Search

IntroductionThere is a cumulative risk of 20-40% of developing brain metastases (BM) in solid cancers. Stereotactic radiotherapy (SRT) enables the application of high focal doses of radiation to a volume and is often used for BM treatment. However, SRT can cause adverse radiation effects (ARE), such as radiation necrosis, which sometimes cause irreversible damage to the brain. It is therefore of clinical interest to identify patients at a high risk of developing ARE. We hypothesized that models trained with radiomics features, deep learning (DL) features, and patient characteristics or their combination can predict ARE risk in patients with BM before SRT.MethodsGadolinium-enhanced T1-weighted MRIs and characteristics from patients treated with SRT for BM were collected for a training and testing cohort (N = 1,404) and a validation cohort (N = 237) from a separate institute. From each lesion in the training set, radiomics features were extracted and used to train an extreme gradient boosting (XGBoost) model. A DL model was trained on the same cohort to make a separate prediction and to extract the last layer of features. Different models using XGBoost were built using only radiomics features, DL features, and patient characteristics or a combination of them. Evaluation was performed using the area under the curve (AUC) of the receiver operating characteristic curve on the external dataset. Predictions for individual lesions and per patient developing ARE were investigated.ResultsThe best-performing XGBoost model on a lesion level was trained on a combination of radiomics features and DL features (AUC of 0.71 and recall of 0.80). On a patient level, a combination of radiomics features, DL features, and patient characteristics obtained the best performance (AUC of 0.72 and recall of 0.84). The DL model achieved an AUC of 0.64 and recall of 0.85 per lesion and an AUC of 0.70 and recall of 0.60 per patient.ConclusionMachine learning models built on radiomics features and DL features extracted from BM combined with patient characteristics show potential to predict ARE at the patient and lesion levels. These models could be used in clinical decision making, informing patients on their risk of ARE and allowing physicians to opt for different therapies.

Introduction: There is a cumulative risk of 20-40% of developing brain metastases (BM) in solid cancers. Stereotactic radiotherapy (SRT) enables the application of high focal doses of radiation to a volume and is often used for BM treatment. However, SRT can cause adverse radiation effects (ARE), such as radiation necrosis, which sometimes cause irreversible damage to the brain. It is therefore of clinical interest to identify patients at a high risk of developing ARE. We hypothesized that models trained with radiomics features, deep learning (DL) features, and patient characteristics or their combination can predict ARE risk in patients with BM before SRT. Methods: Gadolinium-enhanced T1-weighted MRIs and characteristics from patients treated with SRT for BM were collected for a training and testing cohort (N = 1,404) and a validation cohort (N = 237) from a separate institute. From each lesion in the training set, radiomics features were extracted and used to train an extreme gradient boosting (XGBoost) model. A DL model was trained on the same cohort to make a separate prediction and to extract the last layer of features. Different models using XGBoost were built using only radiomics features, DL features, and patient characteristics or a combination of them. Evaluation was performed using the area under the curve (AUC) of the receiver operating characteristic curve on the external dataset. Predictions for individual lesions and per patient developing ARE were investigated. Results: The best-performing XGBoost model on a lesion level was trained on a combination of radiomics features and DL features (AUC of 0.71 and recall of 0.80). On a patient level, a combination of radiomics features, DL features, and patient characteristics obtained the best performance (AUC of 0.72 and recall of 0.84). The DL model achieved an AUC of 0.64 and recall of 0.85 per lesion and an AUC of 0.70 and recall of 0.60 per patient. Conclusion: Machine learning models built on radiomics features and DL features extracted from BM combined with patient characteristics show potential to predict ARE at the patient and lesion levels. These models could be used in clinical decision making, informing patients on their risk of ARE and allowing physicians to opt for different therapies. [ABSTRACT FROM AUTHOR]

Simple Summary: The prediction of pathologic complete response (pCR) to neo-adjuvant systemic therapy (NST) based on radiological assessment of pretreatment MRI exams in breast cancer patients is not possible to date. In this study, we investigated the value of pretreatment MRI-based radiomics analysis for the prediction of pCR to NST. Radiomics, clinical, and combined models were developed and validated based on MRI exams containing 320 tumors collected from two hospitals. The clinical models significantly outperformed the radiomics models for the prediction of pCR to NST and were of similar or better performance than the combined models. This indicates poor performance of the radiomics features and that in these scenarios the radiomic features did not have an added value for the clinical models developed. Due to previous and current work, we tentatively attribute the lack of significant improvement in clinical models following the addition of radiomics features to the effects of variations in acquisition and reconstruction parameters. The lack of reproducibility data meant this effect could not be analyzed. These results indicate the need for reproducibility studies to preselect reproducible features in order to properly assess the potential of radiomics. This retrospective study investigated the value of pretreatment contrast-enhanced Magnetic Resonance Imaging (MRI)-based radiomics for the prediction of pathologic complete tumor response to neoadjuvant systemic therapy in breast cancer patients. A total of 292 breast cancer patients, with 320 tumors, who were treated with neo-adjuvant systemic therapy and underwent a pretreatment MRI exam were enrolled. As the data were collected in two different hospitals with five different MRI scanners and varying acquisition protocols, three different strategies to split training and validation datasets were used. Radiomics, clinical, and combined models were developed using random forest classifiers in each strategy. The analysis of radiomics features had no added value in predicting pathologic complete tumor response to neoadjuvant systemic therapy in breast cancer patients compared with the clinical models, nor did the combined models perform significantly better than the clinical models. Further, the radiomics features selected for the models and their performance differed with and within the different strategies. Due to previous and current work, we tentatively attribute the lack of improvement in clinical models following the addition of radiomics to the effects of variations in acquisition and reconstruction parameters. The lack of reproducibility data (i.e., test-retest or similar) meant that this effect could not be analyzed. These results indicate the need for reproducibility studies to preselect reproducible features in order to properly assess the potential of radiomics. [ABSTRACT FROM AUTHOR]

Simple Summary: Glioblastoma (GBM) is the most malignant primary brain tumor, for which improving patient outcome is limited by a substantial amount of tumor heterogeneity. Magnetic resonance imaging (MRI) in combination with machine learning offers the possibility to collect qualitative and quantitative imaging features which can be used to predict patient prognosis and relevant tumor markers which can aid in selecting the right treatment. This study showed that combining these MRI features with clinical features has the highest prognostic value for GBM patients; this model performed similarly in an independent GBM cohort, showing its reproducibility. The prediction of tumor markers showed promising results in the training set but not could be validated in the independent dataset. This study shows the potential of using MRI to predict prognosis and tumor markers, but further optimization and prospective studies are warranted. Glioblastoma (GBM) is the most malignant primary brain tumor for which no curative treatment options exist. Non-invasive qualitative (Visually Accessible Rembrandt Images (VASARI)) and quantitative (radiomics) imaging features to predict prognosis and clinically relevant markers for GBM patients are needed to guide clinicians. A retrospective analysis of GBM patients in two neuro-oncology centers was conducted. The multimodal Cox-regression model to predict overall survival (OS) was developed using clinical features with VASARI and radiomics features in isocitrate dehydrogenase (IDH)-wild type GBM. Predictive models for IDH-mutation, 06-methylguanine-DNA-methyltransferase (MGMT)-methylation and epidermal growth factor receptor (EGFR) amplification using imaging features were developed using machine learning. The performance of the prognostic model improved upon addition of clinical, VASARI and radiomics features, for which the combined model performed best. This could be reproduced after external validation (C-index 0.711 95% CI 0.64–0.78) and used to stratify Kaplan–Meijer curves in two survival groups (p-value < 0.001). The predictive models performed significantly in the external validation for EGFR amplification (area-under-the-curve (AUC) 0.707, 95% CI 0.582–8.25) and MGMT-methylation (AUC 0.667, 95% CI 0.522–0.82) but not for IDH-mutation (AUC 0.695, 95% CI 0.436–0.927). The integrated clinical and imaging prognostic model was shown to be robust and of potential clinical relevance. The prediction of molecular markers showed promising results in the training set but could not be validated after external validation in a clinically relevant manner. Overall, these results show the potential of combining clinical features with imaging features for prognostic and predictive models in GBM, but further optimization and larger prospective studies are warranted. [ABSTRACT FROM AUTHOR]

• DL-based VOI predictions can be used as a basis for radiomic feature extraction. • DL-based VOI predictions showed high radiomic feature stability. • The VOI predictions showed good accordance with independent manual segmentations. • The DL-based VOI predictions achieved clinical feasibility in a subset of patients. • A specific retraining is necessary to apply the model for clinical GTV prediction. Volume of interest (VOI) segmentation is a crucial step for Radiomics analyses and radiotherapy (RT) treatment planning. Because it can be time-consuming and subject to inter-observer variability, we developed and tested a Deep Learning-based automatic segmentation (DLBAS) algorithm to reproducibly predict the primary gross tumor as VOI for Radiomics analyses in extremity soft tissue sarcomas (STS). A DLBAS algorithm was trained on a cohort of 157 patients and externally tested on an independent cohort of 87 patients using contrast-enhanced MRI. Manual tumor delineations by a radiation oncologist served as ground truths (GTs). A benchmark study with 20 cases from the test cohort compared the DLBAS predictions against manual VOI segmentations of two residents (ERs) and clinical delineations of two radiation oncologists (ROs). The ROs rated DLBAS predictions regarding their direct applicability. The DLBAS achieved a median dice similarity coefficient (DSC) of 0.88 against the GTs in the entire test cohort (interquartile range (IQR): 0.11) and a median DSC of 0.89 (IQR 0.07) and 0.82 (IQR 0.10) in comparison to ERs and ROs, respectively. Radiomics feature stability was high with a median intraclass correlation coefficient of 0.97, 0.95 and 0.94 for GTs, ERs, and ROs, respectively. DLBAS predictions were deemed clinically suitable by the two ROs in 35% and 20% of cases, respectively. The results demonstrate that the DLBAS algorithm provides reproducible VOI predictions for radiomics feature extraction. Variability remains regarding direct clinical applicability of predictions for RT treatment planning. [ABSTRACT FROM AUTHOR]

• Delta-radiomics predicts pathological complete response to neoadjuvant therapy. • Delta-radiomic models were superior to tumor volume and RECIST. • Delta-radiomic models predicted response to chemotherapy and radiotherapy. • Delta-radiomic models were superior to pre- or post-therapeutic radiomic models. • Delta-radiomic predictors may be associated with overall survival. In high-grade soft-tissue sarcomas (STS) the standard of care encompasses multimodal therapy regimens. While there is a growing body of evidence for prognostic pretreatment radiomic models, we hypothesized that temporal changes in radiomic features following neoadjuvant treatment ("delta-radiomics") may be able to predict the pathological complete response (pCR). MRI scans (T1-weighted with fat-saturation and contrast-enhancement (T1FSGd) and T2-weighted with fat-saturation (T2FS)) of patients with STS of the extremities and trunk treated with neoadjuvant therapy were gathered from two independent institutions (training: 103, external testing: 53 patients). pCR was defined as <5% viable cells. After segmentation and preprocessing, 105 radiomic features were extracted. Delta-radiomic features were calculated by subtraction of features derived from MRI scans obtained before and after neoadjuvant therapy. After feature reduction, machine learning modeling was performed in 100 iterations of 3-fold nested cross-validation. Delta-radiomic models were compared with single timepoint models in the testing cohort. The combined delta-radiomic models achieved the best area under the receiver operating characteristic curve (AUC) of 0.75. Pre-therapeutic tumor volume was the best conventional predictor (AUC 0.70). The T2FS-based delta-radiomic model had the most balanced classification performance with a balanced accuracy of 0.69. Delta-radiomic models achieved better reproducibility than single timepoint radiomic models, RECIST or the peri-therapeutic volume change. Delta-radiomic models were significantly associated with survival in multivariate Cox regression. This exploratory analysis demonstrated that MRI-based delta-radiomics improves prediction of pCR over tumor volume and RECIST. Delta-radiomics may one day function as a biomarker for personalized treatment adaptations. [ABSTRACT FROM AUTHOR]

Purpose: The 1p/19q co-deletion status has been demonstrated to be a prognostic biomarker in lower grade glioma (LGG). The objective of this study was to build a magnetic resonance (MRI)-derived radiomics model to predict the 1p/19q co-deletion status.Method: 209 pathology-confirmed LGG patients from 2 different datasets from The Cancer Imaging Archive were retrospectively reviewed; one dataset with 159 patients as the training and discovery dataset and the other one with 50 patients as validation dataset. Radiomics features were extracted from T2- and T1-weighted post-contrast MRI resampled data using linear and cubic interpolation methods. For each of the voxel resampling methods a three-step approach was used for feature selection and a random forest (RF) classifier was trained on the training dataset. Model performance was evaluated on training and validation datasets and clinical utility indexes (CUIs) were computed. The distributions and intercorrelation for selected features were analyzed.Results: Seven radiomics features were selected from the cubic interpolated features and five from the linear interpolated features on the training dataset. The RF classifier showed similar performance for cubic and linear interpolation methods in the training dataset with accuracies of 0.81 (0.75-0.86) and 0.76 (0.71-0.82) respectively; in the validation dataset the accuracy dropped to 0.72 (0.6-0.82) using cubic interpolation and 0.72 (0.6-0.84) using linear resampling. CUIs showed the model achieved satisfactory negative values (0.605 using cubic interpolation and 0.569 for linear interpolation).Conclusions: MRI has the potential for predicting the 1p/19q status in LGGs. Both cubic and linear interpolation methods showed similar performance in external validation. [ABSTRACT FROM AUTHOR]