A predictive model for distinguishing radiation necrosis from tumour progression after gamma knife radiosurgery based on radiomic features from MR images

Leveraging radiomics and machine learning to differentiate radiation necrosis from recurrence in patients with brain metastases

OBJECTIVE

Radiation necrosis (RN) can be difficult to radiographically discern from tumor progression after stereotactic radiosurgery (SRS). The objective of this study was to investigate the utility of radiomics and machine learning (ML) to differentiate RN from recurrence in patients with brain metastases treated with SRS.

METHODS

Patients with brain metastases treated with SRS who developed either RN or tumor reccurence were retrospectively identified. Image preprocessing and radiomic feature extraction were performed using ANTsPy and PyRadiomics, yielding 105 features from MRI T1-weighted post-contrast (T1c), T2, and fluid-attenuated inversion recovery (FLAIR) images. Univariate analysis assessed significance of individual features. Multivariable analysis employed various classifiers on features identified as most discriminative through feature selection. ML models were evaluated through cross-validation, selecting the best model based on area under the receiver operating characteristic (ROC) curve (AUC). Specificity, sensitivity, and F1 score were computed.

RESULTS

Sixty-six lesions from 55 patients were identified. On univariate analysis, 27 features from the T1c sequence were statistically significant, while no features were significant from the T2 or FLAIR sequences. For clinical variables, only immunotherapy use after SRS was significant. Multivariable analysis of features from the T1c sequence yielded an AUC of 76.2% (standard deviation [SD] ± 12.7%), with specificity and sensitivity of 75.5% (± 13.4%) and 62.3% (± 19.6%) in differentiating radionecrosis from recurrence.

CONCLUSIONS

Radiomics with ML may assist the diagnostic ability of distinguishing RN from tumor recurrence after SRS. Further work is needed to validate this in a larger multi-institutional cohort and prospectively evaluate it's utility in patient care.

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.

T1 Pre- and Post-contrast Delta Histogram Parameters in Predicting the Grade of Meningioma and Their Relationship to Ki-67 Proliferation Index

RATIONALE AND OBJECTIVES

To explore the feasibility of delta histogram parameters (including absolute delta histogram parameters (AdHP) and relative delta histogram parameters (RdHP)) in predicting the grade of meningioma and to further investigate whether delta histogram parameters correlate with the Ki-67 proliferation index.

METHODS

92 patients with meningioma who underwent MRI examination (including T1-weighted (T1) and contrast-enhanced T1-weighted images (T1C)) were enrolled in this retrospective study. A total of 46 low-grade cases formed the low-grade group (grade 1, LGM), and a total of 46 high-grade cases formed the high-grade group (38 grade 2, 8 grade 3, HGM). Histogram parameters (HP) of T1 and T1C were extracted. Subsequently, morphological MRI features, AdHP (AdHP=T1CHP-T1HP), and RdHP (RdHP=(T1CHP-T1HP)/T1HP) were recorded and compared, respectively. Binary logistic regression analysis was used to obtain combined performance of the significant parameters. Diagnostic performance was identified by ROC. Spearman's correlation coefficients were taken to assess the relationship between delta histogram parameters and the Ki-67 proliferation index.

RESULTS

In morphological MRI features, HGM is more prone to lobulation and necrosis/cystic changes (all p < 0.05). In delta histogram parameters, HGM exhibits higher mean, Perc.01, Perc.25, Perc.50, Perc.75, Perc.99, SD, and variance of AdHP, maximum, mean, Perc.25, Perc.50, Perc.75, and Perc.99 of RdHP, compared to LGM (all p < 0.00357). The optimal predictive performance was obtained by combining morphological MRI features and delta histogram parameters with an AUC of 0.945. Significant correlations were observed between significant delta histogram parameters and the Ki-67 proliferation index (all p < 0.05).

CONCLUSION

Delta histogram parameter is a promising potential biomarker, which may be helpful in noninvasive predicting the grade and proliferative activity of meningioma.

Dose-Incorporated Deep Ensemble Learning for Improving Brain Metastasis Stereotactic Radiosurgery Outcome Prediction

PURPOSE

To develop a novel deep ensemble learning model for accurate prediction of brain metastasis (BM) local control outcomes after stereotactic radiosurgery (SRS).

METHODS AND MATERIALS

A total of 114 brain metastases (BMs) from 82 patients were evaluated, including 26 BMs that developed biopsy-confirmed local failure post-SRS. The SRS spatial dose distribution (Dmap) of each BM was registered to the planning contrast-enhanced T1 (T1-CE) magnetic resonance imaging (MRI). Axial slices of the Dmap, T1-CE, and planning target volume (PTV) segmentation (PTVseg) intersecting the BM center were extracted within a fixed field of view determined by the 60% isodose volume in Dmap. A spherical projection was implemented to transform planar image content onto a spherical surface using multiple projection centers, and the resultant T1-CE/Dmap/PTVseg projections were stacked as a 3-channel variable. Four Visual Geometry Group (VGG-19) deep encoders were used in an ensemble design, with each submodel using a different spherical projection formula as input for BM outcome prediction. In each submodel, clinical features after positional encoding were fused with VGG-19 deep features to generate logit results. The ensemble's outcome was synthesized from the 4 submodel results via logistic regression. In total, 10 model versions with random validation sample assignments were trained to study model robustness. Performance was compared with (1) a single VGG-19 encoder, (2) an ensemble with a T1-CE MRI as the sole image input after projections, and (3) an ensemble with the same image input design without clinical feature inclusion.

RESULTS

The ensemble model achieved an excellent area under the receiver operating characteristic curve (AUCROC: 0.89 ± 0.02) with high sensitivity (0.82 ± 0.05), specificity (0.84 ± 0.11), and accuracy (0.84 ± 0.08) results. This outperformed the MRI-only VGG-19 encoder (sensitivity: 0.35 ± 0.01, AUCROC: 0.64 ± 0.08), the MRI-only deep ensemble (sensitivity: 0.60 ± 0.09, AUCROC: 0.68 ± 0.06), and the 3-channel ensemble without clinical feature fusion (sensitivity: 0.78 ± 0.08, AUCROC: 0.84 ± 0.03).

CONCLUSIONS

Facilitated by the spherical image projection method, a deep ensemble model incorporating Dmap and clinical variables demonstrated excellent performance in predicting BM post-SRS local failure. Our novel approach could improve other radiation therapy outcome models and warrants further evaluation.

Pelvic bone tumor segmentation fusion algorithm based on fully convolutional neural network and conditional random field

Background and objective

Pelvic bone tumors represent a harmful orthopedic condition, encompassing both benign and malignant forms. Addressing the issue of limited accuracy in current machine learning algorithms for bone tumor image segmentation, we have developed an enhanced bone tumor image segmentation algorithm. This algorithm is built upon an improved full convolutional neural network, incorporating both the fully convolutional neural network (FCNN-4s) and a conditional random field (CRF) to achieve more precise segmentation.

Methodology

The enhanced fully convolutional neural network (FCNN-4s) was employed to conduct initial segmentation on preprocessed images. Following each convolutional layer, batch normalization layers were introduced to expedite network training convergence and enhance the accuracy of the trained model. Subsequently, a fully connected conditional random field (CRF) was integrated to fine-tune the segmentation results, refining the boundaries of pelvic bone tumors and achieving high-quality segmentation.

Results

The experimental outcomes demonstrate a significant enhancement in segmentation accuracy and stability when compared to the conventional convolutional neural network bone tumor image segmentation algorithm. The algorithm achieves an average Dice coefficient of 93.31 %, indicating superior performance in real-time operations.

Conclusion

In contrast to the conventional convolutional neural network segmentation algorithm, the algorithm presented in this paper boasts a more intricate structure, proficiently addressing issues of over-segmentation and under-segmentation in pelvic bone tumor segmentation. This segmentation model exhibits superior real-time performance, robust stability, and is capable of achieving heightened segmentation accuracy.

The dilemma of radiation necrosis from diagnosis to treatment in the management of brain metastases

Radiation therapy with stereotactic radiosurgery (SRS) or whole brain radiation therapy is a mainstay of treatment for patients with brain metastases. The use of SRS in the management of brain metastases is becoming increasingly common and provides excellent local control. Cerebral radiation necrosis (RN) is a late complication of radiation treatment that can be seen months to years following treatment and is often indistinguishable from tumor progression on conventional imaging. In this review article, we explore risk factors associated with the development of radiation necrosis, advanced imaging modalities used to aid in diagnosis, and potential treatment strategies to manage side effects.

High Radiation Dose to the Fornix Causes Symptomatic Radiation Necrosis in Patients with Anaplastic Oligodendroglioma

PURPOSE

Surgery, radiotherapy (RT), and chemotherapy have prolonged the survival of patients with anaplastic oligodendroglioma. However, whether RT induces long-term toxicity remains unknown. We analyzed the relationship between the RT dose to the fornix and symptomatic radiation necrosis (SRN).

MATERIALS AND METHODS

A total of 67 patients treated between 2009 and 2019 were analyzed. SRN was defined according to the following three criteria: 1) radiographic findings, 2) symptoms attributable to the lesion, and 3) treatment resulting in symptom improvement. Various contours, including the fornix, were delineated. Univariate and multivariate analyses of the relationship between RT dose and SRN, as well as receiver operating characteristic curve analysis for cut-off values, were performed.

RESULTS

The most common location was the frontal lobe (n=40, 60%). Gross total resection was performed in 38 patients (57%), and 42 patients (63%) received procarbazine, lomustine, and vincristine chemotherapy. With a median follow-up of 42 months, the median overall and progression-free survival was 74 months. Sixteen patients (24%) developed SRN. In multivariate analysis, age and maximum dose to the fornix were associated with the development of SRN. The cut-off values for the maximum dose to the fornix and age were 59 Gy (equivalent dose delivered in 2 Gy fractions) and 46 years, respectively. The rate of SRN was higher in patients whose maximum dose to the fornix was >59 Gy (13% vs. 43%, p=0.005).

CONCLUSION

The maximum dose to the fornix was a significant factor for SRN development. While fornix sparing may help maintain neurocognitive function, additional studies are needed.

State of the art: radiomics and radiomics-related artificial intelligence on the road to clinical translation

Radiomics and artificial intelligence carry the promise of increased precision in oncologic imaging assessments due to the ability of harnessing thousands of occult digital imaging features embedded in conventional medical imaging data. While powerful, these technologies suffer from a number of sources of variability that currently impede clinical translation. In order to overcome this impediment, there is a need to control for these sources of variability through harmonization of imaging data acquisition across institutions, construction of standardized imaging protocols that maximize the acquisition of these features, harmonization of post-processing techniques, and big data resources to properly power studies for hypothesis testing. For this to be accomplished, it will be critical to have multidisciplinary and multi-institutional collaboration.

Radiation necrosis after radiation therapy treatment of brain metastases: A computational approach

Metastasis is the process through which cancer cells break away from a primary tumor, travel through the blood or lymph system, and form new tumors in distant tissues. One of the preferred sites for metastatic dissemination is the brain, affecting more than 20% of all cancer patients. This figure is increasing steadily due to improvements in treatments of primary tumors. Stereotactic radiosurgery (SRS) is one of the main treatment options for patients with a small or moderate number of brain metastases (BMs). A frequent adverse event of SRS is radiation necrosis (RN), an inflammatory condition caused by late normal tissue cell death. A major diagnostic problem is that RNs are difficult to distinguish from BM recurrences, due to their similarities on standard magnetic resonance images (MRIs). However, this distinction is key to choosing the best therapeutic approach since RNs resolve often without further interventions, while relapsing BMs may require open brain surgery. Recent research has shown that RNs have a faster growth dynamics than recurrent BMs, providing a way to differentiate the two entities, but no mechanistic explanation has been provided for those observations. In this study, computational frameworks were developed based on mathematical models of increasing complexity, providing mechanistic explanations for the differential growth dynamics of BMs relapse versus RN events and explaining the observed clinical phenomenology. Simulated tumor relapses were found to have growth exponents substantially smaller than the group in which there was inflammation due to damage induced by SRS to normal brain tissue adjacent to the BMs, thus leading to RN. ROC curves with the synthetic data had an optimal threshold that maximized the sensitivity and specificity values for a growth exponent β* = 1.05, very close to that observed in patient datasets.

Placental MRI segmentation based on multi-receptive field and mixed attention separation mechanism

OBJECTIVE

To reduce the occurrence of massive bleeding during placental abruption in patients with placenta accrete, we established a medical imaging based on multi-receptive field and mixed attention separation mechanism (MRF-MAS) model to improve the accuracy of MRI placenta segmentation and provide a basis for subsequent placenta accreta.

METHODS

We propose a placenta MRI segmentation technology using the MRF-MAS framework to develop a medical image diagnostic technique. The model first uses the multi-receptive field feature structure to obtain multi-level information, and improves the expression of features at differing scales. Note that the hybrid attention mechanism combines channel attention and spatial attention, separates the input feature sets and computes the attention separately, and finally reorganizes the feature maps. To show that the model can improve the accuracy of segmenting the placenta, we adopt mean Intersection over Union (IoU), Dice similarity coefficient (Dice) and area under the receiver operating characteristic curve (AUC) with U-Net, Mask RCNN, Deeplab v3 for comparison.

RESULTS

The four models achieved different outcomes based on our placenta dataset, with our model IoU and Dice up to 0.8169 and 0.8992, which are 5.51% and 3.03% higher than the average of the three comparison models.

CONCLUSION

The model proposed by us is helpful to assist the imaging diagnosis and at the same time provides a quantitative reference for the precise treatment of placenta accreta, assists the Equationtion of the clinical operation plan of the physician, and promotes the precision medicine of placenta accreta.

Development and validation of a radiomics-based prediction pipeline for the response to stereotactic radiosurgery therapy in brain metastases

OBJECTIVES

The first treatment strategy for brain metastases (BM) plays a pivotal role in the prognosis of patients. Among all strategies, stereotactic radiosurgery (SRS) is considered a promising therapy method. Therefore, we developed and validated a radiomics-based prediction pipeline to prospectively identify BM patients who are insensitive to SRS therapy, especially those who are at potential risk of progressive disease.

METHODS

A total of 337 BM patients (277, 30, and 30 in the training set, internal validation set, and external validation set, respectively) were enrolled in the study. 19,377 radiomics features (3 masks × 3 MRI sequences × 2153 features) extracted from 9 ROIs were filtered through LASSO and Max-Relevance and Min-Redundancy (mRMR) algorithms. The selected radiomics features were combined with 4 clinical features to construct a two-stage cascaded model for the prediction of BM patients' response to SRS therapy using SVM and an ensemble learning classifier. The performance of the model was evaluated by its accuracy, specificity, sensitivity, and AUC curve.

RESULTS

Radiomics features were integrated with the clinical features of patients in our optimal model, which showed excellent discriminative performance in the training set (AUC: 0.95, 95% CI: 0.88-0.98). The model was also verified in the internal validation set and external validation set (AUC 0.93, 95% CI: 0.76-0.95 and AUC 0.90, 95% CI: 0.73-0.93, respectively).

CONCLUSIONS

The proposed prediction pipeline could non-invasively predict the response to SRS therapy in patients with brain metastases thus assisting doctors to precisely designate individualized first treatment decisions.

CLINICAL RELEVANCE STATEMENT

The proposed prediction pipeline combines the radiomics features of multi-modal MRI with clinical features to construct machine learning models that noninvasively predict the response of patients with brain metastases to stereotactic radiosurgery therapy, assisting neuro-oncologists to develop personalized first treatment plans.

KEY POINTS

• The proposed prediction pipeline can non-invasively predict the response to SRS therapy. • The combination of multi-modality and multi-mask contributes significantly to the prediction. • The edema index also shows a certain predictive value.

A Multidimensional Connectomics- and Radiomics-Based Advanced Machine-Learning Framework to Distinguish Radiation Necrosis from True Progression in Brain Metastases

We introduce tumor connectomics, a novel MRI-based complex graph theory framework that describes the intricate network of relationships within the tumor and surrounding tissue, and combine this with multiparametric radiomics (mpRad) in a machine-learning approach to distinguish radiation necrosis (RN) from true progression (TP). Pathologically confirmed cases of RN vs. TP in brain metastases treated with SRS were included from a single institution. The region of interest was manually segmented as the single largest diameter of the T1 post-contrast (T1C) lesion plus the corresponding area of T2 FLAIR hyperintensity. There were 40 mpRad features and 6 connectomics features extracted, as well as 5 clinical and treatment factors. We developed an Integrated Radiomics Informatics System (IRIS) based on an Isomap support vector machine (IsoSVM) model to distinguish TP from RN using leave-one-out cross-validation. Class imbalance was resolved with differential misclassification weighting during model training using the IRIS. In total, 135 lesions in 110 patients were analyzed, including 43 cases (31.9%) of pathologically proven RN and 92 cases (68.1%) of TP. The top-performing connectomics features were three centrality measures of degree, betweenness, and eigenvector centralities. Combining these with the 10 top-performing mpRad features, an optimized IsoSVM model was able to produce a sensitivity of 0.87, specificity of 0.84, AUC-ROC of 0.89 (95% CI: 0.82-0.94), and AUC-PR of 0.94 (95% CI: 0.87-0.97).

Neurotoxicity from Old and New Radiation Treatments for Brain Tumors

Research regarding the mechanisms of brain damage following radiation treatments for brain tumors has increased over the years, thus providing a deeper insight into the pathobiological mechanisms and suggesting new approaches to minimize this damage. This review has discussed the different factors that are known to influence the risk of damage to the brain (mainly cognitive disturbances) from radiation. These include patient and tumor characteristics, the use of whole-brain radiotherapy versus particle therapy (protons, carbon ions), and stereotactic radiotherapy in various modalities. Additionally, biological mechanisms behind neuroprotection have been elucidated.

Assessment of brain cancer atlas maps with multimodal imaging features

BACKGROUND

Glioblastoma Multiforme (GBM) is a fast-growing and highly aggressive brain tumor that invades the nearby brain tissue and presents secondary nodular lesions across the whole brain but generally does not spread to distant organs. Without treatment, GBM can result in death in about 6 months. The challenges are known to depend on multiple factors: brain localization, resistance to conventional therapy, disrupted tumor blood supply inhibiting effective drug delivery, complications from peritumoral edema, intracranial hypertension, seizures, and neurotoxicity.

MAIN TEXT

Imaging techniques are routinely used to obtain accurate detections of lesions that localize brain tumors. Especially magnetic resonance imaging (MRI) delivers multimodal images both before and after the administration of contrast, which results in displaying enhancement and describing physiological features as hemodynamic processes. This review considers one possible extension of the use of radiomics in GBM studies, one that recalibrates the analysis of targeted segmentations to the whole organ scale. After identifying critical areas of research, the focus is on illustrating the potential utility of an integrated approach with multimodal imaging, radiomic data processing and brain atlases as the main components. The templates associated with the outcome of straightforward analyses represent promising inference tools able to spatio-temporally inform on the GBM evolution while being generalizable also to other cancers.

CONCLUSIONS

The focus on novel inference strategies applicable to complex cancer systems and based on building radiomic models from multimodal imaging data can be well supported by machine learning and other computational tools potentially able to translate suitably processed information into more accurate patient stratifications and evaluations of treatment efficacy.

Deep learning-based magnetic resonance imaging of the spine in the diagnosis and physiological evaluation of spinal metastases

Background and objective

Spinal metastasis accounts for 70% of the bone metastases of tumors, so how to diagnose and predict spinal metastasis in time through effective methods is very important for the physiological evaluation of the therapy of patients.

Methods

MRI scans of 941 patients with spinal metastases from the affiliated hospital of Guilin Medical University were collected, analyzed, and preprocessed, and the data were submitted to a deep learning model designed with our convolutional neural network. We also used the Softmax classifier to classify the results and compared them with the actual data to judge the accuracy of our model.

Results

Our research showed that the practical model method could effectively predict spinal metastases. The accuracy was up to 96.45%, which could be used to diagnose the physiological evaluation of spinal metastases.

Conclusion

The model obtained in the final experiment can capture the focal signs of patients with spinal metastases more accurately and can predict the disease in time, which has a good application prospect.

Delta-radiomics based on CT predicts pathologic complete response in ESCC treated with neoadjuvant immunochemotherapy and surgery

Background and purpose

Unnecessary surgery can be avoided, and more appropriate treatment plans can be developed for patients if the efficacy of neoadjuvant immunochemotherapy for esophageal cancer (EC) can be predicted before surgery. The purpose of this study was to evaluate the ability of machine learning models based on delta features of immunochemotherapy CT images to predict the efficacy of neoadjuvant immunochemotherapy in patients with esophageal squamous cell carcinoma (ESCC) compared with machine learning models based solely on postimmunochemotherapy CT images.

Materials and methods

A total of 95 patients were enrolled in our study and randomly divided into a training group (n = 66) and test group (n = 29). We extracted preimmunochemotherapy radiomics features from preimmunochemotherapy enhanced CT images in the preimmunochemotherapy group (pregroup) and postimmunochemotherapy radiomics features from postimmunochemotherapy enhanced CT images in the postimmunochemotherapy group (postgroup). We then subtracted the preimmunochemotherapy features from the postimmunochemotherapy features and obtained a series of new radiomics features that were included in the delta group. The reduction and screening of radiomics features were carried out by using the Mann-Whitney U test and LASSO regression. Five pairwise machine learning models were established, the performance of which was evaluated by receiver operating characteristic (ROC) curve and decision curve analyses.

Results

The radiomics signature of the postgroup was composed of 6 radiomics features; that of the delta-group was composed of 8 radiomics features. The area under the ROC curve (AUC) of the machine learning model with the best efficacy was 0.824 (0.706-0.917) in the postgroup and 0.848 (0.765-0.917) in the delta group. The decision curve showed that our machine learning models had good predictive performance. The delta group performed better than the postgroup for each corresponding machine learning model.

Conclusion

We established machine learning models that have good predictive efficacy and can provide certain reference values for clinical treatment decision-making. Our machine learning models based on delta imaging features performed better than those based on single time-stage postimmunochemotherapy imaging features.

Development of Predictive Models for the Response of Vestibular Schwannoma Treated with Cyberknife®: A Feasibility Study Based on Radiomics and Machine Learning

PURPOSE

to predict vestibular schwannoma (VS) response to radiosurgery by applying machine learning (ML) algorithms on radiomic features extracted from pre-treatment magnetic resonance (MR) images.

METHODS

patients with VS treated with radiosurgery in two Centers from 2004 to 2016 were retrospectively evaluated. Brain T1-weighted contrast-enhanced MR images were acquired before and at 24 and 36 months after treatment. Clinical and treatment data were collected contextually. Treatment responses were assessed considering the VS volume variation based on pre- and post-radiosurgery MR images at both time points. Tumors were semi-automatically segmented and radiomic features were extracted. Four ML algorithms (Random Forest, Support Vector Machine, Neural Network, and extreme Gradient Boosting) were trained and tested for treatment response (i.e., increased or non-increased tumor volume) using nested cross-validation. For training, feature selection was performed using the Least Absolute Shrinkage and Selection Operator, and the selected features were used as input to separately build the four ML classification algorithms. To overcome class imbalance during training, Synthetic Minority Oversampling Technique was used. Finally, trained models were tested on the corresponding held out set of patients to evaluate balanced accuracy, sensitivity, and specificity.

RESULTS

108 patients treated with Cyberknife^® were retrieved; an increased tumor volume was observed at 24 months in 12 patients, and at 36 months in another group of 12 patients. The Neural Network was the best predictive algorithm for response at 24 (balanced accuracy 73% ± 18%, specificity 85% ± 12%, sensitivity 60% ± 42%) and 36 months (balanced accuracy 65% ± 12%, specificity 83% ± 9%, sensitivity 47% ± 27%).

CONCLUSIONS

radiomics may predict VS response to radiosurgery avoiding long-term follow-up as well as unnecessary treatment.

Novel Mechanisms and Future Opportunities for the Management of Radiation Necrosis in Patients Treated for Brain Metastases in the Era of Immunotherapy

Radiation necrosis, also known as treatment-induced necrosis, has emerged as an important adverse effect following stereotactic radiotherapy (SRS) for brain metastases. The improved survival of patients with brain metastases and increased use of combined systemic therapy and SRS have contributed to a growing incidence of necrosis. The cyclic GMP-AMP (cGAMP) synthase (cGAS) and stimulator of interferon genes (STING) pathway (cGAS-STING) represents a key biological mechanism linking radiation-induced DNA damage to pro-inflammatory effects and innate immunity. By recognizing cytosolic double-stranded DNA, cGAS induces a signaling cascade that results in the upregulation of type 1 interferons and dendritic cell activation. This pathway could play a key role in the pathogenesis of necrosis and provides attractive targets for therapeutic development. Immunotherapy and other novel systemic agents may potentiate activation of cGAS-STING signaling following radiotherapy and increase necrosis risk. Advancements in dosimetric strategies, novel imaging modalities, artificial intelligence, and circulating biomarkers could improve the management of necrosis. This review provides new insights into the pathophysiology of necrosis and synthesizes our current understanding regarding the diagnosis, risk factors, and management options of necrosis while highlighting novel avenues for discovery.

KFPredict: An ensemble learning prediction framework for diabetes based on fusion of key features

BACKGROUND AND OBJECTIVE

Diabetes is a disease that requires early detection and early treatment, and complications are likely to occur in late stages of the disease, threatening the life of patients. Therefore, in order to diagnose diabetic patients as early as possible, it is necessary to establish a model that can accurately predict diabetes.

METHODOLOGY

This paper proposes an ensemble learning framework: KFPredict, which combines multi-input models with key features and machine learning algorithms. We first propose a multi-input neural network model (KF_NN) that fuses key features and uses a decision tree-based selection recursive feature elimination algorithm and correlation coefficient method to screen out the key feature inputs and secondary feature inputs in the model. We then ensemble KF_NN with three machine learning algorithms (i.e., Support Vector Machine, Random Forest and K-Nearest Neighbors) for soft voting to form our predictive classifier for diabetes prediction.

RESULTS

Our framework demonstrates good prediction results on the test set with a sensitivity of 0.85, a specificity of 0.98, and an accuracy of 93.5%. Compared with the single prediction method KFPredict, the accuracy is up to 18.18% higher. Concurrently, we also compared KFPredict with the existing prediction methods. It still has good prediction performance, and the accuracy rate is improved by up to 14.93%.

CONCLUSION

This paper constructs a diabetes prediction framework that combines multi-input models with key features and machine learning algorithms. Taking tthe PIMA diabetes dataset as the test data, the experiment shows that the framework presents good prediction results.

Prediction of treatment response in patients with brain metastasis receiving stereotactic radiosurgery based on pre-treatment multimodal MRI radiomics and clinical risk factors: A machine learning model

Objectives

Stereotactic radiosurgery (SRS), a therapy that uses radiation to treat brain tumors, has become a significant treatment procedure for patients with brain metastasis (BM). However, a proportion of patients have been found to be at risk of local failure (LF) after treatment. Hence, accurately identifying patients with LF risk after SRS treatment is critical to the development of successful treatment plans and the prognoses of patients. To accurately predict BM patients with the occurrence of LF after SRS therapy, we develop and validate a machine learning (ML) model based on pre-treatment multimodal magnetic resonance imaging (MRI) radiomics and clinical risk factors.

Patients and methods

In this study, 337 BM patients were included (247, 60, and 30 in the training set, internal validation set, and external validation set, respectively). Four clinical features and 223 radiomics features were selected using least absolute shrinkage and selection operator (LASSO) and Max-Relevance and Min-Redundancy (mRMR) filters. We establish the ML model using the selected features and the support vector machine (SVM) classifier to predict the treatment response of BM patients to SRS therapy.

Results

In the training set, the SVM classifier that uses a combination of clinical and radiomics features demonstrates outstanding discriminative performance (AUC=0.95, 95% CI: 0.93-0.97). Moreover, this model also achieves satisfactory results in the validation sets (AUC=0.95 in the internal validation set and AUC=0.93 in the external validation set), demonstrating excellent generalizability.

Conclusions

This ML model enables a non-invasive prediction of the treatment response of BM patients receiving SRS therapy, which can in turn assist neurologist and radiation oncologists in the development of more precise and individualized treatment plans for BM patients.

Radiomic-signature changes after early treatment improve the prediction of progression-free survival in patients with advanced anaplastic lymphoma kinase-positive non-small cell lung cancer

BACKGROUND

The prognosis of lung cancer varies widely, even in cases wherein the tumor stage, genetic mutation, and treatment regimens are the same. Thus, an effective means for risk stratification of patients with lung cancer is needed.

PURPOSE

To develop and validate a combined model for predicting progression-free survival and risk stratification in patients with advanced anaplastic lymphoma kinase (ALK)-positive non-small cell lung cancer (NSCLC) treated with ensartinib.

MATERIAL AND METHODS

We analyzed 203 tumor lesions in 114 patients and evaluated average radiomic feature measures from all lesions at baseline and changes in these features after early treatment (Δradiomic features). Combined models were developed by integrating clinical with radiomic features. The prediction performance and clinical value of the proposed models were evaluated using receiver operating characteristic analysis, calibration curve, decision curve analysis (DCA), and Kaplan-Meier survival analysis.

RESULTS

Both the baseline and delta combined models achieved predictive efficacy with a high area under the curve. The calibration curve and DCA indicated the high accuracy and clinical usefulness of the combined models for tumor progression prediction. In the Kaplan-Meier analysis, the delta and baseline combined models, Δradiomic signature, and two selected clinical features could distinguish patients with a higher progression risk within 42 weeks. The delta combined model had the best performance.

CONCLUSION

The combination of clinical and radiomic features provided a prognostic value for survival and progression in patients with NSCLC receiving ensartinib. Radiomic-signature changes after early treatment could be more valuable than those at baseline alone.

Dosimetric and clinical analysis of pseudo-progression versus recurrence after hypo-fractionated radiotherapy for brain metastases

BACKGROUND

The main challenge in follow-up duration of patients with brain metastases after stereotactic radiotherapy is to distinguish between pseudo-progression and tumor recurrence. The objective of this study is to retrospectively analyze the predictive factors.

METHODS

The study included 123 patients with enlarged brain metastases after hypo-fractionated radiotherapy in our center from March 2009 to October 2019, and the baseline clinical features, radiotherapy planning parameters, and enhanced magnetic resonance imaging before and after radiation therapy were analyzed. Logistic regression was performed to compare the differences between groups. Independent risk factors with P < 0.05 and associated with recurrence were used to establish a nomogram prediction model and validated by Bootstrap repeated sampling, which was validated in an internal cohort (n = 23) from October 2019 to December 2021.

RESULTS

The median follow-up time was 68.4 months (range, 8.9-146.2 months). A total of 76 (61.8%) patients were evaluated as pseudo-progression, 47 patients (38.2%) were evaluated as tumor recurrence. The median time to pseudo-progression and tumor recurrence were 18.3 months (quartile range, 9.4-27.8 months) and 12.9 months (quartile range, 8.7-19.6 months) respectively. Variables associated with tumor recurrence included: gross tumor volume ≥ 6 cc, biological effective dose < 60 Gy, target coverage < 96% and no targeted therapy. The area under curve values were 0.730 and 0.967 in the training and validation cohorts, respectively. Thirty-one patients received salvage therapy in the tumor recurrence group. The survival time in pseudo-progression and tumor recurrence groups were 66.3 months (95% CI 56.8-75.9 months) and 39.6 months (95% CI 29.2-50.0 months, respectively; P = 0.001).

CONCLUSIONS

Clinical and dosimetry features of hypo-fractionated radiation therapy based on enhanced brain magnetic resonance can help distinguish pseudo-progression from tumor recurrence after hypo-fractionated radiotherapy for brain metastases. Gross tumor volume, biological effective dose, target coverage, and having received targeted therapy or not were factors associated with the occurrence of tumor recurrence, and the individual risk could be estimated by the nomogram effectively.

Artificial intelligence assists precision medicine in cancer treatment

Cancer is a major medical problem worldwide. Due to its high heterogeneity, the use of the same drugs or surgical methods in patients with the same tumor may have different curative effects, leading to the need for more accurate treatment methods for tumors and personalized treatments for patients. The precise treatment of tumors is essential, which renders obtaining an in-depth understanding of the changes that tumors undergo urgent, including changes in their genes, proteins and cancer cell phenotypes, in order to develop targeted treatment strategies for patients. Artificial intelligence (AI) based on big data can extract the hidden patterns, important information, and corresponding knowledge behind the enormous amount of data. For example, the ML and deep learning of subsets of AI can be used to mine the deep-level information in genomics, transcriptomics, proteomics, radiomics, digital pathological images, and other data, which can make clinicians synthetically and comprehensively understand tumors. In addition, AI can find new biomarkers from data to assist tumor screening, detection, diagnosis, treatment and prognosis prediction, so as to providing the best treatment for individual patients and improving their clinical outcomes.

Brain metastases from NSCLC treated with stereotactic radiotherapy: prediction mismatch between two different radiomic platforms

BACKGROUND AND PURPOSE

Radiomics enables the mining of quantitative features from medical images. The influence of the radiomic feature extraction software on the final performance of models is still a poorly understood topic. This study aimed to investigate the ability of radiomic features extracted by two different radiomic platforms to predict clinical outcomes in patients treated with radiosurgery for brain metastases from non-small cell lung cancer. We developed models integrating pre-treatment magnetic resonance imaging (MRI)-derived radiomic features and clinical data.

MATERIALS AND METHODS

Pre-radiotherapy gadolinium enhanced axial T1-weighted MRI scans were used. MRI images were re-sampled, intensity-shifted, and histogram-matched before radiomic extraction by means of two different platforms (PyRadiomics and SOPHiA Radiomics). We adopted LASSO Cox regression models for multivariable analyses by creating radiomic, clinical, and combined models using three survival clinical endpoints (local control, distant progression, and overall survival). The statistical analysis was repeated 50 times with different random seeds and the median concordance index was used as performance metric of the models.

RESULTS

We analysed 276 metastases from 148 patients. The use of the two platforms resulted in differences in both the quality and the number of extractable features. That led to mismatches in terms of end-to-end performance, statistical significance of radiomic scores, and clinical covariates found significant in combined models.

CONCLUSION

This study shed new light on how extracting radiomic features from the same images using two different platforms could yield several discrepancies. That may lead to acute consequences on drawing conclusions, comparing results across the literature, and translating radiomics into clinical practice.

Radiation necrosis or tumor progression? A review of the radiographic modalities used in the diagnosis of cerebral radiation necrosis

PURPOSE

Cerebral radiation necrosis is a complication of radiation therapy that can be seen months to years following radiation treatment. Differentiating radiation necrosis from tumor progression on standard magnetic resonance imaging (MRI) is often difficult and advanced imaging techniques may be needed to make an accurate diagnosis. The purpose of this article is to review the imaging modalities used in differentiating radiation necrosis from tumor progression following radiation therapy for brain metastases.

METHODS

We performed a review of the literature addressing the radiographic modalities used in the diagnosis of radiation necrosis.

RESULTS

Differentiating radiation necrosis from tumor progression remains a diagnostic challenge and advanced imaging modalities are often required to make a definitive diagnosis. If diagnostic uncertainty remains following conventional imaging, a multi-modality diagnostic approach with perfusion MRI, magnetic resonance spectroscopy (MRS), positron emission tomography (PET), single photon emission spectroscopy (SPECT), and radiomics may be used to improve diagnosis.

CONCLUSION

Several imaging modalities exist to aid in the diagnosis of radiation necrosis. Future studies developing advanced imaging techniques are needed.

Integrated radiomics, dose-volume histogram criteria and clinical features for early prediction of saliva amount reduction after radiotherapy in nasopharyngeal cancer patients

PURPOSE

Previously, the evaluation of xerostomia depended on subjective grading systems, rather than the accurate saliva amount reduction. Our aim was to quantify acute xerostomia with reduced saliva amount, and apply radiomics, dose-volume histogram (DVH) criteria and clinical features to predict saliva amount reduction by machine learning techniques.

MATERIAL AND METHODS

Computed tomography (CT) of parotid glands, DVH, and clinical data of 52 patients were collected to extract radiomics, DVH criteria and clinical features, respectively. Firstly, radiomics, DVH criteria and clinical features were divided into 3 groups for feature selection, in order to alleviate the masking effect of the number of features in different groups. Secondly, the top features in the 3 groups composed integrated features, and features selection was performed again for integrated features. In this study, feature selection was used as a combination of eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP) to alleviate multicollinearity. Finally, 6 machine learning techniques were used for predicting saliva amount reduction. Meanwhile, top radiomics features were modeled using the same machine learning techniques for comparison.

RESULT

17 integrated features (10 radiomics, 4 clinical, 3 DVH criteria) were selected to predict saliva amount reduction, with a mean square error (MSE) of 0.6994 and a R² score of 0.9815. Top 17 and 10 selected radiomics features predicted saliva amount reduction, with MSE of 0.7376, 0.7519, and R² score of 0.9805, 0.9801, respectively.

CONCLUSION

With the same number of features, integrated features (radiomics + DVH criteria + clinical) performed better than radiomics features alone. The important DVH criteria and clinical features mainly included, white blood cells (WBC), parotid_glands_Dmax, Age, parotid_glands_V15, hemoglobin (Hb), BMI and parotid_glands_V45.

Growth dynamics of brain metastases differentiate radiation necrosis from recurrence

Background

Radiation necrosis (RN) is a frequent adverse event after fractionated stereotactic radiotherapy (FSRT) or single-session stereotactic radiosurgery (SRS) treatment of brain metastases (BMs). It is difficult to distinguish RN from progressive disease (PD) due to their similarities in the magnetic resonance images. Previous theoretical studies have hypothesized that RN could have faster, although transient, growth dynamics after FSRT/SRS, but no study has proven that hypothesis using patient data. Thus, we hypothesized that lesion size time dynamics obtained from growth laws fitted with data from sequential volumetric measurements on magnetic resonance images may help in discriminating recurrent BMs from RN events.

Methods

A total of 101 BMs from different institutions, growing after FSRT/SRS (60 PDs and 41 RNs) in 86 patients, displaying growth for at least 3 consecutive MRI follow-ups were selected for the study from a database of 1031 BMs. The 3 parameters of the Von Bertalanffy growth law were determined for each BM and used to discriminate statistically PDs from RNs.

Results

Growth exponents in patients with RNs were found to be substantially larger than those of PD, due to the faster, although transient, dynamics of inflammatory processes. Statistically significant differences (P < .001) were found between both groups. The receiver operating characteristic curve (AUC = 0.76) supported the ability of the growth law exponent to classify the events.

Conclusions

Growth law exponents obtained from sequential longitudinal magnetic resonance images after FSRT/SRS can be used as a complementary tool in the differential diagnosis between RN and PD.

Diagnostic accuracy of MRI techniques for treatment response evaluation in patients with brain metastasis: A systematic review and meta-analysis

BACKGROUND

Treatment response assessment in patients with brain metastasis uses contrast enhanced T1-weighted MRI. Advanced MRI techniques have been studied, but the diagnostic accuracy is not well known. Therefore, we performed a metaanalysis to assess the diagnostic accuracy of the currently available MRI techniques for treatment response.

METHODS

A systematic literature search was done. Study selection and data extraction were done by two authors independently. Meta-analysis was performed using a bivariate random effects model. An independent cohort was used for DSC perfusion external validation of diagnostic accuracy.

RESULTS

Anatomical MRI (16 studies, 726 lesions) showed a pooled sensitivity of 79% and a specificity of 76%. DCE perfusion (4 studies, 114 lesions) showed a pooled sensitivity of 74% and a specificity of 92%. DSC perfusion (12 studies, 418 lesions) showed a pooled sensitivity was 83% with a specificity of 78%. Diffusion weighted imaging (7 studies, 288 lesions) showed a pooled sensitivity of 67% and a specificity of 79%. MRS (4 studies, 54 lesions) showed a pooled sensitivity of 80% and a specificity of 78%. Combined techniques (6 studies, 375 lesions) showed a pooled sensitivity of 84% and a specificity of 88%. External validation of DSC showed a lower sensitivity and a higher specificity for the reported cut-off values included in this metaanalysis.

CONCLUSION

A combination of techniques shows the highest diagnostic accuracy differentiating tumor progression from treatment induced abnormalities. External validation of imaging results is important to better define the reliability of imaging results with the different techniques.

Radiomics in neuro-oncological clinical trials

The development of clinical trials has led to substantial improvements in the prevention and treatment of many diseases, including brain cancer. Advances in medicine, such as improved surgical techniques, the development of new drugs and devices, the use of statistical methods in research, and the development of codes of ethics, have considerably influenced the way clinical trials are conducted today. In addition, methods from the broad field of artificial intelligence, such as radiomics, have the potential to considerably affect clinical trials and clinical practice in the future. Radiomics is a method to extract undiscovered features from routinely acquired imaging data that can neither be captured by means of human perception nor conventional image analysis. In patients with brain cancer, radiomics has shown its potential for the non-invasive identification of prognostic biomarkers, automated response assessment, and differentiation between treatment-related changes from tumour progression. Despite promising results, radiomics is not yet established in routine clinical practice nor in clinical trials. In this Viewpoint, the European Organization for Research and Treatment of Cancer Brain Tumour Group summarises the current status of radiomics, discusses its potential and limitations, envisions its future role in clinical trials in neuro-oncology, and provides guidance on how to address the challenges in radiomics.

Assessment of gamma knife radiosurgery for unruptured cerebral arterioveneus malformations based on multi-parameter radiomics of MRI

OBJECTIVE

The treatment of Gamma knife radiosurgery (GKS) for unruptured Arteriovenous Malformations (AVM) remains controversial. A safe, effective and non-invasive method to predict outcome seems attractive for GKS. The purpose of this study was to develop and validate a MRI based multi-parameter radiomics model predicting the outcome of GKS for unruptured AVM.

METHODS

Eighty-eight unruptured AVM patients who initial underwent GKS between January 2011 and December 2016 in our hospital were included in this retrospective study. Patients were divided into two groups named as favourable and unfavourable outcome, according to the clinical outcome. Favourable outcome was defined as obliteration without post-SRS hemorrhage or permanent radiation-induced changes (RIC). Multivariate logistic regression analysis was used to select appropriate clinical features and construct a clinical predicting model. In terms of radiomic model, manually segmentation and radiomics extracted were performed on each AVM lesions. Finally, 1684 radiomics features were extracted and Recursive Feature Elimination (RFE) method combined with Random forest classifier were used for feature selection and model construction. The performance of the radiomics model was evaluated by the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). In addition, the favourable group was further divided into early and late respond subgroup according to the time of obliteration evaluated by 2 years. The selected features were further compared according the respond time.

RESULTS

The median duration of neuroimaging follow-up was 65 months, 56 patients showed favourable outcome and 17 patients were observed obliteration within 2 years. The radiomics model constructed by 12 selected features achieved significant higher AUC of 0.88 (95% confidence interval 0.87-0.90) than traditional scoring system for predicting AVM outcome. Two selected radiomics features named "Dependence Variance" and "firstorder-Skewness" were found significant difference between the patients with early or late-respond.

CONCLUSIONS

The results suggest that the radiomics features could be successfully used for the pretreatment prediction of outcome for GKS in unruptured AVMs, which is helpful for decision-making process on unruptured AVM patients.

Imaging-defined necrosis after treatment with single-fraction stereotactic radiosurgery and immune checkpoint inhibitors and its potential association with improved outcomes in patients with brain metastases: an international multicenter study of 697 patients

OBJECTIVE

Immune checkpoint inhibitors (ICIs) and stereotactic radiosurgery (SRS) are commonly utilized in the management of brain metastases. Treatment-related imaging changes (TRICs) are a frequently observed clinical manifestation and are commonly classified as imaging-defined radiation necrosis. However, these findings are not well characterized and may predict a response to SRS and ICIs. The objective of this study was to investigate predictors of TRICs and their impact on patient survival.

METHODS

This retrospective multicenter cohort study was conducted through the International Radiosurgery Research Foundation. Member institutions submitted de-identified clinical and dosimetric data for patients with non-small cell lung cancer (NSCLC), melanoma, and renal cell carcinoma (RCC) brain metastases that had been treated with SRS and ICIs. Data were collected from March 2020 to February 2021. Univariable and multivariable Cox and logistic regression analyses were performed. The Kaplan-Meier method was used to evaluate overall survival (OS). The diagnosis-specific graded prognostic assessment was used to guide variable selection. TRICs were determined on the basis of MRI, PET/CT, or MR spectroscopy, and consensus by local clinical providers was required.

RESULTS

The analysis included 697 patients with 4536 brain metastases across 11 international institutions in 4 countries. The median follow-up after SRS was 13.6 months. The median age was 66 years (IQR 58-73 years), 54.1% of patients were male, and 57.3%, 36.3%, and 6.4% of tumors were NSCLC, melanoma, and RCC, respectively. All patients had undergone single-fraction radiosurgery to a median margin dose of 20 Gy (IQR 18-20 Gy). TRICs were observed in 9.8% of patients. The median OS for all patients was 24.5 months. On univariable analysis, Karnofsky Performance Status (KPS; HR 0.98, p < 0.001), TRICs (HR 0.67, p = 0.03), female sex (HR 0.67, p < 0.001), and prior resection (HR 0.60, p = 0.03) were associated with improved OS. On multivariable analysis, KPS (HR 0.98, p < 0.001) and TRICs (HR 0.66, p = 0.03) were associated with improved OS. A brain volume receiving ≥ 12 Gy of radiation (V12Gy) ≥ 10 cm3 (OR 2.78, p < 0.001), prior whole-brain radiation therapy (OR 3.46, p = 0.006), and RCC histology (OR 3.10, p = 0.01) were associated with an increased probability of developing TRICs. The median OS rates in patients with and without TRICs were 29.0 and 23.1 months, respectively (p = 0.03, log-rank test).

CONCLUSIONS

TRICs following ICI and SRS were associated with a median OS benefit of approximately 6 months in this retrospective multicenter study. Further prospective study and additional stratification are needed to validate these findings and further elucidate the role and etiology of this common clinical scenario.

Predicting Adverse Radiation Effects in Brain Tumors After Stereotactic Radiotherapy With Deep Learning and Handcrafted Radiomics

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.

Glioblastoma Recurrence Versus Radiotherapy Injury: Combined Model of Diffusion Kurtosis Imaging and 11C-MET Using PET/MRI May Increase Accuracy of Differentiation

PURPOSE

To evaluate the diagnostic potential of decision-tree model of diffusion kurtosis imaging (DKI) and 11C-methionine (11C-MET) PET, for the differentiation of radiotherapy (RT) injury from glioblastoma recurrence.

METHODS

Eighty-six glioblastoma cases with suspected lesions after RT were retrospectively enrolled. Based on histopathology or follow-up, 48 patients were diagnosed with local glioblastoma recurrence, and 38 patients had RT injury between April 2014 and December 2019. All the patients underwent PET/MRI examinations. Multiple parameters were derived based on the ratio of tumor to normal control (TNR), including SUVmax and SUVmean, mean value of kurtosis and diffusivity (MK, MD) from DKI, and histogram parameters. The diagnostic models were established by decision trees. Receiver operating characteristic analysis was used for evaluating the diagnostic accuracy of each independent parameter and all the diagnostic models.

RESULTS

The intercluster correlations of DKI, PET, and texture parameters were relatively weak, whereas the intracluster correlations were strong. Compared with models of DKI alone (sensitivity =1.00, specificity = 0.70, area under the curve [AUC] = 0.85) and PET alone (sensitivity = 0.83, specificity = 0.90, AUC = 0.89), the combined model demonstrated the best diagnostic accuracy (sensitivity = 1.00, specificity = 0.90, AUC = 0.95).

CONCLUSIONS

Diffusion kurtosis imaging, 11C-MET PET, and histogram parameters provide complementary information about tissue. The decision-tree model combined with these parameters has the potential to further increase diagnostic accuracy for the discrimination between RT injury and glioblastoma recurrence over the standard Response Assessment in Neuro-Oncology criteria. 11C-MET PET/MRI may thus contribute to the management of glioblastoma patients with suspected lesions after RT.

Machine learning imaging applications in the differentiation of true tumour progression from treatment‐related effects in brain tumours: A systematic review and meta‐analysis

Introduction

Chemotherapy and radiotherapy can produce treatment‐related effects, which may mimic tumour progression. Advances in Artificial Intelligence (AI) offer the potential to provide a more consistent approach of diagnosis with improved accuracy. The aim of this study was to determine the efficacy of machine learning models to differentiate treatment‐related effects (TRE), consisting of pseudoprogression (PsP) and radiation necrosis (RN), and true tumour progression (TTP).

Methods

The systematic review was conducted in accordance with PRISMA‐DTA guidelines. Searches were performed on PubMed, Scopus, Embase, Medline (Ovid) and ProQuest databases. Quality was assessed according to the PROBAST and CLAIM criteria. There were 25 original full‐text journal articles eligible for inclusion.

Results

For gliomas: PsP versus TTP (16 studies, highest AUC = 0.98), RN versus TTP (4 studies, highest AUC = 0.9988) and TRE versus TTP (3 studies, highest AUC = 0.94). For metastasis: RN vs. TTP (2 studies, highest AUC = 0.81). A meta‐analysis was performed on 9 studies in the gliomas PsP versus TTP group using STATA. The meta‐analysis reported a high sensitivity of 95.2% (95%CI: 86.6–98.4%) and specificity of 82.4% (95%CI: 67.0–91.6%).

Conclusion

TRE can be distinguished from TTP with good performance using machine learning‐based imaging models. There remain issues with the quality of articles and the integration of models into clinical practice. Future studies should focus on the external validation of models and utilize standardized criteria such as CLAIM to allow for consistency in reporting.

Is rectal filling optimal for MRI-based radiomics in preoperative T staging of rectal cancer?

PURPOSE

To determine whether rectal filling with ultrasound gel is clinically more beneficial in preoperative T staging of patients with rectal cancer (RC) using radiomics model based on magnetic resonance imaging (MRI).

METHODS

A total of 94 RC patients were assigned to cohort 1 (leave-one-out cross-validation [LOO-CV] set) and 230 RC patients were assigned to cohort 2 (test set). Patients were grouped according to different pathological T stages. The radiomics features were extracted through high-resolution T2-weighted imaging for all volume of interests in the two cohorts. Optimal features were selected using the least absolute shrinkage and selection operator (LASSO) algorithm. Model 1 (without rectal filling) and model 2 (with rectal filling) were constructed. LOO-CV was adopted for radiomics model building in cohort 1. Thereafter, the cohort 2 was used to test and verify the effectiveness of the two models.

RESULTS

Totally, 204 patients were enrolled, including 60 cases in cohort 1 and 144 cases in cohort 2. Finally, seven optimal features with LASSO were selected to build model 1 and nine optimal features were used for model 2. The ROC curves showed an AUC of 0.806 and 0.946 for model 1 and model 2 in cohort 1, respectively, and an AUC of 0.783 and 0.920 for model 1 and model 2 in cohort 2, respectively (p = 0.021).

CONCLUSION

The radiomics model with rectal filling showed an advantage for differentiating T1 + 2 from T3 and had less inaccurate categories in the test cohort, suggesting that this model may be useful for T-stage evaluation.

Brain Tumor Imaging: Applications of Artificial Intelligence

Artificial intelligence has become a popular field of research with goals of integrating it into the clinical decision-making process. A growing number of predictive models are being employed utilizing machine learning that includes quantitative, computer-extracted imaging features known as radiomic features, and deep learning systems. This is especially true in brain-tumor imaging where artificial intelligence has been proposed to characterize, differentiate, and prognostication. We reviewed current literature regarding the potential uses of machine learning-based, and deep learning-based artificial intelligence in neuro-oncology as it pertains to brain tumor molecular classification, differentiation, and treatment response. While there is promising evidence supporting the use of artificial intelligence in neuro-oncology, there are still more investigations needed on a larger, multicenter scale along with a streamlined and standardized image processing workflow prior to its introduction in routine clinical decision-making protocol.

Novel Imaging Biomarkers to Assess Oncologic Treatment-Related Changes

Cancer therapeutics cause various treatment-related changes that may impact patient follow-up and disease monitoring. Although atypical responses such as pseudoprogression may be misinterpreted as treatment nonresponse, other changes, such as hyperprogressive disease seen with immunotherapy, must be recognized early for timely management. Radiation necrosis in the brain is a known response to radiotherapy and must be distinguished from local tumor recurrence. Radiotherapy can also cause adverse effects such as pneumonitis and local tissue toxicity. Systemic therapies, like chemotherapy and targeted therapies, are known to cause long-term cardiovascular effects. Thus, there is a need for robust biomarkers to identify, distinguish, and predict cancer treatment-related changes. Radiomics, which refers to the high-throughput extraction of subvisual features from radiologic images, has been widely explored for disease classification, risk stratification, and treatment-response prediction. Lately, there has been much interest in investigating the role of radiomics to assess oncologic treatment-related changes. We review the utility and various applications of radiomics in identifying and distinguishing atypical responses to treatments, as well as in predicting adverse effects. Although artificial intelligence tools show promise, several challenges-including multi-institutional clinical validation, deployment in health care settings, and artificial-intelligence bias-must be addressed for seamless clinical translation of these tools.

Advancements in Oncology with Artificial Intelligence—A Review Article

Simple Summary

With the advancement of artificial intelligence, including machine learning, the field of oncology has seen promising results in cancer detection and classification, epigenetics, drug discovery, and prognostication. In this review, we describe what artificial intelligence is and its function, as well as comprehensively summarize its evolution and role in breast, colorectal, and central nervous system cancers. Understanding the origin and current accomplishments might be essential to improve the quality, accuracy, generalizability, cost-effectiveness, and reliability of artificial intelligence models that can be used in worldwide clinical practice. Students and researchers in the medical field will benefit from a deeper understanding of how to use integrative AI in oncology for innovation and research.

Abstract

Well-trained machine learning (ML) and artificial intelligence (AI) systems can provide clinicians with therapeutic assistance, potentially increasing efficiency and improving efficacy. ML has demonstrated high accuracy in oncology-related diagnostic imaging, including screening mammography interpretation, colon polyp detection, glioma classification, and grading. By utilizing ML techniques, the manual steps of detecting and segmenting lesions are greatly reduced. ML-based tumor imaging analysis is independent of the experience level of evaluating physicians, and the results are expected to be more standardized and accurate. One of the biggest challenges is its generalizability worldwide. The current detection and screening methods for colon polyps and breast cancer have a vast amount of data, so they are ideal areas for studying the global standardization of artificial intelligence. Central nervous system cancers are rare and have poor prognoses based on current management standards. ML offers the prospect of unraveling undiscovered features from routinely acquired neuroimaging for improving treatment planning, prognostication, monitoring, and response assessment of CNS tumors such as gliomas. By studying AI in such rare cancer types, standard management methods may be improved by augmenting personalized/precision medicine. This review aims to provide clinicians and medical researchers with a basic understanding of how ML works and its role in oncology, especially in breast cancer, colorectal cancer, and primary and metastatic brain cancer. Understanding AI basics, current achievements, and future challenges are crucial in advancing the use of AI in oncology.

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.

Multiparametric radiomic tissue signature and machine learning for distinguishing radiation necrosis from tumor progression after stereotactic radiosurgery

Background

Stereotactic radiosurgery (SRS) may cause radiation necrosis (RN) that is difficult to distinguish from tumor progression (TP) by conventional MRI. We hypothesize that MRI-based multiparametric radiomics (mpRad) and machine learning (ML) can differentiate TP from RN in a multi-institutional cohort.

Methods

Patients with growing brain metastases after SRS at 2 institutions underwent surgery, and RN or TP were confirmed by histopathology. A radiomic tissue signature (RTS) was selected from mpRad, as well as single T₁ post-contrast (T₁c) and T₂ fluid-attenuated inversion recovery (T₂-FLAIR) radiomic features. Feature selection and supervised ML were performed in a randomly selected training cohort (N = 95) and validated in the remaining cases (N = 40) using surgical pathology as the gold standard.

Results

One hundred and thirty-five discrete lesions (37 RN, 98 TP) from 109 patients were included. Radiographic diagnoses by an experienced neuroradiologist were concordant with histopathology in 67% of cases (sensitivity 69%, specificity 59% for TP). Radiomic analysis indicated institutional origin as a significant confounding factor for diagnosis. A random forest model incorporating 1 mpRad, 4 T₁c, and 4 T₂-FLAIR features had an AUC of 0.77 (95% confidence interval [CI]: 0.66–0.88), sensitivity of 67% and specificity of 86% in the training cohort, and AUC of 0.71 (95% CI: 0.51–0.91), sensitivity of 52% and specificity of 90% in the validation cohort.

Conclusions

MRI-based mpRad and ML can distinguish TP from RN with high specificity, which may facilitate the triage of patients with growing brain metastases after SRS for repeat radiation versus surgical intervention.

Differentiation of Brain Abscess From Cystic Glioma Using Conventional MRI Based on Deep Transfer Learning Features and Hand-Crafted Radiomics Features

Objectives: To develop and validate the model for distinguishing brain abscess from cystic glioma by combining deep transfer learning (DTL) features and hand-crafted radiomics (HCR) features in conventional T1-weighted imaging (T1WI) and T2-weighted imaging (T2WI).

Methods: This single-center retrospective analysis involved 188 patients with pathologically proven brain abscess (102) or cystic glioma (86). One thousand DTL and 105 HCR features were extracted from the T1WI and T2WI of the patients. Three feature selection methods and four classifiers, such as k-nearest neighbors (KNN), random forest classifier (RFC), logistic regression (LR), and support vector machine (SVM), for distinguishing brain abscess from cystic glioma were compared. The best feature combination and classifier were chosen according to the quantitative metrics including area under the curve (AUC), Youden Index, and accuracy.

Results: In most cases, deep learning-based radiomics (DLR) features, i.e., DTL features combined with HCR features, contributed to a higher accuracy than HCR and DTL features alone for distinguishing brain abscesses from cystic gliomas. The AUC values of the model established, based on the DLR features in T2WI, were 0.86 (95% CI: 0.81, 0.91) in the training cohort and 0.85 (95% CI: 0.75, 0.95) in the test cohort, respectively.

Conclusions: The model established with the DLR features can distinguish brain abscess from cystic glioma efficiently, providing a useful, inexpensive, convenient, and non-invasive method for differential diagnosis. This is the first time that conventional MRI radiomics is applied to identify these diseases. Also, the combination of HCR and DTL features can lead to get impressive performance.

Delta radiomics: a systematic review

BACKGROUND

Radiomics can provide quantitative features from medical imaging that can be correlated with various biological features and clinical endpoints. Delta radiomics, on the other hand, consists in the analysis of feature variation at different acquisition time points, usually before and after therapy. The aim of this study was to provide a systematic review of the different delta radiomics approaches.

METHODS

Eligible articles were searched in Embase, PubMed, and ScienceDirect using a search string that included free text and/or Medical Subject Headings (MeSH) with three key search terms: "radiomics", "texture", and "delta". Studies were analysed using QUADAS-2 and the RQS tool.

RESULTS

Forty-eight studies were finally included. The studies were divided into preclinical/methodological (five studies, 10.4%); rectal cancer (six studies, 12.5%); lung cancer (twelve studies, 25%); sarcoma (five studies, 10.4%); prostate cancer (three studies, 6.3%), head and neck cancer (six studies, 12.5%); gastrointestinal malignancies excluding rectum (seven studies, 14.6%), and other disease sites (four studies, 8.3%). The median RQS of all studies was 25% (mean 21% ± 12%), with 13 studies (30.2%) achieving a quality score < 10% and 22 studies (51.2%) < 25%.

CONCLUSIONS

Delta radiomics shows potential benefit for several clinical endpoints in oncology (differential diagnosis, prognosis and prediction of treatment response, and evaluation of side effects). Nevertheless, the studies included in this systematic review suffer from the bias of overall low quality, so that the conclusions are currently heterogeneous, not robust, and not replicable. Further research with prospective and multicentre studies is needed for the clinical validation of delta radiomics approaches.

Radiomic Features Associated with Extent of Resection in Glioma Surgery

Radiomics defines a set of techniques for extraction and quantification of digital medical data in an automated and reproducible way. Its goal is to detect features potentially related to a clinical task, like classification, diagnosis, prognosis, and response to treatment, going beyond the intrinsic limits of operator-dependency and qualitative description of conventional radiological evaluation on a mesoscopic scale. In the field of neuro-oncology, researchers have tried to create prognostic models for a better tumor diagnosis, histological and biomolecular classification, prediction of response to treatment, and identification of disease relapse. Concerning glioma surgery, the most significant aid that radiomics can give to surgery is to improve tumor extension detection and identify areas that are more prone to recurrence to increase the extent of tumor resection, thereby ameliorating the patients' prognosis. This chapter aims to review the fundamentals of radiomics models' creation, the latest advance of radiomics in neuro-oncology, and possible radiomic features associated with the extent of resection in the brain gliomas.

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.

A systematic review and quality of reporting checklist for repeatability and reproducibility of radiomic features

•

Main factors impacting feature stability: Image acquisition, reconstruction, tumor segmentation, and interpolation.

•

Textural features are less robust than morphological or statistical features.

•

A checklist is provided including items that should be reported in a radiomic study.

Purpose

Although quantitative image biomarkers (radiomics) show promising value for cancer diagnosis, prognosis, and treatment assessment, these biomarkers still lack reproducibility. In this systematic review, we aimed to assess the progress in radiomics reproducibility and repeatability in the recent years.

Methods and materials

Four hundred fifty-one abstracts were retrieved according to the original PubMed search pattern with the publication dates ranging from 2017/05/01 to 2020/12/01. Each abstract including the keywords was independently screened by four observers. Forty-two full-text articles were selected for further analysis. Patient population data, radiomic feature classes, feature extraction software, image preprocessing, and reproducibility results were extracted from each article. To support the community with a standardized reporting strategy, we propose a specific reporting checklist to evaluate the feasibility to reproduce each study.

Results

Many studies continue to under-report essential reproducibility information: all but one clinical and all but two phantom studies missed to report at least one important item reporting image acquisition. The studies included in this review indicate that all radiomic features are sensitive to image acquisition, reconstruction, tumor segmentation, and interpolation. However, the amount of sensitivity is feature dependent, for instance, textural features were, in general, less robust than statistical features.

Conclusions

Radiomics repeatability, reproducibility, and reporting quality can substantially be improved regarding feature extraction software and settings, image preprocessing and acquisition, cutoff values for stable feature selection. Our proposed radiomics reporting checklist can serve to simplify and improve the reporting and, eventually, guarantee the possibility to fully replicate and validate radiomic studies.

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.

Risk of symptomatic radiation necrosis in patients treated with stereotactic radiosurgery for brain metastases

INTRODUCTIO

Stereotactic radiosurgery (SRS) is a treatment option in the initial management of patients with brain metastases. While its efficacy has been demonstrated in several prior studies, treatment-related complications, particularly symptomatic radiation necrosis (RN), remains as an obstacle for wider implementation of this treatment modality. We thus examined risk factors associated with the development of symptomatic RN in patients treated with SRS for brain metastases.

PATIENTS AND METHODS

We performed a retrospective review of our institutional database to identify patients with brain metastases treated with SRS. Diagnosis of symptomatic RN was determined by appearance on serial MRIs, MR spectroscopy, requirement of therapy, and the development of new neurological complaints without evidence of disease progression.

RESULTS

We identified 323 brain metastases treated with SRS in 170 patients from 2009 to 2018. Thirteen patients (4%) experienced symptomatic RN after treatment of 23 (7%) lesions. After SRS, the median time to symptomatic RN was 8.3 months. Patients with symptomatic RN had a larger mean target volume (p<0.0001), and thus larger V100% (p<0.0001), V50% (p<0.0001), V12Gy (p<0.0001), and V10Gy (p=0.0002), compared to the rest of the cohort. Single-fraction treatment (p=0.0025) and diabetes (p=0.019) were also significantly associated with symptomatic RN.

CONCLUSION

SRS is an effective treatment option for patients with brain metastases; however, a subset of patients may develop symptomatic RN. We found that patients with larger tumor size, larger plan V100%, V50%, V12Gy, or V10Gy, who received single-fraction SRS, or who had diabetes were all at higher risk of symptomatic RN.