Tomography Radiomics Research Articles

Enhancing COPD classification using combined quantitative computed tomography and texture-based radiomics: a CanCOLD cohort study.

Recent advances in texture-based computed tomography (CT) radiomics have demonstrated its potential for classifying COPD. Participants from the Canadian Cohort Obstructive Lung Disease (CanCOLD) study were evaluated. A total of 108 features were included: eight quantitative CT (qCT), 95 texture-based radiomic and five demographic features. Machine-learning models included demographics along with texture-based radiomics and/or qCT. Combinations of five feature selection and five classification methods were evaluated; a training dataset was used for feature selection and to train the models, and a testing dataset was used for model evaluation. Models for classifying COPD status and severity were evaluated using the area under the receiver operating characteristic curve (AUC) with DeLong's test for comparison. SHapely Additive exPlanations (SHAP) analysis was used to investigate the features selected. A total of 1204 participants were evaluated (n=602 no COPD; n=602 COPD). There were no differences between the groups for sex (p=0.77) or body mass index (p=0.21). For classifying COPD status, the combination of demographics, texture-based radiomics and qCT performed better (AUC=0.87) than the combination of demographics and texture-based radiomics (AUC=0.81, p<0.05) or qCT alone (AUC=0.84, p<0.05). Similarly, for classifying COPD severity, the combination of demographics, texture-based radiomics and qCT performed better (AUC=0.81) than demographics and texture-based radiomics (AUC=0.72, p<0.05) or qCT alone (AUC=0.79, p<0.05). Texture-based radiomics and qCT features were among the top five features selected (15th percentile of the CT density histogram, CT total airway count, pack-years, CT grey-level distance zone matrix zone distance entropy, CT low-attenuation clusters) for classifying COPD status. Texture-based radiomics and conventional qCT features in combination improve machine‑learning models for classification of COPD status and severity.

Clinical characteristics and MRI based radiomics nomograms can predict iPFS and short-term efficacy of third-generation EGFR-TKI in EGFR-mutated lung adenocarcinoma with brain metastases

BackgroundPredicting short-term efficacy and intracranial progression-free survival (iPFS) in epidermal growth factor receptor gene mutated (EGFR-mutated) lung adenocarcinoma patients with brain metastases who receive third-generation epidermal growth factor receptor tyrosine kinase inhibitor (EGFR-TKI) therapy was of great significance for individualized treatment. We aimed to construct and validate nomograms based on clinical characteristics and magnetic resonance imaging (MRI) radiomics for predicting short-term efficacy and intracranial progression free survival (iPFS) of third-generation EGFR-TKI in EGFR-mutated lung adenocarcinoma patients with brain metastases.MethodsOne hundred ninety-four EGFR-mutated lung adenocarcinoma patients with brain metastases who received third-generation EGFR-TKI treatment were included in this study from January 1, 2017 to March 1, 2023. Patients were randomly divided into training cohort and validation cohort in a ratio of 5:3. Radiomics features extracted from brain MRI were screened by least absolute shrinkage and selection operator (LASSO) regression. Logistic regression analysis and Cox proportional hazards regression analysis were used to screen clinical risk factors. Single clinical (C), single radiomics (R), and combined (C + R) nomograms were constructed in short-term efficacy predicting model and iPFS predicting model, respectively. Prediction effectiveness of nomograms were evaluated by calibration curves, Harrell’s concordance index (C-index), receiver operating characteristic (ROC) curves and decision curve analysis (DCA). Kaplan-Meier analysis was used to compare the iPFS of high and low iPFS rad-score patients in the predictive iPFS R model and to compare the iPFS of high-risk and low-risk patients in the predictive iPFS C + R model.ResultsOverall response rate (ORR) was 71.1%, disease control rate (DCR) was 91.8% and median iPFS was 12.67 months (7.88–20.26, interquartile range [IQR]). There were significant differences in iPFS between patients with high and low iPFS rad-scores, as well as between high-risk and low-risk patients. In short-term efficacy model, the C-indexes of C + R nomograms in training cohort and validation cohort were 0.867 (0.835-0.900, 95%CI) and 0.803 (0.753–0.854, 95%CI), while in iPFS model, the C-indexes were 0.901 (0.874–0.929, 95%CI) and 0.753 (0.713–0.793, 95%CI).ConclusionsThe third-generation EGFR-TKI showed significant efficacy in EGFR-mutated lung adenocarcinoma patients with brain metastases, and the combined line plot of C + R can be utilized to predict short-term efficacy and iPFS.

High-performance presurgical differentiation of glioblastoma and metastasis by means of multiparametric neurite orientation dispersion and density imaging (NODDI) radiomics

ObjectivesTo evaluate the performance of multiparametric neurite orientation dispersion and density imaging (NODDI) radiomics in distinguishing between glioblastoma (Gb) and solitary brain metastasis (SBM).Materials and methodsIn this retrospective study, NODDI images were curated from 109 patients with Gb (n = 57) or SBM (n = 52). Automatically segmented multiple volumes of interest (VOIs) encompassed the main tumor regions, including necrosis, solid tumor, and peritumoral edema. Radiomics features were extracted for each main tumor region, using three NODDI parameter maps. Radiomics models were developed based on these three NODDI parameter maps and their amalgamation to differentiate between Gb and SBM. Additionally, radiomics models were constructed based on morphological magnetic resonance imaging (MRI) and diffusion imaging (diffusion-weighted imaging [DWI]; diffusion tensor imaging [DTI]) for performance comparison.ResultsThe validation dataset results revealed that the performance of a single NODDI parameter map model was inferior to that of the combined NODDI model. In the necrotic regions, the combined NODDI radiomics model exhibited less than ideal discriminative capabilities (area under the receiver operating characteristic curve [AUC] = 0.701). For peritumoral edema regions, the combined NODDI radiomics model achieved a moderate level of discrimination (AUC = 0.820). Within the solid tumor regions, the combined NODDI radiomics model demonstrated superior performance (AUC = 0.904), surpassing the models of other VOIs. The comparison results demonstrated that the NODDI model was better than the DWI and DTI models, while those of the morphological MRI and NODDI models were similar.ConclusionThe NODDI radiomics model showed promising performance for preoperative discrimination between Gb and SBM.Clinical relevance statementThe NODDI radiomics model showed promising performance for preoperative discrimination between Gb and SBM, and radiomics features can be incorporated into the multidimensional phenotypic features that describe tumor heterogeneity.Key Points• The neurite orientation dispersion and density imaging (NODDI) radiomics model showed promising performance for preoperative discrimination between glioblastoma and solitary brain metastasis.• Compared with other tumor volumes of interest, the NODDI radiomics model based on solid tumor regions performed best in distinguishing the two types of tumors.• The performance of the single-parameter NODDI model was inferior to that of the combined-parameter NODDI model.

Prediction of Lymphovascular invasion status in breast cancer based on magnetic resonance imaging radiomics features

ObjectiveThis study intended to investigate the feasibility and effectiveness of using clinical magnetic resonance imaging (MRI) radiomics features to predict lymphovascular invasion (LVI) status in breast cancer (BC) patients. MethodsA total of 182 BC patients were retrospectively collected and randomly divided into a training set (n = 127) and a validation set (n = 55) in a 7:3 ratio. Based on pathological examination results, the training set was further divided into LVI group (n = 60) and non-LVI group (n = 67), and the validation set was divided into LVI group (n = 24) and non-LVI group (n = 31). General data and MRI examination indicators were compared. Multivariate logistic regression was utilized to analyze MRI radiomics features and clinically relevant indicators that were significant in the baseline information of patients in training set, independent risk factors were identified, and a logistic regression model was built. The accuracy of logistic model was validated using ROC curves in training and validation sets. ResultsAge, pathohistological classification, tumor length, tumor width, presence or absence of Magnetic Resonance Spectroscopy (MRS) cho peak, presence or absence of spicule sign, peritumoral enhancement, and peritumoral edema were statistically significant (P < 0.05) between the two groups. Multivariate logistic regression analysis presented that spicule and peritumoral edema were independent risk factors for LVI in BC patients (P < 0.05). The ROC curve illustrated that AUC of the logistic regression model in the training set was 0.807 (95%CI: 0.730–0.885) and that in the validation set was 0.837 (95%CI: 0.731–0.944). ConclusionRadiomics features of spicule sign and peritumoral edema were independent risk factors for LVI in BC patients. A logistic regression model based on these factors, along with age, could accurately predict LVI occurrence in BC patients, providing data support for diagnosis and modeling of LVI in BC patients.

Tracheal computed tomography radiomics model for prediction of the Omicron variant of severe acute respiratory syndrome coronavirus2.

The Omicron variant of severe acute respiratory syndrome coronavirus2 (SARS-CoV-2) is highly contagious, fast-spreading, and insidious. Most patients present with normal findings on lung computed tomography (CT). The current study aimed to develop and validate atracheal CT radiomics model to predict Omicron variant infection. In this retrospective study, aradiomics model was developed based on atraining set consisting of 157 patients with an Omicron variant infection and 239 healthy controls between 1January and 30April 2022. Aset of morphological expansions, with dilations of1, 3, 5, 7, and 9voxels, was applied to the trachea, and radiomic features were extracted from different dilation voxels of the trachea. Logistic regression (LR), support vector machines (SVM), and random forests (RF) were developed and evaluated; the models were validated on 67patients with the Omicron variant and on 103 healthy controls between 1May and 30July 2022. Logistic regression with 12radiomic features extracted from the tracheal wall with dilation of 5voxels achieved the highest classification performance compared with the other models. The LR model achieved an area under the curve of 0.993 (95% confidence interval [CI]: 0.987-0.998) in the training set and 0.989 (95% CI: 0.979-0.999) in the validation set. Sensitivity, specificity, and accuracy of the model for the training set were 0.994, 0.946, and 0.965, respectively, whereas those for the validation set were 0.970, 0.952, and 0.959, respectively. The tracheal CT radiomics model reliably identified the Omicron variant of SARS-CoV‑2, and may help in clinical decision-making in future, especially in cases of normal lung CT findings.

Multiparametric MRI-based radiomics nomogram for identifying cervix-corpus junction cervical adenocarcinoma from endometrioid adenocarcinoma.

To developed a magnetic resonance imaging (MRI) radiomics nomogram to identify adenocarcinoma at the cervix-corpus junction originating from the endometrium or cervix in order to better guide clinical treatment. Between February 2011 and September 2021, the clinicopathological data and MRI in 143 patients with histopathologically confirmed cervical adenocarcinoma (CAC, n = 86) and endometrioid adenocarcinoma (EAC, n = 57) were retrospectively analyzed at the cervix-corpus junction. Radiomics features were extracted from fat-suppressed T2-weighted imaging (FS-T2WI), diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC) maps, and delayed phase contrast-enhanced T1-weighted imaging (CE-T1WI) sequences. A radiomics nomogram was developed integrating radscore with independent clinical risk factors. The area under the curve (AUC) was used to evaluate the diagnostic efficacy of the radscore, nomogram and two different experienced radiologists in differentiating CAC from EAC at the cervix-corpus junction, and Delong test was applied to compare the differences of their diagnostic performance. In the training cohort, the AUC was 0.93 for radscore; 0.97 for radiomics nomograms; 0.85 and 0.86 for radiologists 1 and 2, respectively. Delong test showed that the differential efficacy of nomogram was significant better than those of radiologists in the training cohort (both P < 0.05). The nomogram based on radscore and clinical risk factors could better differentiate CAC from EAC at the cervix-corpus junction than radiologists, and preoperatively and non-invasively identify the origin of adenocarcinoma at the cervix-corpus junction, which facilitates clinicians to make individualized treatment decision.

Texture analysis of 18F-FDG PET/CT and CECT: Prediction of refractoriness of Hodgkin lymphoma with mediastinal bulk involvement.

To recognize patients at high risk of refractory disease, the identification of novel prognostic parameters improving stratification of newly diagnosed Hodgkin Lymphoma (HL) is still needed. This study investigates the potential value of metabolic and texture features, extracted from baseline 18F-FDG Positron Emission Tomography/Computed Tomography (PET) and Contrast-Enhanced Computed Tomography scan (CECT), together with clinical data, in predicting first-line therapy refractoriness (R) of classical HL (cHL) with mediastinal bulk involvement. We reviewed 69 cHL patients who underwent staging PET and CECT. Lesion segmentation and texture parameter extraction were performed using the freeware software LIFEx 6.3. The prognostic significance of clinical and imaging features was evaluated in relation to the development of refractory disease. Receiver operating characteristic curve, Cox proportional hazard regression and Kaplan-Meier analyses were performed to examine the potential independent predictors and to evaluate their prognostic value. Among clinical characteristics, only stage according to the German Hodgkin Group (GHSG) classification system significantly differed between R and not-R. Among CECT variables, only parameters derived from second order matrices (gray-level co-occurrence matrix (GLCM) and gray-level run length matrix (GLRLM) demonstrated significant prognostic power. Among PET variables, SUVmean, several variables derived from first (histograms, shape), and second order analyses (GLCM, GLRLM, NGLDM) exhibited significant predictive power. Such variables obtained accuracies greater than 70% at receiver operating characteristic analysis and their PFS curves resulted statistically significant in predicting refractoriness. At multivariate analysis, only HISTO_EntropyPET extracted from PET (HISTO_EntropyPET ) and GHSG stage resulted as significant independent predictors. Their combination identified 4 patient groups with significantly different PFS curves, with worst prognosis in patients with higher HISTO_EntropyPET values, regardless of the stage. Imaging radiomics may provide a reference for prognostic evaluation of patients with mediastinal bulky cHL. The best prognostic value in the prediction of R versus not-R disease was reached by combining HISTO_EntropyPET with GHSG stage.

Establishment and verification of a prediction model based on clinical characteristics and computed tomography radiomics parameters for distinguishing benign and malignant pulmonary nodules.

The radiographic classification of pulmonary nodules into benign versus malignant categories is a pivotal component of early lung cancer diagnosis. The present study aimed to investigate clinical and computed tomography (CT) clinical-radiomics nomogram for preoperative differentiation of benign and malignant pulmonary nodules. This retrospective study included 342 patients with pulmonary nodules who underwent high-resolution CT (HRCT) examination. We assigned them to a training dataset (n=239) and a validation dataset (n=103). There are 1781 tumor characteristics quantified by extracted features from the lesion segmented from patients' CT images. The features with poor reproducibility and high redundancy were removed. Then a least absolute shrinkage and selection operator (LASSO) logistic regression model with 10-fold cross-validation was used to further select features and build radiomics signatures. The independent predictive factors were identified by multivariate logistic regression. A radiomics nomogram was developed to predict the malignant probability. The performance and clinical utility of the clinical-radiomics nomogram was evaluated by receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA). After dimension reduction by the LASSO algorithm and multivariate logistic regression, four radiomic features were selected, including original_shape_Sphericity, exponential_glcm_Maximum Probability, log_sigma_2_0_mm_3D_glcm_Maximum Probability, and ogarithm_firstorder_90Percentile. Multivariate logistic regression showed that carcinoembryonic antigen (CEA) [odds ratio (OR) 95% confidence interval (CI): 1.40 (1.09-1.88)], CT rad score [OR (95% CI): 2.74 (2.03-3.85)], and cytokeratin-19-fragment (CYFRA21-1) [OR (95% CI): 1.80 (1.14-2.94)] were independent influencing factors of malignant pulmonary nodule (all P<0.05). The clinical-radiomics nomogram combining CEA, CYFRA21-1 and radiomics features achieved an area of curve (AUC) of 0.85 and 0.76 in the training group and verification group for the prediction of malignant pulmonary nodules. The clinical-radiomics nomogram demonstrated excellent agreement and practicality, as evidenced by the calibration curve and DCA. The clinical-radiomics nomogram combined of CT-based radiomics signature, along with CYFRA21-1 and CEA, demonstrated strong predictive ability, calibration, and clinical usefulness in distinguishing between benign and malignant pulmonary nodules. The use of CT-based radiomics has the potential to assist clinicians in making informed decisions prior to biopsy or surgery while avoiding unnecessary treatment for non-cancerous lesions.

Photoacoustic Imaging Radiomics to Identify Breast Cancer in BI-RADS 4 or 5 Lesions

ObjectivesTo develop a nomogram based on photoacoustic imaging (PAI) radiomics and BI-RADs to identify breast cancer (BC) in BI-RADS 4 or 5 lesions detected by ultrasound (US). MethodsIn this retrospective study, 119 females with 119 breast lesions at US and PAI examination were included (January 2022 to December 2022). Patients were divided into the training set (n = 83) or testing set (n = 36) to develop a nomogram to identify BC in BI-RADS 4 or 5 lesions. Relevant factors at clinic, BI-RADS category, and PAI were reviewed. Univariate and multivariate regression was used to evaluate factors for associations with BC. To evaluate the diagnostic performance of nomogram, the area under the curve (AUC) of receiver operating characteristic curve, accuracy, specificity and sensitivity was employed. ResultsThe nomogram that included BI-RADS category and PAI radiomics score demonstrated a high AUC of 0.925 (95%CI: 0.8467-0.9712) in the training set and 0.926 (95%CI: 0.846-1.000) in the test set. The nomogram also showed significantly better discrimination than the radiomics score (P = .048) or BI-RADS category (P = .009) in the training set. These significant differences were demonstrated in the testing set, outperform the radiomics score (P = .038) and BI-RADS category (P = .013). ConclusionsThe nomogram developed with BI-RADS and PAI radiomics score can effectively identify BC in BI-RADS 4 or 5 lesions. This technique has the potential to further improve early diagnostic accuracy for BC.

Development and validation of ultrasound-based radiomics model to predict germline BRCA mutations in patients with breast cancer

BackgroundIdentifying breast cancer (BC) patients with germline breast cancer susceptibility gene (gBRCA) mutation is important. The current criteria for germline testing for BC remain controversial. This study aimed to develop a nomogram incorporating ultrasound radiomic features and clinicopathological factors to predict gBRCA mutations in patients with BC.Materials and methodsIn this retrospective study, 497 women with BC who underwent gBRCA genetic testing from March 2013 to May 2022 were included, including 348 for training (84 with and 264 without a gBRCA mutation) and 149 for validation(36 patients with and 113 without a gBRCA mutation). Factors associated with gBRCA mutations were identified to establish a clinicopathological model. Radiomics features were extracted from the intratumoral and peritumoral regions (3 mm and 5 mm) of each image. The least absolute shrinkage and selection operator regression algorithm was used to select the features and logistic regression analysis was used to construct three imaging models. Finally, a nomogram that combined clinicopathological and radiomics features was developed. The models were evaluated based on the area under the receiver operating characteristic curve (AUC), calibration, and clinical usefulness.ResultsAge at diagnosis, family history of BC, personal history of other BRCA-related cancers, and human epidermal growth factor receptor 2 status were independent predictors of the clinicopathological model. The AUC of the imaging radiomics model combining intratumoral and peritumoral 3 mm areas in the validation set was 0.783 (95% confidence interval [CI]: 0.702—0.862), which showed the best performance among three imaging models. The nomogram yielded better performance than the clinicopathological model in validation sets (AUC: 0.824 [0.755—0.894] versus 0.659 [0.563—0.755], p = 0.007).ConclusionThe nomogram based on ultrasound images and clinicopathological factors performs well in predicting gBRCA mutations in BC patients and may help to improve clinical decisions about genetic testing.

Machine learning-based radiomics score improves prognostic prediction accuracy of stage II/III gastric cancer: A multi-cohort study.

Although accurately evaluating the overall survival (OS) of gastric cancer patients remains difficult, radiomics is considered an important option for studying prognosis. To develop a robust and unbiased biomarker for predicting OS using machine learning and computed tomography (CT) image radiomics. This study included 181 stage II/III gastric cancer patients, 141 from Lichuan People's Hospital, and 40 from the Cancer Imaging Archive (TCIA). Primary tumors in the preoperative unenhanced CT images were outlined as regions of interest (ROI), and approximately 1700 radiomics features were extracted from each ROI. The skeletal muscle index (SMI) and skeletal muscle density (SMD) were measured using CT images from the lower margin of the third lumbar vertebra. Using the least absolute shrinkage and selection operator regression with 5-fold cross-validation, 36 radiomics features were identified as important predictors, and the OS-associated CT image radiomics score (OACRS) was calculated for each patient using these important predictors. Patients with a high OACRS had a poorer prognosis than those with a low OACRS score (P < 0.05) and those in the TCIA cohort. Univariate and multivariate analyses revealed that OACRS was a risk factor [RR = 3.023 (1.896-4.365), P < 0.001] independent of SMI, SMD, and pathological features. Moreover, OACRS outperformed SMI and SMD and could improve OS prediction (P < 0.05). A novel biomarker based on machine learning and radiomics was developed that exhibited exceptional OS discrimination potential.

Prognostic Value of a Combined Nomogram Model Integrating 3-Dimensional Deep Learning and Radiomics for Head and Neck Cancer.

The preoperative prediction of the overall survival (OS) status of patients with head and neck cancer (HNC) is significant value for their individualized treatment and prognosis. This study aims to evaluate the impact of adding 3D deep learning features to radiomics models for predicting 5-year OS status. Two hundred twenty cases from The Cancer Imaging Archive public dataset were included in this study; 2212 radiomics features and 304 deep features were extracted from each case. The features were selected by univariate analysis and the least absolute shrinkage and selection operator, and then grouped into a radiomics model containing Positron Emission Tomography /Computed Tomography (PET/CT) radiomics features score, a deep model containing deep features score, and a combined model containing PET/CT radiomics features score +3D deep features score. TumorStage model was also constructed using initial patient tumor node metastasis stage to compare the performance of the combined model. A nomogram was constructed to analyze the influence of deep features on the performance of the model. The 10-fold cross-validation of the average area under the receiver operating characteristic curve and calibration curve were used to evaluate performance, and Shapley Additive exPlanations (SHAP) was developed for interpretation. The TumorStage model, radiomics model, deep model, and the combined model achieved areas under the receiver operating characteristic curve of 0.604, 0.851, 0.840, and 0.895 on the train set and 0.571, 0.849, 0.832, and 0.900 on the test set. The combined model showed better performance of predicting the 5-year OS status of HNC patients than the radiomics model and deep model. The combined model was shown to provide a favorable fit in calibration curves and be clinically useful in decision curve analysis. SHAP summary plot and SHAP The SHAP summary plot and SHAP force plot visually interpreted the influence of deep features and radiomics features on the model results. In predicting 5-year OS status in patients with HNC, 3D deep features could provide richer features for combined model, which showed outperformance compared with the radiomics model and deep model.

RADCURE: An open-source head and neck cancer CT dataset for clinical radiation therapy insights.

This manuscript presents RADCURE, one of the most extensive head and neck cancer (HNC) imaging datasets accessible to the public. Initially collected for clinical radiation therapy (RT) treatment planning, this dataset has been retrospectively reconstructed for use in imaging research. RADCURE encompasses data from 3346 patients, featuring computed tomography (CT) RT simulation images with corresponding target and organ-at-risk contours. These CT scans were collected using systems from three different manufacturers. Standard clinical imaging protocols were followed, and contours were manually generated and reviewed at weekly RT quality assurance rounds. RADCURE imaging and structure set data was extracted from our institution's radiation treatment planning and oncology information systems using a custom-built data mining and processing system. Furthermore, images were linked to our clinical anthology of outcomes data for each patient and includes demographic, clinical and treatment information based on the 7th edition TNM staging system (Tumor-Node-Metastasis Classification System of Malignant Tumors). The median patient age is 63, with the final dataset including 80% males. Half of the cohort is diagnosed with oropharyngeal cancer, while laryngeal, nasopharyngeal, and hypopharyngeal cancers account for 25%, 12%, and 5% of cases, respectively. The median duration of follow-up is five years, with 60% of the cohort surviving until the last follow-up point. The dataset provides images and contours in DICOM CT and RT-STRUCT formats, respectively. We have standardized the nomenclature for individual contours-such as the gross primary tumor, gross nodal volumes, and 19 organs-at-risk-to enhance the RT-STRUCT files' utility. Accompanying demographic, clinical, and treatment data are supplied in a comma-separated values (CSV) file format. This comprehensive dataset is publicly accessible via The Cancer Imaging Archive. RADCURE's amalgamation of imaging, clinical, demographic, and treatment data renders it an invaluable resource for a broad spectrum of radiomics image analysis research endeavors. Researchers can utilize this dataset to advance routine clinical procedures using machine learning or artificial intelligence, to identify new non-invasive biomarkers, or to forge prognostic models.

Unmasking pancreatic cancer: Advanced biomedical imaging for its detection in native versus arterial dual‐energy computed tomography (DECT) scans

AbstractThis study investigates the potential of a machine learning classifier using dual‐ energy computed tomography (DECT) radiomics to differentiate between malignant pancreatic lesions and normal pancreas tissue. A total of 100 patients who underwent third‐generation DECT between November 2018 and October 2022 were included, with 60 patients having pancreatic cancer and 40 normal pancreatic tissue. Radiomics features were extracted from non‐contrast and arterial‐enhanced DECT scans with stepwise feature reduction used to identify relevant features. Thetrained machine learning classifiers achieved a diagnostic accuracy of 0.97 in the arterial‐enhanced model and 0.88 in non‐contrast scans with sensitivities of 0.97 and 0.96, respectively. Areas under the curve were 0.97 (95% CI, 0.92–1.0, p &lt; 0.001) and 0.96 (95% CI, 0.90–1.0, p &lt; 0.001), respectively with no significant differences between both models (p= 0.52). This approach shows promise in enhancing pancreatic cancer detection and improving patient diagnoses, particulary in specific patient groups.

Prediction of Microwave Ablation Recurrence in Pulmonary Malignancies Using Preoperative Computed Tomography Radiomics Models.

Assessing the early efficacy of microwave ablation (MWA) for pulmonary malignancies is a challenge for interventionalists. However, performing an accurate efficacy assessment at an earlier stage can significantly enhance clinical intervention and improve the patient's prognosis. This research aimed to create and assess non-invasive diagnostic techniques using pre-operative computed tomography (CT) radiomics models to predict the recurrence of MWA in pulmonary malignancies. We retrospectively enrolled 116 eligible patients with pulmonary malignancies treated with MWA. we separated the patients into two groups: a recurrence group (n = 28) and a non-recurrence group (n = 88), following the modified Response Evaluation Criteria in Solid Tumors (m-RECIST) criteria. We segmented the preoperative tumor area manually. We expanded outward the tumor boundary 4 times, with a width of 3 mm, using the tumor boundary as the baseline. Five groups of radiomics features were extracted and screened using max-relevance and min-redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) regression. Weight coefficients of the aforementioned features were used to calculate the Radscore and construct radiomics models for both tumoral and peritumoral areas. The Radscore from the radiomics model was combined with clinical risk factors to construct a combined model. The performance and clinical usefulness of the combined models were assessed through the evaluation of receiver operating characteristic (ROC) curves, the Delong test, calibration curves, and decision curve analysis (DCA) curves. The clinical risk factor for recurrence after MWA was tumor diameter (P < 0.05). Both tumoral and four peritumoral radiomics models exhibited high diagnostic efficacy. Furthermore, the combined 1 (C1)-RO model and the combined 2 (C2)-RO model showed higher efficacy with area under the curve (AUCs) of 0.89 and 0.89 in the training cohort, and 0.93 and 0.94 in the validation cohort, respectively. Both combined models demonstrated excellent predictive accuracy and clinical benefit. Preoperative CT radiomics models for both tumoral and peritumoral regions are capable of accurately predicting the recurrence of pulmonary malignancies after MWA. The combination of both models may lead to better performance and may aid in devising more effective preoperative treatment strategies.

Application of magnetic resonance imaging radiomics in endometrial cancer: a systematic review and meta-analysis.

We aimed to systematically assess the methodological quality and clinical potential application of published magnetic resonance imaging (MRI)-based radiomics studies about endometrial cancer (EC). Studies of EC radiomics analyses published between 1 January 2000 and 19 March 2023 were extracted, and their methodological quality was evaluated using the radiomics quality score (RQS) and Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Pairwise correlation analyses and separate meta-analyses of studies exploring differential diagnoses and risk prediction were also performed. Forty-five studies involving 3 aims were included. The mean RQS was 13.77 (range: 9-22.5); publication bias was observed in the areas of 'index test' and 'flow and timing'. A high RQS was significantly associated with therapy selection-aimed studies, low QUADAS-2 risk, recent publication year, and high-performance metrics. Raw data from 6 differential diagnosis and 34 risk prediction models were subjected to meta-analysis, revealing diagnostic odds ratios of 23.81 (95% confidence interval [CI] 8.48-66.83) and 18.23 (95% CI 13.68-24.29), respectively. The methodological quality of radiomics studies involving patients with EC is unsatisfactory. However, MRI-based radiomics analyses showed promising utility in terms of differential diagnosis and risk prediction.

Machine learning-based MRI radiomics for assessing the level of tumor infiltrating lymphocytes in oral tongue squamous cell carcinoma: a pilot study

BackgroundTo investigate the value of machine learning (ML)-based magnetic resonance imaging (MRI) radiomics in assessing tumor-infiltrating lymphocyte (TIL) levels in patients with oral tongue squamous cell carcinoma (OTSCC).MethodsThe study included 68 patients with pathologically diagnosed OTSCC (30 with high TILs and 38 with low TILs) who underwent pretreatment MRI. Based on the regions of interest encompassing the entire tumor, a total of 750 radiomics features were extracted from T2-weighted (T2WI) and contrast-enhanced T1-weighted (ceT1WI) imaging. To reduce dimensionality, reproducibility analysis by two radiologists and collinearity analysis were performed. The top six features were selected from each sequence alone, as well as their combination, using the minimum-redundancy maximum-relevance algorithm. Random forest, logistic regression, and support vector machine models were used to predict TIL levels in OTSCC, and 10-fold cross-validation was employed to assess the performance of the classifiers.ResultsBased on the features selected from each sequence alone, the ceT1WI models outperformed the T2WI models, with a maximum area under the curve (AUC) of 0.820 versus 0.754. When combining the two sequences, the optimal features consisted of one T2WI and five ceT1WI features, all of which exhibited significant differences between patients with low and high TILs (all P < 0.05). The logistic regression model constructed using these features demonstrated the best predictive performance, with an AUC of 0.846 and an accuracy of 80.9%.ConclusionsML-based T2WI and ceT1WI radiomics can serve as valuable tools for determining the level of TILs in patients with OTSCC.

Analysis of the diagnostic value of CT radiomics models in differentiating GIST and other mesenchymal tumors.

To analyze the diagnostic value of computed tomography (CT) radiomics models in differentiating gastrointestinal stromal tumors (GIST) and other mesenchymal tumors. A retrospective analysis of clinical data from 153 patients with pathologically confirmed gastrointestinal mesenchymal tumors treated in our hospital from July 2019 to March 2024 was conducted, including 107 cases of GIST, 18 cases of leiomyoma, and 28 cases of schwannoma. LASSO regression was used for feature selection. Logistic regression and Random Forest (RF) models were established based on selected features using machine learning algorithms, with the dataset divided into training (107 cases) and validation sets (46 cases) at a 7:3 ratio. The diagnostic performance of the models was evaluated using receiver operating characteristic (ROC) curves. In the training set, there were significant differences between GIST and non-GIST in terms of enhancement degree, age, maximum diameter, and tumor location distribution (P<0.05). A total of 180 radiomics features were extracted using A.K software. LASSO regression reduced the high-dimensional data to 13 radiomics features. Logistic regression and RF models were established based on these 13 features. The AUC for the Logistic regression model was 0.753 in the training set and 0.582 in the validation set, while the AUC for the RF model was 0.941 in the training set and 0.746 in the validation set. The RF model showed higher diagnostic performance than the Logistic regression model (P<0.05). Decision curve analysis showed that the net benefit of the RF model in differentiating GIST was superior to classifying all patients as either GIST or non-GIST and also superior to the Logistic regression model within a probability threshold range of 20%-90%. The machine learning models based on radiomics features have good diagnostic value in predicting the pathological classification of GIST and other mesenchymal tumors, with the RF model showing superior diagnostic value compared to the Logistic regression model.

A clinically relevant computed tomography (CT) radiomics strategy for intracranial rodent brain tumour monitoring

Here, we establish a CT-radiomics based method for application in invasive, orthotopic rodent brain tumour models. Twenty four NOD/SCID mice were implanted with U87R-Luc2 GBM cells and longitudinally imaged via contrast enhanced (CE-CT) imaging. Pyradiomics was employed to extract CT-radiomic features from the tumour-implanted hemisphere and non-tumour-implanted hemisphere of acquired CT-scans. Inter-correlated features were removed (Spearman correlation > 0.85) and remaining features underwent predictive analysis (recursive feature elimination or Boruta algorithm). An area under the curve of the receiver operating characteristic curve was implemented to evaluate radiomic features for their capacity to predict defined outcomes. Firstly, we identified a subset of radiomic features which distinguish the tumour-implanted hemisphere and non- tumour-implanted hemisphere (i.e, tumour presence from normal tissue). Secondly, we successfully translate preclinical CT-radiomic pipelines to GBM patient CT scans (n = 10), identifying similar trends in tumour-specific feature intensities (E.g. ‘glszm Zone Entropy’), thereby suggesting a mouse-to-human species conservation (a conservation of radiomic features across species). Thirdly, comparison of features across timepoints identify features which support preclinical tumour detection earlier than is possible by visual assessment of CT scans. This work establishes robust, preclinical CT-radiomic pipelines and describes the application of CE-CT for in-depth orthotopic brain tumour monitoring. Overall we provide evidence for the role of pre-clinical ‘discovery’ radiomics in the neuro-oncology space.

Utility of contrast-enhanced MRI radiomics features combined with clinical indicators for predicting induction chemotherapy response in primary central nervous system lymphoma.

To assess the utility of combining contrast-enhanced magnetic resonance imaging (CE-MRI) radiomics features with clinical variables in predicting the response to induction chemotherapy (IC) for primary central nervous system lymphoma (PCNSL). A total of 131 patients with PCNSL (101 in the training set and 30 in the testing set) who had undergone contrast-enhanced MRI scans were retrospectively analyzed. Pyradiomics was utilized to extract radiomics features, and the clinical variables of the patients were gathered. Radiomics prediction models were developed using different combinations of feature selection methods and machine learning models, and the best combination was ultimately chosen. We screened clinical variables associated with treatment outcomes and developed clinical prediction models. The predictive performance of radiomics model, clinical model, and combined model, which integrates the best radiomics model and clinical characteristics, was independently assessed and compared using Receiver Operating Characteristic (ROC) curves. In total, we extracted 1598 features. The best radiomics model we selected as the best utilized T-test and Recursive Feature Elimination (RFE) for feature selection and logistic regression for model building. Serum Interleukin 2 Receptor (IL-2R) and Eastern Cooperative Oncology Group (ECOG) Score were utilized to develop a clinical predictive model for assessing the response to induction chemotherapy. The results of the testing set revealed that the combined prediction model (radiomics and IL-2R) achieved the highest area under the ROC curve at 0.868 (0.683, 0.967), followed by the radiomics model at 0.857 (0.681, 0.957), and the clinical prediction model (IL-2R and ECOG) at 0.618 (0.413, 0.797). The combined model was significantly more accurate than the clinical model, with an AUC of 0.868 compared to 0.618 (P < 0.05). While the radiomics model had slightly better predictive power than the clinical model, this difference was not statistically significant (AUC, 0.857 vs. 0.618, P > 0.05). Our prediction model, which combines radiomics signatures from CE-MRI with serum IL-2R, can effectively stratify patients with PCNSL before high-dose methotrexate (HD-MTX) -based chemotherapy.