Quantitative CT texture and shape analysis: can it differentiate benign and malignant mediastinal lymph nodes in patients with primary lung cancer?

CT texture analysis for differentiating between peritoneal carcinomatosis and peritoneal tuberculosis: a cross-sectional study

PURPOSE

Peritoneal carcinomatosis (PC) and peritoneal tuberculosis (PTB) have similar clinical and radiologic imaging features, which make it very difficult to differentiate between the two entities clinically. Our aim was to determine if the CT textural parameters of omental lesions among patients with PC were different from those with PTB.

METHODS

All patients who had undergone omental biopsy at our institution from January 2010 to December 2018 and had a tissue diagnosis of PC or PTB were eligible for inclusion. Patients who did not have a contrast-enhanced CT abdomen within one month of the omental biopsy were excluded. A region of interest (ROI) was manually drawn over omental lesions and radiomic features were extracted using open-source LIFEx software. Statistical analysis was performed to compare mean differences in CT texture parameters between the PC and PTB groups.

RESULTS

A total of 66 patients were included in the study of which 38 and 28 had PC and PTB, respectively. Omental lesions in patients with PC had higher mean radiodensity (mean difference: +32.4; p = 0.001), higher mean entropy (mean difference: +0.11; p < 0.001), and lower mean energy (mean difference: -0.024; p = 0.001) compared to those in PTB. Additionally, omental lesions in the PC group had lower gray-level co-occurrence matrix (GLCM) homogeneity (mean difference: -0.073; p < 0.001) and higher GLCM dissimilarity (mean difference: +0.480; p < 0.001) as compared to the PTB group.

CONCLUSION

CT texture parameters of omental lesions differed significantly between patients with PTB and those with PC, which may help clinicians in differentiating between the two entities.

Research in the application of artificial intelligence to lung cancer diagnosis

The morbidity and mortality rates in lung cancer are high worldwide. Early diagnosis and personalized treatment are important to manage this public health issue. In recent years, artificial intelligence (AI) has played increasingly important roles in early screening, auxiliary diagnosis, and prognostic assessment. AI uses algorithms to extract quantitative feature information from high-volume and high-latitude data and learn existing data to predict disease outcomes. In this review, we describe the current uses of AI in lung cancer-focused pathomics, imageomics, and genomics applications.

Preoperative CT radiomics of esophageal squamous cell carcinoma and lymph node to predict nodal disease with a high diagnostic capability

PURPOSE

To develop CT radiomics models of resectable esophageal squamous cell carcinoma (ESCC) and lymph node (LN) to preoperatively identify LN+.

MATERIALS AND METHODS

299 consecutive patients with ESCC were enrolled in the study, 140 of whom were LN+ and 159 were LN-. Of the 299 patients, 249 (from the same hospital) were randomly divided into a training cohort (n = 174) and a test cohort (n = 75). The remaining 50 patients, from a second hospital, were assigned to an external validation cohort. In the training cohort, preoperative contrast-enhanced CT radiomics features of ESCC and LN were extracted, then integrated with clinical features to develop three models: ESCC, LN and combined. The performance of these models was assessed using area under receiver operating characteristic curve (AUC), and F-1 score, which were validated in both the test cohort and external validation cohort.

RESULTS

An ESCC model was developed for the training cohort utilizing the 8 tumor radiomics features, and an LN model was constructed using 9 nodal radiomics features. A combined model was constructed using both ESCC and LN extracted features, in addition to cT stage and LN+ distribution. This combined model had the highest predictive ability among the three models in the training cohort (AUC = 0.948, F1-score = 0.878). The predictive ability was validated in both the test and external validation cohorts (AUC = 0.885 and 0.867, F1-score = 0.816 and 0.773, respectively).

CONCLUSION

To preoperatively determine LN+, the combined model is superior to models of ESCC and LN alone.

Sphericity of lymph nodes using 3D-CT predicts metastasis in lung cancer patients

BACKGROUND

The presence of mediastinal lymph node metastasis is important because it is related to the treatment and prognosis of lung cancer. Although prevalently used, evaluation of lymph nodes is not always reliable. We introduced sphericity as a criterion for evaluating morphologic differences between metastatic and nonmetastatic nodes.

METHODS

We reviewed the cases of 66 patients with N2 disease and of 68 patients with N0-1 disease who underwent lobectomy with mediastinal dissection between January 2012 and December 2021. The sphericity of the dissected station lymph nodes, which represents how close the node is to being a true sphere, was evaluated along with the diameter and volume. Each parameter was obtained and evaluated for ability to predict metastasis.

RESULTS

Metastatic lymph nodes had a larger short-axis diameter (average: 8.2 mm vs. 5.4 mm, p < 0.001) and sphericity (average: 0.72 vs. 0.60, p < 0.001) than those of nonmetastatic lymph nodes. Short-axis diameter ≥ 6 mm and sphericity ≥ 0.60 identified metastasis with 76.2% sensitivity and 70.2% specificity (AUC = 0.78, p < 0.001) and 92.1% sensitivity and 53.9% specificity (AUC = 0.78, p < 0.001), respectively. For lymph nodes with a short-axis diameter ≥ 5 mm, sphericity ≥ 0.60 identified metastasis with 84.1% sensitivity and 89.3% specificity.

CONCLUSION

By using 3D-CT analysis to examine sphericity, we showed that metastatic lymph nodes became spherical. Our method for predicting lymph node metastasis based on sphericity of lymph nodes with a short-axis diameter ≥ 5 mm could do so with higher sensitivity than the conventional method, and with acceptable specificity.

Application of radiomics in diagnosis and treatment of lung cancer

Radiomics has become a research field that involves the process of converting standard nursing images into quantitative image data, which can be combined with other data sources and subsequently analyzed using traditional biostatistics or artificial intelligence (Al) methods. Due to the capture of biological and pathophysiological information by radiomics features, these quantitative radiomics features have been proven to provide fast and accurate non-invasive biomarkers for lung cancer risk prediction, diagnosis, prognosis, treatment response monitoring, and tumor biology. In this review, radiomics has been emphasized and discussed in lung cancer research, including advantages, challenges, and drawbacks.

Altered Thyroid Feedback Loop in Klinefelter Syndrome: From Infancy Through the Transition to Adulthood

CONTEXT

It has been claimed that thyroid dysfunction contributes to the spectrum of Klinefelter syndrome (KS); however, studies are scarce.

OBJECTIVE

In a retrospective longitudinal study, we aimed at describing the hypothalamic-pituitary-thyroid (HPT) axis and thyroid ultrasonographic (US) appearance in patients with KS throughout the life span.

METHODS

A total of 254 patients with KS (25.9 ± 16.1 years) were classified according to their pubertal and gonadal status and compared with different groups of non-KS age-matched individuals with normal thyroid function, treated and untreated hypogonadism, or chronic lymphocytic thyroiditis. We assessed serum thyroid hormone levels, antithyroid antibodies, US thyroid parameters, and in vitro pituitary type 2 deiodinase (D2) expression and activity.

RESULTS

Thyroid autoimmunity was more prevalent among individuals with KS at all ages, although the antibody (Ab)-negative vs Ab-positive cohorts were not different. Signs of thyroid dysfunction (reduced volume, lower echogenicity, and increased inhomogeneity) were more prominent in KS than in euthyroid controls. Free thyroid hormones were lower in prepubertal, pubertal, and adult patients with KS, whereas thyrotropin values were lower only in adults. Peripheral sensitivity to thyroid hormones was unaltered in KS, suggesting a dysfunctional HPT axis. Testosterone (T) was the only factor associated with thyroid function and appearance. In vitro testing demonstrated an inhibitory effect of T on pituitary D2 expression and activity, supporting enhanced central sensing of circulating thyroid hormones in hypogonadism.

CONCLUSION

From infancy through adulthood, KS is characterized by increased morphofunctional abnormalities of the thyroid gland, combined with a central feedback dysregulation sustained by the effect of hypogonadism on D2 deiodinase.

Predicting response to CCRT for esophageal squamous carcinoma by a radiomics-clinical SHAP model

BACKGROUND

Radical concurrent chemoradiotherapy (CCRT) is frequently used as the first-line treatment for patients with locally advanced esophageal cancer. Unfortunately, some patients respond poorly. To predict response to radical concurrent chemoradiotherapy in pre-treatment patients with esophageal squamous carcinoma (ESCC), and compare the predicting efficacies of radiomics features of primary tumor with or without regional lymph nodes, we developed a radiomics-clinical model based on the positioning CT images. Finally, SHapley Additive exPlanation (SHAP) was used to explain the models.

METHODS

This retrospective study enrolled 105 patients with medically inoperable and/or unresectable ESCC who underwent radical concurrent chemoradiotherapy (CCRT) between October 2018 and May 2023. Patients were classified into responder and non-responder groups with RECIST standards. The 11 recently admitted patients were chosen as the validation set, previously admitted patients were randomly split into the training set (n = 70) and the testing set (n = 24). Primary tumor site (GTV), the primary tumor and the uninvolved lymph nodes at risk of microscopic disease (CTV) were identified as Regions of Interests (ROIs). 1762 radiomics features from GTV and CTV were respectively extracted and then filtered by statistical differential analysis and Least Absolute Shrinkage and Selection Operator (LASSO). The filtered radiomics features combined with 13 clinical features were further filtered with Mutual Information (MI) algorithm. Based on the filtered features, we developed five models (Clinical Model, GTV Model, GTV-Clinical Model, CTV Model, and CTV-Clinical Model) using the random forest algorithm and evaluated for their accuracy, precision, recall, F1-Score and AUC. Finally, SHAP algorithm was adopted for model interpretation to achieve transparency and utilizability.

RESULTS

The GTV-Clinical model achieves an AUC of 0.82 with a 95% confidence interval (CI) of 0.76-0.99 on testing set and an AUC of 0.97 with a 95% confidence interval (CI) of 0.84-1.0 on validation set, which are significantly higher than those of other models in predicting ESCC response to CCRT. The SHAP force map provides an integrated view of the impact of each feature on individual patients, while the SHAP summary plots indicate that radiomics features have a greater influence on model prediction than clinical factors in our model.

CONCLUSION

GTV-Clinical model based on texture features and the maximum diameter of lesion (MDL) may assist clinicians in pre-treatment predicting ESCC response to CCRT.

Diagnostic Value of the Texture Analysis Parameters of Retroperitoneal Residual Masses on Computed Tomographic Scan after Chemotherapy in Non-Seminomatous Germ Cell Tumors

After chemotherapy, patients with non-seminomatous germ cell tumors (NSGCTs) with residual masses >1 cm on computed tomography (CT) undergo surgery. However, in approximately 50% of cases, these masses only consist of necrosis/fibrosis. We aimed to develop a radiomics score to predict the malignant character of residual masses to avoid surgical overtreatment. Patients with NSGCTs who underwent surgery for residual masses between September 2007 and July 2020 were retrospectively identified from a unicenter database. Residual masses were delineated on post-chemotherapy contrast-enhanced CT scans. Tumor textures were obtained using the free software LifeX. We constructed a radiomics score using a penalized logistic regression model in a training dataset, and evaluated its performance on a test dataset. We included 76 patients, with 149 residual masses; 97 masses were malignant (65%). In the training dataset (n = 99 residual masses), the best model (ELASTIC-NET) led to a radiomics score based on eight texture features. In the test dataset, the area under the curve (AUC), sensibility, and specificity of this model were respectively estimated at 0.82 (95%CI, 0.69-0.95), 90.6% (75.0-98.0), and 61.1% (35.7-82.7). Our radiomics score may help in the prediction of the malignant nature of residual post-chemotherapy masses in NSGCTs before surgery, and thus limit overtreatment. However, these results are insufficient to simply select patients for surgery.

Evaluation of Purified Protein Derivative Changes Based on Mediastinal Lymph Node Density

Background: The present study evaluated purified protein derivative (PPD) changes based on mediastinal lymph node density. Methods: This cross-sectional observational study was performed on 130 patients who were referred to Valiasr and Amir Al-Momenin Hospitals in Arak, Iran for a CT scan for non-infectious and non-tumor reasons. The gender of the patients was recorded, and they then underwent non-contrast CT, and their mediastinal lymph node density was measured and recorded based on the Hounsfield units. Patients were evaluated for changes in the tuberculin test. The induration diameter obtained from the tuberculin test was recorded for each individual. Data analysis was then carried out using SPSS software ver. 20. Results: There was a positive correlation between mediastinal lymph node density and tuberculin test induration diameter, so larger induration diameter in the tuberculin test results in increasing lymph node density result (r = 0.429, P < 0.001). There was a negative correlation between mediastinal lymph node density and age, i.e., mediastinal lymph node density decreased with increasing age (P < 0.001, r = -0.616). Lymph node density was higher in men than in women (P = 0.022). Conclusions: There is a positive correlation between the mediastinal lymph node density and the tuberculin test induration diameter, and the tuberculin test induration diameter increases with increasing lymph node density. There is a negative correlation between the mediastinal lymph node density and age, i.e., the mediastinal lymph node density decreases with increasing age. Lymph node density was also higher in men than in women. Therefore, the results can help ensure an earlier diagnosis of pulmonary tuberculosis, and measuring the mediastinal lymph node density is recommended.

Diagnostic Accuracy of Slow-Capillary Endobronchial Ultrasound Needle Aspiration in Determining PD-L1 Expression in Non-Small Cell Lung Cancer

INTRODUCTION

The role of EBUS-TBNA in the diagnosis and staging of lung cancer is well established. EBUS-TBNA can be performed using different aspiration techniques. The most common aspiration technique is known as "suction". One alternative to the suction technique is the slow-pull capillary aspiration. To the best of our knowledge, no studies have assessed the diagnostic yield of slow-pull capillary EBUS-TBNA in PD-L1 amplification assessment in NSCLC. Herein, we conducted a single-centre retrospective study to establish the diagnostic yield of slow-pull capillary EBUS-TBNA in terms of PD-L1 in patients with NSCLC and hilar/mediastinal lymphadenopathies subsequent to NSCLC.

MATERIALS AND METHODS

Patients with hilar and/or mediastinal lymph node (LN) NSCLC metastasis, diagnosed by EBUS-TBNA between January 2021 and April 2022 at Pulmonology Unit of "Ospedali Riuniti di Ancona" (Ancona, Italy) were enrolled. We evaluated patient characteristics, including demographic information, CT scan/ FDG-PET features and final histological diagnoses, including PD-L1 assessment.

RESULTS

A total of 174 patients underwent EBUS-TBNA for diagnosis of hilar/mediastinal lymphadenopathies between January 2021 and April 2022 in the Interventional Pulmonology Unit of the "Ospedali Riuniti di Ancona". Slow-pull capillary aspiration was adopted in 60 patients (34.5%), and in 30/60 patients (50.0%) NSCLC was diagnosed. EBUS-TBNA with slow-pull capillary aspiration provided adequate sampling for molecular biology and PD-L1 testing in 96.7% of patients (29/30); in 15/29 (51.7%) samples with more than 1000 viable cells/HPF were identified, whereas in 14/29 (48.3%) samples contained 101-1000 viable cells/HPF.

CONCLUSION

These retrospective study shows that slow-pull capillary aspiration carries an excellent diagnostic accuracy, almost equal to that one reported in literature, supporting its use in EBUS-TBNA for PD-L1 testing in NSCLC.

Integrating Preoperative Computed Tomography and Clinical Factors for Lymph Node Metastasis Prediction in Esophageal Squamous Cell Carcinoma by Feature-Wise Attentional Graph Neural Network

PURPOSE

This study aimed to propose a regional lymph node (LN) metastasis prediction model for patients with esophageal squamous cell carcinoma (ESCC) that can learn and adaptively integrate preoperative computed tomography (CT) image features and nonimaging clinical parameters.

METHODS AND MATERIALS

Contrast-enhanced CT scans taken 2 weeks before surgery and 20 clinical factors, including general, pathologic, hematological, and diagnostic information, were collected from 357 patients with ESCC between October 2013 and November 2018. There were 999 regional LNs (857 negative, 142 positive) with pathologically confirmed status after surgery. All LNs were randomly divided into a training set (n = 738) and a validation set (n = 261) for testing. The feature-wise attentional graph neural network (FAGNN) was composed of (1) deep image feature extraction by the encoder of 3-dimensional UNet and high-level nonimaging factor representation by the clinical parameter encoder; (2) a feature-wise attention module for feature embedding with learnable adaptive weights; and (3) a graph attention layer to integrate the embedded features for final LN level metastasis prediction.

RESULTS

Among the 4 models we constructed, FAGNN using both CT and clinical parameters as input is the model with the best performance, and the area under the curve (AUC) reaches 0.872, which is better than manual CT diagnosis method, multivariable model using CT only (AUC = 0.797), multivariable model with combined CT and clinical parameters (AUC = 0.846), and our FAGNN using CT only (AUC = 0.853).

CONCLUSIONS

Our adaptive integration model improved the metastatic LN prediction performance based on CT and clinical parameters. Our model has the potential to foster effective fusion of multisourced parameters and to support early prognosis and personalized surgery or radiation therapy planning in patients with ESCC.

Artificial intelligence fusion for predicting survival of rectal cancer patients using immunohistochemical expression of Ras homolog family member B in biopsy

Aim

The process of biomarker discovery is being accelerated with the application of artificial intelligence (AI), including machine learning. Biomarkers of diseases are useful because they are indicators of pathogenesis or measures of responses to therapeutic treatments, and therefore, play a key role in new drug development. Proteins are among the candidates for biomarkers of rectal cancer, which need to be explored using state-of-the-art AI to be utilized for prediction, prognosis, and therapeutic treatment. This paper aims to investigate the predictive power of Ras homolog family member B (RhoB) protein in rectal cancer.

Methods

This study introduces the integration of pretrained convolutional neural networks and support vector machines (SVMs) for classifying biopsy samples of immunohistochemical expression of protein RhoB in rectal-cancer patients to validate its biologic measure in biopsy. Features of the immunohistochemical expression images were extracted by the pretrained networks and used for binary classification by the SVMs into two groups of less and more than 5-year survival rates.

Results

The fusion of neural search architecture network (NASNet)-Large for deep-layer feature extraction and classifier using SVMs provided the best average classification performance with a total accuracy = 85%, prediction of survival rate of more than 5 years = 90%, and prediction of survival rate of less than 5 years = 75%.

Conclusions

The finding obtained from the use of AI reported in this study suggest that RhoB expression on rectal-cancer biopsy can be potentially used as a biomarker for predicting survival outcomes in rectal-cancer patients, which can be informative for clinical decision making if the patient would be recommended for preoperative therapy.

A novel nomogram model combining CT texture features and urine energy metabolism to differentiate single benign from malignant pulmonary nodule

Objective

To investigate a novel diagnostic model for benign and malignant pulmonary nodule diagnosis based on radiomic and clinical features, including urine energy metabolism index.

Methods

A total of 107 pulmonary nodules were prospectively recruited and pathologically confirmed as malignant in 86 cases and benign in 21 cases. A chest CT scan and urine energy metabolism test were performed in all cases. A nomogram model was established in combination with radiomic and clinical features, including urine energy metabolism levels. The nomogram model was compared with the radiomic model and the clinical feature model alone to test its diagnostic validity, and receiver operating characteristic (ROC) curves were plotted to assess diagnostic validity.

Results

The nomogram was established using a logistic regression algorithm to combine radiomic features and clinical characteristics including urine energy metabolism results. The predictive performance of the nomogram was evaluated using the area under the ROC and calibration curve, which showed the best performance, area under the curve (AUC) = 0.982, 95% CI = 0.940-1.000, compared to clinical and radiomic models in the testing cohort. The clinical benefit of the model was assessed using the decision curve analysis (DCA) and using the nomogram for benign and malignant pulmonary nodules, and preoperative prediction of benign and malignant pulmonary nodules using nomograms showed better clinical benefit.

Conclusion

This study shows that a coupled model combining CT imaging features and clinical features (including urine energy metabolism) in combination with the nomogram model has higher diagnostic performance than the radiomic and clinical models alone, suggesting that the combination of both methods is more advantageous in identifying benign and malignant pulmonary nodules.

Contribution of F-18 fluorodeoxyglucose PET/CT and contrast-enhanced thoracic CT texture analyses to the differentiation of benign and malignant mediastinal lymph nodes

BACKGROUND

Texture analysis and machine learning methods are useful in distinguishing between benign and malignant tissues.

PURPOSE

To discriminate benign from malignant or metastatic mediastinal lymph nodes using F-18 fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) and contrast-enhanced computed tomography (CT) texture analyses with machine learning and determine lung cancer subtypes based on the analysis of lymph nodes.

MATERIAL AND METHODS

Suitable texture features were entered into the algorithms. Features that statistically significantly differed between the lymph nodes with small cell lung cancer (SCLC), adenocarcinoma (ADC), and squamous cell carcinoma (SCC) were determined.

RESULTS

The most successful algorithms were decision tree with the sensitivity, specificity, and area under the curve (AUC) values of 89%, 50%, and 0.692, respectively, and naive Bayes (NB) with the sensitivity, specificity, and AUC values of 50%, 81%, and 0.756, respectively, for PET/CT, and NB with the sensitivity, specificity, and AUC values of 10%, 96%, and 0.515, respectively, and logistic regression with the sensitivity, specificity, and AUC values of 21%, 83%, and 0.631, respectively, for CT. In total, 13 features were able to differentiate SCLC and ADC, two features SCLC and SCC, and 33 features ADC and SCC lymph node metastases in PET/CT. One feature differed between SCLC and ADC metastases in CT.

CONCLUSION

Texture analysis is beneficial to discriminate between benign and malignant lymph nodes and differentiate lung cancer subtypes based on the analysis of lymph nodes.

Deep learning combined with radiomics for the classification of enlarged cervical lymph nodes

PURPOSE

To investigate the application of deep learning combined with traditional radiomics methods for classifying enlarged cervical lymph nodes.

METHODS

The clinical and computed tomography (CT) imaging data of 276 patients with enlarged cervical lymph nodes (150 with lymph-node metastasis, 65 with lymphoma, and 61 with benign lymphadenopathy) who were treated at the hospital from January 2015 to January 2021 were retrospectively analysed. The patients were randomly divided into a training group and a test group at a ratio of 8:2. The radiomics features were extracted using one-by-one convolution and neural network activation, filtered with the least absolute shrinkage and selection operator (LASSO) model, and used to construct a discrimination model with PyTorch. Then, the performance of the model was compared with the radiologists' diagnostic performance. The neural network model was evaluated using the area under the receiver-operator characteristic curve (AUC), and the accuracy, sensitivity, and specificity were analysed.

RESULTS

A total of 102 features, comprising five traditional radiomic features and 97 deep learning features, were selected with LASSO and used to construct a discrimination model, which achieved a total accuracy of 87.50%. The AUC value, specificity, and sensitivity were, respectively, 0.92, 92.30%, and 90.00% for metastatic lymph nodes, 0.87, 95.45%, and 83.33% for benign lymphadenopathy, and 0.88, 90.47%, and 85.71% for lymphoma. The accuracies of the radiologists' diagnoses were 62.68% and 62.68%. The diagnostic performance of the model was significantly different from that of the radiologists (p < 0.05).

CONCLUSION

CT-based deep learning combined with the traditional radiomics methods has a high diagnostic value for the classification of cervical enlarged lymph nodes.

Radiomics analysis for differentiating of cervical lymphadenopathy between cancer of unknown primary and malignant lymphoma on unenhanced computed tomography

To investigate the usefulness of texture analysis to discriminate between cervical lymph node (LN) metastasis from cancer of unknown primary (CUP) and cervical LN involvement of malignant lymphoma (ML) on unenhanced computed tomography (CT). Cervical LN metastases in 17 patients with CUP and cervical LN involvement in 17 patients with ML were assessed by ¹⁸F-FDG PET/CT. The texture features were obtained in the total cross-sectional area (CSA) of the targeted LN, following the contour of the largest cervical LN on unenhanced CT. Values for the max standardized uptake value (SUVmax) and the mean SUV value (SUVmean), and 34 texture features were compared using a Mann-Whitney U test. The diagnostic accuracy and area under the curve (AUC) of the combination of the texture features were evaluated by support vector machine (SVM) with nested cross-validation. The SUVmax and SUVmean did not differ significantly between cervical LN metastases from CUP and cervical LN involvement from ML. However, significant differences of 9 texture features of the total CSA were observed (p = 0.001 - 0.05). The best AUC value of 0.851 for the texture feature of the total CSA were obtained from the correlation in the gray-level co-occurrence matrix features. SVM had the best AUC and diagnostic accuracy of 0.930 and 84.8%. Radiomics analysis appears to be useful for differentiating cervical LN metastasis from CUP and cervical LN involvement of ML on unenhanced CT.

Computed Tomography-Based Texture Features for the Risk Stratification of Portal Hypertension and Prediction of Survival in Patients With Cirrhosis: A Preliminary Study

Objective

Clinical evidence suggests that the risk stratification of portal hypertension (PH) plays a vital role in disease progression and patient outcomes. However, the gold standard for stratifying PH [portal vein pressure (PVP) measurement] is invasive and therefore not suitable for routine clinical practice. This study is aimed to stratify PH and predict patient outcomes using liver or spleen texture features based on computed tomography (CT) images non-invasively.

Methods

A total of 114 patients with PH were included in this retrospective study and divided into high-risk PH (PVP ≥ 20 mm Hg, n = 57) or low-risk PH (PVP &lt; 20 mm Hg, n = 57), a progression-free survival (PFS) group (n = 14), or a non-PFS group (n = 51) based on patients with rebleeding or death after the transjugular intrahepatic portosystemic shunt (TIPS) procedure. All patients underwent contrast-enhanced CT, and the laboratory data were recorded. Texture features of the liver or spleen were obtained by a manual drawing of the region of interest (ROI) and were performed in the portal venous phase. Logistic regression analysis was applied to select the significant features related to high-risk PH, and PFS-related features were determined by the Cox proportional hazards model and Kaplan-Meier analysis. Receiver operating characteristic (ROC) curves were used to test the diagnostic capacity of each feature.

Results

Five texture features (one first-order feature from the liver and four wavelet features from the spleen) and the international normalized ratio (INR) were identified as statistically significant for stratifying PH (p &lt; 0.05). The best performance was achieved by the spleen-derived feature of wavelet.LLH_ngtdm_Busyness, with an AUC of 0.72. The only log.sigma.3.0.mm.3D_firstorder_RobustMeanAbsoluteDeviation feature from the liver was associated with PFS with a C-index of 0.72 (95% CI 0.566–0.885), which could stratify patients with PH into high- or low-risk groups. The 1-, 2-, and 3-year survival probabilities were 66.7, 50, and 33.3% for the high-risk group and 93.2, 91.5, and 84.4% for the low-risk group, respectively (p &lt; 0.05).

Conclusion

CT-based texture features from the liver or spleen may have the potential to stratify PH and predict patient survival.

Integrative Predictive Models of Computed Tomography Texture Parameters and Hematological Parameters for Lymph Node Metastasis in Lung Adenocarcinomas

Objectives

The aims of the study were to integrate characteristics of computed tomography (CT), texture, and hematological parameters and to establish predictive models for lymph node (LN) metastasis in lung adenocarcinoma.

Methods

A total of 207 lung adenocarcinoma cases with confirmed postoperative pathology and preoperative CT scans between February 2017 and April 2019 were included in this retrospective study. All patients were divided into training and 2 validation cohorts chronologically in the ratio of 3:1:1. The χ² test or Fisher exact test were used for categorical variables. The Shapiro-Wilk test and Mann-Whitney U test were used for continuous variables. Logistic regression and machine learning algorithm models based on CT characteristics, texture, and hematological parameters were used to predict LN metastasis. The performance of the multivariate models was evaluated using a receiver operating characteristic curve; prediction performance was evaluated in the validation cohorts. Decision curve analysis confirmed its clinical utility.

Results

Logistic regression analysis demonstrated that pleural thickening (P = 0.013), percentile 25th (P = 0.033), entropy gray-level co-occurrence matrix 10 (P = 0.019), red blood cell distribution width (P = 0.012), and lymphocyte-to-monocyte ratio (P = 0.049) were independent risk factors associated with LN metastasis. The area under the curve of the predictive model established using the previously mentioned 5 independent risk factors was 0.929 in the receiver operating characteristic analysis. The highest area under the curve was obtained in the training cohort (0.777 using Naive Bayes algorithm).

Conclusions

Integrative predictive models of CT characteristics, texture, and hematological parameters could predict LN metastasis in lung adenocarcinomas. These findings may provide a reference for clinical decision making.

Radiomics and machine learning for the diagnosis of pediatric cervical non-tuberculous mycobacterial lymphadenitis

Non-tuberculous mycobacterial (NTM) infection is an emerging infectious entity that often presents as lymphadenitis in the pediatric age group. Current practice involves invasive testing and excisional biopsy to diagnose NTM lymphadenitis. In this study, we performed a retrospective analysis of 249 lymph nodes selected from 143 CT scans of pediatric patients presenting with lymphadenopathy at the Montreal Children’s Hospital between 2005 and 2018. A Random Forest classifier was trained on the ten most discriminative features from a set of 1231 radiomic features. The model classifying nodes as pyogenic, NTM, reactive, or proliferative lymphadenopathy achieved an accuracy of 72%, a precision of 68%, and a recall of 70%. Between NTM and all other causes of lymphadenopathy, the model achieved an area under the curve (AUC) of 89%. Between NTM and pyogenic lymphadenitis, the model achieved an AUC of 90%. Between NTM and the reactive and proliferative lymphadenopathy groups, the model achieved an AUC of 93%. These results indicate that radiomics can achieve a high accuracy for classification of NTM lymphadenitis. Such a non-invasive highly accurate diagnostic approach has the potential to reduce the need for invasive procedures in the pediatric population.

Non-contrast-enhanced CT texture analysis of primary and metastatic pancreatic ductal adenocarcinomas: value in assessment of histopathological grade and differences between primary and metastatic lesions

PURPOSE

To evaluate the utility of non-contrast-enhanced CT texture analysis (CTTA) for predicting the histopathological differentiation of pancreatic ductal adenocarcinomas (PDAC) and to compare non-contrast-enhanced CTTA texture features between primary PDAC and hepatic metastases of PDAC.

METHODS

This retrospective study included 120 patients with histopathologically confirmed PDAC. Sixty-five patients underwent CT-guided biopsy of primary PDAC, while 55 patients underwent CT-guided biopsy of hepatic PDAC metastasis. All lesions were segmented in non-contrast-enhanced CT scans for CTTA based on histogram analysis, co-occurrence matrix, and run-length matrix. Statistical analysis was conducted for 372 texture features using Mann-Whitney U test, Bonferroni-Holm correction, and receiver operating characteristic (ROC) analysis. A p value < 0.05 was considered statistically significant.

RESULTS

Three features were identified that differed significantly between histopathological G2 and G3 primary tumors. Of these, "low gray-level zone emphasis" yielded the largest AUC (0.87 ± 0.04), reaching a sensitivity and specificity of 0.76 and 0.83, respectively, when a cut-off value of 0.482 was applied. Fifty-four features differed significantly between primary and hepatic metastatic PDAC.

CONCLUSION

Non-contrast-enhanced CTTA of PDAC identified differences in texture features between primary G2 and G3 tumors that could be used for non-invasive tumor assessment. Extensive differences between the features of primary and metastatic PDAC on CTTA suggest differences in tumor microenvironment.

Dual-region radiomics signature: Integrating primary tumor and lymph node computed tomography features improves survival prediction in esophageal squamous cell cancer

BACKGROUND

Preoperative prognostic biomarkers to guide individualized therapy are still in demand in esophageal squamous cell cancer (ESCC). Some studies reported that radiomic analysis based on CT images has been successfully performed to predict individual survival in EC. The aim of this study was to assess whether combining radiomics features from primary tumor and regional lymph nodes predicts overall survival (OS) better than using single-region features only, and to investigate the incremental value of the dual-region radiomics signature.

METHODS

In this retrospective study, three radiomics signatures were built from preoperative enhanced CT in a training cohort (n = 200) using LASSO Cox model. Associations between each signature and survival was assessed on a validation cohort (n = 107). Prediction accuracy for the three signatures was compared. By constructing a clinical nomogram and a radiomics-clinical nomogram, incremental prognostic value of the radiomics signature over clinicopathological factors in OS prediction was assessed in terms of discrimination, calibration, reclassification and clinical usefulness.

RESULTS

The dual-region radiomic signature was an independent factor, significantly associated with OS (HR: 1.869, 95% CI: 1.347, 2.592, P = 1.82e-04), which achieved better OS (C-index: 0.611) prediction either than the single-region signature (C-index:0.594-0.604). The resulted dual-region radiomics-clinical nomogram achieved the best discriminative ability in OS prediction (C-index:0.700). Compared with the clinical nomogram, the radiomics-clinical nomogram improved the calibration and classification accuracy for OS prediction with a total net reclassification improvement (NRI) of 26.9% (P=0.008) and integrated discrimination improvement (IDI) of 6.8% (P<0.001).

CONCLUSION

The dual-region radiomic signature is an independent prognostic marker and outperforms single-region signature in OS for ESCC patients. Integrating the dual-region radiomics signature and clinicopathological factors improves OS prediction.

Contrast enhanced computed tomography assessment of superficial inguinal lymph node metastasis in canine mammary gland tumors

Mammary gland neoplasms are predominant in dogs. However, sentinel lymph node (SLN) status assessment criteria have not been established for these cases. In this retrospective, secondary analysis, diagnostic case control study, CT images of 65 superficial inguinal SLNs were obtained before and 1, 3, 5, and 10 min after intravenous administration of contrast agent (iopamidol 370 mgI/mL). The presence and degree of postcontrast enhancement were assessed, by means of the median absolute density value and the maximum absolute density value at any time point in the center and in the periphery of each SLN measured in Hounsfield units (HU), before and after contrast agent administration. These values were compared with histopathological findings postsurgical excision. Receiver operating characteristic analysis was conducted. The absolute density values ranged widely at each time point and within each group of nodes (negative, positive, control group). At all time points, the median density value in the center and in the periphery was significantly higher in metastatic than in non-metastatic SLNs (P ≤ .014). Among the parameters tested, the median absolute density value measured in the periphery of the SLN 3 min after injection showed the highest sensitivity, specificity, and accuracy (AUC) (87.5%, 82.1%, and 92.1% respectively), with a cutoff value of 50.9 HU. The maximum absolute density value at any time point in the center and periphery of the SLNs was also significantly higher in metastatic SLNs compared to non-metastatic (P ≤ .001). With a cutoff value of 59.5 HU, the maximum absolute density value in the periphery of the SLN displayed high sensitivity and specificity (87.5% and 89.3%, respectively). The results of this study support the hypothesis that contrast enhanced CT imaging may aid in the assessment of SLN metastasis in dogs with mammary gland neoplasms.

Characterizing Brain Tumor Regions Using Texture Analysis in Magnetic Resonance Imaging

Purpose

To extract texture features from magnetic resonance imaging (MRI) scans of patients with brain tumors and use them to train a classification model for supporting an early diagnosis.

Methods

Two groups of regions (control and tumor) were selected from MRI scans of 40 patients with meningioma or glioma. These regions were analyzed to obtain texture features. Statistical analysis was conducted using SPSS (version 20.0), including the Shapiro-Wilk test and Wilcoxon signed-rank test, which were used to test significant differences in each feature between the tumor and healthy regions. T-distributed stochastic neighbor embedding (t-SNE) was used to visualize the data distribution so as to avoid tumor selection bias. The Gini impurity index in random forests (RFs) was used to select the top five out of all features. Based on the five features, three classification models were built respectively with three machine learning classifiers: RF, support vector machine (SVM), and back propagation (BP) neural network.

Results

Sixteen of the 25 features were significantly different between the tumor and healthy areas. Through the Gini impurity index in RFs, standard deviation, first-order moment, variance, third-order absolute moment, and third-order central moment were selected to build the classification model. The classification model trained using the SVM classifier achieved the best performance, with sensitivity, specificity, and area under the curve of 94.04%, 92.3%, and 0.932, respectively.

Conclusion

Texture analysis with an SVM classifier can help differentiate between brain tumor and healthy areas with high speed and accuracy, which would facilitate its clinical application.

Integrative nomogram of intratumoral, peritumoral, and lymph node radiomic features for prediction of lymph node metastasis in cT1N0M0 lung adenocarcinomas

Radiomics studies to predict lymph node (LN) metastasis has only focused on either primary tumor or LN alone. However, combining radiomics features from multiple sources may reflect multiple characteristic of the lesion thereby increasing the discriminative performance of the radiomic model. Therefore, the present study intends to evaluate the efficiency of integrative nomogram, created by combining clinical parameters and radiomics features extracted from gross tumor volume (GTV), peritumoral volume (PTV) and LN, for the preoperative prediction of LN metastasis in clinical cT1N0M0 adenocarcinoma. A primary cohort of 163 patients (training cohort, 113; and internal validation cohort, 50) and an external validation cohort of 53 patients with clinical stage cT1N0M0 were retrospectively included. Features were extracted from three regions of interests (ROIs): GTV; PTV (5.0 mm around the tumor) and LN on pre-operative contrast enhanced computed tomography (CT). LASSO logistic regression method was used to build radiomic signatures. Multivariable regression analysis was used to build a nomogram. The performance of the nomogram was assessed with respect to its calibration, discrimination, and clinical usefulness. The discriminative performance of nomogram was validated both internally and externally. The radiomic signatures using the features of GTV, PTV and LN showed a good ability in predicting LN metastasis with an area under the curve (AUC) of 0.74 (95% CI 0.60–0.88), 0.72 (95% CI 0.57–0.87) and 0.64 (95% CI 0.48–0.80) respectively in external validation cohort. The integration of different signature together further increases the discriminatory ability: GTV + PTV (GPTV): AUC 0.75 (95% CI 0.61–0.89) and GPTV + LN: AUC 0.76 (95% CI 0.61–0.91) in external validation cohort. An integrative nomogram of clinical parameters and radiomic features demonstrated further increase in discriminatory ability with AUC of 0.79 (95% CI 0.66–0.93) in external validation cohort. The nomogram showed good calibration. Decision curve analysis demonstrated that the radiomic nomogram was clinically useful. The integration of information from clinical parameters along with CT radiomics information from GTV, PTV and LN was feasible and increases the predictive performance of the nomogram in predicting LN status in cT1N0M0 adenocarcinoma patients suggesting merit of information integration from multiple sources in building prediction model.

Analysing the possibility of utilizing CBCT radiomics as an independent modality: a phantom study

Aim:

To verify if computed tomography (CT) radiomics were reproducible by cone beam CT (CBCT) radiomics by using Catphan^® 504.

Materials and Methods:

Catphan^® 504 was imaged using the default IGRT OBI CBCT imaging protocols and CT scanner. Seven known density image regions of the phantom were segmented and image feature was extracted by Imaging Biomarker Explorer (IBEX) software. The 49 selected features from four feature categories were analyzed by considering each region of interest (ROI) segment as individual image set. Correlation was studies using interclass correlation coefficient (ICC) and Pearson’s correlation coefficient.

Results:

The ICC of the three feature categories, namely intensity, GLCM, and GLRLM was significant (p-value<0.05) in comparison with CT, while the ICC of the fourth feature category, NID, was no significant. The average absolute Pearson’s correlation coefficient from the features of the images was as follows: CT: r=0.679±0.257, CBC_Thead: r=0.707±0.231, CBCT_thorax: r=0.643±0.260, and CBCT_pelvis: r=0.594±0.276.

Conclusion:

It seems that the various densities of Catphan^® 504 ROI image segments of the CT radiomics are reproducible with CBCT radiomics and CBCT radiomics can be used as an independent modality.

Nodal-based radiomics analysis for identifying cervical lymph node metastasis at levels I and II in patients with oral squamous cell carcinoma using contrast-enhanced computed tomography

OBJECTIVE

Discriminating metastatic from benign cervical lymph nodes (LNs) in oral squamous cell carcinoma (OSCC) patients using pretreatment computed tomography (CT) has been controversial. This study aimed to investigate whether CT-based texture analysis with machine learning can accurately identify cervical lymph node metastasis in OSCC patients.

METHODS

Twenty-three patients (with 201 cervical LNs [150 benign, 51 metastatic] at levels I-V) who underwent preoperative contrast-enhanced CT and subsequent cervical neck dissection were enrolled. Histopathologically proven LNs were randomly divided into the training cohort (70%; n = 141, at levels I-V) and validation cohort (30%; n = 60, at level I/II). Twenty-five texture features and the nodal size of targeted LNs were analyzed on the CT scans. The nodal-based sensitivities, specificities, diagnostic accuracy rates, and the area under the curves (AUCs) of the receiver operating characteristic curves of combined features using a support vector machine (SVM) at levels I/II, I, and II were evaluated and compared with two radiologists and a dentist (readers).

RESULTS

In the validation cohort, the AUCs (0.820 at level I/II, 0.820 at level I, and 0.930 at level II, respectively) of the radiomics approach were superior to three readers (0.798-0.816, 0.773-0.798, and 0.825-0.865, respectively). The best models were more specific at levels I/II and I and accurate at each level than each of the readers (p < .05).

CONCLUSIONS

Machine learning-based analysis with contrast-enhanced CT can be used to noninvasively differentiate between benign and metastatic cervical LNs in OSCC patients.

KEY POINTS

• The best algorithm in the validation cohort can noninvasively differentiate between benign and metastatic cervical LNs at levels I/II, I, and II. • The AUCs of the model at each level were superior to those of multireaders. • Significant differences in the specificities at level I/II and I and diagnostic accuracy rates at each level between the model and multireaders were found.

The Effects of Perinodular Features on Solid Lung Nodule Classification

Lung cancer is the most lethal malignant neoplasm worldwide, with an annual estimated rate of 1.8 million deaths. Computed tomography has been widely used to diagnose and detect lung cancer, but its diagnosis remains an intricate and challenging work, even for experienced radiologists. Computer-aided diagnosis tools and radiomics tools have provided support to the radiologist's decision, acting as a second opinion. The main focus of these tools has been to analyze the intranodular zone; nevertheless, recent works indicate that the interaction between the nodule and its surroundings (perinodular zone) could be relevant to the diagnosis process. However, only a few works have investigated the importance of specific attributes of the perinodular zone and have shown how important they are in the classification of lung nodules. In this context, the purpose of this work is to evaluate the impact of using the perinodular zone on the characterization of lung lesions. Motivated by reproducible research, we used a large public dataset of solid lung nodule images and extracted fine-tuned radiomic attributes from the perinodular and intranodular zones. Our best-evaluated model obtained an average AUC of 0.916, an accuracy of 84.26%, a sensitivity of 84.45%, and specificity of 83.84%. The combination of attributes from the perinodular and intranodular zones in the image characterization resulted in an improvement in all the metrics analyzed when compared to intranodular-only characterization. Therefore, our results highlighted the importance of using the perinodular zone in the solid pulmonary nodules classification process.

Combining machine learning and texture analysis to differentiate mediastinal lymph nodes in lung cancer patients

Evaluate whether texture analysis associated with machine learning approaches could differentiate between malignant and benign lymph nodes. A total 18 patients with lung cancer were selected, with 39 lymph nodes, being 15 malignant and 24 benign. Retrospective computed tomography scans were utilized both with and without contrast medium. The great differential of this work was the use of 15 textures from mediastinal lymph nodes, with five different physicians as operators. First and second order statistical textures such as gray level run length and co-occurrence matrix were extracted and applied to three different machine learning classifiers. The best machine learning classifier demonstrated a variability of less than 5% among operators. The support vector machine (SVM) classifier presented 95% of the area under the ROC curve (AUC) and 89% of sensitivity for sequences without contrast medium. SVM classifier presented 93% of AUC and 86% of sensitivity for sequences with contrast medium. Texture analysis and machine learning may be helpful in the differentiation between malign and benign lymph nodes. This study can aid the physician in diagnosis and staging of lymph nodes and potentially reduce the number of invasive analysis to histopathological confirmation.

Machine learning-based MRI texture analysis to predict occult lymph node metastasis in early-stage oral tongue squamous cell carcinoma

OBJECTIVES

To develop and compare several machine learning models to predict occult cervical lymph node (LN) metastasis in early-stage oral tongue squamous cell cancer (OTSCC) from preoperative MRI texture features.

MATERIALS AND METHODS

We retrospectively enrolled 116 patients with early-stage OTSCC (cT1-2N0) who had been surgically treated by tumor excision and elective neck dissection (END). For each patient, we extracted 86 texture features from T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (ceT1WI), respectively. Dimension reduction was performed in three consecutive steps: reproducibility analysis, collinearity analysis, and information gain algorithm. Models were created using six machine learning methods, including logistic regression (LR), random forest (RF), naïve Bayes (NB), support vector machine (SVM), AdaBoost, and neural network (NN). Their performance was assessed using tenfold cross-validation.

RESULTS

Occult LN metastasis was pathologically detected in 42.2% (49/116) of the patients. No significant association was identified between node status and patients' gender, age, or clinical T stage. Dimension reduction steps selected 6 texture features. The NB model gave the best overall performance, which correctly classified the nodal status in 74.1% (86/116) of the carcinomas, with an AUC of 0.802.

CONCLUSION

Machine learning-based MRI texture analysis offers a feasible tool for preoperative prediction of occult cervical node metastasis in early-stage OTSCC.

KEY POINTS

• A machine learning-based MRI texture analysis approach was adopted to predict occult cervical node metastasis in early-stage OTSCC with no evidence of node involvement on conventional images. • Six texture features from T2WI and ceT1WI of preoperative MRI were selected to construct the predictive model. • After comparing six machine learning methods, naïve Bayes (NB) achieved the best performance by correctly identifying the node status in 74.1% of the patients, using tenfold cross-validation.

A PET/CT nomogram incorporating SUVmax and CT radiomics for preoperative nodal staging in non-small cell lung cancer

Objectives

To develop and validate a PET/CT nomogram for preoperative estimation of lymph node (LN) staging in patients with non-small cell lung cancer (NSCLC).

Methods

A total of 263 pathologically confirmed LNs from 124 patients with NCSLC were retrospectively analyzed. Positron-emission tomography/computed tomography (PET/CT) examination was performed before treatment according to the clinical schedule. In the training cohort (N = 185), malignancy-related features, such as SUVmax, short-axis diameter (SAD), and CT radiomics features, were extracted from the regions of LN based on the PET/CT scan. The Minimum-Redundancy Maximum-Relevance (mRMR) algorithm and the Least Absolute Shrinkage and Selection Operator (LASSO) regression model were used for feature selection and radiomics score building. The radiomics score (Rad-Score) and SUVmax were incorporated in a PET/CT nomogram using the multivariable logistic regression analysis. The performance of the proposed model was evaluated with discrimination, calibration, and clinical application in an independent testing cohort (N = 78).

Results

The radiomics scores consisting of 14 selected features were significantly associated with LN status for both training cohort with AUC of 0.849 (95% confidence interval (CI), 0.796–0.903) and testing cohort with AUC of 0.828 (95% CI, 0.782–0.919). The PET/CT nomogram incorporating radiomics score and SUVmax showed moderate improvement of the efficiency with AUC of 0.881 (95% CI, 0.834–0.928) in the training cohort and AUC of 0.872 (95% CI, 0.797–0.946) in the testing cohort. The decision curve analysis indicated that the PET/CT nomogram was clinically useful.

Conclusion

The PET/CT nomogram, which incorporates Rad-Score and SUVmax, can improve the diagnostic performance of LN metastasis.

Key Points

• The PET/CT nomogram (Int-Score) based on lymph node (LN) PET/CT images can reliably predict LN status in NSCLC.

• Int-Score is a relatively objective diagnostic method, which can play an auxiliary role in the process of clinicians making treatment decisions.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-020-07624-9.

Preoperatively Estimating the Malignant Potential of Mediastinal Lymph Nodes: A Pilot Study Toward Establishing a Robust Radiomics Model Based on Contrast-Enhanced CT Imaging

PURPOSE

To establish and validate a radiomics model to estimate the malignancy of mediastinal lymph nodes (LNs) based on contrast-enhanced CT imaging.

METHOD

In total, 201 pathologically confirmed mediastinal LNs from 129 patients were enrolled and assigned to training and test sets. Radiomics features were extracted from the region of interest (ROI) delineated on venous-phase CT imaging of LN. Feature selection was performed with least absolute shrinkage and selection operator (LASSO) binary logistic regression. Multivariate logistic regression was performed with the backward stepwise elimination. A model was fitted to associate mediastinal LN malignancy with selected features. The performance of the model was assessed and compared to that of five other machine learning algorithms (support vector machine, naive Bayes, random forest, decision tree, K-nearest neighbor) using receiver operating characteristic (ROC) curves. Calibration curves and Hosmer-Lemeshow tests were used to assess the calibration degree. Decision curve analysis (DCA) was used to assess the clinical usefulness of the logistic regression model in both the training and test sets. Stratified analysis was performed for different scanners and slice thicknesses.

RESULT

Among the six machine learning methods, the logistic regression model with the eight strongest features showed a significant association with mediastinal LN status and the satisfactory diagnostic performance for distinguishing malignant LNs from benign LNs. The accuracy, sensitivity, specificity and area under the ROC curve (AUC) were 0.850/0.803, 0.821/0.806, 0.893/0.800, and 0.922/0.850 in the training/test sets, respectively. The Hosmer-Lemeshow test showed that the P value was > 0.05, indicating good calibration, and the calibration curves showed good agreement between the classifications and actual observations. DCA showed that the model would obtain more benefit when the threshold probability was between 30% and 90% in the test set. Stratified analysis showed that the performance was not affected by different scanners or slice thicknesses. There was no significant difference (DeLong test, P > 0.05) between any two subgroups, which showed the generalization of the radiomics score across different factors.

CONCLUSION

The model we built could help assist the preoperative estimation of mediastinal LN malignancy based on contrast-enhanced CT imaging, with stability for different scanners and slice thicknesses.

CT texture analysis in histological classification of epithelial ovarian carcinoma

OBJECTIVES

The study aimed to compare the ability of morphological and texture features derived from contrast-enhanced CT in histological subtyping of epithelial ovarian carcinoma (EOC).

METHODS

Consecutive 205 patients with newly diagnosed EOC who underwent contrast-enhanced CT were included and dichotomised into high-grade serous carcinoma (HGSC) and non-HGSC. Clinical information including age and cancer antigen 125 (CA-125) was documented. The pre-treatment images were analysed using commercial software, TexRAD, by two independent radiologists. Eight qualitative CT morphological features were evaluated, and 36 CT texture features at 6 spatial scale factors (SSFs) were extracted per patient. Features' reduction was based on kappa score, intra-class correlation coefficient (ICC), univariate ROC analysis and Pearson's correlation test. Texture features with ICC ≥ 0.8 were compared by histological subtypes. Patients were randomly divided into training and testing sets by 8:2. Two random forest classifiers were determined and compared: model 1 incorporating selected morphological and clinical features and model 2 incorporating selected texture and clinical features.

RESULTS

HGSC showed specifically higher texture features than non-HGSC (p < 0.05). Both models performed highly in predicting histological subtypes of EOC (model 1: AUC 0.891 and model 2: AUC 0.937), and no statistical significance was found between the two models (p = 0.464).

CONCLUSION

CT texture analysis provides objective and quantitative metrics on tumour characteristics with HGSC demonstrating specifically high texture features. The model incorporating texture analysis could classify histology subtypes of EOC with high accuracy and performed as well as morphological features.

KEY POINTS

• A number of CT morphological and texture features showed good inter- and intra-observer agreements. • High-grade serous ovarian carcinoma showed specifically higher CT texture features than non-high-grade serous ovarian carcinoma. • CT texture analysis could differentiate histological subtypes of epithelial ovarian carcinoma with high accuracy.

Endobronchial Ultrasound Elastography Combined With Computed Tomography in Differentiating Benign from Malignant Intrathoracic Lymph Nodes

Objective. This study was to combine endobronchial ultrasound elastography (UE) with computed tomography (CT) to identify benign and malignant thoracic lymph nodes (LNs) more objectively and accurately. Methods. A total of 42 patients with intrathoracic lymphadenopathy required for endobronchial ultrasound with real-time guided transbronchial needle aspiration (EBUS-TBNA) examination were enrolled. All patients were examined by enhanced chest CT, B-mode ultrasound, and endobronchial ultrasound (EBUS)-guided elastography before EBUS-TBNA. Each lymph node was assessed by describing the characteristics of CT image (short diameter, texture, shape, boundary, and mean CT value), B-mode ultrasound (short diameter, echo characteristic, shape, and boundary), and elastography (image type, grading score, strain rate, and blue area ratio). The pathological results were used as the gold standard. The characteristics were compared alone and in combination between benign and malignant LNs. Results. The blue area ratio of elastography combined with CT had better diagnostic value in differentiating benign and malignant LNs than elastography alone, with the accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) being 92%, 96%, 80%, 94%, and 86% vs 81%, 77%, 93%, 97%, and 56%, respectively. Elastography combined with B-mode ultrasound and CT characteristics showed the highest diagnostic value. Accuracy, sensitivity, specificity, PPV, and NPV were all 100%. Conclusions. Endobronchial UE combined with CT and B-mode ultrasound imaging shows a greater diagnostic value in differentiating benign and malignant intrathoracic LNs than either imaging alone.

CT texture analysis of mediastinal lymphadenopathy: Combining with US-based elastographic parameter and discrimination between sarcoidosis and lymph node metastasis from small cell lung cancer

Objectives

To investigate the potential of computed tomography (CT)-based texture analysis and elastographic data provided by endobronchial ultrasonography (EBUS) for differentiating the mediastinal lymphadenopathy by sarcoidosis and small cell lung cancer (SCLC) metastasis.

Methods

Sixteen patients with sarcoidosis and 14 with SCLC were enrolled. On CT images showing the largest mediastinal lymph node, a fixed region of interest was drawn on the node, and texture features were automatically measured. Among the 30 patients, 19 (12 sarcoidosis and 7 SCLC) underwent endobronchial ultrasound transbronchial needle aspiration, and the fat-to-lesion strain ratio (FLR) was recorded. Texture features and FLRs were compared between the 2 patient groups. Logistic regression analysis was performed to evaluate the diagnostic accuracy of these measurements.

Results

Of the 31 texture features, the differences between 11 texture features of CT ROIs in the patients with sarcoidosis versus patients with SCLC were significant. Among them, the grey-level run length matrix with high gray-level run emphasis (GLRLM-HGRE) showed the greatest difference (P<0.01). Differences between FLRs were significant (P<0.05). Logistic regression analysis together with receiver operating characteristic curve analysis demonstrated that the FLR combined with the GLRLM-HGRE showed a high diagnostic accuracy (100% sensitivity, 92% specificity, 0.988 area under the curve) for discriminating between sarcoidosis and SCLC.

Conclusion

Texture analysis, particularly combined with the FLR, is useful for discriminating between mediastinal lymphadenopathy caused by sarcoidosis from that caused by metastasis from SCLC.

Is the standard deviation of the apparent diffusion coefficient a potential tool for the preoperative prediction of tumor grade in endometrial cancer?

BACKGROUND

The tumor histological grade is closely related to the prognosis of endometrial cancer (EC). The use of the apparent diffusion coefficient (ADC), tumor volume, and MRI-based texture analysis has allowed exciting advances in predicting EC grade before surgery. However, whether this constitutes a simple, convenient, and powerful diagnostic method remains unknown.

PURPOSE

To explore the utility of standard deviation (SD) of the ADC (ADC_SD) for predicting the tumor grade in patients with EC.

MATERIAL AND METHODS

We retrospectively evaluated 138 patients with EC. All patients underwent unenhanced MRI and diffusion-weighted imaging (DWI). The mean ADC value (ADC_mean) and SD were obtained using a freehand region of interest traced on the ADC map. Spearman's linear correlation coefficients were calculated to analyze the correlations between the indexes (including ADC_SD and the ADC_mean) and the Ki-67 index. The Kruskal-Wallis and Mann-Whitney U tests were used to compare differences in the index results among tumor grades.

RESULTS

A significant difference in ADC_SD was observed among the tumor grades (P=0.000), and the ADC_SD value was significantly higher for high-grade EC than for low-grade tumors (289.7 vs. 216.3×10^-6mm² /s, P=0.000). A statistically significant positive correlation was observed between ADC_SD and the Ki-67 index (r=0.364, P=0.000). According to the receiver operating characteristic curve, ADC_SD ≥240.2×10^-6mm² /s predicted high-grade EC with a sensitivity, specificity, and accuracy of 73.1%, 80.2%, and 77.5%, respectively.

CONCLUSION

Based on the intratumor heterogeneity of EC, ADC_SD represents a potential method for the preoperative prediction of high-grade EC, although further studies are needed.

Review of Value of CT Texture Analysis and Machine Learning in Differentiating Fat-Poor Renal Angiomyolipoma from Renal Cell Carcinoma

The diagnosis of patients with suspected angiomyolipoma relies on the detection of abundant macroscopic intralesional fat, which is always of no use to differentiate fat-poor angiomyolipoma (fp-AML) from renal cell carcinoma and diagnosis of fp-AML excessively depends on individual experience. Texture analysis was proven to be a potentially useful biomarker for distinguishing between benign and malignant tumors because of its capability of providing objective and quantitative assessment of lesions by analyzing features that are not visible to the human eye. This review aimed to summarize the literature on the use of texture analysis to diagnose patients with fat-poor angiomyolipoma vs those with renal cell carcinoma and to evaluate its current application, limitations, and future challenges in order to avoid unnecessary surgical resection.

Can artificial intelligence distinguish between malignant and benign mediastinal lymph nodes using sonographic features on EBUS images?

AIMS

This study aimed to develop a new intelligent diagnostic approach using an artificial neural network (ANN). Moreover, we investigated whether the learning-method-guided quantitative analysis approach adequately described mediastinal lymphadenopathies on endobronchial ultrasound (EBUS) images.

METHODS

In total, 345 lymph nodes (LNs) from 345 EBUS images were used as source input datasets for the application group. The group consisted of 300 and 45 textural patterns as input and output variables, respectively. The input and output datasets were processed using MATLAB. All these datasets were utilized for the training and testing of the ANN.

RESULTS

The best diagnostic accuracy was 82% of that obtained from the textural patterns of the LNs pattern (89% sensitivity, 72% specificity, and 78.2% area under the curve). The negative predictive values were 81% compared to the corresponding positive predictive values of 83%. Due to the application group's pattern-based evaluation, the LN pattern was statistically significant (p = .002).

CONCLUSIONS

The proposed intelligent approach could be useful in making diagnoses. Further development is required to improve the diagnostic accuracy of the visual interpretation.

Prediction of liver regeneration in recipients after living-donor liver transplantation in using preoperative CT texture analysis and clinical features

PURPOSE

The aim of the study is to predict the rate of liver regeneration in recipients after living-donor liver transplantation using preoperative CT texture and shape analysis of the future graft.

METHODS

102 donor-recipient pairs who underwent living-donor liver transplantation using right lobe grafts were retrospectively included. We semi-automatically segmented the future graft from preoperative CT. The volume of the future graft (LV_pre) was measured, and texture and shape analyses were performed. The graft liver was segmented from postoperative follow-up CT and the volume of the graft (LV_post) was measured. The regeneration index was defined by the following equation: [(LV_post-LV_pre)/LV_pre] × 100(%). We performed a stepwise, multivariate linear regression analysis to investigate the association between clinical, texture and shape parameters and the RI and to make the best-fit predictive model.

RESULTS

The mean regeneration index was 47.5 ± 38.6%. In univariate analysis, the volume of the future graft, energy, effective diameter, surface area, sphericity, roundness_m, compactness1, and grey-level co-occurrence matrix contrast as well as several clinical parameters were significantly associated with the regeneration index (p < 0.05). The best-fit predictive model for the regeneration index made by multivariate analysis was as follows: Regeneration index (%) = 127.020-0.367 × effective diameter - 1.827 × roundness_m + 47.371 × recipient body surface area (m²) + 12.041 × log(recipient white blood cell count) (× 10³/μL)+ 18.034 (if the donor was female).

CONCLUSION

The effective diameter and roundness_m of the future graft were associated with liver regeneration. Preoperative CT texture analysis of future grafts can be useful for predicting liver regeneration in recipients after living-donor liver transplantation.

Performance improvement of mediastinal lymph node severity detection using GAN and Inception network

BACKGROUND AND OBJECTIVE

In lung cancer, the determination of mediastinal lymph node (MLN) status as benign or malignant influence treatment planning and survival rate. Invasive pathological tests for the classification of MLNs into benign and malignant have various shortcomings like painfulness, the risk associated with anesthesia, and depends to a large extent on skillset and preferences of the surgeon performing the test. Hence, computer-aided system for MLNs severity detection has been explored widely by the researchers. Very recently, in our earlier concluded work on non-invasive method for MLNs differential diagnosis in computed tomography (CT) images, combination of different data augmentation approaches and state-of-art fully convolutional network (FCN) were implemented to enhance the performance of malignancy detection. However, the performance of FCN network were highly depended on the selection of appropriate data augmentation approach and control of their hyperparameters. Moreover, a standard practice to get hierarchical features in convolutional neural network (CNN) models requires deeper stacking of layers. This leads to an increase in number of trainable parameters which prone to overfitting of the network.

METHODS

In view of the above mention limitations, in this paper, authors have proposed an approach that includes: 1) Generative Adversarial Network (GAN) for data augmentation, and 2) Inception network for malignancy detection. Unlike conventional data augmentation strategy, GAN based augmentation approach generates data that correlates to original data distribution. In the case of Inception based model, it uses multiple size kernels with factorized convolution for hierarchical feature extraction. This helps to a significant reduction in trainable parameters and the problem of overfitting.

RESULTS

In this paper, experiments with different GAN approaches, as well as with different Inception architectures, are conducted to evaluate and justify the selection of appropriate GAN and Inception architecture, respectively for MLNs severity detection. The proposed approach achieves superior results with an average accuracy, sensitivity, specificity, and area under curve of 94.95%, 93.65%, 96.67%, and 95%, respectively.

CONCLUSION

The obtained results validate the usefulness of GANs for data augmentation in the differential diagnosis of benign and malignant MLNs. The proposed Inception network based classifier for malignancy detection shows promising results compared to all investigated methods presented in various literature.

Radiomics in Lung Cancer from Basic to Advanced: Current Status and Future Directions

Ideally, radiomics features and radiomics signatures can be used as imaging biomarkers for diagnosis, staging, prognosis, and prediction of tumor response. Thus, the number of published radiomics studies is increasing exponentially, leading to a myriad of new radiomics-based evidence for lung cancer. Consequently, it is challenging for radiologists to keep up with the development of radiomics features and their clinical applications. In this article, we review the basics to advanced radiomics in lung cancer to guide young researchers who are eager to start exploring radiomics investigations. In addition, we also include technical issues of radiomics, because knowledge of the technical aspects of radiomics supports a well-informed interpretation of the use of radiomics in lung cancer.

Assessment of Clinical Stage IA Lung Adenocarcinoma with pN1/N2 Metastasis Using CT Quantitative Texture Analysis

OBJECTIVE

To explore the application of texture analysis basing on computed tomography (CT) images in predicting lymph-node metastasis in patients with clinical stage IA lung adenocarcinoma.

METHODS

In total, 256 patients with clinical stage IA lung adenocarcinoma who had underwentgone preoperative CT examinations were enrolled. A total of 25 texture features using MaZda (version 4.6) software and conventional radiological features were extracted from raw CT data sets. Based on surgical results, patients were stratified into lymph node metastasis-positive and -negative groups. Independent-sample t-tests and Mann-Whitney U tests were used to compare continuous variables between the groups. Continuity-correction and χ2 tests were used for categorical variable comparison. Univariate and multivariate logistic regression analyses were performed to identify independent predictors of lymph-node metastasis.

RESULTS

In total, 256 clinical stage IA lung adenocarcinoma cases were proved by pathology: 39 (15.23%) cases with lymph-node metastasis (14 N1a, seven N1b, six N2a1, ten N2a2, and two N2b) and 217 (84.77%) cases without lymph-node metastasis. Univariate and multivariate logistic regression analyses demonstrated that total volume (OR 3.777, p=0.015), average CT value of whole tumor (OR 16.271, p<0.001), three texture parameters (mean OR 8.473, p<0.001; skewness OR 6.393, p=0.001; and entropy OR 0.343, p=0.049) were independent factors associated with lymph-node status. As such, early-stage lung adenocarcinoma with higher total volume (>4.05 cm3), average CT value of whole tumor (>-70 HU), mean (>133.79), entropy (>1.98), and lower skewness (≤0.02) pointed to positive lymph-node metastasis.

CONCLUSION

Texture parameters were independent factors associated with lymph-node status in clinical stage IA lung adenocarcinoma.

Radiomic Texture and Shape Descriptors of the Rectal Environment on Post-Chemoradiation T2-Weighted MRI are Associated with Pathologic Tumor Stage Regression in Rectal Cancers: A Retrospective, Multi-Institution Study

(1) Background: The relatively poor expert restaging accuracy of MRI in rectal cancer after neoadjuvant chemoradiation may be due to the difficulties in visual assessment of residual tumor on post-treatment MRI. In order to capture underlying tissue alterations and morphologic changes in rectal structures occurring due to the treatment, we hypothesized that radiomics texture and shape descriptors of the rectal environment (e.g., wall, lumen) on post-chemoradiation T2-weighted (T2w) MRI may be associated with tumor regression after neoadjuvant chemoradiation therapy (nCRT). (2) Methods: A total of 94 rectal cancer patients were retrospectively identified from three collaborating institutions, for whom a 1.5 or 3T T2w MRI was available after nCRT and prior to surgical resection. The rectal wall and the lumen were annotated by an expert radiologist on all MRIs, based on which 191 texture descriptors and 198 shape descriptors were extracted for each patient. (3) Results: Top-ranked features associated with pathologic tumor-stage regression were identified via cross-validation on a discovery set (n = 52, 1 institution) and evaluated via discriminant analysis in hold-out validation (n = 42, 2 institutions). The best performing features for distinguishing low (ypT0-2) and high (ypT3-4) pathologic tumor stages after nCRT comprised directional gradient texture expression and morphologic shape differences in the entire rectal wall and lumen. Not only were these radiomic features found to be resilient to variations in magnetic field strength and expert segmentations, a quadratic discriminant model combining them yielded consistent performance across multiple institutions (hold-out AUC of 0.73). (4) Conclusions: Radiomic texture and shape descriptors of the rectal wall from post-treatment T2w MRIs may be associated with low and high pathologic tumor stage after neoadjuvant chemoradiation therapy and generalized across variations between scanners and institutions.

Preoperative staging of the mediastinum is an essential and multidisciplinary task

Mediastinal staging is a crucial step in the management of patients with NSCLC. With the recent development of novel techniques, mediastinal staging has evolved from an activity of interest mainly for thoracic surgeons to a joint effort carried out by many specialists. In this regard, the debate of cases in MDT sessions is crucial for optimal management of patients. Current evidence-based clinical guidelines for preoperative NSCLC staging recommend that mediastinal staging should be performed with increasing invasiveness. Image-based techniques are the first approach, although they have limited accuracy and findings must be confirmed by pathology in almost all cases. In this setting, the advent of radiomics is promising. Invasive staging depends on procedural factors rather than diagnostic performance. The choice between endoscopy-based or surgical procedures should depend on the local expertise of each centre. As the extension of mediastinal disease in terms of number of involved lymph nodes and nodal stations affects prognosis and the choice of treatment, systematic samplings are preferred over random targeted samplings. Following this approach, a diagnosis of single mediastinal nodal involvement can be unreliable if all reachable mediastinal nodal stations have not been assessed. The performance of confirmatory mediastinoscopy after a negative endoscopy-based procedure is controversial but currently recommended. Current indications of invasive staging in patients with radiologically normal mediastinum have to be re-evaluated, especially for central tumour location.

Contrast-Enhanced CT Texture Analysis for Distinguishing Fat-Poor Renal Angiomyolipoma From Chromophobe Renal Cell Carcinoma

Objective:

To evaluate the value of 2-dimensional (2D) and 3-dimensional (3D) computed tomography texture analysis (CTTA) models in distinguishing fat-poor angiomyolipoma (fpAML) from chromophobe renal cell carcinoma (chRCC).

Methods:

We retrospectively enrolled 32 fpAMLs and 24 chRCCs. Texture features were extracted from 2D and 3D regions of interest in triphasic CT images. The 2D and 3D CTTA models were constructed with the least absolute shrinkage and selection operator algorithm and texture scores were calculated. The diagnostic performance of the 2D and 3D CTTA models was evaluated with respect to calibration, discrimination, and clinical usefulness.

Results:

Of the 177 and 183 texture features extracted from 2D and 3D regions of interest, respectively, 5 2D features and 8 3D features were selected to build 2D and 3D CTTA models. The 2D CTTA model (area under the curve [AUC], 0.811; 95% confidence interval [CI], 0.695-0.927) and the 3D CTTA model (AUC, 0.915; 95% CI, 0.838-0.993) showed good discrimination and calibration (P > .05). There was no significant difference in AUC between the 2 models (P = .093). Decision curve analysis showed the 3D model outperformed the 2D model in terms of clinical usefulness.

Conclusions:

The CTTA models based on contrast-enhanced CT images had a high value in differentiating fpAML from chRCC.

2-[18F]FDG PET/CT radiomics in lung cancer: An overview of the technical aspect and its emerging role in management of the disease

Lung cancer is the most common cancer, worldwide, and a major health issue with a remarkable mortality rate. 2-[¹⁸F]fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography (2-[¹⁸F]FDG PET/CT) plays an indispensable role in the management of lung cancer patients. Long-established quantitative parameters such as size, density, and metabolic activity have been and are being employed in the current practice to enhance interpretation and improve diagnostic and prognostic value. The introduction of radiomics analysis revolutionized the quantitative evaluation of medical imaging, revealing data within images beyond visual interpretation. The "big data" are extracted from high-quality images and are converted into information that correlates to relevant genetic, pathologic, clinical, or prognostic features. Technically advanced, diverse methods have been implemented in different studies. The standardization of image acquisition, segmentation and features analysis is still a debated issue. Importantly, a body of features has been extracted and employed for diagnosis, staging, risk stratification, prognostication, and therapeutic response. 2-[¹⁸F]FDG PET/CT-derived features show promising value in non-invasively diagnosing the malignant nature of pulmonary nodules, differentiating lung cancer subtypes, and predicting response to different therapies as well as survival. In this review article, we aimed to provide an overview of the technical aspects used in radiomics analysis in non-small cell lung cancer (NSCLC) and elucidate the role of 2-[¹⁸F]FDG PET/CT-derived radiomics in the diagnosis, prognostication, and therapeutic response.

Differentiating hypovascular pancreatic neuroendocrine tumors from pancreatic ductal adenocarcinoma based on CT texture analysis

Background

Hypovascular pancreatic neuroendocrine tumor is usually misdiagnosed as pancreatic ductal adenocarcinoma.

Purpose

To investigate the value of texture analysis in differentiating hypovascular pancreatic neuroendocrine tumors from pancreatic ductal adenocarcinoma on contrast-enhanced computed tomography (CT) images.

Material and Methods

Twenty-one patients with hypovascular pancreatic neuroendocrine tumors and 63 patients with pancreatic ductal adenocarcinomas were included in this study. All patients underwent preoperative unenhanced and dynamic contrast-enhanced CT examinations. Two radiologists independently and manually contoured the region of interest of each lesion using texture analysis software on pancreatic parenchymal and portal phase CT images. Multivariate logistic regression analysis was performed to identify significant features to differentiate hypovascular pancreatic neuroendocrine tumors from pancreatic ductal adenocarcinomas. Receiver operating characteristic curve analysis was performed to ascertain diagnostic ability.

Results

The following CT texture features were obtained to differentiate hypovascular pancreatic neuroendocrine tumors from pancreatic ductal adenocarcinomas: RMS (root mean square) (odds ratio [OR] = 0.50, P<0.001), Quantile50 (OR = 1.83, P<0.001), and sumAverage (OR = 0.92, P=0.007) in parenchymal images and “contrast” in portal phase images (OR = 6.08, P<0.001). The areas under the curves were 0.76 for RMS (sensitivity = 0.75, specificity = 0.67), 0.73 for Quantile50 (sensitivity = 0.60, specificity = 0.77), 0.70 for sumAverage (sensitivity = 0.65, specificity = 0.82), 0.85 for the combined texture features (sensitivity = 0.77, specificity = 0.85).

Conclusion

CT texture analysis may be helpful to differentiate hypovascular pancreatic neuroendocrine tumors from pancreatic ductal adenocarcinomas. The three combined texture features showed acceptable diagnostic performance.