Texture Analysis of Fat-Suppressed T2-Weighted Magnetic Resonance Imaging and Use of Machine Learning to Discriminate Nasal and Paranasal Sinus Small Round Malignant Cell Tumors

Classification of nasal polyps and inverted papillomas using CT-based radiomics

OBJECTIVES

Nasal polyp (NP) and inverted papilloma (IP) are two common types of nasal masses. And their differentiation is essential for determining optimal surgical strategies and predicting outcomes. Thus, we aimed to develop several radiomic models to differentiate them based on computed tomography (CT)-extracted radiomic features.

METHODS

A total of 296 patients with nasal polyps or papillomas were enrolled in our study. Radiomics features were extracted from non-contrast CT images. For feature selection, three methods including Boruta, random forest, and correlation coefficient were used. We choose three models, namely SVM, naive Bayes, and XGBoost, to perform binary classification on the selected features. And the data was validated with tenfold cross-validation. Then, the performance was assessed by receiver operator characteristic (ROC) curve and related parameters.

RESULTS

In this study, the performance ability of the models was in the following order: XGBoost > SVM > Naive Bayes. And the XGBoost model showed excellent AUC performance at 0.922, 0.9078, 0.9184, and 0.9141 under four conditions (no feature selection, Boruta, random forest, and correlation coefficient).

CONCLUSIONS

We demonstrated that CT-based radiomics plays a crucial role in distinguishing IP from NP. It can provide added diagnostic value by distinguishing benign nasal lesions and reducing the need for invasive diagnostic procedures and may play a vital role in guiding personalized treatment strategies and developing optimal therapies.

CRITICAL RELEVANCE STATEMENT

Based on the extraction of radiomic features of tumor regions from non-contrast CT, optimized by radiomics to achieve non-invasive classification of IP and NP which provide support for respective therapy of IP and NP.

KEY POINTS

• CT images are commonly used to diagnose IP and NP. • Radiomics excels in feature extraction and analysis. • CT-based radiomics can be applied to distinguish IP from NP. • Use multiple feature selection methods and classifier models. • Derived from real clinical cases with abundant data.

Advances in Image-Based Artificial Intelligence in Otorhinolaryngology-Head and Neck Surgery: A Systematic Review

OBJECTIVE

To update the literature and provide a systematic review of image-based artificial intelligence (AI) applications in otolaryngology, highlight its advances, and propose future challenges.

DATA SOURCES

Web of Science, Embase, PubMed, and Cochrane Library.

REVIEW METHODS

Studies written in English, published between January 2020 and December 2022. Two independent authors screened the search results, extracted data, and assessed studies.

RESULTS

Overall, 686 studies were identified. After screening titles and abstracts, 325 full-text studies were assessed for eligibility, and 78 studies were included in this systematic review. The studies originated from 16 countries. Among these countries, the top 3 were China (n = 29), Korea (n = 8), the United States, and Japan (n = 7 each). The most common area was otology (n = 35), followed by rhinology (n = 20), pharyngology (n = 18), and head and neck surgery (n = 5). Most applications of AI in otology, rhinology, pharyngology, and head and neck surgery mainly included chronic otitis media (n = 9), nasal polyps (n = 4), laryngeal cancer (n = 12), and head and neck squamous cell carcinoma (n = 3), respectively. The overall performance of AI in accuracy, the area under the curve, sensitivity, and specificity were 88.39 ± 9.78%, 91.91 ± 6.70%, 86.93 ± 11.59%, and 88.62 ± 14.03%, respectively.

CONCLUSION

This state-of-the-art review aimed to highlight the increasing applications of image-based AI in otorhinolaryngology head and neck surgery. The following steps will entail multicentre collaboration to ensure data reliability, ongoing optimization of AI algorithms, and integration into real-world clinical practice. Future studies should consider 3-dimensional (3D)-based AI, such as 3D surgical AI.

Radiomics analysis based on CT for the prediction of pulmonary metastases in ewing sarcoma

OBJECTIVES

This study aimed to develop and validate radiomics models on the basis of computed tomography (CT) and clinical features for the prediction of pulmonary metastases (MT) in patients with Ewing sarcoma (ES) within 2 years after diagnosis.

MATERIALS AND METHODS

A total of 143 patients with a histopathological diagnosis of ES were enrolled in this study (114 in the training cohort and 29 in the validation cohort). The regions of interest (ROIs) were handcrafted along the boundary of each tumor on the CT and CT-enhanced (CTE) images, and radiomic features were extracted. Six different models were built, including three radiomics models (CT, CTE and ComB models) and three clinical-radiomics models (CT_clinical, CTE_clinical and ComB_clinical models). The area under the receiver operating characteristic curve (AUC), and accuracy were calculated to evaluate the different models, and DeLong test was used to compare the AUCs of the models.

RESULTS

Among the clinical risk factors, the therapeutic method had significant differences between the MT and non-MT groups (P＜0.01). The six models performed well in predicting pulmonary metastases in patients with ES, and the ComB model (AUC: 0.866/0.852 in training/validation cohort) achieved the highest AUC among the six models. However, no statistically significant difference was observed between the AUC of the models.

CONCLUSIONS

In patients with ES, clinical-radiomics model created using radiomics signature and clinical features provided favorable ability and accuracy for pulmonary metastases prediction.

Deep learning-enhanced radiomics for histologic classification and grade stratification of stage IA lung adenocarcinoma: a multicenter study

Background

Preoperative prediction models for histologic subtype and grade of stage IA lung adenocarcinoma (LUAD) according to the update of the WHO Classification of Tumors of the Lung in 2021 and the 2020 new grade system are yet to be explored. We aim to develop the noninvasive pathology and grade evaluation approach for patients with stage IA LUAD via CT-based radiomics approach and evaluate their performance in clinical practice.

Methods

Chest CT scans were retrospectively collected from patients who were diagnosed with stage IA LUAD and underwent complete resection at two hospitals. A deep learning segmentation algorithm was first applied to assist lesion delineation. Expansion strategies such as bounding-box annotations were further applied. Radiomics features were then extracted and selected followed by radiomics modeling based on four classic machine learning algorithms for histologic subtype classification and grade stratification. The area under the receiver operating characteristic curve (AUC) was used to evaluate model performance.

Results

The study included 294 and 145 patients with stage IA LUAD from two hospitals for radiomics analysis, respectively. For classification of four histological subtypes, multilayer perceptron (MLP) algorithm presented no annotation strategy preference and achieved the average AUC of 0.855, 0.922, and 0.720 on internal, independent, and external test sets with 1-pixel expansion annotation. Bounding-box annotation strategy also enabled MLP an acceptable and stable accuracy among test sets. Meanwhile, logistic regression was selected for grade stratification and achieved the average AUC of 0.928, 0.837, and 0.748 on internal, independent, and external test sets with optimal annotation strategies.

Conclusions

DL-enhanced radiomics models had great potential to predict the fine histological subtypes and grades of early-stage LUADs based on CT images, which might serve as a promising noninvasive approach for the diagnosis and management of early LUADs.

Principal component analysis of texture features for grading of meningioma: not effective from the peritumoral area but effective from the tumor area

PURPOSE

To investigate whether texture features from tumor and peritumoral areas based on sequence combinations can differentiate between low- and non-low-grade meningiomas.

METHODS

Consecutive patients diagnosed with meningioma by surgery (77 low-grade and 28 non-low-grade meningiomas) underwent preoperative magnetic resonance imaging including T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and contrast-enhanced T1WI (CE-T1WI). Manual segmentation of the tumor area was performed to extract texture features. Segmentation of the peritumoral area was performed for peritumoral high-signal intensity (PHSI) on T2WI. Principal component analysis was performed to fuse the texture features to principal components (PCs), and PCs of each sequence of the tumor and peritumoral areas were compared between low- and non-low-grade meningiomas. Only PCs with statistical significance were used for the model construction using a support vector machine algorithm. k-fold cross-validation with receiver operating characteristic curve analysis was used to evaluate diagnostic performance.

RESULTS

Two, one, and three PCs of T1WI, apparent diffusion coefficient (ADC), and CE-T1WI, respectively, for the tumor area, were significantly different between low- and non-low-grade meningiomas, while PCs of T2WI for the tumor area and PCs for the peritumoral area were not. No significant differences were observed in PHSI. Among models of sequence combination, the model with PCs of ADC and CE-T1WI for the tumor area showed the highest area under the curve (0.84).

CONCLUSION

The model with PCs of ADC and CE-T1WI for the tumor area showed the highest diagnostic performance for differentiating between low- and non-low-grade meningiomas. Neither PHSI nor PCs in the peritumoral area showed added value.

Collinearity and Dimensionality Reduction in Radiomics: Effect of Preprocessing Parameters in Hypertrophic Cardiomyopathy Magnetic Resonance T1 and T2 Mapping

Radiomics and artificial intelligence have the potential to become a valuable tool in clinical applications. Frequently, radiomic analyses through machine learning methods present issues caused by high dimensionality and multicollinearity, and redundant radiomic features are usually removed based on correlation analysis. We assessed the effect of preprocessing-in terms of voxel size resampling, discretization, and filtering-on correlation-based dimensionality reduction in radiomic features from cardiac T1 and T2 maps of patients with hypertrophic cardiomyopathy. For different combinations of preprocessing parameters, we performed a dimensionality reduction of radiomic features based on either Pearson's or Spearman's correlation coefficient, followed by the computation of the stability index. With varying resampling voxel size and discretization bin width, for both T1 and T2 maps, Pearson's and Spearman's dimensionality reduction produced a slightly different percentage of remaining radiomic features, with a relatively high stability index. For different filters, the remaining features' stability was instead relatively low. Overall, the percentage of eliminated radiomic features through correlation-based dimensionality reduction was more dependent on resampling voxel size and discretization bin width for textural features than for shape or first-order features. Notably, correlation-based dimensionality reduction was less sensitive to preprocessing when considering radiomic features from T2 compared with T1 maps.

Combination of pre-treatment dynamic [18F]FET PET radiomics and conventional clinical parameters for the survival stratification in patients with IDH-wildtype glioblastoma

PURPOSE

The aim of this study was to build and evaluate a prediction model which incorporates clinical parameters and radiomic features extracted from static as well as dynamic [18F]FET PET for the survival stratification in patients with newly diagnosed IDH-wildtype glioblastoma.

METHODS

A total of 141 patients with newly diagnosed IDH-wildtype glioblastoma and dynamic [18F]FET PET prior to surgical intervention were included. Patients with a survival time ≤ 12 months were classified as short-term survivors. First order, shape, and texture radiomic features were extracted from pre-treatment static (tumor-to-background ratio; TBR) and dynamic (time-to-peak; TTP) images, respectively, and randomly divided into a training (n = 99) and a testing cohort (n = 42). After feature normalization, recursive feature elimination was applied for feature selection using 5-fold cross-validation on the training cohort, and a machine learning model was constructed to compare radiomic models and combined clinical-radiomic models with selected radiomic features and clinical parameters. The area under the ROC curve (AUC), accuracy, sensitivity, specificity, and positive and negative predictive values were calculated to assess the predictive performance for identifying short-term survivors in both the training and testing cohort.

RESULTS

A combined clinical-radiomic model comprising six clinical parameters and six selected dynamic radiomic features achieved highest predictability of short-term survival with an AUC of 0.74 (95% confidence interval, 0.60-0.88) in the independent testing cohort.

CONCLUSIONS

This study successfully built and evaluated prediction models using [18F]FET PET-based radiomic features and clinical parameters for the individualized assessment of short-term survival in patients with a newly diagnosed IDH-wildtype glioblastoma. The combination of both clinical parameters and dynamic [18F]FET PET-based radiomic features reached highest accuracy in identifying patients at risk. Although the achieved accuracy level remained moderate, our data shows that the integration of dynamic [18F]FET PET radiomic data into clinical prediction models may improve patient stratification beyond established prognostic markers.

Predicting IDH Mutation Status in Low-Grade Gliomas Based on Optimal Radiomic Features Combined with Multi-Sequence Magnetic Resonance Imaging

The IDH somatic mutation status is an important basis for the diagnosis and classification of gliomas. We proposed a "6-Step" general radiomics model to noninvasively predict the IDH mutation status by simultaneously tuning combined multi-sequence MRI and optimizing the full radiomics processing pipeline. Radiomic features (n = 3776) were extracted from multi-sequence MRI (T1, T2, FLAIR, and T1Gd) in low-grade gliomas (LGGs), and a total of 45,360 radiomics pipeline were investigated according to different settings. The predictive ability of the general radiomics model was evaluated with regards to accuracy, stability, and efficiency. Based on numerous experiments, we finally reached an optimal pipeline for classifying IDH mutation status, namely the T2+FLAIR combined multi-sequence with the wavelet image filter, mean data normalization, PCC dimension reduction, RFE feature selection, and SVM classifier. The mean and standard deviation of AUC, accuracy, sensitivity, and specificity were 0.873 ± 0.05, 0.876 ± 0.09, 0.875 ± 0.11, and 0.877 ± 0.15, respectively. Furthermore, 14 radiomic features that best distinguished the IDH mutation status of the T2+FLAIR multi-sequence were analyzed, and the gray level co-occurrence matrix (GLCM) features were shown to be of high importance. Apart from the promising prediction of the molecular subtypes, this study also provided a general tool for radiomics investigation.

Differentiating between cardiac amyloidosis and hypertrophic cardiomyopathy on non-contrast cine-magnetic resonance images using machine learning-based radiomics

Objectives

This study aimed to determine whether texture analysis (TA) and machine learning-based classifications can be applied in differential diagnosis of cardiac amyloidosis (CA) and hypertrophic cardiomyopathy (HCM) using non-contrast cine cardiac magnetic resonance (CMR) images.

Methods

In this institutional review board-approved study, we consecutively enrolled 167 patients with CA (n = 85), HCM (n = 82), and 84 patients with normal CMR served as controls. All cases were randomized into training [119 patients (70%)] and validation [48 patients (30%)] groups. A total of 275 texture features were extracted from cine images. Based on regression analysis with the least absolute shrinkage and selection operator (LASSO), nine machine learning models were established and their diagnostic performance determined.

Results

Nineteen radiomics texture features derived from cine images were used to differentiate CA and HCM. In the validation cohort, the support vector machine (SVM), which had an accuracy of 0.85, showed the best performance (MCC = 0.637). Gray level non-uniformity (GLevNonU) was the single most effective feature. The combined model of radiomics texture features and conventional MR metrics had superior discriminatory performance (AUC = 0.89) over conventional MR metrics model (AUC = 0.79). Moreover, results showed that GLevNonU levels in HCM patients were significantly higher compared with levels in CA patients and control groups (P < 0.001). A cut-off of GLevNonU ≥ 25 was shown to differentiate between CA and HCM patients, with an area under the curve (AUC) of 0.86 (CI:0.804–0.920). Multiple comparisons tests showed that GLevNonU was significantly greater in LGE+, relative to LGE-patient groups (CA+ vs. CA- and HCM+ vs. HCM-, P = 0.01, 0.001, respectively).

Conclusion

Machine learning-based classifiers can accurately differentiate between CA and HCM on non-contrast cine images. The radiomics-MR combined model can be used to improve the discriminatory performance. TA may be used to assess myocardial microstructure changes that occur during different stages of cardiomyopathies.