Quantitative MRI Biomarkers of Stereotactic Radiotherapy Outcome in Brain Metastasis

Prediction of treatment response after stereotactic radiosurgery of brain metastasis using deep learning and radiomics on longitudinal MRI data

We developed artificial intelligence models to predict the brain metastasis (BM) treatment response after stereotactic radiosurgery (SRS) using longitudinal magnetic resonance imaging (MRI) data and evaluated prediction accuracy changes according to the number of sequential MRI scans. We included four sequential MRI scans for 194 patients with BM and 369 target lesions for the Developmental dataset. The data were randomly split (8:2 ratio) for training and testing. For external validation, 172 MRI scans from 43 patients with BM and 62 target lesions were additionally enrolled. The maximum axial diameter (Dmax), radiomics, and deep learning (DL) models were generated for comparison. We evaluated the simple convolutional neural network (CNN) model and a gated recurrent unit (Conv-GRU)-based CNN model in the DL arm. The Conv-GRU model performed superior to the simple CNN models. For both datasets, the area under the curve (AUC) was significantly higher for the two-dimensional (2D) Conv-GRU model than for the 3D Conv-GRU, Dmax, and radiomics models. The accuracy of the 2D Conv-GRU model increased with the number of follow-up studies. In conclusion, using longitudinal MRI data, the 2D Conv-GRU model outperformed all other models in predicting the treatment response after SRS of BM.

Using MRI radiomics to predict the efficacy of immunotherapy for brain metastasis in patients with small cell lung cancer

BACKGROUND

Brain metastases (BMs) are common in small cell lung cancer (SCLC), and the efficacy of immune checkpoint inhibitors (ICIs) in these patients is uncertain. In this study we aimed to develop and validate a radiomics nomogram based on magnetic resonance imaging (MRI) for intracranial efficacy prediction of ICIs in patients with BMs from SCLC.

METHODS

The training and validation cohorts consisted of 101 patients from two centers. The interclass correlation coefficient (ICC), logistic univariate regression analysis, and random forest were applied to select the radiomic features, generating the radiomics score (Rad-score) through the formula. Using multivariable logistic regression analysis, a nomogram was created by the combined model. The discrimination, calibration, and clinical utility were used to assess the performance of the nomogram. Kaplan-Meier curves were plotted based on the nomogram scores.

RESULTS

Ten radiomic features were selected for calculating the Rad-score as they could differentiate the intracranial efficacy in the training (area under the curve [AUC], 0.759) and the validation cohort (AUC, 0.667). A nomogram was created by combining Rad-score, treatment lines, and neutrophil-to-lymphocyte ratio (NLR). The training cohort obtained an AUC of 0.878 for the combined model, verified in the validation cohort (AUC = 0.875). Kaplan-Meier analyses showed the nomogram was associated with progression-free survival (PFS) (p = 0.0152) and intracranial progression-free survival (iPFS) (p = 0.0052) but not overall survival (OS) (p = 0.4894).

CONCLUSION

A radiomics nomogram model for predicting the intracranial efficacy of ICIs in SCLC patients with BMs can provide suggestions for exploring individual-based treatments for patients.

Can machine learning models improve early detection of brain metastases using diffusion weighted imaging-based radiomics?

Background

Metastatic complications are a major cause of cancer-related morbidity, with up to 40% of cancer patients experiencing at least one brain metastasis. Earlier detection may significantly improve patient outcomes and overall survival. We investigated machine learning (ML) models for early detection of brain metastases based on diffusion weighted imaging (DWI) radiomics.

Methods

Longitudinal diffusion imaging from 116 patients previously treated with stereotactic radiosurgery (SRS) for brain metastases were retrospectively analyzed. Clinical contours from 600 metastases were extracted from radiosurgery planning computed tomography, and rigidly registered to corresponding contrast enhanced-T1 and apparent diffusion coefficient (ADC) maps. Contralateral contours located in healthy brain tissue were used as control. The dataset consisted of (I) radiomic features using ADC maps, (II) radiomic feature change calculated using timepoints before the metastasis manifested on contrast enhanced-T1, (III) primary cancer, and (IV) anatomical location. The dataset was divided into training and internal validation sets using an 80/20 split with stratification. Four classification algorithms [Linear Support Vector Machine (SVM), Random Forest (RF), AdaBoost, and XGBoost] underwent supervised classification training, with contours labeled either 'control' or 'metastasis'. Hyperparameters were optimized towards balanced accuracy. Various model metrics (receiver operating characteristic curve area scores, accuracy, recall, and precision) were calculated to gauge performance.

Results

The radiomic and clinical data set, feature engineering, and ML models developed were able to identify metastases with an accuracy of up to 87.7% on the training set, and 85.8% on an unseen test set. XGBoost and RF showed superior accuracy (XGBoost: 0.877±0.021 and 0.833±0.47, RF: 0.823±0.024 and 0.858±0.045) for training and validation sets, respectively. XGBoost and RF also showed strong area under the receiver operating characteristic curve (AUC) performance on the validation set (0.910±0.037 and 0.922±0.034, respectively). AdaBoost performed slightly lower in all metrics. SVM model generalized poorly with the internal validation set. Important features involved changes in radiomics months before manifesting on contrast enhanced-T1.

Conclusions

The proposed models using diffusion-based radiomics showed encouraging results in differentiating healthy brain tissue from metastases using clinical imaging data. These findings suggest that longitudinal diffusion imaging and ML may help improve patient care through earlier diagnosis and increased patient monitoring/follow-up. Future work aims to improve model classification metrics, robustness, user-interface, and clinical applicability.

Predicting stereotactic radiosurgery outcomes with multi-observer qualitative appearance labelling versus MRI radiomics

Qualitative observer-based and quantitative radiomics-based analyses of T1w contrast-enhanced magnetic resonance imaging (T1w-CE MRI) have both been shown to predict the outcomes of brain metastasis (BM) stereotactic radiosurgery (SRS). Comparison of these methods and interpretation of radiomics-based machine learning (ML) models remains limited. To address this need, we collected a dataset of n = 123 BMs from 99 patients including 12 clinical features, 107 pre-treatment T1w-CE MRI radiomic features, and BM post-SRS progression scores. A previously published outcome model using SRS dose prescription and five-way BM qualitative appearance scoring was evaluated. We found high qualitative scoring interobserver variability across five observers that negatively impacted the model's risk stratification. Radiomics-based ML models trained to replicate the qualitative scoring did so with high accuracy (bootstrap-corrected AUC = 0.84-0.94), but risk stratification using these replicated qualitative scores remained poor. Radiomics-based ML models trained to directly predict post-SRS progression offered enhanced risk stratification (Kaplan-Meier rank-sum p = 0.0003) compared to using qualitative appearance. The qualitative appearance scoring enabled interpretation of the progression radiomics-based ML model, with necrotic BMs and a subset of heterogeneous BMs predicted as being at high-risk of post-SRS progression, in agreement with current radiobiological understanding. Our study's results show that while radiomics-based SRS outcome models out-perform qualitative appearance analysis, qualitative appearance still provides critical insight into ML model operation.

Clinical implementation of magnetic resonance imaging simulation for radiation oncology planning: 5 year experience

PURPOSE

Integrating magnetic resonance (MR) into radiotherapy planning has several advantages. This report details the clinical implementation of an MR simulation (MR-planning) program for external beam radiotherapy (EBRT) in one of North America's largest radiotherapy programs.

METHODS AND MATERIALS

An MR radiotherapy planning program was developed and implemented at Sunnybrook Health Sciences Center in 2016 with two dedicated wide-bore MR platforms (1.5 and 3.0 Tesla). Planning MR was sequentially implemented every 3 months for separate treatment sites, including the central nervous system (CNS), gynecologic (GYN), head and neck (HN), genitourinary (GU), gastrointestinal (GI), breast, and brachial plexus. Essential protocols and processes were detailed in this report, including clinical workflow, optimized MR-image acquisition protocols, MR-adapted patient setup, strategies to overcome risks and challenges, and an MR-planning quality assurance program. This study retrospectively reviewed simulation site data for all MR-planning sessions performed for EBRT over the past 5 years.

RESULTS

From July 2016 to December 2021, 8798 MR-planning sessions were carried out, which corresponds to 25% of all computer tomography (CT) simulations (CT-planning) performed during the same period at our institution. There was a progressive rise from 80 MR-planning sessions in 2016 to 1126 in 2017, 1492 in 2018, 1824 in 2019, 2040 in 2020, and 2236 in 2021. As a result, the relative number of planning MR/CT increased from 3% of all planning sessions in 2016 to 36% in 2021. The most common site of MR-planning was CNS (49%), HN (13%), GYN (12%), GU (12%), and others (8%).

CONCLUSION

Detailed clinical processes and protocols of our MR-planning program were presented, which have been improved over more than 5 years of robust experience. Strategies to overcome risks and challenges in the implementation process are highlighted. Our work provides details that can be used by institutions interested in implementing an MR-planning program.

The emerging potential of quantitative MRI biomarkers for the early prediction of brain metastasis response after stereotactic radiosurgery: a scoping review

Background

At present, the simple prognostic models based on clinical information for predicting the treatment outcomes of brain metastases (BMs) are subjective and delayed. Thus, we performed this systematic review of multiple studies to assess the potential of quantitative magnetic resonance imaging (MRI) biomarkers for the early prediction of treatment outcomes of brain metastases with stereotactic radiosurgery (SRS).

Methods

We systematically searched the PubMed, Embase, Cochrane, Web of Science, and Clinical Trials.gov databases for articles published between February 1, 1991, and April 11, 2022, with no language restrictions. We included studies involving patients with BMs receiving SRS; the included patients were required to have definite pathology of a primary tumor and complete imaging data (pre- and post-SRS). We excluded the articles that included patients who had undergone previous surgery and those that did not include regular follow-up or corresponding MRI scans.

Results

We identified 2,162 studies, of which 26 were included in our analysis, involving a total of 1,362 participants. All 26 studies explored the relevant MRI parameters to predict the prognosis of patients with BMs who received SRS. The outcomes were generalized according to the relationships between the anatomical/morphological, microstructural, vascular, and metabolic changes and SRS. Generally, with traditional MRI, there are several quantitative prognostic models based on preradiosurgical radiomics that predict the outcome of SRS treatment in local BM control. With the implementation of advanced MRI, the relative apparent diffusion coefficient (ADC), perfusion fraction (f), relative cerebral blood volume (rCBV), relative regional cerebral blood flow (rrCBF), interstitial fluid pressure (IFP), quadratic of time-dependent leakage (K_trans ²), extracellular extravascular volume (v_e), choline/creatine (Cho/Cr), nuclear Overhauser effect (NOE) peak, and intraextracellular water exchange rate constant (k_IE ) were confirmed to be indicative of the therapeutic effect of SRS for BMs.

Conclusions

Quantitative MRI biomarkers extracted from traditional or advanced MRI at different time points, which can represent the anatomical/morphological, microstructural, vascular, and metabolic changes, respectively, have been proposed as promising markers for the early prediction of SRS response in those with BMs. There are some limitations in this review, including the risk of selection bias, the limited number of study objects, the incomparability of the total data, and the subjectivity of the review process.

Dual-center validation of using magnetic resonance imaging radiomics to predict stereotactic radiosurgery outcomes

Background

MRI radiomic features and machine learning have been used to predict brain metastasis (BM) stereotactic radiosurgery (SRS) outcomes. Previous studies used only single-center datasets, representing a significant barrier to clinical translation and further research. This study, therefore, presents the first dual-center validation of these techniques.

Methods

SRS datasets were acquired from 2 centers (n = 123 BMs and n = 117 BMs). Each dataset contained 8 clinical features, 107 pretreatment T1w contrast-enhanced MRI radiomic features, and post-SRS BM progression endpoints determined from follow-up MRI. Random decision forest models were used with clinical and/or radiomic features to predict progression. 250 bootstrap repetitions were used for single-center experiments.

Results

Training a model with one center's dataset and testing it with the other center's dataset required using a set of features important for outcome prediction at both centers, and achieved area under the receiver operating characteristic curve (AUC) values up to 0.70. A model training methodology developed using the first center's dataset was locked and externally validated with the second center's dataset, achieving a bootstrap-corrected AUC of 0.80. Lastly, models trained on pooled data from both centers offered balanced accuracy across centers with an overall bootstrap-corrected AUC of 0.78.

Conclusions

Using the presented validated methodology, radiomic models trained at a single center can be used externally, though they must utilize features important across all centers. These models' accuracies are inferior to those of models trained using each individual center's data. Pooling data across centers shows accurate and balanced performance, though further validation is required.

Performance sensitivity analysis of brain metastasis stereotactic radiosurgery outcome prediction using MRI radiomics

Recent studies have used T1w contrast-enhanced (T1w-CE) magnetic resonance imaging (MRI) radiomic features and machine learning to predict post-stereotactic radiosurgery (SRS) brain metastasis (BM) progression, but have not examined the effects of combining clinical and radiomic features, BM primary cancer, BM volume effects, and using multiple scanner models. To investigate these effects, a dataset of n = 123 BMs from 99 SRS patients with 12 clinical features, 107 pre-treatment T1w-CE radiomic features, and BM progression determined by follow-up MRI was used with a random decision forest model and 250 bootstrapped repetitions. Repeat experiments assessed the relative accuracy across primary cancer sites, BM volume groups, and scanner model pairings. Correction for accuracy imbalances across volume groups was investigated by removing volume-correlated features. We found that using clinical and radiomic features together produced the most accurate model with a bootstrap-corrected area under the receiver operating characteristic curve of 0.77. Accuracy also varied by primary cancer site, BM volume, and scanner model pairings. The effect of BM volume was eliminated by removing features at a volume-correlation coefficient threshold of 0.25. These results show that feature type, primary cancer, volume, and scanner model are all critical factors in the accuracy of radiomics-based prognostic models for BM SRS that must be characterised and controlled for before clinical translation.

High grade glioma radiation therapy on a high field 1.5 Tesla MR-Linac - workflow and initial experience with daily adapt-to-position (ATP) MR guidance: A first report

PURPOSE

This study reports the workflow and initial clinical experience of high grade glioma (HGG) radiotherapy on the 1.5 T MR-Linac (MRL), with a focus on the temporal variations of the tumor and feasibility of multi-parametric image (mpMRI) acquisition during routine treatment workflow.

MATERIALS AND METHODS

Ten HGG patients treated with radiation within the first year of the MRL's clinical operation, between October 2019 and August 2020, were identified from a prospective database. Workflow timings were recorded and online adaptive plans were generated using the Adapt-To-Position (ATP) workflow. Temporal variation within the FLAIR hyperintense region (FHR) was assessed by the relative FHR volumes (n = 281 contours) and migration distances (maximum linear displacement of the volume). Research mpMRIs were acquired on the MRL during radiation and changes in selected functional parameters were investigated within the FHR.

RESULTS

All patients completed radiotherapy to a median dose of 60 Gy (range, 54-60 Gy) in 30 fractions (range, 30-33), receiving a total of 287 fractions on the MRL. The mean in-room time per fraction with or without post-beam research imaging was 42.9 minutes (range, 25.0-69.0 minutes) and 37.3 minutes (range, 24.0-51.0 minutes), respectively. Three patients (30%) required re-planning between fractions 9 to 12 due to progression of tumor and/or edema identified on daily MRL imaging. At the 10, 20, and 30-day post-first fraction time points 3, 3, and 4 patients, respectively, had a FHR volume that changed by at least 20% relative to the first fraction. Research mpMRIs were successfully acquired on the MRL. The median apparent diffusion coefficient (ADC) within the FHR and the volumes of FLAIR were significantly correlated when data from all patients and time points were pooled (R=0.68, p<.001).

CONCLUSION

We report the first clinical series of HGG patients treated with radiotherapy on the MRL. The ATP workflow and treatment times were clinically acceptable, and daily online MRL imaging triggered adaptive re-planning for selected patients. Acquisition of mpMRIs was feasible on the MRL during routine treatment workflow. Prospective clinical outcomes data is anticipated from the ongoing UNITED phase 2 trial to further refine the role of MR-guided adaptive radiotherapy.

A Self-Attention-Guided 3D Deep Residual Network With Big Transfer to Predict Local Failure in Brain Metastasis After Radiotherapy Using Multi-Channel MRI

A noticeable proportion of larger brain metastases (BMs) are not locally controlled after stereotactic radiotherapy, and it may take months before local progression is apparent on standard follow-up imaging. This work proposes and investigates new explainable deep-learning models to predict the radiotherapy outcome for BM. A novel self-attention-guided 3D residual network is introduced for predicting the outcome of local failure (LF) after radiotherapy using the baseline treatment-planning MRI. The 3D self-attention modules facilitate capturing long-range intra/inter slice dependencies which are often overlooked by convolution layers. The proposed model was compared to a vanilla 3D residual network and 3D residual network with CBAM attention in terms of performance in outcome prediction. A training recipe was adapted for the outcome prediction models during pretraining and training the down-stream task based on the recently proposed big transfer principles. A novel 3D visualization module was coupled with the model to demonstrate the impact of various intra/peri-lesion regions on volumetric multi-channel MRI upon the network's prediction. The proposed self-attention-guided 3D residual network outperforms the vanilla residual network and the residual network with CBAM attention in accuracy, F1-score, and AUC. The visualization results show the importance of peri-lesional characteristics on treatment-planning MRI in predicting local outcome after radiotherapy. This study demonstrates the potential of self-attention-guided deep-learning features derived from volumetric MRI in radiotherapy outcome prediction for BM. The insights obtained via the developed visualization module for individual lesions can possibly be applied during radiotherapy planning to decrease the chance of LF.

Impact of Tumour Segmentation Accuracy on Efficacy of Quantitative MRI Biomarkers of Radiotherapy Outcome in Brain Metastasis

Simple Summary

Radiotherapy is a major treatment option for patients with brain metastasis. However, response to radiotherapy is highly varied among the patients, and it may take months before the response of brain metastasis to radiotherapy is apparent on standard follow-up imaging. This is not desirable, especially given the fact that patients diagnosed with brain metastasis suffer from a short median survival. Recent studies have shown the high potential of machine learning methods for analyzing quantitative imaging features (biomarkers) to predict the response of brain metastasis before or early after radiotherapy. However, these methods require manual delineation of individual tumours on imaging that is tedious and time-consuming, hindering further development and widespread application of these techniques. Here, we investigated the impact of using less accurate but automatically generated tumour outlines on the efficacy of the derived imaging biomarkers for radiotherapy response prediction. Our findings demonstrate that while the effect of tumour delineation accuracy is considerable for automatic contours with low accuracy, imaging biomarkers and prediction models are rather robust to imperfections in the produced tumour masks. The results of this study open the avenue to utilizing automatically generated tumour contours for discovering imaging biomarkers without sacrificing their accuracy.

Abstract

Significantly affecting patients’ clinical course and quality of life, a growing number of cancer cases are diagnosed with brain metastasis (BM) annually. Stereotactic radiotherapy is now a major treatment option for patients with BM. However, it may take months before the local response of BM to stereotactic radiation treatment is apparent on standard follow-up imaging. While machine learning in conjunction with radiomics has shown great promise in predicting the local response of BM before or early after radiotherapy, further development and widespread application of such techniques has been hindered by their dependency on manual tumour delineation. In this study, we explored the impact of using less-accurate automatically generated segmentation masks on the efficacy of radiomic features for radiotherapy outcome prediction in BM. The findings of this study demonstrate that while the effect of tumour delineation accuracy is substantial for segmentation models with lower dice scores (dice score ≤ 0.85), radiomic features and prediction models are rather resilient to imperfections in the produced tumour masks. Specifically, the selected radiomic features (six shared features out of seven) and performance of the prediction model (accuracy of 80% versus 80%, AUC of 0.81 versus 0.78) were fairly similar for the ground-truth and automatically generated segmentation masks, with dice scores close to 0.90. The positive outcome of this work paves the way for adopting high-throughput automatically generated tumour masks for discovering diagnostic and prognostic imaging biomarkers in BM without sacrificing accuracy.

Artificial intelligence in oncologic imaging

Radiology is integral to cancer care. Compared to molecular assays, imaging has its advantages. Imaging as a noninvasive tool can assess the entirety of tumor unbiased by sampling error and is routinely acquired at multiple time points in oncological practice. Imaging data can be digitally post-processed for quantitative assessment. The ever-increasing application of Artificial intelligence (AI) to clinical imaging is challenging radiology to become a discipline with competence in data science, which plays an important role in modern oncology. Beyond streamlining certain clinical tasks, the power of AI lies in its ability to reveal previously undetected or even imperceptible radiographic patterns that may be difficult to ascertain by the human sensory system. Here, we provide a narrative review of the emerging AI applications relevant to the oncological imaging spectrum and elaborate on emerging paradigms and opportunities. We envision that these technical advances will change radiology in the coming years, leading to the optimization of imaging acquisition and discovery of clinically relevant biomarkers for cancer diagnosis, staging, and treatment monitoring. Together, they pave the road for future clinical translation in precision oncology.

Artificial Intelligence for Survival Prediction in Brain Tumors on Neuroimaging

Survival prediction of patients affected by brain tumors provides essential information to guide surgical planning, adjuvant treatment selection, and patient counseling. Current reliance on clinical factors, such as Karnofsky Performance Status Scale, and simplistic radiological characteristics are, however, inadequate for survival prediction in tumors such as glioma that demonstrate molecular and clinical heterogeneity with variable survival outcomes. Advances in the domain of artificial intelligence have afforded powerful tools to capture a large number of hidden high-dimensional imaging features that reflect abundant information about tumor structure and physiology. Here, we provide an overview of current literature that apply computational analysis tools such as radiomics and machine learning methods to the pipeline of image preprocessing, tumor segmentation, feature extraction, and construction of classifiers to establish survival prediction models based on neuroimaging. We also discuss challenges relating to the development and evaluation of such models and explore ethical issues surrounding the future use of machine learning predictions.

The radiomic-clinical model using the SHAP method for assessing the treatment response of whole-brain radiotherapy: a multicentric study

OBJECTIVE

To develop and validate a pretreatment magnetic resonance imaging (MRI)-based radiomic-clinical model to assess the treatment response of whole-brain radiotherapy (WBRT) by using SHapley Additive exPlanations (SHAP), which is derived from game theory, and can explain the output of different machine learning models.

METHODS

We retrospectively enrolled 228 patients with brain metastases from two medical centers (184 in the training cohort and 44 in the validation cohort). Treatment responses of patients were categorized as a non-responding group vs. a responding group according to the Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) criteria. For each tumor, 960 features were extracted from the MRI sequence. The least absolute shrinkage and selection operator (LASSO) was used for feature selection. A support vector machine (SVM) model incorporating clinical factors and radiomic features wase used to construct the radiomic-clinical model. SHAP method explained the SVM model by prioritizing the importance of features, in terms of assessment contribution.

RESULTS

Three radiomic features and three clinical factors were identified to build the model. Radiomic-clinical model yielded AUCs of 0.928 (95%CI 0.901-0.949) and 0.851 (95%CI 0.816-0.886) for assessing the treatment response in the training cohort and validation cohort, respectively. SHAP summary plot illustrated the feature's value affected the feature's impact attributed to model, and SHAP force plot showed the integration of features' impact attributed to individual response.

CONCLUSION

The radiomic-clinical model with the SHAP method can be useful for assessing the treatment response of WBRT and may assist clinicians in directing personalized WBRT strategies in an understandable manner.

KEY POINTS

• Radiomic-clinical model can be useful for assessing the treatment response of WBRT. • SHAP could explain and visualize radiomic-clinical machine learning model in a clinician-friendly way.

A deep learning-based radiomics approach to predict head and neck tumor regression for adaptive radiotherapy

Early regression—the regression in tumor volume during the initial phase of radiotherapy (approximately 2 weeks after treatment initiation)—is a common occurrence during radiotherapy. This rapid radiation-induced tumor regression may alter target coordinates, necessitating adaptive radiotherapy (ART). We developed a deep learning-based radiomics (DLR) approach to predict early head and neck tumor regression and thereby facilitate ART. Primary gross tumor volume (GTVp) was monitored in 96 patients and nodal GTV (GTVn) in 79 patients during treatment. All patients underwent two computed tomography (CT) scans: one before the start of radiotherapy for initial planning and one during radiotherapy for boost planning. Patients were assigned to regression and nonregression groups according to their median tumor regression rate (ΔGTV/treatment day from initial to boost CT scan). We input a GTV image into the convolutional neural network model, which was pretrained using natural image datasets, via transfer learning. The deep features were extracted from the last fully connected layer. To clarify the prognostic power of the deep features, machine learning models were trained. The models then predicted the regression and nonregression of GTVp and GTVn and evaluated the predictive performance by 0.632 + bootstrap area under the curve (AUC). Predictive performance for GTVp regression was highest using the InceptionResNetv2 model (mean AUC = 0.75) and that for GTVn was highest using NASNetLarge (mean AUC = 0.73). Both models outperformed the handcrafted radiomics features (mean AUC = 0.63 for GTVp and 0.61 for GTVn) or clinical factors (0.64 and 0.67, respectively). DLR may facilitate ART for improved radiation side-effects and target coverage.

Deep learning of quantitative ultrasound multi-parametric images at pre-treatment to predict breast cancer response to chemotherapy

In this study, a novel deep learning-based methodology was investigated to predict breast cancer response to neo-adjuvant chemotherapy (NAC) using the quantitative ultrasound (QUS) multi-parametric imaging at pre-treatment. QUS multi-parametric images of breast tumors were generated using the data acquired from 181 patients diagnosed with locally advanced breast cancer and planned for NAC followed by surgery. The ground truth response to NAC was identified for each patient after the surgery using the standard clinical and pathological criteria. Two deep convolutional neural network (DCNN) architectures including the residual network and residual attention network (RAN) were explored for extracting optimal feature maps from the parametric images, with a fully connected network for response prediction. In different experiments, the features maps were derived from the tumor core only, as well as the core and its margin. Evaluation results on an independent test set demonstrate that the developed model with the RAN architecture to extract feature maps from the expanded parametric images of the tumor core and margin had the best performance in response prediction with an accuracy of 88% and an area under the receiver operating characteristic curve of 0.86. Ten-year survival analyses indicate statistically significant differences between the survival of the responders and non-responders identified based on the model prediction at pre-treatment and the standard criteria at post-treatment. The results of this study demonstrate the promising capability of DCNNs with attention mechanisms in predicting breast cancer response to NAC prior to the start of treatment using QUS multi-parametric images.

Beyond Glioma: The Utility of Radiomic Analysis for Non-Glial Intracranial Tumors

Simple Summary

Tumor qualities, such as growth rate, firmness, and intrusion into healthy tissue, can be very important for operation planning and further treatment. Radiomics is a promising new method that allows the determination of some of these qualities on images performed before surgery. In this article, we provide a review of the use of radiomics in various tumors of the central nervous system, such as metastases, lymphoma, meningioma, medulloblastoma, and pituitary tumors.

Abstract

The field of radiomics is rapidly expanding and gaining a valuable role in neuro-oncology. The possibilities related to the use of radiomic analysis, such as distinguishing types of malignancies, predicting tumor grade, determining the presence of particular molecular markers, consistency, therapy response, and prognosis, can considerably influence decision-making in medicine in the near future. Even though the main focus of radiomic analyses has been on glial CNS tumors, studies on other intracranial tumors have shown encouraging results. Therefore, as the main focus of this review, we performed an analysis of publications on PubMed and Web of Science databases, focusing on radiomics in CNS metastases, lymphoma, meningioma, medulloblastoma, and pituitary tumors.

Quality of Radiomics Research on Brain Metastasis: A Roadmap to Promote Clinical Translation

Objective

Our study aimed to evaluate the quality of radiomics studies on brain metastases based on the radiomics quality score (RQS), Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) checklist, and the Image Biomarker Standardization Initiative (IBSI) guidelines.

Materials and Methods

PubMed MEDLINE, and EMBASE were searched for articles on radiomics for evaluating brain metastases, published until February 2021. Of the 572 articles, 29 relevant original research articles were included and evaluated according to the RQS, TRIPOD checklist, and IBSI guidelines.

Results

External validation was performed in only three studies (10.3%). The median RQS was 3.0 (range, -6 to 12), with a low basic adherence rate of 50.0%. The adherence rate was low in comparison to the “gold standard” (10.3%), stating the potential clinical utility (10.3%), performing the cut-off analysis (3.4%), reporting calibration statistics (6.9%), and providing open science and data (3.4%). None of the studies involved test-retest or phantom studies, prospective studies, or cost-effectiveness analyses. The overall rate of adherence to the TRIPOD checklist was 60.3% and low for reporting title (3.4%), blind assessment of outcome (0%), description of the handling of missing data (0%), and presentation of the full prediction model (0%). The majority of studies lacked pre-processing steps, with bias-field correction, isovoxel resampling, skull stripping, and gray-level discretization performed in only six (20.7%), nine (31.0%), four (3.8%), and four (13.8%) studies, respectively.

Conclusion

The overall scientific and reporting quality of radiomics studies on brain metastases published during the study period was insufficient. Radiomics studies should adhere to the RQS, TRIPOD, and IBSI guidelines to facilitate the translation of radiomics into the clinical field.

Brain metastases: the role of clinical imaging

Imaging of brain metastases (BMs) has advanced greatly over the past decade. In this review, we discuss the main challenges that BMs pose in clinical practice and describe the role of imaging.Firstly, we describe the increased incidence of BMs of different primary tumours and the rationale for screening. A challenge lies in selecting the right patients for screening: not all cancer patients develop BMs in their disease course.Secondly, we discuss the imaging techniques to detect BMs. A three-dimensional (3D) T1W MRI sequence is the golden standard for BM detection, but additional anatomical (susceptibility weighted imaging, diffusion weighted imaging), functional (perfusion MRI) and metabolic (MR spectroscopy, positron emission tomography) information can help to differentiate BMs from other intracranial aetiologies.Thirdly, we describe the role of imaging before, during and after treatment of BMs. For surgical resection, imaging is used to select surgical patients, but also to assist intraoperatively (neuronavigation, fluorescence-guided surgery, ultrasound). For treatment planning of stereotactic radiosurgery, MRI is combined with CT. For surveillance after both local and systemic therapies, conventional MRI is used. However, advanced imaging is increasingly performed to distinguish true tumour progression from pseudoprogression.FInally, future perspectives are discussed, including radiomics, new biomarkers, new endogenous contrast agents and theranostics.

Development of a Prognostic Model for Overall Survival in Patients with Extracranial Oligometastatic Disease Treated with Stereotactic Body Radiation Therapy

BACKGROUND

Patients with oligometastatic disease (OMD) may experience durable disease control with ablative therapy to all sites of disease. Stereotactic body radiation therapy (SBRT) is an important modality in the management of OMD patients though a validated prognostic model for OMD patients treated with SBRT is currently lacking. The purpose of this study was to develop a prognostic model for overall survival (OS) in OMD patients treated with SBRT.

METHODS

A multi-institutional database of extracranial OMD patients treated with SBRT was used for model development. The final prognostic model was generated in a training set using recursive partitioning analysis representing 75% of the population. Model performance was evaluated in the reserved test set.

RESULTS

1,033 patients were included in the analysis. The median OS for the entire cohort was 44.2 months (95% confidence interval: 39.2-48.8 months). The variables used in the regression tree, in order of importance, were primary histology, lung-only OMD on presentation, the timing of OMD presentation and age at the start of SBRT. A full 5-category risk stratification system based on the terminal nodes possessed fair to good discriminative power with a Harrell's concordance statistic of 0.683 (0.634-0.731) and time-dependent area under the receiver operating characteristic curve of 0.709 (0706-0.711) in the test set, with good calibration. A simplified risk stratification system consisting of 3 risk categories was also proposed for greater ease-of-use with comparable performance.

CONCLUSION

A clinical prognostic model for OS in patients with extracranial OMD treated with SBRT has been developed and validated.

Machine Learning-Based Radiomics in Neuro-Oncology

In the last decades, modern medicine has evolved into a data-centered discipline, generating massive amounts of granular high-dimensional data exceeding human comprehension. With improved computational methods, machine learning and artificial intelligence (AI) as tools for data processing and analysis are becoming more and more important. At the forefront of neuro-oncology and AI-research, the field of radiomics has emerged. Non-invasive assessments of quantitative radiological biomarkers mined from complex imaging characteristics across various applications are used to predict survival, discriminate between primary and secondary tumors, as well as between progression and pseudo-progression. In particular, the application of molecular phenotyping, envisioned in the field of radiogenomics, has gained popularity for both primary and secondary brain tumors. Although promising results have been obtained thus far, the lack of workflow standardization and availability of multicenter data remains challenging. The objective of this review is to provide an overview of novel applications of machine learning- and deep learning-based radiomics in primary and secondary brain tumors and their implications for future research in the field.

The role of feature-based radiomics for predicting response and radiation injury after stereotactic radiation therapy for brain metastases: A critical review by the Young Group of the Italian Association of Radiotherapy and Clinical Oncology (yAIRO)

Introduction

differential diagnosis of tumor recurrence and radiation injury after stereotactic radiotherapy (SRT) is challenging. The advances in imaging techniques and feature-based radiomics could aid to discriminate radionecrosis from progression.

Methods

we performed a systematic review of current literature, key references were obtained from a PubMed query. Data extraction was performed by 3 researchers and disagreements were resolved with a discussion among the authors.

Results

we identified 15 retrospective series, one prospective trial, one critical review and one editorial paper. Radiomics involves a wide range of imaging features referred to necrotic regions, rate of contrast-enhancing area or the measure of edema surrounding the metastases. Features were mainly defined through a multistep extraction/reduction/selection process and a final validation and comparison.

Conclusions

feature-based radiomics has an optimal potential to accurately predict response and radionecrosis after SRT of BM and facilitate differential diagnosis. Further validation studies are eagerly awaited to confirm radiomics reliability.

Genomic and Transcriptomic Profiling of Brain Metastases

Simple Summary

Brain metastases (BM) are the most common brain tumors in adults and are the main cause of cancer-associated death. Omics analysis of BM will allow for a better understanding of metastatic progression, prognosis and therapeutic targeting. In this study, BM samples underwent comprehensive molecular profiling with genomics and transcriptomics. Mutational signatures suggested that most mutations were gained prior to metastasis. A novel copy number event centered around the MCL1 gene was found in 75% of all samples. Transcriptomics revealed that melanoma BM formed a distinct cluster in comparison to other subtypes. Poor survival correlated to self-identified black race and absence of radiation treatment but not molecular profiles. These data identify potential new drivers of brain metastatic progression, implicate that melanoma BM are distinctive and likely responsive to unique therapies, and further investigation of sociodemographic and clinical features are needed in BM cohorts.

Abstract

Brain metastases (BM) are the most common brain tumors in adults occurring in up to 40% of all cancer patients. Multi-omics approaches allow for understanding molecular mechanisms and identification of markers with prognostic significance. In this study, we profile 130 BM using genomics and transcriptomics and correlate molecular characteristics to clinical parameters. The most common tumor origins for BM were lung (40%) followed by melanoma (21%) and breast (15%). Melanoma and lung BMs contained more deleterious mutations than other subtypes (p < 0.001). Mutational signatures suggested that the bulk of the mutations were gained before metastasis. A novel copy number event centered around the MCL1 gene was found in 75% of all samples, suggesting a broader role in promoting metastasis. Unsupervised hierarchical cluster analysis of transcriptional signatures available in 65 samples based on the hallmarks of cancer revealed four distinct clusters. Melanoma samples formed a distinctive cluster in comparison to other BM subtypes. Characteristics of molecular profiles did not correlate with survival. However, patients with self-identified black race or those who did not receive radiation correlated with poor survival. These data identify potential new drivers of brain metastatic progression. Our data also suggest further investigation of sociodemographic and clinical features is needed in BM cohorts.

A priori prediction of local failure in brain metastasis after hypo-fractionated stereotactic radiotherapy using quantitative MRI and machine learning

This study investigated the effectiveness of pre-treatment quantitative MRI and clinical features along with machine learning techniques to predict local failure in patients with brain metastasis treated with hypo-fractionated stereotactic radiation therapy (SRT). The predictive models were developed using the data from 100 patients (141 lesions) and evaluated on an independent test set with data from 20 patients (30 lesions). Quantitative MRI radiomic features were derived from the treatment-planning contrast-enhanced T1w and T2-FLAIR images. A multi-phase feature reduction and selection procedure was applied to construct an optimal quantitative MRI biomarker for predicting therapy outcome. The performance of standard clinical features in therapy outcome prediction was evaluated using a similar procedure. Survival analyses were conducted to compare the long-term outcome of the two patient cohorts (local control/failure) identified based on prediction at pre-treatment, and standard clinical criteria at last patient follow-up after SRT. The developed quantitative MRI biomarker consists of four features with two features quantifying heterogeneity in the edema region, one feature characterizing intra-tumour heterogeneity, and one feature describing tumour morphology. The predictive models with the radiomic and clinical feature sets yielded an AUC of 0.87 and 0.62, respectively on the independent test set. Incorporating radiomic features into the clinical predictive model improved the AUC of the model by up to 16%, relatively. A statistically significant difference was observed in survival of the two patient cohorts identified at pre-treatment using the radiomics-based predictive model, and at post-treatment using the the RANO-BM criteria. Results of this study revealed a good potential for quantitative MRI radiomic features at pre-treatment in predicting local failure in relatively large brain metastases undergoing SRT, and is a step forward towards a precision oncology paradigm for brain metastasis.

Differentiation Between Glioblastoma Multiforme and Metastasis From the Lungs and Other Sites Using Combined Clinical/Routine MRI Radiomics

Background

Differentiation between cerebral glioblastoma multiforme (GBM) and solitary brain metastasis (MET) is important. The existing radiomic differentiation method ignores the clinical and routine magnetic resonance imaging (MRI) features.

Purpose

To differentiate between GBM and MET and between METs from the lungs (MET-lung) and other sites (MET-other) through clinical and routine MRI, and radiomics analyses.

Methods and Materials

A total of 350 patients were collected from two institutions, including 182 patients with GBM and 168 patients with MET, which were all proven by pathology. The ROI of the tumor was obtained on axial postcontrast MRI which was performed before operation. Seven radiomic feature selection methods and four classification algorithms constituted 28 classifiers in two classification strategies, with the best classifier serving as the final radiomics model. The clinical and combination models were constructed using the nomograms developed. The performance of the nomograms was evaluated in terms of calibration, discrimination, and clinical usefulness. Student’s t-test or the chi-square test was used to assess the differences in the clinical and radiological characteristics between the training and internal validation cohorts. Receiver operating characteristic curve analysis was performed to assess the performance of developed models with the area under the curve (AUC).

Results

The classifier fisher_decision tree (fisher_DT) showed the best performance (AUC: 0.696, 95% CI:0.608-0.783) for distinguishing between GBM and MET in internal validation cohorts; the classifier reliefF_random forest (reliefF_RF) showed the best performance (AUC: 0.759, 95% CI: 0.613-0.904) for distinguishing between MET-lung and MET-other in internal validation cohorts. The combination models incorporating the radiomics signature and clinical-radiological characteristics were superior to the clinical-radiological models in the two classification strategies (AUC: 0.764 for differentiation between GBM in internal validation cohorts and MET and 0.759 or differentiation between MET-lung and MET-other in internal validation cohorts). The nomograms showed satisfactory performance and calibration and were considered clinically useful, as revealed in the decision curve analysis.

Data Conclusion

The combination of radiomic and non-radiomic features is helpful for the differentiation among GBM, MET-lung, and MET-other.

Enhancement of Radiosurgical Treatment Outcome Prediction Using MRI Radiomics in Patients with Non-Small Cell Lung Cancer Brain Metastases

Simple Summary

Non-small cell lung cancer (NSCLC) is the most common cause of brain metastasis (BM). Approximately 50% of patients with metastatic NSCLC harbor BMs. Within the past decade, Gamma Knife radiosurgery (GKRS) has become one of the first-line treatments for BMs. Ability to predict treatment response after GKRS can therefore guide treatment strategy. This study aimed to determine whether pre-radiosurgical neuroimaging radiomics can predict survival and local tumor control after GKRS. Based on the collected magnetic resonance images and clinical characteristics of the 237 NSCLC BM patients with BMs (for survival prediction) and 256 NSCLC patients with 976 BMs (for prediction of local tumor control), we concluded that the identified radiomic features could provide valuable additional information to enhance the prediction of BM responses after GKRS. The proposed approach provided physicians with an intuitive way to predict the patient outcome based on pre-radiosurgical magnetic resonance images.

Abstract

The diagnosis of brain metastasis (BM) is commonly observed in non-small cell lung cancer (NSCLC) with poor outcomes. Accordingly, developing an approach to early predict BM response to Gamma Knife radiosurgery (GKRS) may benefit the patient treatment and monitoring. A total of 237 NSCLC patients with BMs (for survival prediction) and 256 patients with 976 BMs (for prediction of local tumor control) treated with GKRS were retrospectively analyzed. All the survival data were recorded without censoring, and the status of local tumor control was determined by comparing the last MRI follow-up in patients’ lives with the pre-GKRS MRI. Overall 1763 radiomic features were extracted from pre-radiosurgical magnetic resonance images. Three prediction models were constructed, using (1) clinical data, (2) radiomic features, and (3) clinical and radiomic features. Support vector machines with a 30% hold-out validation approach were constructed. For treatment outcome predictions, the models derived from both the clinical and radiomics data achieved the best results. For local tumor control, the combined model achieved an area under the curve (AUC) of 0.95, an accuracy of 90%, a sensitivity of 91%, and a specificity of 89%. For patient survival, the combined model achieved an AUC of 0.81, an accuracy of 77%, a sensitivity of 78%, and a specificity of 80%. The pre-radiosurgical radiomics data enhanced the performance of local tumor control and survival prediction models in NSCLC patients with BMs treated with GRKS. An outcome prediction model based on radiomics combined with clinical features may guide therapy in these patients.

Tumor habitat analysis by magnetic resonance imaging distinguishes tumor progression from radiation necrosis in brain metastases after stereotactic radiosurgery

OBJECTIVES

The identification of viable tumor after stereotactic radiosurgery (SRS) is important for future targeted therapy. This study aimed to determine whether tumor habitat on structural and physiologic MRI can distinguish viable tumor from radiation necrosis of brain metastases after SRS.

METHOD

Multiparametric contrast-enhanced T1- and T2-weighted imaging, apparent diffusion coefficient (ADC), and cerebral blood volume (CBV) were obtained from 52 patients with 69 metastases, showing enlarging enhancing masses after SRS. Voxel-wise clustering identified three structural MRI habitats (enhancing, solid low-enhancing, and nonviable) and three physiologic MRI habitats (hypervascular cellular, hypovascular cellular, and nonviable). Habitat-based predictors for viable tumor or radiation necrosis were identified by logistic regression. Performance was validated using the area under the curve (AUC) of the receiver operating characteristics curve in an independent dataset with 24 patients.

RESULTS

None of the physiologic MRI habitats was indicative of viable tumor. Viable tumor was predicted by a high-volume fraction of solid low-enhancing habitat (low T2-weighted and low CE-T1-weighted values; odds ratio [OR] 1.74, p <.001) and a low-volume fraction of nonviable tissue habitat (high T2-weighted and low CE-T1-weighted values; OR 0.55, p <.001). Combined structural MRI habitats yielded good discriminatory ability in both development (AUC 0.85, 95% confidence interval [CI]: 0.77-0.94) and validation sets (AUC 0.86, 95% CI:0.70-0.99), outperforming single ADC (AUC 0.64) and CBV (AUC 0.58) values. The site of progression matched with the solid low-enhancing habitat (72%, 8/11).

CONCLUSION

Solid low-enhancing and nonviable tissue habitats on structural MRI can help to localize viable tumor in patients with brain metastases after SRS.

KEY POINTS

• Structural MRI habitats helped to differentiate viable tumor from radiation necrosis. • Solid low-enhancing habitat was most helpful to find viable tumor. • Providing spatial information, the site of progression matched with solid low-enhancing habitat.

[Artificial intelligence, radiomics and pathomics to predict response and survival of patients treated with radiations]

Artificial intelligence approaches in medicine are more and more used and are extremely promising due to the growing number of data produced and the variety of data they allow to exploit. Thus, the computational analysis of medical images in particular, radiological (radiomics), or anatomopathological (pathomics), has shown many very interesting results for the prediction of the prognosis and the response of cancer patients. Radiotherapy is a discipline that particularly benefits from these new approaches based on computer science and imaging. This review will present the main principles of an artificial intelligence approach and in particular machine learning, the principles of a radiomic and pathomic approach and the potential of their use for the prediction of the prognosis of patients treated with radiotherapy.

Characterizing intra-tumor regions on quantitative ultrasound parametric images to predict breast cancer response to chemotherapy at pre-treatment

The efficacy of quantitative ultrasound (QUS) multi-parametric imaging in conjunction with unsupervised classification algorithms was investigated for the first time in characterizing intra-tumor regions to predict breast tumor response to chemotherapy before the start of treatment. QUS multi-parametric images of breast tumors were generated using the ultrasound radiofrequency data acquired from 181 patients diagnosed with locally advanced breast cancer and planned for neo-adjuvant chemotherapy followed by surgery. A hidden Markov random field (HMRF) expectation maximization (EM) algorithm was applied to identify distinct intra-tumor regions on QUS multi-parametric images. Several features were extracted from the segmented intra-tumor regions and tumor margin on different parametric images. A multi-step feature selection procedure was applied to construct a QUS biomarker consisting of four features for response prediction. Evaluation results on an independent test set indicated that the developed biomarker coupled with a decision tree model with adaptive boosting (AdaBoost) as the classifier could predict the treatment response of patient at pre-treatment with an accuracy of 85.4% and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.89. In comparison, the biomarkers consisted of the features derived from the entire tumor core (without consideration of the intra-tumor regions), and the entire tumor core and the tumor margin could predict the treatment response of patients with an accuracy of 74.5% and 76.4%, and an AUC of 0.79 and 0.76, respectively. Standard clinical features could predict the therapy response with an accuracy of 69.1% and an AUC of 0.6. Long-term survival analyses indicated that the patients predicted by the developed model as responders had a significantly better survival compared to the non-responders. Similar findings were observed for the two response cohorts identified at post-treatment based on standard clinical and pathological criteria. The results obtained in this study demonstrated the potential of QUS multi-parametric imaging integrated with unsupervised learning methods in identifying distinct intra-tumor regions in breast cancer to characterize its responsiveness to chemotherapy prior to the start of treatment.

Classification of true progression after radiotherapy of brain metastasis on MRI using artificial intelligence: a systematic review and meta-analysis

Background

Classification of true progression from nonprogression (eg, radiation-necrosis) after stereotactic radiotherapy/radiosurgery of brain metastasis is known to be a challenging diagnostic task on conventional magnetic resonance imaging (MRI). The scope and status of research using artificial intelligence (AI) on classifying true progression are yet unknown.

Methods

We performed a systematic literature search of MEDLINE and EMBASE databases to identify studies that investigated the performance of AI-assisted MRI in classifying true progression after stereotactic radiotherapy/radiosurgery of brain metastasis, published before November 11, 2020. Pooled sensitivity and specificity were calculated using bivariate random-effects modeling. Meta-regression was performed for the identification of factors contributing to the heterogeneity among the studies. We assessed the quality of the studies using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) criteria and a modified version of the radiomics quality score (RQS).

Results

Seven studies were included, with a total of 485 patients and 907 tumors. The pooled sensitivity and specificity were 77% (95% CI, 70–83%) and 74% (64–82%), respectively. All 7 studies used radiomics, and none used deep learning. Several covariates including the proportion of lung cancer as the primary site, MR field strength, and radiomics segmentation slice showed a statistically significant association with the heterogeneity. Study quality was overall favorable in terms of the QUADAS-2 criteria, but not in terms of the RQS.

Conclusion

The diagnostic performance of AI-assisted MRI seems yet inadequate to be used reliably in clinical practice. Future studies with improved methodologies and a larger training set are needed.

Brain Tumor Biobank Development for Precision Medicine: Role of the Neurosurgeon

Neuro-oncology biobanks are critical for the implementation of a precision medicine program. In this perspective, we review our first year experience of a brain tumor biobank with integrated next generation sequencing. From our experience, we describe the critical role of the neurosurgeon in diagnosis, research, and precision medicine efforts. In the first year of implementation of the biobank, 117 patients (Female: 62; Male: 55) had 125 brain tumor surgeries. 75% of patients had tumors biobanked, and 16% were of minority race/ethnicity. Tumors biobanked were as follows: diffuse gliomas (45%), brain metastases (29%), meningioma (21%), and other (5%). Among biobanked patients, 100% also had next generation sequencing. Eleven patients qualified for targeted therapy based on identification of actionable gene mutations. One patient with a hereditary cancer predisposition syndrome was also identified. An iterative quality improvement process was implemented to streamline the workflow between the operating room, pathology, and the research laboratory. Dedicated tumor bank personnel in the department of neurosurgery greatly improved standard operating procedure. Intraoperative selection and processing of tumor tissue by the neurosurgeon was integral to increasing success with cell culture assays. Currently, our institutional protocol integrates standard histopathological diagnosis, next generation sequencing, and functional assays on surgical specimens to develop precision medicine protocols for our patients. This perspective reviews the critical role of neurosurgeons in brain tumor biobank implementation and success as well as future directions for enhancing precision medicine efforts.

Computer Tomography Radiomics-Based Nomogram in the Survival Prediction for Brain Metastases From Non-Small Cell Lung Cancer Underwent Whole Brain Radiotherapy

Prognostic parameters and models were believed to be helpful in improving the treatment outcome for patients with brain metastasis (BM). The purpose of this study was to investigate the feasibility of computer tomography (CT) radiomics based nomogram to predict the survival of patients with BM from non-small cell lung cancer (NSCLC) treated with whole brain radiotherapy (WBRT). A total of 195 patients with BM from NSCLC who underwent WBRT from January 2012 to December 2016 were retrospectively reviewed. Radiomics features were extracted and selected from pretherapeutic CT images with least absolute shrinkage and selection operator (LASSO) regression. A nomogram was developed and evaluated by integrating radiomics features and clinical factors to predict the survival of individual patient. Five radiomics features were screened out from 105 radiomics features according to the LASSO Cox regression. According to the optimal cutoff value of radiomics score (Rad-score), patients were stratified into low-risk (Rad-score <= −0.14) and high-risk (Rad-score > −0.14) groups. Multivariable analysis indicated that sex, karnofsky performance score (KPS) and Rad-score were independent predictors for overall survival (OS). The concordance index (C-index) of the nomogram in the training cohort and validation cohort was 0.726 and 0.660, respectively. An area under curve (AUC) of 0.786 and 0.788 was achieved for the short-term and long-term survival prediction, respectively. In conclusion, the nomogram based on radiomics features from CT images and clinical factors was feasible to predict the OS of BM patients from NSCLC who underwent WBRT.

A Brain Tumor Segmentation Framework Based on Outlier Detection Using One-Class Support Vector Machine

Accurate segmentation of brain tumors is a challenging task and also a crucial step in diagnosis and treatment planning for cancer patients. Magnetic resonance imaging (MRI) is the standard imaging modality for detection, characterization, treatment planning and outcome evaluation of brain tumors. MRI scans are usually acquired at multiple sessions before and after the treatment. An automatic segmentation framework is highly desirable to segment brain tumors in MR images as it streamlines the image-guided radiation therapy workflow considerably. Automatic segmentation of brain tumors also facilitates an incremental development of data-driven systems for therapy outcome prediction based on radiomics analysis. In this study, an outlier-detection-based segmentation framework is proposed to delineate brain tumors in magnetic resonance (MR) images automatically. The proposed method considers the tumor and edema pixels in an MR image as outliers compared to the pixels associated with the healthy tissue. The framework generates two outlier masks using independent one-class support vector machines that operate on post-contrast T1-weighted (T1w) and T2-weighted-fluid-attenuation-inversion-recovery (T2-FLAIR) images. The outlier masks are subsequently refined and fused using a number of morphological and logical operators to estimate a tumor mask for each image slice. The framework was constructed and evaluated using the MRI data acquired from 35 and 5 patients with brain metastasis, respectively. The obtained results demonstrated an average Dice similarity coefficient and Hausdorff distance of 0.84 ± 0.06 and 1.85 ± 0.48 mm, respectively, between the manual (ground truth) and automatic tumor contours, on the independent test set.

Predicting Local Failure after Stereotactic Radiation Therapy in Brain Metastasis using Quantitative CT and Machine Learning

Despite recent advances in cancer treatment, the prognosis of patients diagnosed with brain metastasis is still poor. The median survival is limited to months even for patients undergoing treatment. Radiation therapy is a main component of treatment for brain metastasis. However, radiotherapy cannot control local progression in up to 20% of the metastatic brain tumours. An early prediction of radiotherapy outcome for individual patients could facilitate therapy adjustments to improve its efficacy. This study investigated the potential of quantitative CT biomarkers in conjunction with machine learning methods to predict local failure after radiotherapy in brain metastasis. Volumetric CT images were acquired for radiation treatment planning from 120 patients undergoing stereotactic radiotherapy. Quantitative features characterizing the morphology and texture were extracted from different regions of each lesion. A feature reduction/selection framework was adapted to define a quantitative CT biomarker of radiotherapy outcome. Different machine learning methods were applied and evaluated to predict the local failure outcome at pre-treatment. The optimum biomarker consisting of two features in conjunction with an AdaBoost with decision tree could predict the local failure outcome with 71% accuracy on an independent test set (20 patients, 31 lesions). This study is a step forward towards prediction of radiotherapy outcome in brain metastasis using quantitative imaging and machine learning.

A Cascaded Deep-Learning Framework for Segmentation of Metastatic Brain Tumors Before and After Stereotactic Radiation Therapy

Radiation therapy is a major treatment option for brain metastasis. For radiation treatment planning and outcome evaluation, magnetic resonance (MR) images are acquired before and at multiple sessions after the treatment. Accurate segmentation of brain tumors on MR images is crucial for treatment planning, response evaluation, and developing data-driven models for outcome prediction. Due to the high volume of imaging data acquired from each patient at multiple follow-up sessions, manual tumor segmentation is resource- and time-consuming in clinic, hence developing an automatic segmentation framework is highly desirable. In this work, we proposed a cascaded 2D-3D Unet framework to segment brain tumors automatically on contrast-enhanced T1- weighted images acquired before and at multiple scan sessions after radiotherapy. 2D Unet is a well-known structure for medical image segmentation. 3D Unet is an extension of 2D Unet with a volumetric input image to provide richer spatial information. The limitation of 3D Unet is that it is memory consuming and cannot process large volumetric images. To address this limitation, a large volumetric input of 3D Unet is often patched to smaller volumes which leads to loss of context. To overcome this problem, we proposed using two cascaded 2D Unets to crop the input volume around the tumor area and reduce the input size of the 3D Unet, obviating the need to patch the input images. The framework was trained using images acquired from 96 patients before radiation therapy and tested using images acquired from 10 patients before and at four follow-up scans after radiotherapy. The segmentation results for the images of independent test set demonstrated that the cascaded framework outperformed the 2D and 3D Unets alone, with an average Dice score of 0.9 versus 0.86 and 0.88 for the baseline, and 0.87 versus 0.83 and 0.84 for the first followup. Similar results were obtained for the other follow-up scans.

Quantitative magnetic resonance imaging on hybrid magnetic resonance linear accelerators: Perspective on technical and clinical validation

Many preclinical and clinical observations support that functional magnetic resonance imaging (MRI), such as diffusion weighted (DW) and dynamic contrast enhanced (DCE) MRI, might have a predictive value for radiotherapy. The aim of this review was to assess the current status of quantitative MRI on hybrid MR-Linacs. In a literature research, four publications were identified, investigating technical feasibility, accuracy, repeatability and reproducibility of DW and DCE-MRI in phantoms and first patients. Accuracy and short term repeatability was < 5% for DW-MRI in current MR-Linac systems. Consequently, quantitative imaging providing accurate and reproducible functional information seems possible in MR-Linacs.

Glioma consensus contouring recommendations from a MR-Linac International Consortium Research Group and evaluation of a CT-MRI and MRI-only workflow

Introduction

This study proposes contouring recommendations for radiation treatment planning target volumes and organs-at-risk (OARs) for both low grade and high grade gliomas.

Methods

Ten cases consisting of 5 glioblastomas and 5 grade II or III gliomas, including their respective gross tumor volume (GTV), clinical target volume (CTV), and OARs were each contoured by 6 experienced neuro-radiation oncologists from 5 international institutions. Each case was first contoured using only MRI sequences (MRI-only), and then re-contoured with the addition of a fused planning CT (CT-MRI). The level of agreement among all contours was assessed using simultaneous truth and performance level estimation (STAPLE) with the kappa statistic and Dice similarity coefficient.

Results

A high level of agreement was observed between the GTV and CTV contours in the MRI-only workflow with a mean kappa of 0.88 and 0.89, respectively, with no statistically significant differences compared to the CT-MRI workflow (p = 0.88 and p = 0.82 for GTV and CTV, respectively). Agreement in cochlea contours improved from a mean kappa of 0.39 to 0.41, to 0.69 to 0.71 with the addition of CT information (p < 0.0001 for both cochleae). Substantial to near perfect level of agreement was observed in all other contoured OARs with a mean kappa range of 0.60 to 0.90 in both MRI-only and CT-MRI workflows.

Conclusions

Consensus contouring recommendations for low grade and high grade gliomas were established using the results from the consensus STAPLE contours, which will serve as a basis for further study and clinical trials by the MR-Linac Consortium.

Electronic supplementary material

The online version of this article (10.1007/s11060-020-03605-6) contains supplementary material, which is available to authorized users.

Reinventing radiation therapy with machine learning and imaging bio-markers (radiomics): State-of-the-art, challenges and perspectives

Radiation therapy is a pivotal cancer treatment that has significantly progressed over the last decade due to numerous technological breakthroughs. Imaging is now playing a critical role on deployment of the clinical workflow, both for treatment planning and treatment delivery. Machine-learning analysis of predefined features extracted from medical images, i.e. radiomics, has emerged as a promising clinical tool for a wide range of clinical problems addressing drug development, clinical diagnosis, treatment selection and implementation as well as prognosis. Radiomics denotes a paradigm shift redefining medical images as a quantitative asset for data-driven precision medicine. The adoption of machine-learning in a clinical setting and in particular of radiomics features requires the selection of robust, representative and clinically interpretable biomarkers that are properly evaluated on a representative clinical data set. To be clinically relevant, radiomics must not only improve patients' management with great accuracy but also be reproducible and generalizable. Hence, this review explores the existing literature and exposes its potential technical caveats, such as the lack of quality control, standardization, sufficient sample size, type of data collection, and external validation. Based upon the analysis of 165 original research studies based on PET, CT-scan, and MRI, this review provides an overview of new concepts, and hypotheses generating findings that should be validated. In particular, it describes evolving research trends to enhance several clinical tasks such as prognostication, treatment planning, response assessment, prediction of recurrence/relapse, and prediction of toxicity. Perspectives regarding the implementation of an AI-based radiotherapy workflow are presented.

Radiomic analysis of magnetic resonance imaging predicts brain metastases velocity and clinical outcome after upfront radiosurgery

Background

Brain metastasis velocity (BMV) predicts outcomes after initial distant brain failure (DBF) following upfront stereotactic radiosurgery (SRS). We developed an integrated model of clinical predictors and pre-SRS MRI-derived radiomic scores (R-scores) to identify high-BMV (BMV-H) patients upon initial identification of brain metastases (BMs).

Methods

In total, 256 patients with BMs treated with upfront SRS alone were retrospectively included. R-scores were built from 1246 radiomic features in 2 target volumes by using the Extreme Gradient Boosting algorithm to predict BMV-H groups, as defined by BMV at least 4 or leptomeningeal disease at first DBF. Two R-scores and 3 clinical predictors were integrated into a predictive clinico-radiomic (CR) model.

Results

The related R-scores showed significant differences between BMV-H and low BMV (BMV-L), as defined by BMV less than 4 or no DBF (P < .001). Regression analysis identified BMs number, perilesional edema, and extracranial progression as significant predictors. The CR model using these 5 predictors achieved a bootstrapping corrected C-index of 0.842 and 0.832 in the discovery and test sets, respectively. Overall survival (OS) after first DBF was significantly different between the CR-predicted BMV-L and BMV-H groups (median OS: 26.7 vs 13.0 months, P = .016). Among patients with a diagnosis-specific graded prognostic assessment of 1.5–2 or 2.5–4, the median OS after initial SRS was 33.8 and 67.8 months for CR-predicted BMV-L, compared to 13.5 and 31.0 months for CR-predicted BMV-H (P < .001 and <.001), respectively.

Conclusion

Our CR model provides a novel approach showing good performance to predict BMV and clinical outcomes.