Radiomics-Based Detection of Radionecrosis Using Harmonized Multiparametric MRI

Radiomic Analysis of Treatment Effect for Patients with Radiation Necrosis Treated with Pentoxifylline and Vitamin E

BACKGROUND

The combination of oral pentoxifylline (Ptx) and vitamin E (VitE) has been used to treat radiation-induced fibrosis and soft tissue injury. Here, we review outcomes and perform a radiomic analysis of treatment effects in patients prescribed Ptx + VitE at our institution for the treatment of radiation necrosis (RN).

METHODS

A total of 48 patients treated with stereotactic radiosurgery (SRS) had evidence of RN and had MRI before and after starting Ptx + VitE. The radiation oncologist's impression of the imaging in the electronic medical record was used to score response to treatment. Support Vector Machine (SVM) was used to train a model of radiomics features derived from radiation necrosis on pre- and 1st post-treatment T1 post-contrast MRIs that can classify the ultimate response to treatment with Ptx + VitE.

RESULTS

A total of 43.8% of patients showed evidence of improvement, 18.8% showed no change, and 25% showed worsening RN upon imaging after starting Ptx + VitE. The median time-to-response assessment was 3.17 months. Nine patients progressed significantly and required Bevacizumab, hyperbaric oxygen therapy, or surgery. Patients who had multiple lesions treated with SRS were less likely to show improvement (p = 0.037). A total of 34 patients were also prescribed dexamethasone, either before (7), with (16), or after starting (11) treatment. The use of dexamethasone was not associated with an improved response to Ptx + VitE (p = 0.471). Three patients stopped treatment due to side effects. Finally, we were able to develop a machine learning (SVM) model of radiomic features derived from pre- and 1st post-treatment MRIs that was able to predict the ultimate treatment response to Ptx + VitE with receiver operating characteristic (ROC) area under curve (AUC) of 0.69.

CONCLUSIONS

Ptx + VitE appears safe for the treatment of RN, but randomized data are needed to assess efficacy and validate radiomic models, which may assist with prognostication.

DeepComBat: A statistically motivated, hyperparameter-robust, deep learning approach to harmonization of neuroimaging data

Neuroimaging data acquired using multiple scanners or protocols are increasingly available. However, such data exhibit technical artifacts across batches which introduce confounding and decrease reproducibility. This is especially true when multi-batch data are analyzed using complex downstream models which are more likely to pick up on and implicitly incorporate batch-related information. Previously proposed image harmonization methods have sought to remove these batch effects; however, batch effects remain detectable in the data after applying these methods. We present DeepComBat, a deep learning harmonization method based on a conditional variational autoencoder and the ComBat method. DeepComBat combines the strengths of statistical and deep learning methods in order to account for the multivariate relationships between features while simultaneously relaxing strong assumptions made by previous deep learning harmonization methods. As a result, DeepComBat can perform multivariate harmonization while preserving data structure and avoiding the introduction of synthetic artifacts. We apply this method to cortical thickness measurements from a cognitive-aging cohort and show DeepComBat qualitatively and quantitatively outperforms existing methods in removing batch effects while preserving biological heterogeneity. Additionally, DeepComBat provides a new perspective for statistically motivated deep learning harmonization methods.

Analysis of Hybrid Feature Optimization Techniques Based on the Classification Accuracy of Brain Tumor Regions Using Machine Learning and Further Evaluation Based on the Institute Test Data

Aim

The goal of this study was to get optimal brain tumor features from magnetic resonance imaging (MRI) images and classify them based on the three groups of the tumor region: Peritumoral edema, enhancing-core, and necrotic tumor core, using machine learning classification models.

Materials and Methods

This study's dataset was obtained from the multimodal brain tumor segmentation challenge. A total of 599 brain MRI studies were employed, all in neuroimaging informatics technology initiative format. The dataset was divided into training, validation, and testing subsets online test dataset (OTD). The dataset includes four types of MRI series, which were combined together and processed for intensity normalization using contrast limited adaptive histogram equalization methodology. To extract radiomics features, a python-based library called pyRadiomics was employed. Particle-swarm optimization (PSO) with varying inertia weights was used for feature optimization. Inertia weight with a linearly decreasing strategy (W1), inertia weight with a nonlinear coefficient decreasing strategy (W2), and inertia weight with a logarithmic strategy (W3) were different strategies used to vary the inertia weight for feature optimization in PSO. These selected features were further optimized using the principal component analysis (PCA) method to further reducing the dimensionality and removing the noise and improve the performance and efficiency of subsequent algorithms. Support vector machine (SVM), light gradient boosting (LGB), and extreme gradient boosting (XGB) machine learning classification algorithms were utilized for the classification of images into different tumor regions using optimized features. The proposed method was also tested on institute test data (ITD) for a total of 30 patient images.

Results

For OTD test dataset, the classification accuracy of SVM was 0.989, for the LGB model (LGBM) was 0.992, and for the XGB model (XGBM) was 0.994, using the varying inertia weight-PSO optimization method and the classification accuracy of SVM was 0.996 for the LGBM was 0.998, and for the XGBM was 0.994, using PSO and PCA-a hybrid optimization technique. For ITD test dataset, the classification accuracy of SVM was 0.994 for the LGBM was 0.993, and for the XGBM was 0.997, using the hybrid optimization technique.

Conclusion

The results suggest that the proposed method can be used to classify a brain tumor as used in this study to classify the tumor region into three groups: Peritumoral edema, enhancing-core, and necrotic tumor core. This was done by extracting the different features of the tumor, such as its shape, grey level, gray-level co-occurrence matrix, etc., and then choosing the best features using hybrid optimal feature selection techniques. This was done without much human expertise and in much less time than it would take a person.

A three-dimensional deep learning model for inter-site harmonization of structural MR images of the brain: Extensive validation with a multicenter dataset

In multicenter MRI studies, pooling the imaging data can introduce site-related variabilities and can therefore bias the subsequent analyses. To harmonize the intensity distributions of brain MR images in a multicenter dataset, unsupervised deep learning methods can be employed. Here, we developed a model based on cycle-consistent adversarial networks for the harmonization of T1-weighted brain MR images. In contrast to previous works, it was designed to process three-dimensional whole-brain images in a stable manner while optimizing computation resources. Using six different MRI datasets for healthy adults (n=1525 in total) with different acquisition parameters, we tested the model in (i) three pairwise harmonizations with site effects of various sizes, (ii) an overall harmonization of the six datasets with different age distributions, and (iii) a traveling-subject dataset. Our results for intensity distributions, brain volumes, image quality metrics and radiomic features indicated that the MRI characteristics at the various sites had been effectively homogenized. Next, brain age prediction experiments and the observed correlation between the gray-matter volume and age showed that thanks to an appropriate training strategy and despite biological differences between the dataset populations, the model reinforced biological patterns. Furthermore, radiologic analyses of the harmonized images attested to the conservation of the radiologic information in the original images. The robustness of the harmonization model (as judged with various datasets and metrics) demonstrates its potential for application in retrospective multicenter studies.

ComBat Harmonization of Myocardial Radiomic Features Sensitive to Cardiac MRI Acquisition Parameters

Purpose

To investigate the effect of ComBat harmonization methods on the robustness of cardiac MRI-derived radiomic features to variations in imaging parameters.

Materials and Methods

This Health Insurance Portability and Accountability Act-compliant retrospective study used a publicly available data set of 11 healthy controls (mean age, 33 years ± 16 [SD]; six men) and five patients (mean age, 52 years ± 16; four men). A single midventricular short-axis section was acquired with 3-T MRI using cine balanced steady-state free precision, T1-weighted, T2-weighted, T1 mapping, and T2 mapping imaging sequences. Each sequence was acquired using baseline parameters and after variations in flip angle, spatial resolution, section thickness, and parallel imaging. Image registration was performed for all sequences at a per-individual level. Manual myocardial contouring was performed, and 1652 radiomic features per sequence were extracted using baseline and variations in imaging parameters. Radiomic feature stability to change in imaging parameters was assessed using Cohen d sensitivity. The stability of radiomic features was assessed both without and after ComBat harmonization of radiomic features. Three ComBat methods were studied: parametric, nonparametric, and Gaussian mixture model (GMM).

Results

For all sequences combined, 51.4% of features were robust to changes in imaging parameters when no ComBat method was applied. ComBat harmonization substantially increased the number of stable features to 95.1% (95% CI: 94.9, 95.3) when parametric ComBat was used and 90.9% (95% CI: 90.6, 91.2) when nonparametric ComBat was used. GMM combat resulted in only 52.6% stable features.

Conclusion

ComBat harmonization improved the stability of radiomic features to changes in imaging parameters across all cardiac MRI sequences.Keywords: Cardiac MRI, Radiomics, ComBat, Harmonization Supplemental material is available for this article. © RSNA, 2023.

Image harmonization: A review of statistical and deep learning methods for removing batch effects and evaluation metrics for effective harmonization

Magnetic resonance imaging and computed tomography from multiple batches (e.g. sites, scanners, datasets, etc.) are increasingly used alongside complex downstream analyses to obtain new insights into the human brain. However, significant confounding due to batch-related technical variation, called batch effects, is present in this data; direct application of downstream analyses to the data may lead to biased results. Image harmonization methods seek to remove these batch effects and enable increased generalizability and reproducibility of downstream results. In this review, we describe and categorize current approaches in statistical and deep learning harmonization methods. We also describe current evaluation metrics used to assess harmonization methods and provide a standardized framework to evaluate newly-proposed methods for effective harmonization and preservation of biological information. Finally, we provide recommendations to end-users to advocate for more effective use of current methods and to methodologists to direct future efforts and accelerate development of the field.

DeepComBat: A Statistically Motivated, Hyperparameter-Robust, Deep Learning Approach to Harmonization of Neuroimaging Data

Neuroimaging data from multiple batches (i.e. acquisition sites, scanner manufacturer, datasets, etc.) are increasingly necessary to gain new insights into the human brain. However, multi-batch data, as well as extracted radiomic features, exhibit pronounced technical artifacts across batches. These batch effects introduce confounding into the data and can obscure biological effects of interest, decreasing the generalizability and reproducibility of findings. This is especially true when multi-batch data is used alongside complex downstream analysis models, such as machine learning methods. Image harmonization methods seeking to remove these batch effects are important for mitigating these issues; however, significant multivariate batch effects remain in the data following harmonization by current state-of-the-art statistical and deep learning methods. We present DeepCombat, a deep learning harmonization method based on a conditional variational autoencoder architecture and the ComBat harmonization model. DeepCombat learns and removes subject-level batch effects by accounting for the multivariate relationships between features. Additionally, DeepComBat relaxes a number of strong assumptions commonly made by previous deep learning harmonization methods and is empirically robust across a wide range of hyperparameter choices. We apply this method to neuroimaging data from a large cognitive-aging cohort and find that DeepCombat outperforms existing methods, as assessed by a battery of machine learning methods, in removing scanner effects from cortical thickness measurements while preserving biological heterogeneity. Additionally, DeepComBat provides a new perspective for statistically-motivated deep learning harmonization methods.

Differentiating radiation necrosis from tumor recurrence: a systematic review and diagnostic meta-analysis comparing imaging modalities

PURPSOSE

Cerebral radiation necrosis (RN) is often a delayed phenomenon occurring several months to years after the completion of radiation treatment. Differentiating RN from tumor recurrence presents a diagnostic challenge on standard MRI. To date, no evidence-based guidelines exist regarding imaging modalities best suited for this purpose. We aim to review the current literature and perform a diagnostic meta-analysis comparing various imaging modalities that have been studied to differentiate tumor recurrence and RN.

METHODS

A systematic search adherent to PRISMA guidelines was performed using Scopus, PubMed/MEDLINE, and Embase. Pooled sensitivities and specificities were determined using a random-effects or fixed-effects proportional meta-analysis based on heterogeneity. Using diagnostic odds ratios, a diagnostic frequentist random-effects network meta-analysis was performed, and studies were ranked using P-score hierarchical ranking.

RESULTS

The analysis included 127 studies with a total of 220 imaging datasets, including the following imaging modalities: MRI (n = 10), MR Spectroscopy (MRS) (n = 28), dynamic contrast-enhanced MRI (n = 7), dynamic susceptibility contrast MRI (n = 36), MR arterial spin labeling (n = 5), diffusion-weighted imaging (n = 13), diffusion tensor imaging (DTI) (n = 2), PET (n = 89), and single photon emission computed tomography (SPECT) (n = 30). MRS had the highest pooled sensitivity (90.7%). DTI had the highest pooled specificity (90.5%). Our hierarchical ranking ranked SPECT and MRS as most preferable, and MRI was ranked as least preferable.

CONCLUSION

These findings suggest SPECT and MRS carry greater utility than standard MRI in distinguishing RN from tumor recurrence.

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.

Prospective clinical research of radiomics and deep learning in oncology: A translational review

Radiomics and deep learning (DL) hold transformative promise and substantial and significant advances in oncology; however, most methods have been tested in retrospective or simulated settings. There is considerable interest in the biomarker validation, clinical utility, and methodological robustness of these studies and their deployment in real-world settings. This review summarizes the characteristics of studies, the level of prospective validation, and the overview of research on different clinical endpoints. The discussion of methodological robustness shows the potential for independent external replication of prospectively reported results. These in-depth analyses further describe the barriers limiting the translation of radiomics and DL into primary care options and provide specific recommendations regarding clinical deployment. Finally, we propose solutions for integrating novel approaches into the treatment environment to unravel the critical process of translating AI models into the clinical routine and explore strategies to improve personalized medicine.

Towards updated understanding of brain metastasis

Brain metastasis (BM) is a common complication in cancer patients with advanced disease and attributes to treatment failure and final mortality. Currently there are several therapeutic options available; however these are only suitable for limited subpopulation: surgical resection or radiosurgery for cases with a limited number of lesions, targeted therapies for approximately 18% of patients, and immune checkpoint inhibitors with a response rate of 20-30%. Thus, there is a pressing need for development of novel diagnostic and therapeutic options. This overview article aims to provide research advances in disease model, targeted therapy, blood brain barrier (BBB) opening strategies, imaging and its incorporation with artificial intelligence, external radiotherapy, and internal targeted radionuclide theragnostics. Finally, a distinct type of BM, leptomeningeal metastasis is also covered.

Radiomics-guided radiation therapy: opportunities and challenges

Radiomics is an advanced image-processing framework, which extracts image features and considers them as biomarkers towards personalized medicine. Applications include disease detection, diagnosis, prognosis, and therapy response assessment/prediction. As radiation therapy aims for further individualized treatments, radiomics could play a critical role in various steps before, during and after treatment. Elucidation of the concept of radiomics-guided radiation therapy (RGRT) is the aim of this review, attempting to highlight opportunities and challenges underlying the use of radiomics to guide clinicians and physicists towards more effective radiation treatments. This work identifies the value of RGRT in various steps of radiotherapy from patient selection to follow-up, and subsequently provides recommendations to improve future radiotherapy using quantitative imaging features.