MRI Radiomics Research Articles

Molecular subtypes of breast cancer identified by dynamically enhanced MRI radiomics: the delayed phase cannot be ignored

ObjectivesTo compare the diagnostic performance of intratumoral and peritumoral features from different contrast phases of breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) by building radiomics models for differentiating molecular subtypes of breast cancer.MethodsThis retrospective study included 377 patients with pathologically confirmed breast cancer. Patients were divided into training set (n = 202), validation set (n = 87) and test set (n = 88). The intratumoral volume of interest (VOI) and peritumoral VOI were delineated on primary breast cancers at three different DCE-MRI contrast phases: early, peak, and delayed. Radiomics features were extracted from each phase. After feature standardization, the training set was filtered by variance analysis, correlation analysis, and least absolute shrinkage and selection (LASSO). Using the extracted features, a logistic regression model based on each tumor subtype (Luminal A, Luminal B, HER2-enriched, triple-negative) was established. Ten models based on intratumoral or/plus peritumoral features from three different phases were developed for each differentiation.ResultsRadiomics features extracted from delayed phase DCE-MRI demonstrated dominant diagnostic performance over features from other phases. However, the differences were not statistically significant. In the full fusion model for differentiating different molecular subtypes, the most frequently screened features were those from the delayed phase. According to the Shapley additive explanation (SHAP) method, the most important features were also identified from the delayed phase.ConclusionsThe intratumoral and peritumoral radiomics features from the delayed phase of DCE-MRI can provide additional information for preoperative molecular typing. The delayed phase of DCE-MRI cannot be ignored.Critical relevance statementRadiomics features extracted and radiomics models constructed from the delayed phase of DCE-MRI played a crucial role in molecular subtype classification, although no significant difference was observed in the test cohort.Key PointsThe molecular subtype of breast cancer provides a basis for setting treatment strategy and prognosis.The delayed-phase radiomics model outperformed that of early-/peak-phases, but no differently than other phases or combinations.Both intra- and peritumoral radiomics features offer valuable insights for molecular typing.Graphical

Preoperative prediction of HER-2 expression status in breast cancer based on MRI radiomics model

Objective: This study aims to explore the predictive value of T2-weighted imaging (T2WI), apparent diffusion coefficient (ADC), and early-delayed phases enhanced magnetic resonance imaging (DCE-MRI) radiomics prediction model in determining human epidermal growth factor receptor 2 status in breast cancer. Methods: A retrospective study was conducted, involving 187 patients with confirmed breast cancer by postsurgical pathology at Zhenjiang First People's Hospital during January 2021 and May 2023. Immunohistochemistry or fluorescence in situ hybridization was used to determine the HER-2 status of these patients, with 48 cases classified as HER-2 positive and 139 cases as HER-2 negative. The training set was used to construct the prediction models and the validation set was used to verify the prediction models. Layers of T2WI, ADC, and early-delayed phase DCE-MRI images were used to delineate the volumeof interest and 960 radiomic features were extracted from each case using Pyradiomic. After screening and dimensionality reduction by intraclass correlation coefficient, Pearson correlation analysis, least absolute shrinkage, and selection operator, the radiomics labels were established. Logistic regression analysis was used to construct the T2WI radiomics model, ADC radiomics model, DCE-2 radiomics model, DCE-6 radiomics model, and the joint sequence radiomics model to predict the HER-2 expression status of breast cancer, respectively. Based on the clinical, pathological, and MRI image characteristics of patients, univariate and multivariate logistic regression analysis wasused to construct a clinicopathological MRI feature model. The radscore of every patient and the clinicopathological MRI features which were statistically significant after screening were used to construct a nomogram model. The receiver operating characteristic (ROC) curve was used to evaluate the predictive performance of each model and the decision curve analysis wasused to evaluate the clinical usefulness. Results: The T2WI, ADC, DCE-2, DCE-6, and joint sequence radiomics models, the clinicopathological MRI feature model, and the nomogram model were successfully constructed to predict the expression status of HER-2 in breast cancer. ROC analysis showed that in the training set and validation set, the areas under the curve (AUC) of the T2WI radiomics model were 0.797 and 0.760, of the ADC radiomics model were 0.776 and 0.634, of the DCE-2 radiomics model were 0.804 and 0.759, of the DCE-6 radiomics model were 0.869 and 0.798, of the combined sequence radiomics model were 0.908 and 0.847, of the clinicopathological MRI feature model were 0.703 and 0.693, and of the nomogram model were 0.938 and 0.859, respectively. In the training set, the combined sequence radiomics model outperformed the clinicopathological features model (P＜0.001). In the training and validation sets, the nomogram outperformed the clinicopathological features model (P＜0.05). In addition, the diagnostic performance of the nomogram was better than that of the four single-modality radiomics models in the training cohort (P＜0.05) and was better than that of DCE-2 and ADC models in the validation cohort (P＜0.05). Decision curve analysis indicated that the value of individualized prediction models was higher than clinical and pathological prediction models in clinical practice. The calibration curve showed that the multimodal radiomics model had a high consistency with the actual results in predicting HER-2 expression. Conclusions: T2WI, ADC and early-delayed phase DCE-MRI imaging histology models for HER-2 expression status in breast cancer are expected to provide a non-invasive virtual pathological basis for decision-making on preoperative neoadjuvant regimens in breast cancer.

MRI radiomics based on deep learning automated segmentation to predict early recurrence of hepatocellular carcinoma.

To investigate the utility of deep learning (DL) automated segmentation-based MRI radiomic features and clinical-radiological characteristics in predicting early recurrence after curative resection of single hepatocellular carcinoma (HCC). This single-center, retrospective study included consecutive patients with surgically proven HCC who underwent contrast-enhanced MRI before curative hepatectomy from December 2009 to December 2021. Using 3D U-net-based DL algorithms, automated segmentation of the liver and HCC was performed on six MRI sequences. Radiomic features were extracted from the tumor, tumor border extensions (5 mm, 10 mm, and 20 mm), and the liver. A hybrid model incorporating the optimal radiomic signature and preoperative clinical-radiological characteristics was constructed via Cox regression analyses for early recurrence. Model discrimination was characterized with C-index and time-dependent area under the receiver operating curve (tdAUC) and compared with the widely-adopted BCLC and CNLC staging systems. Four hundred and thirty-four patients (median age, 52.0 years; 376 men) were included. Among all radiomic signatures, HCC with 5 mm tumor border extension and liver showed the optimal predictive performance (training set C-index, 0.696). By incorporating this radiomic signature, rim arterial phase hyperenhancement (APHE), and incomplete tumor "capsule," a hybrid model demonstrated a validation set C-index of 0.706 and superior 2-year tdAUC (0.743) than both the BCLC (0.550; p < 0.001) and CNLC (0.635; p = 0.032) systems. This model stratified patients into two prognostically distinct risk strata (both datasets p < 0.001). A preoperative imaging model incorporating the DL automated segmentation-based radiomic signature with rim APHE and incomplete tumor "capsule" accurately predicted early postsurgical recurrence of a single HCC. The DL automated segmentation-based MRI radiomic model with rim APHE and incomplete tumor "capsule" hold the potential to facilitate individualized risk estimation of postsurgical early recurrence in a single HCC. A hybrid model integrating MRI radiomic signature was constructed for early recurrence prediction of HCC. The hybrid model demonstrated superior 2-year AUC than the BCLC and CNLC systems. The model categorized the low-risk HCC group carried longer RFS.

Radiomic profiles improve prognostication and reveal targets for therapy in cervical cancer.

Cervical cancer (CC) is a major global health problem with 570,000 new cases and 266,000 deaths annually. Prognosis is poor for advanced stage disease, and few effective treatments exist. Preoperative diagnostic imaging is common in high-income countries and MRI measured tumor size routinely guides treatment allocation of cervical cancer patients. Recently, the role of MRI radiomics has been recognized. However, its potential to independently predict survival and treatment response requires further clarification. This retrospective cohort study demonstrates how non-invasive, preoperative, MRI radiomic profiling may improve prognostication and tailoring of treatments and follow-ups for cervical cancer patients. By unsupervised clustering based on 293 radiomic features from 132 patients, we identify three distinct clusters comprising patients with significantly different risk profiles, also when adjusting for FIGO stage and age. By linking their radiomic profiles to genomic alterations, we identify putative treatment targets for the different patient clusters (e.g., immunotherapy, CDK4/6 and YAP-TEAD inhibitors and p53 pathway targeting treatments).

Association Analysis Between Intratumoral and Peritumoral MRI Radiomics Features and Overall Survival of Neoadjuvant Therapy in Rectal Cancer.

The use of peritumoral features to determine the survival time of patients with rectal cancer (RC) is still imprecise. To explore the correlation between intratumoral, peritumoral and combined features, and overall survival (OS). Retrospective. One hundred sixty-six RC patients (53 women, 113 men; average age: 55 ± 12 years) who underwent radical resection after neoadjuvant therapy. 3 T; T2WI sagittal, T1WI axial, T2WI axial with fat suppression, and high-resolution T2WI axial sequences, enhanced T1WI axial and sagittal sequences with fat suppression. Radiologist A segmented 166 patients, and radiologist B randomly segmented 30 patients. Intratumoral and peritumoral features were extracted, and features with good stability (ICC ≥0.75) were retained through intra-observer analysis. Seven classifiers, including Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest (RF), Extremely randomized trees (ET), eXtreme Gradient Boosting (XGBoost), and LightGBM (LGBM), were applied to select the classifier with the best performance. Next, the Rad-score of best classifier and the clinical features were selected to establish the models, thus, nomogram was built to identify the association with 1-, 3-, and 5-year OS. LASSO, regression analysis, ROC, DeLong method, Kaplan-Meier curve. P < 0.05 indicated a significant difference. Only Node (irregular tumor nodules in the surrounding mesentery) and ExtraMRF (lymph nodes outside the perirectal mesentery) were significantly different in 20 clinical features. Twelve intratumoral, 3 peritumoral, and 14 combined features related to OS were selected. LR, SVM, and RF classier showed the best efficacy in the intratumoral, peritumoral, and combined model, respectively. The combined model (AUC = 0.954 and 0.821) had better survival association than the intratumoral model (AUC = 0.833 and 0.813) and the peritumoral model (AUC = 0.824 and 0.687). The proposed peritumoral model with radiomics features may serve as a tool to improve estimated survival time. 3 TECHNICAL EFFICACY: Stage 4.

Personalizing Deep Brain Stimulation Therapy for Parkinson's Disease With Whole-Brain MRI Radiomics and Machine Learning.

Background Deep brain stimulation (DBS) is a well-recognised treatment for advanced Parkinson's disease (PD) patients. Structural brain alterations of the white matter can correlate with disease progression and act as a biomarker for DBS therapy outcomes. This study aims to develop a machine learning-driven predictive model for DBS patient selection using whole-brain white matter radiomics and common clinical variables. Methodology A total of 120 PD patients underwent DBS of the subthalamic nucleus. Their therapy effect was assessed at the one-year follow-up with the Unified Parkinson's Disease Rating Scale-part III (UPDRSIII) motor component. Radiomics analysis of whole-brain white matter was performed with PyRadiomics. The following machine learning methods were used: logistic regression (LR), support vector machine, naïve Bayes, K-nearest neighbours, and random forest (RF) to allow prediction of clinically meaningful UPRDSIII motor response before and after. Clinical variables were also added to the model to improve accuracy. Results The RF model showed the best performance on the final whole dataset with an area under the curve (AUC) of 0.99, accuracy of 0.95, sensitivity of 0.93, and specificity of 0.97. At the same time, the LR model showed an AUC of 0.93, accuracy of 0.88, sensitivity of 0.84, and specificity of 0.91. Conclusions Machine learning models can be used in clinical decision support tools which can deliver true personalised therapy recommendations for PD patients. Clinicians and engineers should choose between best-performing, less interpretable models vs. most interpretable, lesser-performing models. Larger clinical trials would allow to build trust among clinicians and patients to widely use these AI tools in the future.

Abstract PO3-28-10: MRI Radiomic phenotypes derived from the ECOG-ACRIN E4112 Trial to assess high-risk ductal carcinoma in situ

Abstract INTRODUCTION Ductal carcinoma in situ (DCIS) is a non-lethal pre-invasive breast cancer that can co-exist with invasive disease. Dynamic contrast-enhanced (DCE) MRI is sensitive for the detection of high-grade DCIS and invasive cancer while Oncotype DCIS Score is a 12-gene assay that can assess recurrence risk. In practice, it is difficult to distinguish low- from high-risk DCIS, which leads to overtreatment for up to half of women diagnosed with DCIS. We hypothesize that radiomic phenotypes of DCIS derived from DCE-MRI data may serve as prognostic markers to improve risk stratification by capturing disease heterogeneity. Here we evaluate the ability of these phenotypes to predict DCIS Score and upstaging of DCIS to invasive disease on wide local excision in a multicenter trial. METHODS Data: DCE-MRI data from the ECOG-ACRIN E4112 trial were retrospectively analyzed. Primary analysis focused on participants with data on disease upstaging (N=295), with secondary analysis in a subset (N=174) of participants with DCIS Scores (dichotomized as &amp;gt;55 and 55) and pure DCIS. Clinical information included patient demographics, lesion morphology on MRI, background parenchymal enhancement, DCIS grade, central necrosis, and hormone receptor status. Data analysis: Radiologist-drawn lesion segmentations and publicly available software, CaPTk, were used to compute 64 radiomic features from first post-contrast images for each participant. Radiomic phenotypes were identified using hierarchical clustering on the extracted features. A Chi-square test was used to evaluate the association between radiomic phenotypes and each outcome. The likelihood ratio test was used to compare two logistic regression models: 1)clinical model using only clinical information as predictors and 2) clinical+phenotypes model using clinical information and phenotype assignment as predictors. Each model was used for the prediction of upstaging to invasive disease and DCIS score. Model performance was evaluated as the 10-fold cross-validated area under the receiver operator characteristic curve (AUC). A p&amp;lt; 0.05 was considered significant. RESULTS A total of 45 (15%) cases upstaged to invasive disease. Two radiomic phenotypes were identified: Phenotype 1 indicated greater lesion signal heterogeneity, while Phenotype 2 indicated lower heterogeneity. Radiomic phenotype was strongly associated with disease upstaging (p=0.0034) – with a higher rate of upstaging for Phenotype 1 – but not with DCIS score (p=0.1174, Table 1). For predicting disease upstaging, the clinical+phenotypes model yielded a higher AUC=0.72 and a significantly better fit to the data (p=0.0022) compared to the clinical model parameterized by clinical information alone (AUC=0.69). For predicting DCIS Score, the clinical+phenotypes model (AUC=0.77) showed similar performance compared to the clinical model (AUC=0.76) and no significant improvement in fit to the data (p=0.2920). CONCLUSION Radiomic phenotypes capturing disease heterogeneity show promise as prognostic predictors for predicting disease upstaging in DCIS compared to clinical information alone and may enable more efficient disease management. We observed that phenotypes did not have independent predictive outcome for DCIS score, suggesting that MRI and DCIS Score offer independent information and could be combined in future models to better predict disease recurrence or progression. Clinical applications of radiomic phenotypes may improve risk stratification and potentially result in decreased overtreatment of women diagnosed with DCIS. Table 1: Association between radiomic phenotypes and DCIS outcomes using a Chi square test. Citation Format: Kalina Slavkova, Ruya Kang, Vivian Belenky, Anum Kazerouni, Debosmita Biswas, Hannah Horng, Rhea Chitalia, Michael Hirano, Jennifer Xiao, Ralph Corsetti, Sarah Javid, Derrick Spell, Antonio Wolff, Joseph Sparano, Seema Khan, Christopher Comstock, Justin Romanoff, Jon Steingrimsson, Constantine Gatsonis, Constance Lehman, Savannah Partridge, Despina Kontos, Habib Rahbar. MRI Radiomic phenotypes derived from the ECOG-ACRIN E4112 Trial to assess high-risk ductal carcinoma in situ [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO3-28-10.

Predicting the presence of adherent perinephric fat using MRI radiomics combined with machine learning

ObjectivesAdherent perinephric fat (APF) poses significant challenges to surgical procedures. This study aimed to evaluate the usefulness of machine learning algorithms combined with MRI-based radiomics features for predicting the presence of APF. Materials and MethodsPatients with renal cell carcinoma who underwent surgery between April 2019 and February 2022 at Chonnam National University Hwasun Hospital were retrospectively screened, and 119 patients included. Twenty-one and seventeen patients were set aside for the internal and external test sets, respectively. Pre-operative T1-weighted MRI acquired at 60 s following a contrast injection (T1w-60) were collected. For each T1w-60 data, two regions of interest (ROIs) were manually drawn: the perinephric fat tissue and an aorta segment on the same level as the targeted kidney. Preprocessing steps included resizing voxels, N4 Bias Correction filtering, and aorta-based normalization. For each patient, 851 radiomics features were extracted from the ROI of perinephric fat tissue. Gender and BMI were added as clinical factors. Least Absolute Shrinkage and Selection Operator was adopted for feature selection. We trained and evaluated five models using a 4-fold cross validation. The final model was chosen based on the highest mean AUC across four folds. The performance of the final model was evaluated on the internal and external test sets. ResultsA total of 15 features were selected in the final set. The final model achieved the accuracy, sensitivity, specificity, and AUC of 81% (95% confidence interval, 61.9–95.2%), 72.7% (42.9–100%), 90% (66.7–100%), and 0.855 (0.615–1.0), respectively on the internal test set, and 88.2% (70.6–100%), 100% (100–100%), 80% (50%–100%), 0.971 (0.871–1.0), respectively on the external test set. ConclusionsOur study demonstrated the feasibility of machine learning algorithms trained with MRI-based radiomics features for APF prediction. Further studies with a multi-center approach are necessary to validate our findings.

Contrast Agent Dynamics Determine Radiomics Profiles in Oncologic Imaging.

The reproducibility of radiomics features extracted from CT and MRI examinations depends on several physiological and technical factors. The aim was to evaluate the impact of contrast agent timing on the stability of radiomics features using dynamic contrast-enhanced perfusion CT (dceCT) or MRI (dceMRI) in prostate and lung cancers. Radiomics features were extracted from dceCT or dceMRI images in patients with biopsy-proven peripheral prostate cancer (pzPC) or biopsy-proven non-small cell lung cancer (NSCLC), respectively. Features that showed significant differences between contrast phases were identified using linear mixed models. An L2-penalized logistic regression classifier was used to predict class labels for pzPC and unaffected prostate regions-of-interest (ROIs). Nine pzPC and 28 NSCLC patients, who were imaged with dceCT and/or dceMRI, were included in this study. After normalizing for individual enhancement patterns by defining seven individual phases based on a reference vessel, 19, 467 and 128 out of 1204 CT features showed significant temporal dynamics in healthy prostate parenchyma, prostate tumors and lung tumors, respectively. CT radiomics-based classification accuracy of healthy and tumor ROIs was highly dependent on contrast agent phase. For dceMRI, 899 and 1027 out of 1118 features were significantly dependent on time after contrast agent injection for prostate and lung tumors. CT and MRI radiomics features in both prostate and lung tumors are significantly affected by interindividual differences in contrast agent dynamics.

Survival Outcome Prediction in Glioblastoma: Insights from MRI Radiomics.

Background: Extracting multiregional radiomic features from multiparametric MRI for predicting pretreatment survival in isocitrate dehydrogenase (IDH) wild-type glioblastoma (GBM) patients is a promising approach. Methods: MRI data from 49 IDH wild-type glioblastoma patients pre-treatment were utilized. Diffusion and perfusion maps were generated, and tumor subregions segmented. Radiomic features were extracted for each tissue type and map. Feature selection on 1862 radiomic features identified 25 significant features. The Cox proportional-hazards model with LASSO regularization was used to perform survival analysis. Internal and external validation used a 38-patient training cohort and an 11-patient validation cohort. Statistical significance was set at p < 0.05. Results: Age and six radiomic features (shape and first and second order) from T1W, diffusion, and perfusion maps contributed to the final model. Findings suggest that a small necrotic subregion, inhomogeneous vascularization in the solid non-enhancing subregion, and edema-related tissue damage in the enhancing and edema subregions are linked to poor survival. The model's C-Index was 0.66 (95% C.I. 0.54-0.80). External validation demonstrated good accuracy (AUC > 0.65) at all time points. Conclusions: Radiomics analysis, utilizing segmented perfusion and diffusion maps, provide predictive indicators of survival in IDH wild-type glioblastoma patients, revealing associations with microstructural and vascular heterogeneity in the tumor.

Development and Validation of MRI Radiomics Models to Differentiate HER2-Zero, -Low, and -Positive Breast Cancer.

BACKGROUND. Breast cancer HER2 expression has been redefined using a three-tiered system, with HER2-zero cancers considered ineligible for HER2-targeted therapy, HER2-low cancers considered candidates for novel HER2-targeted drugs, and HER2-positive cancers treated with traditional HER2-targeted medications. OBJECTIVE. The purpose of this study was to assess MRI radiomics models for a three-tiered classification of HER2 expression of breast cancer. METHODS. This retrospective study included 592 patients with pathologically confirmed breast cancer (mean age, 47.0 ± 18.0 [SD] years) who underwent breast MRI at either of a health system's two hospitals from April 2016 through June 2022. Three-tiered HER2 status was pathologically determined. Radiologists assessed the conventional MRI features of tumors and manually segmented the tumors on multiparametric sequences (T2-weighted images, DWI, ADC maps, and T1-weighted delayed contrast-enhanced images) to extract radiomics features. Least absolute shrinkage and selection operator analysis was used to develop two radiomics signatures, to differentiate HER2-zero cancers from HER2-low or HER2-positive cancers (task 1) as well as to differentiate HER2-low cancers from HER2-positive cancers (task 2). Patients from hospital 1 were randomly assigned to a discovery set (task 1: n = 376; task 2: n = 335) or an internal validation set (task 1: n = 161; task 2: n = 143); patients from hospital 2 formed an external validation set (task 1: n = 55; task 2: n = 50). Multivariable logistic regression analysis was used to create nomograms combining radiomics signatures with clinicopathologic and conventional MRI features. RESULTS. AUC, sensitivity, and specificity in the discovery, internal validation, and external validation sets were as follows: for task 1, 0.89, 99.4%, and 69.0%; 0.86, 98.6%, and 76.5%; and 0.78, 100.0%, and 0.0%, respectively; for task 2, 0.77, 93.8%, and 32.3%; 0.75, 92.9%, and 6.8%; and 0.77, 97.0%, and 29.4%, respectively. For task 1, no nomogram was created because no clinicopathologic or conventional MRI feature was associated with HER2 status independent of the MRI radiomics signature. For task 2, a nomogram including an MRI radiomics signature and three pathologic features (histologic grade of III, high Ki-67 index, and positive progesterone receptor status) that were independently associated with HER2-low expression had an AUC of 0.87, 0.83, and 0.80 in the three sets. CONCLUSION. MRI radiomics features were used to differentiate HER2-zero from HER2-low cancers or HER2-positives cancers as well as to differentiate HER2-low cancers from HER2-positive cancers. CLINICAL IMPACT. MRI radiomics may help select patients for novel or traditional HER2-targeted therapies, particularly those patients with ambiguous results of immunohistochemical staining results or limited access to fluorescence in situ hybridization.

An integrated radiology-pathology machine learning classifier for outcome prediction following radical prostatectomy: Preliminary findings

ObjectivesTo evaluate the added benefit of integrating features from pre-treatment MRI (radiomics) and digitized post-surgical pathology slides (pathomics) in prostate cancer (PCa) patients for prognosticating outcomes post radical-prostatectomy (RP) including a) rising prostate specific antigen (PSA), and b) extraprostatic-extension (EPE). MethodsMulti-institutional data (N = 58) of PCa patients who underwent pre-treatment 3-T MRI prior to RP were included in this retrospective study. Radiomic and pathomic features were extracted from PCa regions on MRI and RP specimens delineated by expert clinicians. On training set (D1, N = 44), Cox Proportional-Hazards models MR, MP and MRaP were trained using radiomics, pathomics, and their combination, respectively, to prognosticate rising PSA (PSA > 0.03 ng/mL). Top features from MRaP were used to train a model to predict EPE on D1 and test on external dataset (D2, N = 14). C-index, Kalplan-Meier curves were used for survival analysis, and area under ROC (AUC) was used for EPE. MRaP was compared with the existing post-treatment risk-calculator, CAPRA (MC). ResultsPatients had median follow-up of 34 months. MRaP (c-index = 0.685 ± 0.05) significantly outperformed MR (c-index = 0.646 ± 0.05), MP (c-index = 0.631 ± 0.06) and MC (c-index = 0.601 ± 0.071) (p < 0.0001). Cross-validated Kaplan-Meier curves showed significant separation among risk groups for rising PSA for MRaP (p < 0.005, Hazard Ratio (HR) = 11.36) as compared to MR (p = 0.64, HR = 1.33), MP (p = 0.19, HR = 2.82) and MC (p = 0.10, HR = 3.05). Integrated radio-pathomic model MRaP (AUC = 0.80) outperformed MR (AUC = 0.57) and MP (AUC = 0.76) in predicting EPE on external-data (D2). ConclusionsResults from this preliminary study suggest that a combination of radiomic and pathomic features can better predict post-surgical outcomes (rising PSA and EPE) compared to either of them individually as well as extant prognostic nomogram (CAPRA).

An MRI radiomics approach to discriminate hemorrhage prone intracranial tumors before stereotactic biopsy.

To explore imaging biomarkers predictive of intratumoral hemorrhage for lesions intended for elective stereotactic biopsy. This study included a retrospective cohort of 143 patients with 175 intracranial lesions intended for stereotactic biopsy. All the lesions were randomly split into a training dataset (n=121) and a test dataset (n=54) at a ratio of 7:3. 34 lesions were defined as "hemorrhage-prone tumors" as hemorrhage occurred between initial diagnostic MRI acquisition and the scheduled biopsy procedure. Radiomics features were extracted from the contrast-enhanced T1WI and T2WI images. Features informative of hemorrhage were then selected by the LASSO algorithm and an SVM model was built with selected features. The SVM model was further simplified by discarding features with low importance calculated using a "permutation importance" method. The model's performance was evaluated with confusion matrix-derived metrics and AUC value on the independent test dataset. Nine radiomics features were selected as hemorrhage related features of intracranial tumors by the LASSO algorithm. The simplified model's sensitivity, specificity, accuracy, and AUC reached 0.909, 0.930, 0.926, and 0.949 (95%CI: 0.865-1.000) on the test dataset in the discrimination of "hemorrhage-prone tumors". The permutation method rated feature "T2_gradient_firstorder_10Percentile" as the most important, the absence of which decreased the model's accuracy by 10.9%. Radiomics features extracted on contrast-enhanced T1WI and T2WI sequences were predictive of future hemorrhage of intracranial tumors with favorable accuracy. This model may assist in the arrangement of biopsy procedures and the selection of target lesions in patients with multiple lesions.

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

This study aimed to evaluate the value of machine learning models (ML) based on MRI radiomics in diagnosing early parotid gland injury in primary Sjögren's syndrome (pSS). A total of 164 patients (114 in the training cohort and 50 in the testing cohort) with pSS (n=82) or healthy controls (HC) (n=82) were enrolled. Itksnap software was used to perform two-dimensional segmentation of the bilateral parotid glands on T1-weighted (T1WI) and fat-suppressed T2-weighted imaging (fs-T2WI) images. A total of 1548 texture features of the parotid glands were extracted using radiomics software. A radiomics score (Radscore) was constructed and calculated. A t-test was used to compare the Radscore between the two groups. Finally, five machine learning models were trained and tested to identify early pSS parotid injury, and the performance of the machine learning models was evaluated by calculating the acceptance operating curve (ROC) and other parameters. The Radscores between the pSS and HC groups showed significant statistical differences (p<0.001). Among the five machine learning models, the Extra Trees Classifier (ETC) model performed high predictive efficacy in identifying early pSS parotid injury, with an AUC of 0.87 in the testing set. MRI radiomics-based machine learning models can effectively diagnose early parotid gland injury in primary Sjögren's syndrome.

An MRI Radiomics Approach to Predict the Hypercoagulable Status of Gliomas.

Venous thromboembolic events are frequent complications of Glioblastoma Multiforme (GBM) and low-grade gliomas (LGGs). The overexpression of tissue factor (TF) plays an essential role in the local hypercoagulable phenotype that underlies these complications. Our aim was to build an MRI radiomics model for the non-invasive exploration of the hypercoagulable status of LGG/GBM. Radiogenomics data from The Cancer Genome Atlas (TCGA) and REMBRANDT (Repository for molecular BRAin Neoplasia DaTa) cohorts were used. A logistic regression model (Radscore) was built in order to identify the top 20% TF-expressing tumors, considered to be at high thromboembolic risk. The most contributive MRI radiomics features from LGG/GBM linked to high TF were identified in TCGA using Least Absolute Shrinkage and Selection Operator (LASSO) regression. A logistic regression model was built, whose performance was analyzed with ROC in the TCGA/training and REMBRANDT/validation cohorts: AUC = 0.87 [CI95: 0.81-0.94, p < 0.0001] and AUC = 0.78 [CI95: 0.56-1.00, p = 0.02], respectively. In agreement with the key role of the coagulation cascade in gliomas, LGG patients with a high Radscore had lower overall and disease-free survival. The Radscore was linked to the presence of specific genomic alterations, the composition of the tumor coagulome and the tumor immune infiltrate. Our findings suggest that a non-invasive assessment of the hypercoagulable status of LGG/GBM is possible with MRI radiomics.

Nomograms based on multiparametric MRI radiomics integrated with clinical-radiological features for predicting the response to induction chemotherapy in nasopharyngeal carcinoma

ObjectiveTo establish nomograms integrating multiparametric MRI radiomics with clinical-radiological features to identify the responders and non-responders to induction chemotherapy (ICT) in nasopharyngeal carcinoma (NPC). MethodsWe retrospectively analyzed the clinical and MRI data of 168 NPC patients between December 2015 and April 2022. We used 3D-Slicer to segment the regions of interest (ROIs) and the “Pyradiomic” package to extract radiomics features. We applied the least absolute shrinkage and selection operator regression to select radiomics features. We developed clinical-only, radiomics-only, and the combined clinical-radiomics nomograms using logistic regression analysis. The receiver operating characteristic curves, DeLong test, calibration, and decision curves were used to assess the discriminative performance of the models. The model was internally validated using 10-fold cross-validation. ResultsA total of 14 optimal features were finally selected to develop a radiomic signature, with an AUC of 0.891 (95 % CI, 0.825–0.946) in the training cohort and 0.837 (95 % CI, 0.723–0.932) in the testing cohort. The nomogram based on the Rad-Score and clinical-radiological factors for evaluating tumor response to ICT yielded an AUC of 0.926 (95 % CI, 0.875–0.965) and 0.901 (95 % CI, 0.815–0.979) in the two cohorts, respectively. Decision curves demonstrated that the combined clinical-radiomics nomograms were clinically useful. ConclusionNomograms integrating multiparametric MRI-based radiomics and clinical-radiological features could non-invasively discriminate ICT responders from non-responders in NPC patients.

Enhancing recurrence risk prediction for bladder cancer using multi-sequence MRI radiomics

ObjectiveWe aimed to develop a radiomics-clinical nomogram using multi-sequence MRI to predict recurrence-free survival (RFS) in bladder cancer (BCa) patients and assess its superiority over clinical models.MethodsA retrospective cohort of 229 BCa patients with preoperative multi-sequence MRI was divided into a training set (n = 160) and a validation set (n = 69). Radiomics features were extracted from T2-weighted images, diffusion-weighted imaging, apparent diffusion coefficient, and dynamic contrast-enhanced images. Effective features were identified using the least absolute shrinkage and selection operator (LASSO) method. Clinical risk factors were determined via univariate and multivariate Cox analysis, leading to the creation of a radiomics-clinical nomogram. Kaplan-Meier analysis and log-rank tests assessed the relationship between radiomics features and RFS. We calculated the net reclassification improvement (NRI) to evaluate the added value of the radiomics signature and used decision curve analysis (DCA) to assess the nomogram’s clinical validity.ResultsRadiomics features significantly correlated with RFS (log-rank p < 0.001) and were independent of clinical factors (p < 0.001). The combined model, incorporating radiomics features and clinical data, demonstrated the best prognostic value, with C-index values of 0.853 in the training set and 0.832 in the validation set. Compared to the clinical model, the radiomics-clinical nomogram exhibited superior calibration and classification (NRI: 0.6768, 95% CI: 0.5549-0.7987, p < 0.001).ConclusionThe radiomics-clinical nomogram, based on multi-sequence MRI, effectively assesses the BCa recurrence risk. It outperforms both the radiomics model and the clinical model in predicting BCa recurrence risk.Critical relevance statementThe radiomics-clinical nomogram, utilizing multi-sequence MRI, holds promise for predicting bladder cancer recurrence, enhancing individualized clinical treatment, and performing tumor surveillance.Key points• Radiomics plays a vital role in predicting bladder cancer recurrence.• Precise prediction of tumor recurrence risk is crucial for clinical management.• MRI-based radiomics models excel in predicting bladder cancer recurrence.Graphical

MRI-based radiomics for prediction of extraprostatic extension of prostate cancer: a systematic review and meta-analysis.

We to systematically evaluate the diagnostic performance of MRI radiomics in detecting extracapsular extension (EPE) of prostate cancer (PCa). A literature search of online databases of PubMed, EMBASE, Cochrane Library, Web of Science, and Google Scholar online scientific publication databases was performed to identify studies published up to July 2023. The summary estimates were pooled with the hierarchical summary receiver-operating characteristic (HSROC) model. This study was reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement, the quality of included studies was assessed with the Quality Assessment of Diagnostic Accuracy Studies-2 tool (QUADAS-2) and the radiomics quality score (RQS). Meta-regression and subgroup analyses were performed to explore the impact of varying clinical settings. A total of ten studies met the inclusion criteria. The pooled sensitivity and specificity were 0.77 (95% CI 0.68-0.84, I2 = 83.5%) and 0.75 (95% CI 0.67-0.82, I2 = 83.5%), respectively, with an area under the HSROC curve of 0.88 (95% CI 0.85-0.91). Study quality was not high while assessing with the RQS. Substantial heterogeneity was observed between studies; however, meta-regression analysis did not reveal any significant contributing factors. MRI radiomics demonstrated moderate sensitivity and specificity, offering similar diagnostic performance with previous risk stratifications and models that primarily based on radiologists' subjective experience. However, all studies included were retrospective, thus the performance of radiomics needs to validate in prospective, multicenter studies.

Peritumoral MRI Radiomics Features Increase the Evaluation Efficiency for Response to Chemotherapy in Patients With Epithelial Ovarian Cancer.

It remains unclear whether extracting peritumoral volume (PTV) radiomics features are useful tools for evaluating response to chemotherapy of epithelial ovarian cancer (EOC). To evaluate MRI radiomics signatures (RS) capturing subtle changes of PTV and their added evaluation performance to whole tumor volume (WTV) for response to chemotherapy in patients with EOC. Retrospective. 219 patients aged from 15 to 79 years were enrolled. 3.0 or 1.5T, axial fat-suppressed T2-weighted imaging (FS-T2WI), diffusion-weighted imaging (DWI), and contrast enhanced T1-weighted imaging (CE-T1WI). MRI features were extracted from the four axial sequences and six different volumes of interest (VOIs) (WTV and WTV + PTV (WPTV)) with different peritumor sizes (PS) ranging from 1 to 5 mm. Those features underwent preprocessing, and the most informative features were selected using minimum redundancy maximum relevance and least absolute shrinkage and selection operator to construct the RS. The optimal RS, with the highest area under the curve (AUC) of receiver operating characteristic was then integrated with independent clinical characteristics through multivariable logistic regression to construct the radiomics-clinical model (RCM). Mann-Whitney U test, chi-squared test, DeLong test, log-rank test. P < 0.05 indicated a significant difference. All the RSs constructed on WPTV exhibited higher AUCs (0.720-0.756) than WTV (0.671). Of which, RS with PS = 2 mm displayed a significantly better performance (AUC = 0.756). International Federation of Gynecology and Obstetrics (FIGO) stage was identified as the exclusive independent clinical evaluation characteristic, and the RCM demonstrated higher AUC (0.790) than the RS, but without statistical significance (P = 0.261). The radiomics features extracted from PTV could increase the efficiency of WTV radiomics for evaluating the chemotherapy response of EOC. The cut-off of 2 mm PTV was a reasonable value to obtain effective evaluation efficiency. 4 TECHNICAL EFFICACY: Stage 2.

Abstract 3510: A radiogenomic approach for triple-negative breast cancer risk stratification

Abstract Background: Triple-negative breast cancer (TNBC) is an aggressive disease that accounts for 15-20% of all breast cancers. Expressions of ER, PR and HER2 receptors are lacking in this disease, and thus targeted therapies are not effective. TNBC has a shorter relapse-free survival, higher metastasis rate and decreased overall survival compared with other breast cancers. However, when undergoing standard treatment, some patients respond well, while others have poor outcome, suggesting TNBC heterogeneity. Early stratification of patients with long versus short survival could identify the subgroup of patients who would not benefit from exposure to toxicity of chemotherapy treatment. Here, we developed a non-invasive radiogenomic approach for TNBC risk stratification. Methods: A transcriptomic-based prognostic gene signature was previously developed using the TCGA-BRCA cohort (n=860). Briefly, LASSO Cox regression model analysis with the ‘glmnet’ R package was used to identify the transcriptomic signature gene-set consisting of 50 genes. We tested this signature to prognosticate overall survival in a Stanford cohort (n=63) and a previously published SCANB cohort (n=604). The patients were stratified into high- and low-risk groups based on the median risk-score. Next, we developed a machine learning model that identified a radiomic feature set to predict the prognostic transcriptomic risk-groups. Radiomic features were extracted from pre-treatment breast MRI. Radiomics features were extracted using PyRadiomics. The model utilized Decision Tree Classifier and LeaveOneOut method was used for cross-validation. Results: The transcriptomic signature low-risk group was significantly associated with improved overall survival in the two TNBC cohorts, with hazard ratios of 0.11 [95% CI: 0.01-0.88] for the Stanford cohort and 0.71 [95% CI: 0.52-0.97] for the SCANB cohort (log-rank p-values p=0.012 and p=0.032, respectively). Including this transcriptomic signature in a multivariate analysis, which adjusted for clinical features (patient age, grade, stage and Ki67%), the transcriptomic prognostic signature remained a significant prognostic factor (p&amp;lt;0.05). The radiomic feature set (consisting of 20 features) predicted the high- and low-risk transcriptomic groups with a mean accuracy of 72.2% and a mean AUROC of 71%. The precision, F1 and recall scores were 67%, 74% and 82%, respectively. In an independent dataset consisting of 116 Stanford TNBC patients, we used this model to predict risk groups based on the MRI radiomics features, and evaluated the prognostic effects of predicted risk groups. The overall survival of the predicted high-risk group was significantly poorer than the predicted low-risk group (p=0.013). Conclusions: We present a prognostic model that can non-invasively stratify TNBC patients for low versus high mortality risk using radiomic features derived from pre-treatment patient MRI data. Citation Format: Humaira Noor, Yuanning Zheng, Adam Mantz, Ryle Zhou, Andrew Kozlov, Wendy B. DeMartini, Shu-tian Chen, Satoko Okamoto, Debra Ikeda, Sarah Mattonen, Sandy Napel, Melinda L. Telli, George Sledge, Allison Kurian, Mina Satoyoshi, Olivier Gevaert, Haruka Itakura. A radiogenomic approach for triple-negative breast cancer risk stratification [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3510.