteristic curve analysis and calculated the area under the curve. We set the cutoff points that maximized the sensitivity and specificity for each curve according to the Youden J statistic.

RESULTS

We found that 20 texture features significantly differed between metastatic and non-metastatic lymph nodes. Among them, only the gray-level run length matrix feature of run length non-uniformity and the gray-level zone length matrix features of gray-level non-uniformity and zone length non-uniformity showed an excellent ability to discriminate between metastatic and non-metastatic lymph nodes as indicated by the area under the curve and the sum of sensitivity and specificity.

CONCLUSIONS

Analysis of the texture features of run length non-uniformity, gray-level non-uniformity, and zone length non-uniformity values allows for differentiation between metastatic and non-metastatic lymph nodes, with the use of gray-level non-uniformity appearing to be the best means of predicting metastatic lymph nodes.

Differential diagnosis of parotid gland tumors using apparent diffusion coefficient, texture features, and their combination

OBJECTIVES

Warthin's tumors (WT) and pleomorphic adenomas (PA) are the commonest parotid gland tumors; however, their differentiation remains difficult. This study aimed to investigate the utility of the apparent diffusion coefficient (ADC) value, texture features, and their combination for the differential diagnosis of parotid gland tumors.

METHODS

Patients who underwent magnetic resonance imaging (MRI) between April 2008 and March 2021 for parotid gland tumors were included and divided into two groups according to the tumor type: WT and PA. The tumor types were used as predictor variables, while the ADC value, texture features, and their combination were the outcome variables. Texture features were measured on short tau inversion recovery (STIR) images and selected using the Fisher's coefficient method and probability of error, and average correlation coefficients. The Mann-Whitney U-test was used to analyze bivariate statistics. Receiver operating characteristic curve analysis was used to assess the ability of the ADC value, texture features, and their combination to distinguishing between the two tumor types.

RESULTS

A total of 22 patients were included, 11 in each group. The ADC value, 10 texture features, and their combination were significantly different between the two groups (p < .001). Moreover, all three variables had high area under the curve values of 0.93-0.96.

CONCLUSION

The ADC value, texture features, and their combination demonstrated good diagnostic ability to distinguish between WTs and PAs. This method may be used to aid the differential diagnosis of parotid gland tumors, thereby promoting timely and adequate treatment.

Development and validation of CT-based radiomics nomogram for the classification of benign parotid gland tumors

PURPOSE

Accurate preoperative diagnosis of parotid tumor is essential for the formulation of optimal individualized surgical plans. The study aims to investigate the diagnostic performance of radiomics nomogram based on contrast-enhanced computed tomography (CT) images in the differentiation of the two most common benign parotid gland tumors.

METHODS

One hundred and ten patients with parotid gland tumors including 76 with pleomorphic adenoma (PA) and 34 with adenolymphoma (AL) confirmed by histopathology were included in this study. Radiomics features were extracted from contrast-enhanced CT images of venous phase. A radiomics model was established and a radiomics score (Rad-score) was calculated. Clinical factors including clinical data and CT features were assessed to build a clinical factor model. Finally, a nomogram incorporating the Rad-score and independent clinical factors was constructed. Receiver operator characteristics (ROC) curve was generated and the area under the ROC curve (AUC) was calculated to quantify the discriminative performance of each model on both the training and validation cohorts. Decision curve analysis (DCA) was conducted to evaluate the clinical usefulness of each model.

RESULTS

The radiomics model showed good discrimination in the training cohort [AUC, 0.89; 95% confidence interval (CI), 0.80-0.98] and validation cohort (AUC, 0.89; 95% CI, 0.77-1.00). The radiomics nomogram showed excellent discrimination in the training cohort (AUC, 0.98; 95% CI, 0.96-1.00) and validation cohort (AUC, 0.95; 95% CI, 0.88-1.00) and displayed better discrimination efficacy compared with the clinical factor model (AUC, 0.93; 95% CI, 0.88-0.99) in the training cohort (p < 0.05). The DCA demonstrated that the combined radiomics nomogram provided superior clinical usefulness than clinical factor model and radiomics model.

CONCLUSIONS

The CT-based radiomics nomogram combining Rad-score and clinical factors exhibits excellent predictive capability for differentiating parotid PA from AL, which might hold promise in assisting radiologists and clinicians in the exact differential diagnosis and formulation of appropriate treatment strategy.

Using deep learning to distinguish malignant from benign parotid tumors on plain computed tomography images

Objectives

Evaluating the diagnostic efficiency of deep-learning models to distinguish malignant from benign parotid tumors on plain computed tomography (CT) images.

Materials and methods

The CT images of 283 patients with parotid tumors were enrolled and analyzed retrospectively. Of them, 150 were benign and 133 were malignant according to pathology results. A total of 917 regions of interest of parotid tumors were cropped (456 benign and 461 malignant). Three deep-learning networks (ResNet50, VGG16_bn, and DenseNet169) were used for diagnosis (approximately 3:1 for training and testing). The diagnostic efficiencies (accuracy, sensitivity, specificity, and area under the curve [AUC]) of three networks were calculated and compared based on the 917 images. To simulate the process of human diagnosis, a voting model was developed at the end of the networks and the 283 tumors were classified as benign or malignant. Meanwhile, 917 tumor images were classified by two radiologists (A and B) and original CT images were classified by radiologist B. The diagnostic efficiencies of the three deep-learning network models (after voting) and the two radiologists were calculated.

Results

For the 917 CT images, ResNet50 presented high accuracy and sensitivity for diagnosing malignant parotid tumors; the accuracy, sensitivity, specificity, and AUC were 90.8%, 91.3%, 90.4%, and 0.96, respectively. For the 283 tumors, the accuracy, sensitivity, and specificity of ResNet50 (after voting) were 92.3%, 93.5% and 91.2%, respectively.

Conclusion

ResNet50 presented high sensitivity in distinguishing malignant from benign parotid tumors on plain CT images; this made it a promising auxiliary diagnostic method to screen malignant parotid tumors.

Differentiation of Benign From Malignant Parotid Gland Tumors Using Conventional MRI Based on Radiomics Nomogram

Objectives

We aimed to develop and validate radiomic nomograms to allow preoperative differentiation between benign- and malignant parotid gland tumors (BPGT and MPGT, respectively), as well as between pleomorphic adenomas (PAs) and Warthin tumors (WTs).

Materials and Methods

This retrospective study enrolled 183 parotid gland tumors (68 PAs, 62 WTs, and 53 MPGTs) and divided them into training (n = 128) and testing (n = 55) cohorts. In total, 2553 radiomics features were extracted from fat-saturated T2-weighted images, apparent diffusion coefficient maps, and contrast-enhanced T1-weighted images to construct single-, double-, and multi-sequence combined radiomics models, respectively. The radiomics score (Rad-score) was calculated using the best radiomics model and clinical features to develop the radiomics nomogram. The receiver operating characteristic curve and area under the curve (AUC) were used to assess these models, and their performances were compared using DeLong’s test. Calibration curves and decision curve analysis were used to assess the clinical usefulness of these models.

Results

The multi-sequence combined radiomics model exhibited better differentiation performance (BPGT vs. MPGT, AUC=0.863; PA vs. MPGT, AUC=0.929; WT vs. MPGT, AUC=0.825; PA vs. WT, AUC=0.927) than the single- and double sequence radiomics models. The nomogram based on the multi-sequence combined radiomics model and clinical features attained an improved classification performance (BPGT vs. MPGT, AUC=0.907; PA vs. MPGT, AUC=0.961; WT vs. MPGT, AUC=0.879; PA vs. WT, AUC=0.967).

Conclusions

Radiomics nomogram yielded excellent diagnostic performance in differentiating BPGT from MPGT, PA from MPGT, and PA from WT.

Usefulness of MRI-based radiomic features for distinguishing Warthin tumor from pleomorphic adenoma: performance assessment using T2-weighted and post-contrast T1-weighted MR images

Purpose

Differentiating Warthin tumor (WT) from pleomorphic adenoma (PA) is of primary importance due to differences in patient management, treatment and outcome. We sought to evaluate the performance of MRI-based radiomic features in discriminating PA from WT in the preoperative setting.

Methods

We retrospectively evaluated 81 parotid gland lesions (48 PA and 33 WT) on T2-weighted (T2w) images and 52 of them on post-contrast fat-suppressed T1-weighted (pcfsT1w) images. All MRI examinations were carried out on a 1.5-Tesla MRI scanner, and images were segmented manually using the software ITK-SNAP (www.itk-snap.org).

Results

The most discriminative feature on pcfsT1w images was GLCM_InverseVariance, yielding area under the curve (AUC), sensitivity and specificity of 0.9, 86 % and 87 %, respectively. Skewness was the feature extracted from T2w images with the highest specificity (88 %) in discriminating WT from PA.

Conclusion

Radiomic analysis could be an important tool to improve diagnostic accuracy in differentiating PA from WT.

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.

The role of MRI-based texture analysis to predict the severity of brain injury in neonates with perinatal asphyxia

OBJECTIVE

To evaluate the efficacy of the MRI-based texture analysis (TA) of the basal ganglia and thalami to distinguish moderate-to-severe hypoxic-ischemic encephalopathy (HIE) from mild HIE in neonates.

METHODS

This study included 68 neonates (15 with mild, 20 with moderate-to-severe HIE, and 33 control) were born at 37 gestational weeks or later and underwent MRI in first 10 days after birth. The basal ganglia and thalami were delineated for TA on the apparent diffusion coefficient (ADC) maps, T₁-, and T₂ weighted images. The basal ganglia, thalami, and the posterior limb of the internal capsule (PLIC) were also evaluated visually on diffusion-weighted imaging and T₁ weighted sequence. Receiver operating characteristic curve and logistic regression analyses were used.

RESULTS

Totally, 56 texture features for the basal ganglia and 46 features for the thalami were significantly different between the HIE groups on the ADC maps, T₂-, and T₂ weighted sequences. Using a Histogram_entropy log-10 value as >1.8 from the basal ganglia on the ADC maps (p < 0.001; OR, 266) and the absence of hyperintensity of the PLIC on T₁ weighted images (p = 0.012; OR, 17.11) were found as independent predictors for moderate-to-severe HIE. Using only a Histogram_entropy log-10 value had an equal diagnostic yield when compared to its combination with other texture features and imaging findings.

CONCLUSION

The Histogram_entropy log-10 value can be used as an indicator to differentiate from moderate-to-severe to mild HIE.

ADVANCES IN KNOWLEDGE

MRI-based TA may provide quantitative findings to indicate different stages in neonates with perinatal asphyxia.

Clot-based radiomics features predict first pass effect in acute ischemic stroke

PURPOSE

Our aim was to evaluate the performance of clot-based radiomics features (RFs) for predicting first pass effect (FPE) in patients with acute ischemic stroke (AIS). The secondary purpose was to search for any other variables associated with FPE.

MATERIALS AND METHODS

Patients who underwent mechanical thrombectomy (MT) for anterior circulation large vessel stroke in a single center were retrospectively reviewed. Patients were divided into two groups: FPE and non-FPE. Two observers extracted RFs from the clot on pretreatment noncontrast computed tomography (NCCT) images. Demographic, clinical, periprocedural, and RFs were compared between the groups and receiver operating characteristic (ROC) curves were constructed. Logistic regression analysis was used to determine the independent predictors of FPE.

RESULTS

Fifty-two patients (27 female, 25 male; mean age 64.50 ± 15.15) who were treated by stent retrievers as the first option were included in the study. FPE was achieved in 25 patients (25/52, 48.1%). Twelve RFs were significantly different between patients with FPE and non-FPE. The long-run low gray-level emphasis (odds ratio = 44.24, p = 0.003) and the zone percentage (odds ratio = 16.88, p = 0.017) were found as independent predictors of FPE. Female sex and a baseline ASPECT score of >8.5 were the other independent variables to predict FPE. The diagnostic accuracy to predict FPE was observed as 83% when using all independent predictors in our predictive model.

CONCLUSIONS

Clot-based RFs on NCCT may help to estimate the success of the intended outcome of MT in patients with AIS.

MRI-Based Radiomics to Differentiate between Benign and Malignant Parotid Tumors With External Validation

Background

The differentiation between benign and malignant parotid lesions is crucial to defining the treatment plan, which highly depends on the tumor histology. We aimed to evaluate the role of MRI-based radiomics using both T2-weighted (T2-w) images and Apparent Diffusion Coefficient (ADC) maps in the differentiation of parotid lesions, in order to develop predictive models with an external validation cohort.

Materials and Methods

A sample of 69 untreated parotid lesions was evaluated retrospectively, including 37 benign (of which 13 were Warthin’s tumors) and 32 malignant tumors. The patient population was divided into three groups: benign lesions (24 cases), Warthin’s lesions (13 cases), and malignant lesions (32 cases), which were compared in pairs. First- and second-order features were derived for each lesion. Margins and contrast enhancement patterns (CE) were qualitatively assessed. The model with the final feature set was achieved using the support vector machine binary classification algorithm.

Results

Models for discriminating between Warthin’s and malignant tumors, benign and Warthin’s tumors and benign and malignant tumors had an accuracy of 86.7%, 91.9% and 80.4%, respectively. After the feature selection process, four parameters for each model were used, including histogram-based features from ADC and T2-w images, shape-based features and types of margins and/or CE. Comparable accuracies were obtained after validation with the external cohort.

Conclusions

Radiomic analysis of ADC, T2-w images, and qualitative scores evaluating margins and CE allowed us to obtain good to excellent diagnostic accuracies in differentiating parotid lesions, which were confirmed with an external validation cohort.

Diagnostic value of maximum signal intensity on T1-weighted MRI images for differentiating parotid gland tumours along with pathological correlation

AIM

To investigate the efficacy of the maximum signal intensity of tumour on T1-weighted magnetic resonance imaging (MRI) images for differentiating Warthin's tumours (WTs) from pleomorphic adenomas (PAs) and malignant tumours (MTs).

MATERIALS AND METHODS

One hundred and fifty-four histopathologically confirmed parotid tumours, including 76 PAs, 45 WTs, and 33 MTs, were analysed. MRI results were compared with pathological findings. The maximum signal intensity of tumour and the average signal intensity of spinal cord were measured on T1-weighted images, then the tumour-to-spinal cord signal intensity ratio (T1-max-SIR) was calculated. The distribution of T1-max-SIRs among the three groups of tumours was analysed using the Mann-Whitney U-test. Receiver operating characteristic curves were generated to assess the ability of T1-max-SIRs to differentiate parotid tumours. In addition, the interobserver agreement between readers was assessed using interclass correlation coefficient (ICC).

RESULTS

T1-max-SIRs were higher in WTs than in PAs (p<0.001) and MTs (p<0.001), and no significant difference was found between PAs and MTs (p=0.151). The area under the curve (AUC) of T1-max-SIRs for differentiating WTs from PAs was 0.901, with a sensitivity of 91.1% and a specificity of 82.9%. The AUC of T1-max-SIRs for differentiating WTs from MTs was 0.851, with a sensitivity of 88.9% and a specificity of 78.8%. Readers had excellent interobserver agreement on T1-max-SIRs (ICC = 0.989; 95% confidence interval, 0.985-0.992).

CONCLUSIONS

T1-max-SIRs can be useful for differentiating WTs from PAs and MTs with high diagnostic efficiency.