A hybrid radiomics framework integrating genetic algorithm-optimized random forest for preoperative identification of Luminal B breast cancer and Ki-67 prediction: A multicenter study.

BackgroundBreast cancer remains the predominant contributor to global cancer-related morbidity and mortality in women. Luminal subtypes, accounting for approximately 70% of cases, demonstrate favorable prognoses through endocrine-targeted therapeutic regimens owing to hormone receptor positivity. Conversely, non-luminal breast cancer variants, including human epidermal growth factor receptor 2 (HER2)-enriched and triple-negative subtypes, exhibit aggressive biological characteristics, intrinsic endocrine therapy resistance, and require molecularly guided therapeutic strategies such as HER2-directed biologicals, platinum-based cytotoxic regimens, or radiation therapy. This study aims to evaluate whether preoperative multiparametric magnetic resonance imaging (MRI)-based intratumoral and peritumoral radiomics can effectively discriminate between luminal and non-luminal breast cancer subtypes.MethodsThis retrospective study analyzed 305 female breast cancer patients. Center 1 (Affiliated Hospital of Qinghai University) was randomly split into a training set (n=140) and an internal test set (n=59) in a 7:3 ratio, while Center 2 (Second Hospital of Lanzhou University) (n=67) and Center 3 (The Cancer Imaging Archive I-SPY1 trial) (n=39) served as external test sets 1 and 2, respectively. Tumor subtypes were classified as luminal or non-luminal based on estrogen receptor (ER) and progesterone receptor (PR) status. Two radiologists performed manual tumor segmentation using 3D Slicer on multiparametric MRI sequences: dynamic contrast enhancement (DCE; phases 3 or 4), fat-suppressed T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI). Peritumoral regions were defined by a 3 mm expansion from the tumor volume of interest (VOI). For each sequence (intratumoral and peritumoral), 2,252 radiomics features were extracted using PyRadiomics. After Z-score normalization, features were selected through univariate analysis, correlation analysis, and simulated annealing. Eight radiomics models were constructed using random forest (RF), including intratumoral-only, combined intratumoral-peritumoral (3 mm), and multisequence fusion models. Performance was assessed using area under the curve (AUC), calibration curves, and decision curve analysis (DCA).ResultsAfter feature selection, eight optimal radiomics features were used for model development. The combined DWI_Peri3 + T2WI_Peri3 + DCE_Peri3 RF model demonstrated superior performance, with AUCs of 0.819 [95% confidence interval (CI): 0.748–0.889], 0.795 (95% CI: 0.676–0.915), and 0.771 (95% CI: 0.640–0.902) in training, internal validation, and external validation set 1, respectively. Among single-parameter models, T2WI_Peri3 RF showed the best classification performance (AUC =0.774, 95% CI: 0.698–0.849) for luminal vs. non-luminal differentiation.ConclusionsThe model constructed based on multiparametric MRI intratumor combined with peritumor radiomics features can better predict luminal and non-luminal types of breast cancer. This study can provide a reference basis for individualized treatment plans for breast cancer.

Prostate-specific membrane antigen (PSMA) PET/CT plays an increasing role in prostate cancer management. Radiomics analysis of PSMA PET/CT images may provide additional information for risk stratification. This study aimed to evaluate the performance of PSMA PET/CT radiomics analysis in differentiating between Gleason Grade Groups (GGG 1–3 vs. GGG 4–5) and predicting PSA levels (below vs. at or above 20 ng/ml) in patients with newly diagnosed prostate cancer. In this multicenter study, patients with confirmed primary prostate cancer were enrolled who underwent [68Ga]Ga-PSMA PET/CT for staging. Inclusion criteria required intraprostatic lesions on PET and the International Society of Urological Pathology (ISUP) grade information. Three different segments were delineated including intraprostatic PSMA-avid lesions on PET, the whole prostate in PET, and the whole prostate in CT. Radiomic features (RFs) were extracted from all segments. Dimensionality reduction was achieved through principal component analysis (PCA) prior to model training on data from two centers (186 cases) with 10-fold cross-validation. Model performance was validated with external data set (57 cases) using various machine learning models including random forest, nearest centroid, support vector machine (SVM), calibrated classifier CV and logistic regression. In this retrospective study, 243 patients with a median age of 69 (range: 46–89) were enrolled. For distinguishing GGG 1–3 from GGG 4–5, the nearest centroid classifier using radiomic features (RFs) from whole-prostate PET achieved the best performance in the internal test set, while the random forest classifier using RFs from PSMA-avid lesions in PET performed best in the external test set. However, when considering both internal and external test sets, a calibrated classifier CV using RFs from PSMA-avid PET data showed slightly improved overall performance. Regarding PSA level classification (< 20 ng/ml vs. ≥20 ng/ml), the nearest centroid classifier using RFs from the whole prostate in PET achieved the best performance in the internal test set. In the external test set, the highest performance was observed using RFs derived from the concatenation of PET and CT. Notably, when combining both internal and external test sets, the best performance was again achieved with RFs from the concatenated PET/CT data. Our research suggests that [68Ga]Ga-PSMA PET/CT radiomic features, particularly features derived from intraprostatic PSMA-avid lesions, may provide valuable information for pre-biopsy risk stratification in newly diagnosed prostate cancer.

This study aimed to establish a mammography-based radiomics model for predicting the risk of estrogen receptor (ER)-positive, lymph node (LN)-negative invasive breast cancer recurrence based on Oncotype DX and validated it by using multicenter data. A total of 304 potentially eligible patients with pre-operative mammography images and available Oncotype DX score were retrospectively enrolled from two hospitals. The patients were grouped as training set (168 patients), internal test set (72 patients), and external test set (64 patients). Radiomics features were extracted from the mammography images of each patient. Spearman correlation analysis, analysis of variance, and least absolute shrinkage and selection operator regression were performed to reduce the redundant features in the training set, and the least absolute shrinkage and selection operator algorithm was used to construct the radiomics signature based on selected features. Multivariate logistic regression was utilized to construct classification models that included radiomics signature and clinical risk factors to predict low vs intermediate and high recurrence risk of ER-positive, LN-negative invasive breast cancer in the training set. The models were evaluated with the receiver operating characteristic curve in the training set. The internal and external test sets were used to confirm the discriminatory power of the models. The clinical usefulness was evaluated by using decision curve analysis. The radiomics signature consisting of three radiomics features achieved favorable prediction performance. The multivariate logistic regression model including radiomics signature and clinical risk factors (tumor grade and HER 2) showed good performance with areas under the curve of 0.92 (95% confidence interval [CI] 0.86 to 0.97), 0.88 (95% CI 0.75 to 1.00), and 0.84 (95% CI 0.69 to 0.99) in the training, internal and external test sets, respectively. The DCA indicated that when the threshold probability is ranges from 0.1 to 1.0, the radiomics model adds more net benefit than the "treat all" or "treat none" scheme in internal and external test sets. As a non-invasive pre-operative prediction tool, the mammography-based radiomics model incorporating radiomics and clinical factors show favorable predictive performance for predicting the risk of ER-positive, LN-negative invasive breast cancer recurrence based on Oncotype DX. The mammography-based radiomics model incorporating radiomics and clinical factors shows favorable predictive performance for predicting the risk of ER-positive, LN-negative invasive breast cancer recurrence.

BackgroundAccurate assessment of human epidermal growth factor receptor 2 (HER2) status can guide eligibility for HER2-targeted therapy in breast cancer. We aimed to develop and externally validate a nomogram that combines ultrasound (US) radiomics features from intratumoral and peritumoral regions with clinical variables to predict HER2 status in patients with IHC 2 + breast cancer.MethodsWe retrospectively included 440 IHC 2 + breast cancers with FISH results and randomly split them into a training cohort (n = 308) and an internal testing cohort (n = 132). Two independent cohorts provided external validation (pooled, n = 153; single center, n = 102). Radiomics features were extracted from the intratumoral region (ITR), peritumoral region (PTR) at 1/3/5 mm, and combined intratumoral and peritumoral region (IPTR) on 2D US. The models were trained with mRMR and LASSO-regularized logistic regression. A Rad-score was derived and combined with key clinical variables to build a nomogram. Performance was assessed with the AUC, calibration curves, and DCA.ResultsThe combined model using the IPTR3 Rad-score achieved AUCs of 0.821 (95% CI 0.772–0.869), 0.828 (95% CI 0.756–0.900), 0.774 (95% CI 0.697–0.851), and 0.803 (95% CI 0.699–0.906) in the training, internal testing, external validation 1, and external validation 2 cohorts, respectively. The calibration curves indicated good agreement. DCA showed greater net benefit than the clinical or radiomics model across most thresholds.ConclusionsA nomogram combining US-based intratumoral and peritumoral radiomics features with key clinical variables showed potential utility for noninvasive, preoperative prediction of HER2 status in patients with IHC 2 + breast cancer and may assist in individualized treatment planning.

To develop a machine learning-based ultrasound (US) radiomics model for predicting tumour deposits (TDs) preoperatively. From December 2015 to December 2017, 127 patients with rectal cancer were prospectively enrolled and divided into training and validation sets. Endorectal ultrasound (ERUS) and shear-wave elastography (SWE) examinations were conducted for each patient. A total of 4176 US radiomics features were extracted for each patient. After the reduction and selection of US radiomics features , a predictive model using an artificial neural network (ANN) was constructed in the training set. Furthermore, two models (one incorporating clinical information and one based on MRI radiomics) were developed. These models were validated by assessing their diagnostic performance and comparing the areas under the curve (AUCs) in the validation set. The training and validation sets included 29 (33.3%) and 11 (27.5%) patients with TDs, respectively. A US radiomics ANN model was constructed. The model for predicting TDs showed an accuracy of 75.0% in the validation cohort. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and AUC were 72.7%, 75.9%, 53.3%, 88.0% and 0.743, respectively. For the model incorporating clinical information, the AUC improved to 0.795. Although the AUC of the US radiomics model was improved compared with that of the MRI radiomics model (0.916 vs. 0.872) in the 90 patients with both ultrasound and MRI data (which included both the training and validation sets), the difference was nonsignificant (p = 0.384). US radiomics may be a potential model to accurately predict TDs before therapy. • We prospectively developed an artificial neural network model for predicting tumour deposits based on US radiomics that had an accuracy of 75.0%. • The area under the curve of the US radiomics model was improved than that of the MRI radiomics model (0.916 vs. 0.872), but the difference was not significant (p = 0.384). • The US radiomics-based model may potentially predict TDs accurately before therapy, but this model needs further validation with larger samples.

ObjectivesTo develop and validate a combined model integrating traditional clinical characteristics, imaging features and radiomic features based on head and neck computed tomography angiography (CTA) to predict ischemic events in ipsilateral cerebral vessels.MethodsIn this multicenter retrospective study, 223 patients from 3 independent centers were divided into training set (n = 134), internal test set (n = 34) and external validation set (n = 55). Based on recent symptoms (presence or absence of ipsilateral cerebral ischemia), patients were categorized into symptomatic group (n = 110) and asymptomatic group (n = 113). The traditional clinical characteristics, imaging features and radiomic features of all patients were collected. The traditional quantitative variables independently related to symptomatic carotid plaque were identified using univariate analysis and multivariate logistic regression analysis, and the intraclass correlation coefficient (ICC) and Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis were applied to select robust radiomic features. Subsequently, three predictive models – the traditional model, radiomic model, and combined model integrating clinical, imaging and radiomic features – were constructed. Model performance was evaluated using receiver operating characteristic curves (ROCs) analysis, area under the curves (AUCs), calibration curves and decision curves analysis, and the accuracies of the models were verified in internal test set and external validation set.ResultsUnivariate analysis and multivariate logistic regression analysis showed that platelet distribution width (PDW) (odds ratio [OR] = 0.88; 95% confidence interval [CI], 0.80–0.97) and plaque ulceration (OR = 5.67; 95% CI, 2.86–11.23) were independently related to symptomatic plaque. Twelve radiomic features significantly related to symptomatic plaque were selected. The combined model demonstrated superior performance compared with both the radiomic model and the traditional model, the AUCs of the training set and internal test set were 0.819(95% CI: 0.749–0.888) and 0.785(95% CI: 0.620–0.950), and also demonstrated robust performance in external validation set (AUC: 0.868; 95% CI: 0.765–0.970).ConclusionThe Combined model demonstrated the highest diagnostic performance in identifying symptomatic plaque, which helps clinicians to analyze patients’ condition more comprehensively and provides additional value for identifying high-risk individuals and improving prognosis.

ObjectivesTo assess the predictive value of intratumoral and multiregion peritumoral radiomics based on multiparametric MRI for preoperatively predicting the efficacy of high-intensity focused ultrasound (HIFU) ablation of uterine fibroids.Materials and methodsThis retrospective study included 360 patients with uterine fibroids treated with high-intensity focused ultrasound (HIFU) at Center A (training set: N = 240; internal testing set: N = 60) and Center B (external testing set: N = 60). Patients were grouped into sufficient or insufficient ablation categories based on postoperative non-perfusion volume ratio. Intratumoral regions (TRs) were manually delineated on T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (CE-T1WI). Peritumoral regions (PTRs) were generated by expanding the tumor boundary by 1 mm, 3 mm, and 5 mm. Radiomics features were extracted from TRs and PTRs on both MRI sequences. Key features for preoperative prediction were selected using t-tests, Pearson correlation, and LASSO regression. Support vector machine (SVM) models were built for TRs from T2WI and CE-T1WI, and for combined intratumoral and peritumoral regions (T-PTRs). A fusion model integrated optimal T-PTRs features from both sequences. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC).ResultsThe T-PTRs radiomics models outperformed the TR models, with the T-PTRs (3 mm) model demonstrating optimal performance. The integration of T2WI and CE-T1WI further enhanced the T-PTRs model, yielding an AUC of 0.892(0.814-0.969) on the internal test set and an AUC of 0.828(0.741 - 0.915) on the external validation set.ConclusionThe predictive model based on intratumoral and peritumoral radiomics features serves as a valuable tool for predicting the therapeutic efficacy of HIFU ablation of uterine fibroids.

ObjectivesWe aimed to develop a combined model based on clinical and radiomic features to classify fracture age.MethodsWe included 1219 rib fractures from 239 patients from our center between March 2016 and September 2022. We created an external dataset using 120 rib fractures from 32 patients from another center between October 2019 and August 2023. According to tasks (fracture age between < 3 and ≥ 3 weeks, 3–12, and > 12 weeks), the internal dataset was randomly divided into training and internal test sets. A radiomic model was built using radiomic features. A combined model was constructed using clinical features and radiomic signatures by multivariate logistic regression, visualized as a nomogram. Internal and external test sets were used to validate model performance.ResultsFor classifying fracture age between < 3 and ≥ 3 weeks, the combined model had higher areas under the curve (AUCs) than the radiomic model in the training set (0.915 vs 0.900, p = 0.009), internal test (0.897 vs 0.854, p < 0.001), and external test sets (0.881 vs 0.811, p = 0.003). For classifying fracture age between 3–12 and > 12 weeks, the combined model had higher AUCs than the radiomic model in the training model (0.848 vs 0.837, p = 0.12) and internal test sets (0.818 vs 0.793, p < 0.003). In the external test set, the AUC of the nomogram-assisted radiologist was 0.966.ConclusionThe combined radiomic and clinical model showed good performance and has the potential to assist in the classification of rib fracture age. This will be beneficial for clinical practice and forensic decision-making.Critical relevance statementThis study describes the development of a combined radiomic and clinical model with good performance in the classification of the age of rib fractures, with potential clinical and forensic applications.Key points• Complex factors make it difficult to determine the age of a fracture.• Our model based on radiomic features performed well in classifying fracture age.• Associating the radiomic features with clinical features improved the model’s performance.Graphical

ObjectiveThe aim of this study was to develop and validate an ultrasound-based radiomics nomogram model by integrating the clinical risk factors and radiomics score (Rad-Score) to predict the Ki-67 status in patients with breast carcinoma.MethodsUltrasound images of 284 patients (196 high Ki-67 expression and 88 low Ki-67 expression) were retrospectively analyzed, of which 198 patients belonged to the training set and 86 patients to the test set. The region of interest of tumor was delineated, and the radiomics features were extracted. Radiomics features underwent dimensionality reduction analysis by using the independent sample t test and least absolute shrinkage and selection operator (LASSO) algorithm. The support vector machine (SVM), logistic regression (LR), decision tree (DT), random forest (RF), naive Bayes (NB) and XGBoost (XGB) machine learning classifiers were trained to establish prediction model based on the selected features. The classifier with the highest AUC value was selected to convert the output of the results into the Rad-Score and was regarded as Rad-Score model. In addition, the logistic regression method was used to integrate Rad-Score and clinical risk factors to generate the nomogram model. The leave group out cross-validation (LGOCV) method was performed 200 times to verify the reliability and stability of the nomogram model.ResultsSix classifier models were established based on the 15 non-zero coefficient features. Among them, the LR classifier achieved the best performance in the test set, with the area under the receiver operating characteristic curve (AUC) value of 0.786, and was obtained as the Rad-Score model, while the XGB performed the worst (AUC, 0.615). In multivariate analysis, independent risk factor for high Ki-67 status was age (odds ratio [OR] = 0.97, p = 0.04). The nomogram model based on the age and Rad-Score had a slightly higher AUC than that of Rad-Score model (AUC, 0.808 vs. 0.798) in the test set, but no statistical difference (p = 0.144, DeLong test). The LGOCV yielded a median AUC of 0.793 in the test set.ConclusionsThis study proposed a convenient, clinically useful ultrasound radiomics nomogram model that can be used for the preoperative individualized prediction of the Ki-67 status in patients with BC.

ObjectivesIdentifying patients at risk of chemoresistant osteosarcoma enables risk-adapted management. This study aimed to predict chemoresistant osteosarcoma using baseline clinical and magnetic resonance (MRI)-derived radiomics features, with histological response as the reference standard and external validation included.Materials and methodsThis retrospective single-center study included 115 patients with osteosarcoma from an institutional registry as the internal cohort, divided into training and test sets, and 49 patients from another institution as an external validation cohort. Tumor and peritumoral regions were manually segmented on baseline fat-suppressed T2-weighted MRI. Radiomics features were extracted using PyRadiomics, followed by two feature selection methods to identify potential predictors. Six machine learning models with varying feature combinations were trained to classify histologic chemoresistance in the internal training set. Model performance was assessed in the internal test set, and the best model was externally validated.ResultsThe support vector machine model combining eight tumor radiomics features and four clinical-imaging parameters (presence of tumor necrosis > 50% on contrast-enhanced MRI, age, body mass index, and presence of metastasis at presentation) demonstrated the best performance. In the internal test set, it achieved a sensitivity of 83.3%, a specificity of 72.7%, an area under the receiver operating characteristic curve (AUROC) of 0.84, and a positive likelihood ratio of 3.06. External validation yielded a sensitivity of 88.5%, a specificity of 47.8%, and an AUROC of 0.77.ConclusionA model combining tumor radiomics and clinical parameters at diagnosis showed strong performance in predicting chemoresistant osteosarcoma, with results confirmed by external validation. This approach may support personalized treatment strategies in high-grade osteosarcoma.Relevance statementThe validated model may support early, individualized osteosarcoma management.Key PointsBaseline T2-weighted MRI radiomics and clinical data can predict chemoresistant osteosarcoma.Tumor radiomics combined with clinical features achieved strong predictive accuracy.The support vector machine model reached an AUROC of 0.84 for the internal testing and of 0.77 for the external validation.The validated model may support early, individualized osteosarcoma management.Graphical

ObjectivesTo develop and evaluate a deep convolutional neural network (DCNN) for automated liver segmentation, volumetry, and radiomic feature extraction on contrast-enhanced portal venous phase magnetic resonance imaging (MRI).Materials and methodsThis retrospective study included hepatocellular carcinoma patients from an institutional database with portal venous MRI. After manual segmentation, the data was randomly split into independent training, validation, and internal testing sets. From a collaborating institution, de-identified scans were used for external testing. The public LiverHccSeg dataset was used for further external validation. A 3D DCNN was trained to automatically segment the liver. Segmentation accuracy was quantified by the Dice similarity coefficient (DSC) with respect to manual segmentation. A Mann-Whitney U test was used to compare the internal and external test sets. Agreement of volumetry and radiomic features was assessed using the intraclass correlation coefficient (ICC).ResultsIn total, 470 patients met the inclusion criteria (63.9±8.2 years; 376 males) and 20 patients were used for external validation (41±12 years; 13 males). DSC segmentation accuracy of the DCNN was similarly high between the internal (0.97±0.01) and external (0.96±0.03) test sets (p=0.28) and demonstrated robust segmentation performance on public testing (0.93±0.03). Agreement of liver volumetry was satisfactory in the internal (ICC, 0.99), external (ICC, 0.97), and public (ICC, 0.85) test sets. Radiomic features demonstrated excellent agreement in the internal (mean ICC, 0.98±0.04), external (mean ICC, 0.94±0.10), and public (mean ICC, 0.91±0.09) datasets.ConclusionAutomated liver segmentation yields robust and generalizable segmentation performance on MRI data and can be used for volumetry and radiomic feature extraction.Clinical relevance statementLiver volumetry, anatomic localization, and extraction of quantitative imaging biomarkers require accurate segmentation, but manual segmentation is time-consuming. A deep convolutional neural network demonstrates fast and accurate segmentation performance on T1-weighted portal venous MRI.

Machine Learning-Based Breast Tumor Ultrasound Radiomics for Pre-operative Prediction of Axillary Sentinel Lymph Node Metastasis Burden in Early-Stage Invasive Breast Cancer

P6-01-19: Multiparametric MRI-based Longitudinal-radiomics Analysis for Early Prediction of Treatment Response of Breast Cancers to Neoadjuvant Chemotherapy: A Multicenter Study

ObjectivesThis study aimed to develop and validate a novel strain elastography (SE) radiomics nomogram for diagnosing breast cancer (BC) by analyzing intratumoral and peritumoral regions.MethodsA cohort of 322 patients, comprising 217 from hospital #1 (06/2021–05/2023) and 105 from hospital #2 (06/2022–05/2023) with breast lesions, was enrolled. Radiomic features were extracted from intratumoral and peritumoral (0–1 mm, 1–2 mm, 2–3 mm) regions on strain elastography images. Significant features were selected using Mann–Whitney U test, Spearman's correlation coefficient, and LASSO logistic regression. A radiomic model was constructed utilizing these features, followed by the development of a radiomic nomogram integrating optimal features.ResultsThe intratumoral radiomic model exhibited an area under the receiver operating characteristic curve (AUC) of 0.774 (95% CI: 0.626–0.922) in the internal testing set. Combining peritumoral radiomics, the intratumoral & peritumoral_0–1 mm radiomic model emerged as the optimal model with an AUC of 0.884 (95% CI: 0.766–0.998) in the internal testing set, signifying improved BC identification. The optimal model demonstrated an AUC of 0.841 (95% CI: 0.762–0.920) in the external testing set, indicating robustness and generalization.ConclusionsThe radiomic model incorporating intratumoral & peritumoral_0–1 mm radiomic features shows promise in diagnosing BC, aiding in devising effective clinical treatment strategies.

Predictive Analysis of Neoadjuvant Chemotherapy Efficacy in Breast Cancer Using Multi-Region Ultrasound Imaging Features Combined With Pathological Parameters.