MRI-Based radiomics nomogram for differentiation of benign and malignant lesions of the parotid gland

MR-Neurography of the facial nerve in parotid tumors: intra-parotid nerve visualization and surgical correlation

PURPOSE

One of the most severe complications in surgery of parotid tumors is facial palsy. Imaging of the intra-parotid facial nerve is challenging due to small dimensions. Our aim was to assess, in patients with parotid tumors, the ability of high-resolution 3D double-echo steady-state sequence with water excitation (DE3D-WE) (1) to visualize the extracranial facial nerve and its tracts, (2) to evaluate their relationship to the parotid lesion and (3) to compare MRI and surgical findings.

METHODS

A retrospective study was conducted including all patients with parotid tumors, who underwent MRI from April 2022 to December 2023. Two radiologists independently reviewed DE3D-WE images, assessing quality of visualization of the facial nerve bilaterally and localizing the nerve's divisions in relation to the tumor. MRI data were compared with surgical findings.

RESULTS

Forty consecutive patients were included (M:F = 22:18; mean age 56.3 ± 17.4 years). DE3D-WE could excellently visualize the nerve main trunk and the temporofacial division in all cases. The cervicofacial branch was visible in 99% of cases and visibility was good. Distal divisions were displayed in 34% of cases with a higher visibility on the tumor side (p < 0.05). Interrater agreement was high (weighted kappa 0.94 ± 0.01 [95% CI 0.92-0.97]). Compared to surgery accuracy of MRI in localizing the nerve was 100% for the main trunk, 96% for the temporofacial and 89% for the cervicofacial branches.

CONCLUSIONS

Facial nerve MR-neurography represents a reliable tool. DE3D-WE can play an important role in surgical planning of patients with parotid tumors, reducing the risk of nerve injury.

The value of MRI-based radiomics for evaluating early parotid gland injury in primary Sjögren's syndrome

OBJECTIVE

This study aimed to evaluate the value of machine learning models (ML) based on MRI radiomics in diagnosing early parotid gland injury in primary Sjögren's syndrome (pSS).

METHODS

A total of 164 patients (114 in the training cohort and 50 in the testing cohort) with pSS (n=82) or healthy controls (HC) (n=82) were enrolled. Itksnap software was used to perform two-dimensional segmentation of the bilateral parotid glands on T1-weighted (T1WI) and fat-suppressed T2-weighted imaging (fs-T2WI) images. A total of 1548 texture features of the parotid glands were extracted using radiomics software. A radiomics score (Radscore) was constructed and calculated. A t-test was used to compare the Radscore between the two groups. Finally, five machine learning models were trained and tested to identify early pSS parotid injury, and the performance of the machine learning models was evaluated by calculating the acceptance operating curve (ROC) and other parameters.

RESULTS

The Radscores between the pSS and HC groups showed significant statistical differences (p<0.001). Among the five machine learning models, the Extra Trees Classifier (ETC) model performed high predictive efficacy in identifying early pSS parotid injury, with an AUC of 0.87 in the testing set.

CONCLUSION

MRI radiomics-based machine learning models can effectively diagnose early parotid gland injury in primary Sjögren's syndrome.

Deep learning for the automatic detection and segmentation of parotid gland tumors on MRI

OBJECTIVES

Parotid gland tumors (PGTs) often occur as incidental findings on magnetic resonance images (MRI) that may be overlooked. This study aimed to construct and validate a deep learning model to automatically identify parotid glands (PGs) with a PGT from normal PGs, and in those with a PGT to segment the tumor.

MATERIALS AND METHODS

The nnUNet combined with a PG-specific post-processing procedure was used to develop the deep learning model trained on T1-weighed images (T1WI) in 311 patients (180 PGs with tumors and 442 normal PGs) and fat-suppressed (FS)-T2WI in 257 patients (125 PGs with tumors and 389 normal PGs), for detecting and segmenting PGTs with five-fold cross-validation. Additional validation set separated by time, comprising T1WI in 34 and FS-T2WI in 41 patients, was used to validate the model performance.

RESULTS AND CONCLUSION

To identify PGs with tumors from normal PGs, using combined T1WI and FS-T2WI, the deep learning model achieved an accuracy, sensitivity and specificity of 98.2% (497/506), 100% (119/119) and 97.7% (378/387), respectively, in the cross-validation set and 98.5% (67/68), 100% (20/20) and 97.9% (47/48), respectively, in the validation set. For patients with PGTs, automatic segmentation of PGTs on T1WI and FS-T2WI achieved mean dice coefficients of 86.1% and 84.2%, respectively, in the cross-validation set, and of 85.9% and 81.0%, respectively, in the validation set. The proposed deep learning model may assist the detection and segmentation of PGTs and, by acting as a second pair of eyes, ensure that incidentally detected PGTs on MRI are not missed.

MRI-based radiomics for predicting histology in malignant salivary gland tumors: methodology and "proof of principle"

Defining the exact histological features of salivary gland malignancies before treatment remains an unsolved problem that compromises the ability to tailor further therapeutic steps individually. Radiomics, a new methodology to extract quantitative information from medical images, could contribute to characterizing the individual cancer phenotype already before treatment in a fast and non-invasive way. Consequently, the standardization and implementation of radiomic analysis in the clinical routine work to predict histology of salivary gland cancer (SGC) could also provide improvements in clinical decision-making. In this study, we aimed to investigate the potential of radiomic features as imaging biomarker to distinguish between high grade and low-grade salivary gland malignancies. We have also investigated the effect of image and feature level harmonization on the performance of radiomic models. For this study, our dual center cohort consisted of 126 patients, with histologically proven SGC, who underwent curative-intent treatment in two tertiary oncology centers. We extracted and analyzed the radiomics features of 120 pre-therapeutic MRI images with gadolinium (T1 sequences), and correlated those with the definitive post-operative histology. In our study the best radiomic model achieved average AUC of 0.66 and balanced accuracy of 0.63. According to the results, there is significant difference between the performance of models based on MRI intensity normalized images + harmonized features and other models (p value < 0.05) which indicates that in case of dealing with heterogeneous dataset, applying the harmonization methods is beneficial. Among radiomic features minimum intensity from first order, and gray level-variance from texture category were frequently selected during multivariate analysis which indicate the potential of these features as being used as imaging biomarker. The present bicentric study presents for the first time the feasibility of implementing MR-based, handcrafted radiomics, based on T1 contrast-enhanced sequences and the ComBat harmonization method in an effort to predict the formal grading of salivary gland carcinoma with satisfactory performance.

Deep learning-assisted diagnosis of benign and malignant parotid tumors based on ultrasound: a retrospective study

BACKGROUND

To develop a deep learning(DL) model utilizing ultrasound images, and evaluate its efficacy in distinguishing between benign and malignant parotid tumors (PTs), as well as its practicality in assisting clinicians with accurate diagnosis.

METHODS

A total of 2211 ultrasound images of 980 pathologically confirmed PTs (Training set: n = 721; Validation set: n = 82; Internal-test set: n = 89; External-test set: n = 88) from 907 patients were retrospectively included in this study. The optimal model was selected and the diagnostic performance evaluation is conducted by utilizing the area under curve (AUC) of the receiver-operating characteristic(ROC) based on five different DL networks constructed at varying depths. Furthermore, a comparison of different seniority radiologists was made in the presence of the optimal auxiliary diagnosis model. Additionally, the diagnostic confusion matrix of the optimal model was calculated, and an analysis and summary of misjudged cases' characteristics were conducted.

RESULTS

The Resnet18 demonstrated superior diagnostic performance, with an AUC value of 0.947, accuracy of 88.5%, sensitivity of 78.2%, and specificity of 92.7% in internal-test set, and with an AUC value of 0.925, accuracy of 89.8%, sensitivity of 83.3%, and specificity of 90.6% in external-test set. The PTs were subjectively assessed twice by six radiologists, both with and without the assisted of the model. With the assisted of the model, both junior and senior radiologists demonstrated enhanced diagnostic performance. In the internal-test set, there was an increase in AUC values by 0.062 and 0.082 for junior radiologists respectively, while senior radiologists experienced an improvement of 0.066 and 0.106 in their respective AUC values.

CONCLUSIONS

The DL model based on ultrasound images demonstrates exceptional capability in distinguishing between benign and malignant PTs, thereby assisting radiologists of varying expertise levels to achieve heightened diagnostic performance, and serve as a noninvasive imaging adjunct diagnostic method for clinical purposes.

An ultrasound-based ensemble machine learning model for the preoperative classification of pleomorphic adenoma and Warthin tumor in the parotid gland

OBJECTIVES

The preoperative classification of pleomorphic adenomas (PMA) and Warthin tumors (WT) in the parotid gland plays an essential role in determining therapeutic strategies. This study aims to develop and validate an ultrasound-based ensemble machine learning (USEML) model, employing nonradiative and noninvasive features to differentiate PMA from WT.

METHODS

A total of 203 patients with histologically confirmed PMA or WT who underwent parotidectomy from two centers were enrolled. Clinical factors, ultrasound (US) features, and radiomic features were extracted to develop three types of machine learning model: clinical models, US models, and USEML models. The diagnostic performance of the USEML model, as well as that of physicians based on experience, was evaluated and validated using receiver operating characteristic (ROC) curves in internal and external validation cohorts. DeLong's test was used for comparisons of AUCs. SHAP values were also utilized to explain the classification model.

RESULTS

The USEML model achieved the highest AUC of 0.891 (95% CI, 0.774-0.961), surpassing the AUCs of both the US (0.847; 95% CI, 0.720-0.932) and clinical (0.814; 95% CI, 0.682-0.908) models. The USEML model also outperformed physicians in both internal and external validation datasets (both p < 0.05). The sensitivity, specificity, negative predictive value, and positive predictive value of the USEML model and physician experience were 89.3%/75.0%, 87.5%/54.2%, 87.5%/65.6%, and 89.3%/65.0%, respectively.

CONCLUSIONS

The USEML model, incorporating clinical factors, ultrasound factors, and radiomic features, demonstrated efficient performance in distinguishing PMA from WT in the parotid gland.

CLINICAL RELEVANCE STATEMENT

This study developed a machine learning model for preoperative diagnosis of pleomorphic adenoma and Warthin tumor in the parotid gland based on clinical, ultrasound, and radiomic features. Furthermore, it outperformed physicians in an external validation dataset, indicating its potential for clinical application.

KEY POINTS

• Differentiating pleomorphic adenoma (PMA) and Warthin tumor (WT) affects management decisions and is currently done by invasive biopsy. • Integration of US-radiomic, clinical, and ultrasound findings in a machine learning model results in improved diagnostic accuracy. • The ultrasound-based ensemble machine learning (USEML) model consistently outperforms physicians, suggesting its potential applicability in clinical settings.

Differentiation of parotid pleomorphic adenoma from Warthin tumor using signal intensity ratios on fat-suppressed T2-weighted magnetic resonance imaging

OBJECTIVE

To investigate the value of magnetic resonance imaging (MRI) signal intensity ratios (SIRs) based on fat-suppressed T2-weighted imaging (FS-T2WI), together with demographic features, MRI anatomical characteristics, and SIRs of histopathological patterns of the tumors, in the differentiation of parotid pleomorphic adenoma (PA) from Warthin tumor (WT).

STUDY DESIGN

In total, 90 patients with PA and 56 patients with WT were enrolled in the study. SIRs of tumor to normal parotid gland (SIR-T/P), spinal cord (SIR-T/S), and muscle (SIR-T/M) were calculated. Demographic and radiological features of the 2-patient groups were compared with univariate analysis and multivariate logistic regression analysis. The area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were analyzed to evaluate the utility of SIRs in distinguishing between PA and WT.

RESULTS

SIR-T/P exhibited outstanding discriminating ability (AUC = 0.934), SIR-T/S had excellent discrimination (AUC = 0.839), and SIR-T/M showed acceptable discrimination (AUC = 0.728). When SIR-T/P of 1.96 was selected as the cutoff value, sensitivity and specificity were 0.756 and 0.982, respectively. SIR-T/P, age, sex, and number of lesions were identified as independent predictors by multivariate logistic regression analysis. Differences in SIRs between histopathological patterns were significant.

CONCLUSION

SIR-T/P based on FS-T2WI is an effective discriminator in the differential diagnosis between PA and WT. Age, sex, and number of lesions provided additional value in differentiation.

Application of Machine Learning and Deep EfficientNets in Distinguishing Neonatal Adrenal Hematomas From Neuroblastoma in Enhanced Computed Tomography Images

Background

The aim of the study was to employ a combination of radiomic indicators based on computed tomography (CT) imaging and machine learning (ML), along with deep learning (DL), to differentiate between adrenal hematoma and adrenal neuroblastoma in neonates.

Methods

A total of 76 neonates were included in this retrospective study (40 with neuroblastomas and 36 with adrenal hematomas) who underwent CT and divided into a training group (n = 38) and a testing group (n = 38). The regions of interest (ROIs) were segmented by two radiologists to extract radiomics features using Pyradiomics package. ML classifications were done using support vector machine (SVM), AdaBoost, Extra Trees, gradient boosting, multi-layer perceptron (MLP), and random forest (RF). EfficientNets was employed and classified, based on radiometrics. The area under curve (AUC) of the receiver operating characteristic (ROC) was calculated to assess the performance of each model.

Results

Among all features, the least absolute shrinkage and selection operator (LASSO) logistic regression selected nine features. These radiomics features were used to construct radiomics model. In the training cohort, the AUCs of SVM, MLP and Extra Trees models were 0.967, 0.969 and 1.000, respectively. The corresponding AUCs of the test cohort were 0.985, 0.971 and 0.958, respectively. In the classification task, the AUC of the DL framework was 0.987.

Conclusion

ML decision classifiers and DL framework constructed from CT-based radiomics features offered a non-invasive method to differentiate neonatal adrenal hematoma from neuroblastoma and performed better than the clinical experts.

Bronchiolar adenoma/ciliated muconodular papillary tumour: advancing clinical, pathological, and imaging insights for future perspectives

Bronchiolar adenoma/ciliated muconodular papillary tumour (BA/CMPT) is a benign peripheral lung tumour composed of bilayered bronchiolar-type epithelium containing a continuous basal cell layer; however, the similarities in imaging and tissue biopsy findings at histopathology between BA/CMPT and malignant tumours, including lung adenocarcinoma, pose significant challenges in accurately diagnosing BA/CMPT preoperatively. This difficulty in differentiation often results in misdiagnosis and unnecessary overtreatment. The objective of this article is to provide a comprehensive and systematic review of BA/CMPT, encompassing its clinical manifestations, pathological basis, imaging features, and differential diagnosis. By enhancing healthcare professionals' understanding of this disease, we aim to improve the accuracy of preoperative BA/CMPT diagnosis. This improvement is crucial for the development of appropriate therapeutic strategies and the overall improvement of patient prognosis.

Construction and Application of a Nomogram for Predicting Benign and Malignant Parotid Tumors

OBJECTIVE

A prediction model of benign and malignant differentiation was established by magnetic resonance signs of parotid gland tumors to provide an important basis for the preoperative diagnosis and treatment of parotid gland tumor patients.

METHODS

The data from 138 patients (modeling group) who were diagnosed based on a pathologic evaluation in the Department of Stomatology of Jilin University from June 2019 to August 2021 were retrospectively analyzed. The independent factors influencing benign and malignant differentiation of parotid tumors were selected by logistic regression analysis, and a mathematical prediction model for benign and malignant tumors was established. The data from 35 patients (validation group) who were diagnosed based on pathologic evaluation from September 2021 to February 2022 were collected for verification.

RESULTS

Univariate and multivariate logistic regression analysis showed that tumor morphology, tumor boundary, tumor signal, and tumor apparent diffusion coefficient (ADC) were independent risk factors for predicting benign and malignant parotid gland tumors ( P < 0.05). Based on multivariate logistic regression analysis of the modeling group, a mathematical prediction model was established as follows: Y = the ex/(1 + ex) and X = 0.385 + (1.416 × tumor morphology) + (1.473 × tumor border) + (1.306 × tumor signal) + (2.312 × tumor ADC value). The results showed that the area under the receiver operating characteristic curve of the model was 0.832 (95% confidence interval, 0.75-0.91), the sensitivity was 82.6%, and the specificity was 70.65%. The validity of the model was verified using validation group data, for which the sensitivity was 85.71%, the specificity was 96.4%, and the correct rate was 94.3%. The results showed that the area under receiver operating characteristic curve was 0.936 (95% confidence interval, 0.83-0.98).

CONCLUSIONS

Combined with tumor morphology, tumor ADC, tumor boundary, and tumor signal, the established prediction model provides an important reference for preoperative diagnosis of benign and malignant parotid gland tumors.

Identification of vulnerable carotid plaque with CT-based radiomics nomogram

AIM

To develop and validate a radiomics nomogram for identifying high-risk carotid plaques on computed tomography (CT) angiography (CTA).

MATERIALS AND METHODS

A total of 280 patients with symptomatic (n=131) and asymptomatic (n=139) carotid plaques were divided into a training set (n=135), validation set (n=58), and external test set (n=87). Radiomic features were extracted from CTA images. A radiomics model was constructed based on selected features and a radiomics score (rad-score) was calculated. A clinical factor model was constructed by demographics and CT findings. A radiomics nomogram combining independent clinical factors and the rad-score was constructed. The diagnostic performance of three models was evaluated and validated by region of characteristic curves.

RESULTS

Calcification and maximum plaque thickness were the independent clinical factors. Twenty-four features were used to build the radiomics signature. In the validation set, the nomogram (area under the curve [AUC], 0.977; 95% CI, 0.899-0.999) performed better (p=0.017 and p=0.031) than the clinical factor model (AUC, 0.862; 95% CI, 0.746-0.938) and radiomics signature (AUC, 0.944; 95% CI, 0.850-0.987). In external test set, the nomogram (AUC, 0.952; 95% CI, 0.884-0.987) and radiomics signature (AUC, 0.932; 95% CI, 0.857-0.975) showed better discrimination capability (p=0.002 and p=0.037) than clinical factor model (AUC, 0.818; 95% CI, 0.721-0.892).

CONCLUSION

The CT-based nomogram showed satisfactory performance in identification of high-risk plaques in carotid arteries, and it may serve as a potential non-invasive tool to identify carotid plaque vulnerability and risk stratification.

Radiomics Analysis in Characterization of Salivary Gland Tumors on MRI: A Systematic Review

Radiomics analysis can potentially characterize salivary gland tumors (SGTs) on magnetic resonance imaging (MRI). The procedures for radiomics analysis were various, and no consistent performances were reported. This review evaluated the methodologies and performances of studies using radiomics analysis to characterize SGTs on MRI. We systematically reviewed studies published until July 2023, which employed radiomics analysis to characterize SGTs on MRI. In total, 14 of 98 studies were eligible. Each study examined 23-334 benign and 8-56 malignant SGTs. Least absolute shrinkage and selection operator (LASSO) was the most common feature selection method (in eight studies). Eleven studies confirmed the stability of selected features using cross-validation or bootstrap. Nine classifiers were used to build models that achieved area under the curves (AUCs) of 0.74 to 1.00 for characterizing benign and malignant SGTs and 0.80 to 0.96 for characterizing pleomorphic adenomas and Warthin's tumors. Performances were validated using cross-validation, internal, and external datasets in four, six, and two studies, respectively. No single feature consistently appeared in the final models across the studies. No standardized procedure was used for radiomics analysis in characterizing SGTs on MRIs, and various models were proposed. The need for a standard procedure for radiomics analysis is emphasized.

Deep learning-assisted diagnosis of benign and malignant parotid tumors based on contrast-enhanced CT: a multicenter study

OBJECTIVES

To develop deep learning-assisted diagnosis models based on CT images to facilitate radiologists in differentiating benign and malignant parotid tumors.

METHODS

Data from 573 patients with histopathologically confirmed parotid tumors from center 1 (training set: n = 269; internal-testing set: n = 116) and center 2 (external-testing set: n = 188) were retrospectively collected. Six deep learning models (MobileNet V3, ShuffleNet V2, Inception V3, DenseNet 121, ResNet 50, and VGG 19) based on arterial-phase CT images, and a baseline support vector machine (SVM) model integrating clinical-radiological features with handcrafted radiomics signatures were constructed. The performance of senior and junior radiologists with and without optimal model assistance was compared. The net reclassification index (NRI) and integrated discrimination improvement (IDI) were calculated to evaluate the clinical benefit of using the optimal model.

RESULTS

MobileNet V3 had the best predictive performance, with sensitivity increases of 0.111 and 0.207 (p < 0.05) in the internal- and external-testing sets, respectively, relative to the SVM model. Clinical benefit and overall efficiency of junior radiologist were significantly improved with model assistance; for the internal- and external-testing sets, respectively, the AUCs improved by 0.128 and 0.102 (p < 0.05), the sensitivity improved by 0.194 and 0.120 (p < 0.05), the NRIs were 0.257 and 0.205 (p < 0.001), and the IDIs were 0.316 and 0.252 (p < 0.001).

CONCLUSIONS

The developed deep learning models can assist radiologists in achieving higher diagnostic performance and hopefully provide more valuable information for clinical decision-making in patients with parotid tumors.

KEY POINTS

• The developed deep learning models outperformed the traditional SVM model in predicting benign and malignant parotid tumors. • Junior radiologist can obtain greater clinical benefits with assistance from the optimal deep learning model. • The clinical decision-making process can be accelerated in patients with parotid tumors using the established deep learning model.

REliability of consensus-based segMentatIoN in raDiomic feature reproducibility (REMIND): A word of caution

OBJECTIVE

To evaluate the reliability of consensus-based segmentation in terms of reproducibility of radiomic features.

METHODS

In this retrospective study, three tumor data sets were investigated: breast cancer (n = 30), renal cell carcinoma (n = 30), and pituitary macroadenoma (n = 30). MRI was utilized for breast and pituitary data sets, while CT was used for renal data set. 12 readers participated in the segmentation process. Consensus segmentation was created by making corrections on a previous region or volume of interest. Four experiments were designed to evaluate the reproducibility of radiomic features. Reliability was assessed with intraclass correlation coefficient (ICC) with two cut-off values: 0.75 and 0.9.

RESULTS

Considering the lower bound of the 95% confidence interval and the ICC threshold of 0.90, at least 61% of the radiomic features were not reproducible in the inter-consensus analysis. In the susceptibility experiment, at least half (54%) became non-reproducible when the first reader is replaced with a different reader. In the intra-consensus analysis, at least about one-third (32%) were non-reproducible when the same second reader segmented the image over the same first reader two weeks later. Compared to inter-reader analysis based on independent single readers, the inter-consensus analysis did not statistically significantly improve the rates of reproducible features in all data sets and analyses.

CONCLUSIONS

Despite the positive connotation of the word "consensus", it is essential to REMIND that consensus-based segmentation has significant reproducibility issues. Therefore, the usage of consensus-based segmentation alone should be avoided unless a reliability analysis is performed, even if it is not practical in clinical settings.

The Role of an MRI-Based Radiomic Signature in Predicting Malignancy of Parotid Gland Tumors

The aim of this study was to assess the ability of MRI radiomic features to differentiate between benign parotid gland tumors (BPGT) and malignant parotid gland tumors (MPGT). This retrospective study included 93 patients who underwent MRI examinations of the head and neck region (78 patients presenting unique PGT, while 15 patients presented double PGT). A total of 108 PGT with histological confirmation were eligible for the radiomic analysis and were assigned to a training group (n = 83; 58 BPGT; 25 MPGT) and a testing group (n = 25; 16 BPGT; 9 MPGT). The radiomic features were extracted from 3D segmentations of the PGT on the T2-weighted and fat-saturated, contrast-enhanced T1-weighted images. Following feature reduction techniques, including LASSO regression analysis, a radiomic signature (RS) was built with five radiomic features. The RS presented a good diagnostic performance in differentiating between PGT, achieving an area under the curve (AUC) of 0.852 (p < 0.001) in the training set and 0.786 (p = 0.017) in the testing set. In both datasets, the RS proved to have lower values in the BPGT group as compared to MPGT group (p < 0.001 and p = 0.023, respectively). The multivariate analysis revealed that RS was independently associated with PGT malignancy, together with the ill-defined margin pattern (p = 0.031, p = 0.001, respectively). The complex model, using clinical data, MRI features and the RS, presented a higher diagnostic performance (AUC of 0.976) in comparison to the RS alone. MRI-based radiomic features could be considered potential additional imaging biomarkers able to discriminate between benign and malignant parotid gland tumors.

Radiomics analysis of T1WI and T2WI magnetic resonance images to differentiate between IgG4-related ophthalmic disease and orbital MALT lymphoma

BACKGROUND

Preoperative differentiation between IgG4-related orbital disease (IgG4-ROD) and orbital mucosa-associated lymphoid tissue (MALT) lymphoma has a significant impact on clinical decision-making. Our research aims to construct and evaluate a magnetic resonance imaging (MRI)-based radiomics model to assist clinicians to better identify IgG4-ROD and orbital MALT lymphoma and make better preoperative medical decisions.

METHODS

MR images and clinical data from 20 IgG4-ROD patients and 30 orbital MALT lymphoma patients were classified into a training (21 MALT; 14 IgG4-ROD) or validation set (nine MALT; six IgG4-ROD). Radiomics features were collected from T1-weighted (T1WI) and T2-weighted images (T2WI). Student's t-test, the least absolute shrinkage and selection operator (LASSO) and principal component analysis (PCA) were conducted to screen and select the radiomics features. Support vector machine (SVM) classifiers developed from the selected radiomic features for T1WI, T2WI and combined T1WI and T2WI were trained and tested on the training and validation set via five-fold cross-validation, respectively. Diagnostic performance of the classifiers were evaluated with area under the curve (AUC) readings of the receiver operating characteristic (ROC) curve, and readouts for precision, accuracy, recall and F1 score.

RESULTS

Among 12 statistically significant features from T1WI, four were selected for SVM modelling after LASSO analysis. For T2WI, eight of 51 statistically significant features were analyzed by LASSO followed by PCA, with five features finally used for SVM. Combined analysis of T1WI and T2WI features selected two and four, respectively, for SVM. The AUC values for T1WI and T2WI classifiers separately were 0.722 ± 0.037 and 0.744 ± 0.027, respectively, while combined analysis of T1WI and T2WI classifiers further enhanced the classification performances with AUC values ranging from 0.727 to 0.821.

CONCLUSION

The radiomics model based on features from both T1WI and T2WI images is effective and promising for the differential diagnosis of IgG4-ROD and MALT lymphoma. More detailed radiomics features and advanced techniques should be considered to further explore the differences between these diseases.

CT based intratumor and peritumoral radiomics for differentiating complete from incomplete capsular characteristics of parotid pleomorphic adenoma: a two-center study

OBJECTIVE

Capsular characteristics of pleomorphic adenoma (PA) has various forms. Patients without complete capsule has a higher risk of recurrence than patients with complete capsule. We aimed to develop and validate CT-based intratumoral and peritumoral radiomics models to make a differential diagnosis between parotid PA with and without complete capsule.

METHODS

Data of 260 patients (166 patients with PA from institution 1 (training set) and 94 patients (test set) from institution 2) were retrospectively analyzed. Three Volume of interest (VOIs) were defined in the CT images of each patient: tumor volume of interest (VOI_tumor), VOI_peritumor, and VOI_{intra-plus peritumor}. Radiomics features were extracted from each VOI and used to train nine different machine learning algorithms. Model performance was evaluated using receiver operating characteristic (ROC) curves and the area under the curve (AUC).

RESULTS

The results showed that the radiomics models based on features from VOI_{intra-plus peritumor} achieved higher AUCs compared to models based on features from VOI_tumor. The best performing model was Linear discriminant analysis, which achieved an AUC of 0.86 in the tenfold cross-validation and 0.869 in the test set. The model was based on 15 features, including shape-based features and texture features.

CONCLUSIONS

We demonstrated the feasibility of combining artificial intelligence with CT-based peritumoral radiomics features can be used to accurately predict capsular characteristics of parotid PA. This may assist in clinical decision-making by preoperative identification of capsular characteristics of parotid PA.

Application of DCE-MRI radiomics signature analysis in differentiating molecular subtypes of luminal and non-luminal breast cancer

Background

The goal of this study was to develop and validate a radiomics signature based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) preoperatively differentiating luminal and non-luminal molecular subtypes in patients with invasive breast cancer.

Methods

One hundred and thirty-five invasive breast cancer patients with luminal (n = 78) and non-luminal (n = 57) molecular subtypes were divided into training set (n = 95) and testing set (n = 40) in a 7:3 ratio. Demographics and MRI radiological features were used to construct clinical risk factors. Radiomics signature was constructed by extracting radiomics features from the second phase of DCE-MRI images and radiomics score (rad-score) was calculated. Finally, the prediction performance was evaluated in terms of calibration, discrimination, and clinical usefulness.

Results

Multivariate logistic regression analysis showed that no clinical risk factors were independent predictors of luminal and non-luminal molecular subtypes in invasive breast cancer patients. Meanwhile, the radiomics signature showed good discrimination in the training set (AUC, 0.86; 95% CI, 0.78-0.93) and the testing set (AUC, 0.80; 95% CI, 0.65-0.95).

Conclusion

The DCE-MRI radiomics signature is a promising tool to discrimination luminal and non-luminal molecular subtypes in invasive breast cancer patients preoperatively and noninvasively.

Predictive Value of a Radiomics Nomogram Model Based on Contrast-Enhanced Computed Tomography for KIT Exon 9 Gene Mutation in Gastrointestinal Stromal Tumors

OBJECTIVES

To establish and validate a radiomics nomogram model for preoperative prediction of KIT exon 9 mutation status in patients with gastrointestinal stromal tumors (GISTs).

MATERIALS AND METHODS

Eighty-seven patients with pathologically confirmed GISTs were retrospectively enrolled in this study. Imaging and clinicopathological data were collected and randomly assigned to the training set (n = 60) and test set (n = 27) at a ratio of 7:3. Based on contrast-enhanced CT (CE-CT) arterial and venous phase images, the region of interest (ROI) of the tumors were manually drawn layer by layer, and the radiomics features were extracted. The intra-class correlation coefficient (ICC) was used to test the consistency between observers. Least absolute shrinkage and selection operator regression (LASSO) were used to further screen the features. The nomogram of integrated radiomics score (Rad-Score) and clinical risk factors (extra-gastric location and distant metastasis) was drawn on the basis of multivariate logistic regression. The area under the receiver operating characteristic (AUC) curve and decision curve analysis were used to evaluate the predictive efficiency of the nomogram, and the clinical benefits that the decision curve evaluation model may bring to patients.

RESULTS

The selected radiomics features (arterial phase and venous phase features) were significantly correlated with the KIT exon 9 mutation status of GISTs. The AUC, sensitivity, specificity, and accuracy in the radiomics model were 0.863, 85.7%, 80.4%, and 85.0% for the training group (95% confidence interval [CI]: 0.750-0.938), and 0.883, 88.9%, 83.3%, and 81.5% for the test group (95% CI: 0.701-0.974), respectively. The AUC, sensitivity, specificity, and accuracy in the nomogram model were 0.902 (95% confidence interval [CI]: 0.798-0.964), 85.7%, 86.9%, and 91.7% for the training group, and 0.907 (95% CI: 0.732-0.984), 77.8%, 94.4%, and 88.9% for the test group, respectively. The decision curve showed the clinical application value of the radiomic nomogram.

CONCLUSION

The radiomics nomogram model based on CE-CT can effectively predict the KIT exon 9 mutation status of GISTs and may be used for selective gene analysis in the future, which is of great significance for the accurate treatment of GISTs.

Value of T2-weighted-based radiomics model in distinguishing Warthin tumor from pleomorphic adenoma of the parotid

OBJECTIVES

The differentiation of Warthin tumor and pleomorphic adenoma before treatment is crucial for clinical strategies. The aim of this study was to develop and test a T2-weighted-based radiomics model for differentiating pleomorphic adenoma from Warthin tumor of the parotid gland.

METHODS

A total of 117 patients, including 61 cases of Warthin tumor and 56 cases of pleomorphic adenoma, were retrospectively enrolled from two centers between January 2010 and June 2022. The training set included 82 cases, and the validation set included 35 cases. From T2-weighted images, 971 radiomics features were extracted. Seven radiomics features remained after a two-step selection process. We used the seven radiomics features and clinical factors through multivariable logistic regression to build radiomics and clinical models, respectively. A radiomics-clinical model was also built that combined the independent clinical predictors with the radiomics features. Through ROC curves, the three models were evaluated and compared.

RESULTS

In the radiomics model, AUCs were 0.826 and 0.796 in training and validation sets, respectively. In the clinical model, the AUCs were 0.923 and 0.926 in the training and validation sets, respectively. Decision curve analysis revealed that the radiomics-clinical model had the best diagnostic performance for distinguishing Warthin tumor from pleomorphic adenoma of the parotid gland (AUC = 0.962 and 0.934 for the training and validation sets, respectively).

CONCLUSION

The radiomics-clinical model performed well in differentiating pleomorphic adenoma from Warthin tumor of the parotid gland.

KEY POINTS

• The clinical model outperformed the radiomics model in distinguishing pleomorphic adenoma from Warthin tumor of the parotid gland. • The radiomics features extracted from T2-weighted images could help differentiate pleomorphic adenoma from Warthin tumor of the parotid gland. • The radiomics-clinical model was superior to the radiomics and the clinical models for differentiating pleomorphic adenoma from Warthin tumor of the parotid gland.

The Role of Radiomics in Salivary Gland Imaging: A Systematic Review and Radiomics Quality Assessment

Background: Radiomics of salivary gland imaging can support clinical decisions in different clinical scenarios, such as tumors, radiation-induced xerostomia and sialadenitis. This review aims to evaluate the methodological quality of radiomics studies on salivary gland imaging. Material and Methods: A systematic search was performed, and the methodological quality was evaluated using the radiomics quality score (RQS). Subgroup analyses according to the first author's professional role (medical or not medical), journal type (radiological journal or other) and the year of publication (2021 or before) were performed. The correlation of RQS with the number of patients was calculated. Results: Twenty-three articles were included (mean RQS 11.34 ± 3.68). Most studies well-documented the imaging protocol (87%), while neither prospective validations nor cost-effectiveness analyses were performed. None of the included studies provided open-source data. A statistically significant difference in RQS according to the year of publication was found (p = 0.009), with papers published in 2021 having slightly higher RQSs than older ones. No differences according to journal type or the first author's professional role were demonstrated. A moderate relationship between the overall RQS and the number of patients was found. Conclusions: Radiomics application in salivary gland imaging is increasing. Although its current clinical applicability can be affected by the somewhat inadequate quality of the papers, a significant improvement in radiomics methodologies has been demonstrated in the last year.

Radiomics for Discriminating Benign and Malignant Salivary Gland Tumors; Which Radiomic Feature Categories and MRI Sequences Should Be Used?

The lack of a consistent MRI radiomic signature, partly due to the multitude of initial feature analyses, limits the widespread clinical application of radiomics for the discrimination of salivary gland tumors (SGTs). This study aimed to identify the optimal radiomics feature category and MRI sequence for characterizing SGTs, which could serve as a step towards obtaining a consensus on a radiomics signature. Preliminary radiomics models were built to discriminate malignant SGTs (n = 34) from benign SGTs (n = 57) on T1-weighted (T1WI), fat-suppressed (FS)-T2WI and contrast-enhanced (CE)-T1WI images using six feature categories. The discrimination performances of these preliminary models were evaluated using 5-fold-cross-validation with 100 repetitions and the area under the receiver operating characteristic curve (AUC). The differences between models’ performances were identified using one-way ANOVA. Results show that the best feature categories were logarithm for T1WI and CE-T1WI and exponential for FS-T2WI, with AUCs of 0.828, 0.754 and 0.819, respectively. These AUCs were higher than the AUCs obtained using all feature categories combined, which were 0.750, 0.707 and 0.774, respectively (p < 0.001). The highest AUC (0.846) was obtained using a combination of T1WI + logarithm and FS-T2WI + exponential features, which reduced the initial features by 94.0% (from 1015 × 3 to 91 × 2). CE-T1WI did not improve performance. Using one feature category rather than all feature categories combined reduced the number of initial features without compromising radiomic performance.

An attention base U-net for parotid tumor autosegmentation

A parotid neoplasm is an uncommon condition that only accounts for less than 3% of all head and neck cancers, and they make up less than 0.3% of all new cancers diagnosed annually. Due to their nonspecific imaging features and heterogeneous nature, accurate preoperative diagnosis remains a challenge. Automatic parotid tumor segmentation may help physicians evaluate these tumors. Two hundred eighty-five patients diagnosed with benign or malignant parotid tumors were enrolled in this study. Parotid and tumor tissues were segmented by 3 radiologists on T1-weighted (T1w), T2-weighted (T2w) and T1-weighted contrast-enhanced (T1wC) MR images. These images were randomly divided into two datasets, including a training dataset (90%) and an validation dataset (10%). A 10-fold cross-validation was performed to assess the performance. An attention base U-net for parotid tumor autosegmentation was created on the MRI T1w, T2 and T1wC images. The results were evaluated in a separate dataset, and the mean Dice similarity coefficient (DICE) for both parotids was 0.88. The mean DICE for left and right tumors was 0.85 and 0.86, respectively. These results indicate that the performance of this model corresponds with the radiologist's manual segmentation. In conclusion, an attention base U-net for parotid tumor autosegmentation may assist physicians to evaluate parotid gland tumors.

Distinguishing Parotid Polymorphic Adenoma and Warthin Tumor Based on the CT Radiomics Nomogram: A Multicenter Study

RATIONALE AND OBJECTIVES

To develop, validate, and test a comprehensive radiomics prediction model to distinguish parotid polymorphic adenomas (PAs) and warthin tumors (WTs) using clinical data and enhanced computed tomography (CT) from a multicenter cohort.

MATERIALS AND METHODS

A total of 267 patients with PAs (n =172) or WTs (n = 95) from two hospitals were randomly divided into training (n =188) and validation (n =79) datasets. Radiomics features were extracted from the enhanced CT (arterial phase) followed by dimensionality reduction. Clinical and CT features were combined to establish a prediction model. A radiomics nomogram was constructed by combining RadScore and clinical factors. Moreover, an independent dataset of 31 patients from a third hospital was employed to test the model. Thus, the performance of the nomogram, radiomics signature, and clinical models was evaluated on the training, validation, and the independent testing datasets. Receiver operating characteristic (ROC) curves were used to compare the performance, and decision curve analysis (DCA) was used to evaluate the clinical effectiveness of the model.

RESULTS

A total of 15 radiomics features were selected from CT data as the imaging markers to generate RadScores, and demographics or clinical data like age, sex, and smoking factors combined with RadScores were used to distinguish PAs and WTs based on multivariate logistic regression analyses. The results showed that radiomics nomograms combining clinical factors and RadScores provided satisfactory predictive values for distinguishing PAs from WTs, with areas under ROC curves (AUC) of 0.979, 0.922, and 0.903 for the training, validation, and the independent testing datasets, respectively. Decision curve analysis revealed that the radiomics nomogram outperformed the clinical factor models in terms of accuracy and effectiveness.

CONCLUSION

CT-based radiomics nomograms combining RadScores and clinical factors can be used to identify PAs and WTs, which may help tumor management by clinicians.

A computed tomography-based radiomics signature for predicting expression of programmed death ligand 1 in head and neck squamous cell carcinoma

OBJECTIVES

Accurate prediction of the expression of programmed death ligand 1 (PD-L1) in head and neck squamous cell carcinoma (HNSCC) before immunotherapy is crucial. This study was performed to construct and validate a contrast-enhanced computed tomography (CECT)-based radiomics signature to predict the expression of PD-L1 in HNSCC.

METHODS

In total, 157 patients with confirmed HNSCC who underwent CECT scans and immunohistochemical examination of tumor PD-L1 expression were enrolled in this study. The patients were divided into a training set (n = 104; 62 PD-L1-positive and 42 PD-L1-negative) and an external validation set (n = 53; 34 PD-L1-positive and 19 PD-L1-negative). A radiomics signature was constructed from radiomics features extracted from the CECT images, and a radiomics score was calculated. Performance of the radiomics signature was assessed using receiver operating characteristics analysis.

RESULTS

Nine features were finally selected to construct the radiomics signature. The performance of the radiomics signature to distinguish between a PD-L1-positive and PD-L1-negative status in both the training and validation sets was good, with an area under the receiver operating characteristics curve of 0.852 and 0.802 for the training and validation sets, respectively.

CONCLUSIONS

A CECT-based radiomics signature was constructed to predict the expression of PD-L1 in HNSCC. This model showed favorable predictive efficacy and might be useful for identifying patients with HNSCC who can benefit from anti-PD-L1 immunotherapy.

KEY POINTS

• Accurate prediction of the expression of PD-L1 in HNSCC before immunotherapy is crucial. • A CECT-based radiomics signature showed favorable predictive efficacy in estimation of the PD-L1 expression status in patients with HNSCC.

Comparison of Different Machine Models Based on Multi-Phase Computed Tomography Radiomic Analysis to Differentiate Parotid Basal Cell Adenoma From Pleomorphic Adenoma

Objective

This study explored the value of different radiomic models based on multiphase computed tomography in differentiating parotid pleomorphic adenoma (PA) and basal cell tumor (BCA) concerning the predominant phase and the optimal radiomic model.

Methods

This study enrolled 173 patients with pathologically confirmed parotid tumors (training cohort: n=121; testing cohort: n=52). Radiomic features were extracted from the nonenhanced, arterial, venous, and delayed phases CT images. After dimensionality reduction and screening, logistic regression (LR), K-nearest neighbor (KNN) and support vector machine (SVM) were applied to develop radiomic models. The optimal radiomic model was selected by using ROC curve analysis. Univariate and multivariable logistic regression was performed to analyze clinical-radiological characteristics and to identify variables for developing a clinical model. A combined model was constructed by integrating clinical and radiomic features. Model performances were assessed by ROC curve analysis.

Results

A total of 1036 radiomic features were extracted from each phase of CT images. Sixteen radiomic features were considered valuable by dimensionality reduction and screening. Among radiomic models, the SVM model of the arterial and delayed phases showed superior predictive efficiency and robustness (AUC, training cohort: 0.822, 0.838; testing cohort: 0.752, 0.751). The discriminatory capability of the combined model was the best (AUC, training cohort: 0.885; testing cohort: 0.834).

Conclusions

The diagnostic performance of the arterial and delayed phases contributed more than other phases. However, the combined model demonstrated excellent ability to distinguish BCA from PA, which may provide a non-invasive and efficient method for clinical decision-making.

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.

The Potential and Emerging Role of Quantitative Imaging Biomarkers for Cancer Characterization

Simple Summary

Modern, personalized therapy approaches are increasingly changing advanced cancer into a chronic disease. Compared to imaging, novel omics methodologies in molecular biology have already achieved an individual characterization of cancerous lesions. With quantitative imaging biomarkers, analyzed by radiomics or deep learning, an imaging-based assessment of tumoral biology can be brought into clinical practice. Combining these with other non-invasive methods, e.g., liquid profiling, could allow for more individual decision making regarding therapies and applications.

Abstract

Similar to the transformation towards personalized oncology treatment, emerging techniques for evaluating oncologic imaging are fostering a transition from traditional response assessment towards more comprehensive cancer characterization via imaging. This development can be seen as key to the achievement of truly personalized and optimized cancer diagnosis and treatment. This review gives a methodological introduction for clinicians interested in the potential of quantitative imaging biomarkers, treating of radiomics models, texture visualization, convolutional neural networks and automated segmentation, in particular. Based on an introduction to these methods, clinical evidence for the corresponding imaging biomarkers—(i) dignity and etiology assessment; (ii) tumoral heterogeneity; (iii) aggressiveness and response; and (iv) targeting for biopsy and therapy—is summarized. Further requirements for the clinical implementation of these imaging biomarkers and the synergistic potential of personalized molecular cancer diagnostics and liquid profiling are discussed.

Multiphasic CT-Based Radiomics Analysis for the Differentiation of Benign and Malignant Parotid Tumors

Objective

This study aims to investigate the value of machine learning models based on clinical-radiological features and multiphasic CT radiomics features in the differentiation of benign parotid tumors (BPTs) and malignant parotid tumors (MPTs).

Methods

This retrospective study included 312 patients (205 cases of BPTs and 107 cases of MPTs) who underwent multiphasic enhanced CT examinations, which were randomly divided into training (N = 218) and test (N = 94) sets. The radiomics features were extracted from the plain, arterial, and venous phases. The synthetic minority oversampling technique was used to balance minority class samples in the training set. Feature selection methods were done using the least absolute shrinkage and selection operator (LASSO), mutual information (MI), and recursive feature extraction (RFE). Two machine learning classifiers, support vector machine (SVM), and logistic regression (LR), were then combined in pairs with three feature selection methods to build different radiomics models. Meanwhile, the prediction performances of different radiomics models based on single phase (plain, arterial, and venous phase) and multiphase (three-phase combination) were compared to determine which model construction method and phase were more discriminative. In addition, clinical models based on clinical-radiological features and combined models integrating radiomics features and clinical-radiological features were established. The prediction performances of the different models were evaluated by the area under the receiver operating characteristic (ROC) curve (AUC) and the drawing of calibration curves.

Results

Among the 24 established radiomics models composed of four different phases, three feature selection methods, and two machine learning classifiers, the LASSO-SVM model based on a three-phase combination had the optimal prediction performance with AUC (0.936 [95% CI = 0.866, 0.976]), sensitivity (0.78), specificity (0.90), and accuracy (0.86) in the test set, and its prediction performance was significantly better than with the clinical model based on LR (AUC = 0.781, p = 0.012). In the test set, the combined model based on LR had a lower AUC than the optimal radiomics model (AUC = 0.933 vs. 0.936), but no statistically significant difference (p = 0.888).

Conclusion

Multiphasic CT-based radiomics analysis showed a machine learning model based on clinical-radiological features and radiomics features has the potential to provide a valuable tool for discriminating benign from malignant parotid tumors.

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.

CT-based radiomics analysis of different machine learning models for differentiating benign and malignant parotid tumors

OBJECTIVES

This study aimed to explore and validate the value of different radiomics models for differentiating benign and malignant parotid tumors preoperatively.

METHODS

This study enrolled 388 patients with pathologically confirmed parotid tumors (training cohort: n = 272; test cohort: n = 116). Radiomics features were extracted from CT images of the non-enhanced, arterial, and venous phases. After dimensionality reduction and selection, radiomics models were constructed by logistic regression (LR), support vector machine (SVM), and random forest (RF). The best radiomic model was selected by using ROC curve analysis. Univariate and multivariable logistic regression was applied to analyze clinical-radiological characteristics and identify variables for developing a clinical model. A combined model was constructed by incorporating radiomics and clinical features. Model performances were assessed by ROC curve analysis, and decision curve analysis (DCA) was used to estimate the models' clinical values.

RESULTS

In total, 2874 radiomic features were extracted from CT images. Ten radiomics features were deemed valuable by dimensionality reduction and selection. Among radiomics models, the SVM model showed greater predictive efficiency and robustness, with AUCs of 0.844 in the training cohort; and 0.840 in the test cohort. Ultimate clinical features constructed a clinical model. The discriminatory capability of the combined model was the best (AUC, training cohort: 0.904; test cohort: 0.854). Combined model DCA revealed optimal clinical efficacy.

CONCLUSIONS

The combined model incorporating radiomics and clinical features exhibited excellent ability to distinguish benign and malignant parotid tumors, which may provide a noninvasive and efficient method for clinical decision making.

KEY POINTS

The current study is the first to compare the value of different radiomics models (LR, SVM, and RF) for preoperative differentiation of benign and malignant parotid tumors. A CT-based combined model, integrating clinical-radiological and radiomics features, is conducive to distinguishing benign and malignant parotid tumors, thereby improving diagnostic performance and aiding treatment.

A CT-based radiomics nomogram for differentiation of squamous cell carcinoma and non-Hodgkin's lymphoma of the palatine tonsil

OBJECTIVES

Accurate preoperative differentiation between squamous cell carcinoma (SCC) and non-Hodgkin's lymphoma (NHL) in the palatine tonsil is crucial because of their different treatment. This study aimed to construct and validate a contrast-enhanced CT (CECT)-based radiomics nomogram for preoperative differentiation of SCC and NHL in the palatine tonsil.

METHODS

This study enrolled 135 patients with a pathological diagnosis of SCC or NHL from two clinical centers, who were divided into training (n = 94; SCC = 50, NHL = 44) and external validation sets (n = 41; SCC = 22, NHL = 19). A radiomics signature was constructed from radiomics features extracted from routine CECT images and a radiomics score (Rad-score) was calculated. A clinical model was established using demographic features and CT findings. The independent clinical factors and Rad-score were combined to construct a radiomics nomogram. Performance of the clinical model, radiomics signature, and nomogram was assessed using receiver operating characteristics analysis and decision curve analysis.

RESULTS

Eleven features were finally selected to construct the radiomics signature. The radiomics nomogram incorporating gender, mean CECT value, and radiomics signature showed better predictive value for differentiating SCC from NHL than the clinical model for training (AUC, 0.919 vs. 0.801, p = 0.004) and validation (AUC, 0.876 vs. 0.703, p = 0.029) sets. Decision curve analysis demonstrated that the radiomics nomogram was more clinically useful than the clinical model.

CONCLUSIONS

A CECT-based radiomics nomogram was constructed incorporating gender, mean CECT value, and radiomics signature. This nomogram showed favorable predictive efficacy for differentiating SCC from NHL in the palatine tonsil, and might be useful for clinical decision-making.

KEY POINTS

• Differential diagnosis between SCC and NHL in the palatine tonsil is difficult by conventional imaging modalities. • A radiomics nomogram integrated with the radiomics signature, gender, and mean contrast-enhanced CT value facilitates differentiation of SCC from NHL with improved diagnostic efficacy.

A nomogram based on clinical information, conventional ultrasound and radiomics improves prediction of malignant parotid gland lesions

Although conventional ultrasound (CUS) allows for clear detection of parotid gland lesions (PGLs), it fails to accurately provide benign-malignant differentiation due to overlapping morphological features. Radiomics is capable of processing large-quantity volume of data hidden in CUS image undiscovered by naked eyes. The aim was to explore the potential of CUS-based radiomics score (Rad-score) in distinguishing benign (BPGLs) and malignant PGLs (MPGLs). A consecutive of 281 PGLs (197 in training set and 84 in test set) with definite pathological confirmation was retrospectively enrolled. 1465 radiomics features were extracted from CUS images and Rad-score was constructed by using Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. Different nomogram models, including clinic-radiomics (Clin + Rad-score), CUS-clinic (CUS + Clin) and combined CUS-clinic-radiomics (CUS + Clin + Rad-score), were built using logistic regression. The diagnostic performance of different models were calculated and compared by area under receiver operating curve (AUC) and corresponding sensitivity and specificity. Finally, 26 radiomics features were independent signatures for predicting MPGLs, with MPGLs having higher Rad-scores in both cohorts (both P < 0.05). In the test population, CUS + Clin + Rad-score obtained an excellent diagnostic result, with significantly higher AUC value (AUC = 0.91) when compared to that of CUS + Clin (AUC = 0.84) and Clin + Rad-score (AUC = 0.74), respectively (both P < 0.05). In addition, the sensitivity of this combined model was higher than that of single Rad-score model (100.00% vs. 71.43%, P = 0.031) without compromising the specificity value (82.86% vs. 88.57%, P = 0.334). The calibration curve and decision curve analysis also indicated the clinical effectiveness of the proposed combined nomogram. The combined CUS-clinic-radiomics model may help improve the discrimination of BPGLs from MPGLs.

Radiomics and deep learning approach to the differential diagnosis of parotid gland tumors

PURPOSE OF REVIEW

Advances in computer technology and growing expectations from computer-aided systems have led to the evolution of artificial intelligence into subsets, such as deep learning and radiomics, and the use of these systems is revolutionizing modern radiological diagnosis. In this review, artificial intelligence applications developed with radiomics and deep learning methods in the differential diagnosis of parotid gland tumors (PGTs) will be overviewed.

RECENT FINDINGS

The development of artificial intelligence models has opened new scenarios owing to the possibility of assessing features of medical images that usually are not evaluated by physicians. Radiomics and deep learning models come to the forefront in computer-aided diagnosis of medical images, even though their applications in the differential diagnosis of PGTs have been limited because of the scarcity of data sets related to these rare neoplasms. Nevertheless, recent studies have shown that artificial intelligence tools can classify common PGTs with reasonable accuracy.

SUMMARY

All studies aimed at the differential diagnosis of benign vs. malignant PGTs or the identification of the commonest PGT subtypes were identified, and five studies were found that focused on deep learning-based differential diagnosis of PGTs. Data sets were created in three of these studies with MRI and in two with computed tomography (CT). Additional seven studies were related to radiomics. Of these, four were on MRI-based radiomics, two on CT-based radiomics, and one compared MRI and CT-based radiomics in the same patients.

Evaluation of Blood Markers at Admission for Predicting Community Acquired Pneumonia in Chronic Obstructive Pulmonary Disease

Acute exacerbations of Chronic Obstructive Pulmonary Disease (AECOPD) and community acquired pneumonia (CAP) are two common acute attacks in COPD patients and it is not always easy to determine whether a COPD patient at admission has parenchymal infection or bronchial infection. Comprehensive comparison between AECOPD patients and CAP patients with COPD (COPD + CAP) can help us understand them better. We retrospectively collected the medical records of AECOPD and COPD + CAP patients. Systemic inflammation, eosinophilic inflammation, damage to other organs, common chronic comorbidities, structural changes, phenotype and endotype distributions and coagulation functions between two groups were compared and correlations of these characteristics in total subjects, AECOPD patients and COPD + CAP patients were analyzed. Logistic regression analysis was performed to select helpful biomarkers for distinguishing between them. Receiver operator characteristic (ROC) curve was plotted to assess the diagnostic value of selected biomarkers and their combination. A nomogram was established for the differential diagnosis of AECOPD and COPD + CAP. A total of 206 patients were included into our analysis. In these subjects, 104 patients were classified as AECOPD group and 102 patients were considered to have COPD + CAP mainly based on their chest CT scan results. The counts of eosinophils (EOS), basophils (BAS) and lymphocytes (LYM) and percentage of total white blood cell count, hemoglobin and hematocrit were increased in AECOPD patients compared with COPD + CAP patients. The counts of neutrophils (NEU) and percentage of total white blood cell count, C-reactive protein (CRP), Erythrocyte sedimentation rate (ESR), fibrinogen, D-dimer and N-Terminal pro-brain natriuretic peptide (NT-proBNP) levels were increased in COPD + CAP patients. After logistic regression analysis, EOS < 0.5 × 10⁹/L, ESR ≥ 8 mm/H and NT-proBNP ≥ 100 pg/mL were selected as helpful biomarkers for diagnosis of COPD + CAP instead of AECOPD. Area under the ROC curve (AUC) of the combination of selected biomarkers was 0.764(0.698-0.829). A nomogram was established and the calibration curve suggested that fitting efficiency of the nomogram was good. AECOPD and COPD + CAP are markedly different, mainly reflected in eosinophilic inflammation, systemic inflammation and coagulation function. Correlations between some common inflammatory biomarkers are also different in the two groups. A nomogram was established to offer help to clinicians for differential diagnosis of these two diseases.

Quantitative Analysis and Pathological Basis of Signal Intensity on T2-Weighted MR Images in Benign and Malignant Parotid Tumors

Objective

To investigate the value of the signal intensity on T2-weighted magnetic resonance (MR) imaging using quantitative analysis in the differentiation of parotid tumors.

Materials and Methods

MR data of 80 pleomorphic adenomas (PAs), 68 Warthin tumors (WTs), and 34 malignant tumors (MTs) confirmed by surgery and histology were retrospectively analyzed. The signal intensities of tumor, normal parotid gland, spinal cord, and buccal subcutaneous fat were measured, and the signal intensity ratios (SIRs) between the tumor and the three references were calculated. Receiver operating characteristic curve was used to determine the optimal threshold and diagnostic efficiency of SIR for differentiating PAs, WTs, and MTs.

Results

The area under the curve (AUC) of tumor to parotid gland SIR (SIR_P), tumor to spinal cord SIR (SIR_C), and tumor to buccal subcutaneous fat SIR (SIR_F) for differentiating PAs and WTs was 0.922, 0.918, and 0.934, respectively. The sensitivity and specificity at an optimal SIR threshold were 86.3% and 91.2%, 80.0% and 97.1%, and 85.0% and 94.1%, respectively. The AUC of SIR_P, SIR_C, and SIR_F for distinguishing PAs from MTs was 0.793, 0.802, and 0.774, respectively. The sensitivity and specificity at an optimal SIR threshold was 86.3% and 61.8%, 80.0% and 73.5%, and 82.5% and 73.5%, respectively. The AUC of SIR_P, SIR_C, and SIR_F for distinguishing WTs from MTs was 0.716, 0.709, and 0.759, respectively. The sensitivity and specificity at an optimal SIR threshold were 61.8% and 82.4%, 55.9% and 82.4%, and 64.7% and 86.8%, respectively.

Conclusion

SIR_P, SIR_C, and SIR_F on T2-weighted MR images had high diagnostic efficiency for differentiating between PAs and WTs, while SIR_P and SIR_C for differentiating between PAs and MTs, and SIR_F for differentiating between WTs and MTs had relatively high diagnostic efficiency.

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.

Discriminating low-grade ductal carcinoma in situ (DCIS) from non-low-grade DCIS or DCIS upgraded to invasive carcinoma: effective texture features on ultrafast dynamic contrast-enhanced magnetic resonance imaging

PURPOSE

To investigate effective model composed of features from ultrafast dynamic contrast-enhanced magnetic resonance imaging (UF-MRI) for distinguishing low- from non-low-grade ductal carcinoma in situ (DCIS) lesions or DCIS lesions upgraded to invasive carcinoma (upgrade DCIS lesions) among lesions diagnosed as DCIS on pre-operative biopsy.

MATERIALS AND METHODS

Eighty-six consecutive women with 86 DCIS lesions diagnosed by biopsy underwent UF-MRI including pre- and 18 post-contrast ultrafast scans (temporal resolution of 3 s/phase). The last phase of UF-MRI was used to perform 3D segmentation. The time point at 6 s after the aorta started to enhance was used to obtain subtracted images. From the 3D segmentation and subtracted images, enhancement, shape, and texture features were calculated and compared between low- and non-low-grade or upgrade DCIS lesions using univariate analysis. Feature selection by least absolute shrinkage and selection operator (LASSO) algorithm and k-fold cross-validation were performed to evaluate the diagnostic performance.

RESULTS

Surgical specimens revealed 16 low-grade DCIS lesions, 37 non-low-grade lesions and 33 upgrade DCIS lesions. In univariate analysis, five shape and seven texture features were significantly different between low- and non-low-grade lesions or upgrade DCIS lesions, whereas enhancement features were not. The six features including surface/volume ratio, irregularity, diff variance, uniformity, sum average, and variance were selected using LASSO algorism and the mean area under the receiver operating characteristic curve for training and validation folds were 0.88 and 0.88, respectively.

CONCLUSION

The model with shape and texture features of UF-MRI could effectively distinguish low- from non-low-grade or upgrade DCIS lesions.

Preoperative prediction of clinically relevant postoperative pancreatic fistula after pancreaticoduodenectomy

OBJECTIVES

To develop a radiomics model and a combined model for preoperative prediction of clinically relevant postoperative pancreatic fistula (CR-POPF) in patients undergoing pancreaticoduodenectomy and to compare the predictive performance of the two models with the traditional Fistula Risk Score system.

METHODS

A total of 250 patients who underwent pancreaticoduodenectomy (PD) with preoperative computed tomography (CT) were divided into a training set (n = 175) and validation set (n = 75). The pancreatic area was automatically segmented on the portal venous phase CT images using a 3D U-Net segmentation model. A radiomics model was developed using radiomics features extracted from the volume of interest (VOI) and a combined model was developed using radiomics features, demographic information and radiological features. The FRS was also used to predict POPF. The predictive performance of the prediction models was assessed using receiver operating characteristic (ROC) curves, calibration curves and decision curve analysis (DCA).

RESULTS

Eleven and 18 features were extracted for the radiomics model and combined model, respectively. The combined model showed excellent predictive value, with an AUC of 0.871 (95 %CI 0.816,0.926) and 0.869 (95 %CI 0.779,0.958) in the training cohort and validation cohort, respectively. Calibration curves and DCA showed that the combined model outperformed the traditional FRS system and radiomics model.

CONCLUSION

The combined model exhibited excellent predictive performance and outperformed the traditional FRS system and radiomics model in the preoperative prediction of CR-POPF.