Normative Baseline for Radiomics in Brain MRI: Evaluating the Robustness, Regional Variations, and Reproducibility on FLAIR Images

Deep learning in neurosurgery: a systematic literature review with a structured analysis of applications across subspecialties

Objective

This study systematically reviewed deep learning (DL) applications in neurosurgical practice to provide a comprehensive understanding of DL in neurosurgery. The review process included a systematic overview of recent developments in DL technologies, an examination of the existing literature on their applications in neurosurgery, and insights into the future of neurosurgery. The study also summarized the most widely used DL algorithms, their specific applications in neurosurgical practice, their limitations, and future directions.

Materials and methods

An advanced search using medical subject heading terms was conducted in Medline (via PubMed), Scopus, and Embase databases restricted to articles published in English. Two independent neurosurgically experienced reviewers screened selected articles.

Results

A total of 456 articles were initially retrieved. After screening, 162 were found eligible and included in the study. Reference lists of all 162 articles were checked, and 19 additional articles were found eligible and included in the study. The 181 included articles were divided into 6 categories according to the subspecialties: general neurosurgery (n = 64), neuro-oncology (n = 49), functional neurosurgery (n = 32), vascular neurosurgery (n = 17), neurotrauma (n = 9), and spine and peripheral nerve (n = 10). The leading procedures in which DL algorithms were most commonly used were deep brain stimulation and subthalamic and thalamic nuclei localization (n = 24) in the functional neurosurgery group; segmentation, identification, classification, and diagnosis of brain tumors (n = 29) in the neuro-oncology group; and neuronavigation and image-guided neurosurgery (n = 13) in the general neurosurgery group. Apart from various video and image datasets, computed tomography, magnetic resonance imaging, and ultrasonography were the most frequently used datasets to train DL algorithms in all groups overall (n = 79). Although there were few studies involving DL applications in neurosurgery in 2016, research interest began to increase in 2019 and has continued to grow in the 2020s.

Conclusion

DL algorithms can enhance neurosurgical practice by improving surgical workflows, real-time monitoring, diagnostic accuracy, outcome prediction, volumetric assessment, and neurosurgical education. However, their integration into neurosurgical practice involves challenges and limitations. Future studies should focus on refining DL models with a wide variety of datasets, developing effective implementation techniques, and assessing their affect on time and cost efficiency.

T2-weighted MRI radiomics for the prediction of pediatric and young adult rhabdomyosarcoma alveolar subtype and distant metastasis: a pilot study

INTRODUCTION

Rhabdomyosarcomas are the most common soft tissue sarcoma in children. While treatment outcomes have improved, risk-based therapy classification relies on staging and tumor subtypes for therapeutic planning.

OBJECTIVE

This study investigated the utility of T2-weighted MR radiomics features and machine learning models in identifying the presence of distant metastasis and alveolar histological subtypes at baseline imaging in children diagnosed with rhabdomyosarcoma.

MATERIALS AND METHODS

This retrospective cross-sectional study utilized MRIs from 86 patients, 49 (median age (IQR) 59 months (37-161), alveolar subtype=15, distant metastasis=9) of whom had been imaged at outside imaging centers (training set); and 37 (median age 52 months (24-164), alveolar subtype=14, distant metastasis=8) of whom were imaged at our institution (holdout validation set). Radiomic features were extracted from T2-weighted images. We selected features that demonstrated intra-scan repeatability and used maximum relevance and minimum redundancy supervised feature selection to identify the 50 most important features. Lasso logistic regression and support vector machine (SVM) classifiers were trained to predict binary outcomes. The median of all predictions for a given patient was used as patient-level predictions. DeLong's test compared the area under the receiver operating characteristic curves (AUC). Cut-offs obtained by maximizing the Youden index were evaluated on an external validation set, and accuracy metrics were reported.

RESULTS

On the validation set, the Lasso and SVM classifiers obtained patient level AUCs of 0.76 (95% CI 0.59-0.94) and 0.73 (0.54-0.92), respectively, in predicting alveolar subtype, with the Lasso regressor obtaining 71.4% (41.9-91.6) sensitivity and 60.9% (38.5-80.3) specificity. When predicting the presence of distant metastasis, the Lasso and SVM classifier had AUCs of 0.81 (0.67-0.95) and 0.77 (0.58-0.97), respectively. There were no differences between model performance (P>0.05). A total of 12 and 18 features had nonzero coefficients in the Lasso regressors for predicting alveolar subtype and tumor metastasis, respectively.

CONCLUSION

MRI radiomics from baseline T2-weighted MRI demonstrated potential in predicting alveolar subtype and distant metastatic disease at presentation. Larger studies are needed to explore multinomial multiclass models for better prognostication of pediatric rhabdomyosarcomas.

Radiomic detection of abnormal brain regions in tuberous sclerosis complex

BACKGROUND

Radiomics refers to the extraction of quantitative information from medical images and is most commonly utilized in oncology to provide ancillary information for solid tumor diagnosis, prognosis, and treatment response. The traditional radiomic pipeline involves segmentation of volumes of interest with comparison to normal brain. In other neurologic disorders, such as epilepsy, lesion delineation may be difficult or impossible due to poor anatomic definition, small size, and multifocal or diffuse distribution. Tuberous sclerosis complex (TSC) is a rare genetic disease in which brain magnetic resonance imaging (MRI) demonstrates multifocal abnormalities with variable imaging and epileptogenic features.

PURPOSE

The purpose of this study was to develop a radiomic workflow for identification of abnormal brain regions in TSC, using a whole-brain atlas-based approach with generation of heatmaps based on signal deviation from normal controls.

METHODS

This was a retrospective pilot study utilizing high-resolution whole-brain 3D FLAIR MRI datasets from retrospective enrollment of tuberous sclerosis complex (TSC) patients and normal controls. Subjects underwent MRI including high-resolution 3D FLAIR sequences. Preprocessing included skull stripping, coregistration, and intensity normalization. Using the Brainnetome and Harvard-Oxford atlases, brain regions were parcellated into 318 discrete regions. Expert neuroradiologists spatially labeled all tubers in TSC patients using ITK-SNAP. The pyradiomics toolbox was used to extract 88 radiomic features based on IBSI guidelines, comparing tuber-affected and non-tuber-affected parenchyma in TSC patients, as well as normal brain tissue in control patients. For model training and validation, regions with tubers from 20 TSC patients and 30 normal control subjects were randomly divided into two training sets (80%) and two validation sets (20%). Additional model testing was performed on a separate group of 20 healthy controls. LASSO (least absolute shrinkage and selection operator) was used to perform variable selection and regularization to identify regions containing tubers. Relevant radiomic features selected by LASSO were combined to produce a radiomic score ω, defined as the sum of squared differences from average control group values. Region-specific ω scores were converted to heat maps and spatially coregistered with brain MRI to reflect overall radiomic deviation from normal.

RESULTS

The proposed radiomic workflow allows for quantification of deviation from normal in 318 regions of the brain with the use of a summative radiomic score ω. This score can be used to generate spatially registered heatmaps to identify brain regions with radiomic abnormalities. The pilot study of TSC showed radiomic scores ω that were statistically different in regions containing tubers from regions without tubers/normal brain (p < 0.0001). Our model exhibits an AUC of 0.81 (95% confidence interval: 0.78-0.84) on the testing set, and the best threshold obtained on the training set, when applied to the testing set, allows us to identify regions with tubers with a specificity of 0.91 and a sensitivity of 0.60.

CONCLUSION

We describe a whole-brain atlas-based radiomic approach to identify abnormal brain regions in TSC patients. This approach may be helpful for identifying specific regions of interest based on relatively greater signal deviation, particularly in clinical scenarios with numerous or poorly defined anatomic lesions.

A Comprehensive Evaluation of Radiomic Features in Normal Brain Magnetic Resonance Imaging: Investigating Robustness and Region Variations

Background

Despite extensive research on various brain diseases, a few studies have focused on radiomic feature distribution in healthy brain images. The present study applied a novel radiomic framework to investigate the robustness and baseline values of radiomic features in normal brain magnetic resonance imaging (MRIs) regions.

Materials and Methods

Analyses were performed on T1 and T2 images including 276 normal brains and 14 healthy volunteers were scanned with three scanners using the same protocols. The images were divided into 1024 three-dimensional nonoverlap patches with the same pixel size. Seven patches located in the thalamus, putamen, hippocampus and brain stem were selected as volume of interest (VOI). Eighty-five radiomic features were generated. To investigate the variation of features across VOIs, the analysis of variance was performed and coefficient of variation (COV) and intraclass correlation coefficient (ICC) were explored to examine the features repeatability.

Results

Thalamus (right and left) and hippocampus (left) resulted in more stable features (COV ≤ 6%) in T1 and T2 images, respectively. The inter-scanner ICC analysis demonstrated the features of T2 sequences represented more repeatable results and the brain stem and thalamus (both T1 and T2) showed particularly high repeatability (higher ICC values). Robust results (ICC ≥ 0.9) were identified for energy and range features of the first order class and several textures features across different brain regions.

Conclusion

Our results indicated the baselines of the repeatable texture features in healthy brain structural MRI highlighting inter-scanner stability. According to the findings, MRI sequencing and VOI location impact feature robustness and should be considered in brain radiomic studies.

Enhancing the Clinical Utility of Radiomics: Addressing the Challenges of Repeatability and Reproducibility in CT and MRI

Radiomics, which integrates the comprehensive characterization of imaging phenotypes with machine learning algorithms, is increasingly recognized for its potential in the diagnosis and prognosis of oncological conditions. However, the repeatability and reproducibility of radiomic features are critical challenges that hinder their widespread clinical adoption. This review aims to address the paucity of discussion regarding the factors that influence the reproducibility and repeatability of radiomic features and their subsequent impact on the application of radiomic models. We provide a synthesis of the literature on the repeatability and reproducibility of CT/MR-based radiomic features, examining sources of variation, the number of reproducible features, and the availability of individual feature repeatability indices. We differentiate sources of variation into random effects, which are challenging to control but can be quantified through simulation methods such as perturbation, and biases, which arise from scanner variability and inter-reader differences and can significantly affect the generalizability of radiomic model performance in diverse settings. Four suggestions for repeatability and reproducibility studies are suggested: (1) detailed reporting of variation sources, (2) transparent disclosure of calculation parameters, (3) careful selection of suitable reliability indices, and (4) comprehensive reporting of reliability metrics. This review underscores the importance of random effects in feature selection and harmonizing biases between development and clinical application settings to facilitate the successful translation of radiomic models from research to clinical practice.

Deep Learning for MRI Segmentation and Molecular Subtyping in Glioblastoma: Critical Aspects from an Emerging Field

Deep learning (DL) has been applied to glioblastoma (GBM) magnetic resonance imaging (MRI) assessment for tumor segmentation and inference of molecular, diagnostic, and prognostic information. We comprehensively overviewed the currently available DL applications, critically examining the limitations that hinder their broader adoption in clinical practice and molecular research. Technical limitations to the routine application of DL include the qualitative heterogeneity of MRI, related to different machinery and protocols, and the absence of informative sequences, possibly compensated by artificial image synthesis. Moreover, taking advantage from the available benchmarks of MRI, algorithms should be trained on large amounts of data. Additionally, the segmentation of postoperative imaging should be further addressed to limit the inaccuracies previously observed for this task. Indeed, molecular information has been promisingly integrated in the most recent DL tools, providing useful prognostic and therapeutic information. Finally, ethical concerns should be carefully addressed and standardized to allow for data protection. DL has provided reliable results for GBM assessment concerning MRI analysis and segmentation, but the routine clinical application is still limited. The current limitations could be prospectively addressed, giving particular attention to data collection, introducing new technical advancements, and carefully regulating ethical issues.

A nomogram for preoperative risk stratification based on MR morphological parameters in patients with endometrioid adenocarcinoma

PURPOSE

To develop and validate a nomogram based on MRI morphological parameters to preoperatively discriminate between low-risk and non-low-risk patients with endometrioid endometrial carcinoma (EEC).

METHODS

Two hundred eighty-one women with histologically confirmed EEC were divided into training (1.5-T MRI, n = 182) and validation cohorts (3.0-T MRI, n = 99). According to the European Society of Medical Oncology guidelines, the patients were divided into four risk groups: low, intermediate, high-intermediate, and high. Binary classification models were developed (low-risk vs. non-low-risk). Univariate logistic regression (LR) analyses were used to determine which variables to select to build the predictive models. Five classification models were constructed, and the best model was selected. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the performance of the prediction model and nomogram. P < 0.05 indicated a statistically significant difference.

RESULTS

Age and four morphological parameters (tumor size, tumor volume, maximum anteroposterior tumor diameter on sagittal T2-weighted images (APsag), and tumor area ratio (TAR)) were selected, and the LR model was used to construct an MRI morphological nomogram. The AUCs for the nomogram in predicting a non-low-risk of EEC among patients in the training and validation cohorts were 0.856 (sensitivity = 75.0%, specificity = 83.1%) and 0.849 (sensitivity = 74.6%, specificity = 85.0%), respectively.

CONCLUSION

An MRI morphological nomogram was developed and achieved high diagnostic performance for classifying low-risk and non-low-risk EEC preoperatively, which could provide support for therapeutic decision-making. Furthermore, our findings indicate that this nomogram is robust in the clinical application of various field strength data.

Robustness of radiomics to variations in segmentation methods in multimodal brain MRI

Radiomics in neuroimaging uses fully automatic segmentation to delineate the anatomical areas for which radiomic features are computed. However, differences among these segmentation methods affect radiomic features to an unknown extent. A scan-rescan dataset (n = 46) of T1-weighted and diffusion tensor images was used. Subjects were split into a sleep-deprivation and a control group. Scans were segmented using four segmentation methods from which radiomic features were computed. First, we measured segmentation agreement using the Dice-coefficient. Second, robustness and reproducibility of radiomic features were measured using the intraclass correlation coefficient (ICC). Last, difference in predictive power was assessed using the Friedman-test on performance in a radiomics-based sleep deprivation classification application. Segmentation agreement was generally high (interquartile range = 0.77–0.90) and median feature robustness to segmentation method variation was higher (ICC > 0.7) than scan-rescan reproducibility (ICC 0.3–0.8). However, classification performance differed significantly among segmentation methods (p < 0.001) ranging from 77 to 84%. Accuracy was higher for more recent deep learning-based segmentation methods. Despite high agreement among segmentation methods, subtle differences significantly affected radiomic features and their predictive power. Consequently, the effect of differences in segmentation methods should be taken into account when designing and evaluating radiomics-based research methods.

Intensity standardization of MRI prior to radiomic feature extraction for artificial intelligence research in glioma-a systematic review

OBJECTIVES

Radiomics is a promising avenue in non-invasive characterisation of diffuse glioma. Clinical translation is hampered by lack of reproducibility across centres and difficulty in standardising image intensity in MRI datasets. The study aim was to perform a systematic review of different methods of MRI intensity standardisation prior to radiomic feature extraction.

METHODS

MEDLINE, EMBASE, and SCOPUS were searched for articles meeting the following eligibility criteria: MRI radiomic studies where one method of intensity normalisation was compared with another or no normalisation, and original research concerning patients diagnosed with diffuse gliomas. Using PRISMA criteria, data were extracted from short-listed studies including number of patients, MRI sequences, validation status, radiomics software, method of segmentation, and intensity standardisation. QUADAS-2 was used for quality appraisal.

RESULTS

After duplicate removal, 741 results were returned from database and reference searches and, from these, 12 papers were eligible. Due to a lack of common pre-processing and different analyses, a narrative synthesis was sought. Three different intensity standardisation techniques have been studied: histogram matching (5/12), limiting or rescaling signal intensity (8/12), and deep learning (1/12)-only two papers compared different methods. From these studies, histogram matching produced the more reliable features compared to other methods of altering MRI signal intensity.

CONCLUSION

Multiple methods of intensity standardisation have been described in the literature without clear consensus. Further research that directly compares different methods of intensity standardisation on glioma MRI datasets is required.

KEY POINTS

• Intensity standardisation is a key pre-processing step in the development of robust radiomic signatures to evaluate diffuse glioma. • A minority of studies compared the impact of two or more methods. • Further research is required to directly compare multiple methods of MRI intensity standardisation on glioma datasets.

The stability of oncologic MRI radiomic features and the potential role of deep learning: a review

The use of MRI radiomic models for the diagnosis, prognosis and treatment response prediction of tumors has been increasingly reported in literature. However, its widespread adoption in clinics is hampered by issues related to features stability. In the MRI radiomic workflow, the main factors that affect radiomic features computation can be found in the image acquisition and reconstruction phase, in the image pre-processing steps, and in the segmentation of the region of interest on which radiomic indices are extracted. Deep Neural Networks (DNNs), having shown their potentiality in the medical image processing and analysis field, can be seen as an attractive strategy to partially overcome the issues related to radiomic stability and mitigate their impact. In fact, DNN approaches can be prospectively integrated in the MRI radiomic workflow to improve image quality, obtain accurate and reproducible segmentations and generate standardized images. In this review, DNN methods that can be included in the image processing steps of the radiomic workflow are described and discussed, in the light of a detailed analysis of the literature in the context of MRI radiomic reliability.

Acquisition repeatability of MRI radiomics features in the head and neck: a dual-3D-sequence multi-scan study

Radiomics has increasingly been investigated as a potential biomarker in quantitative imaging to facilitate personalized diagnosis and treatment of head and neck cancer (HNC), a group of malignancies associated with high heterogeneity. However, the feature reliability of radiomics is a major obstacle to its broad validity and generality in application to the highly heterogeneous head and neck (HN) tissues. In particular, feature repeatability of radiomics in magnetic resonance imaging (MRI) acquisition, which is considered a crucial confounding factor of radiomics feature reliability, is still sparsely investigated. This study prospectively investigated the acquisition repeatability of 93 MRI radiomics features in ten HN tissues of 15 healthy volunteers, aiming for potential magnetic resonance-guided radiotherapy (MRgRT) treatment of HNC. Each subject underwent four MRI acquisitions with MRgRT treatment position and immobilization using two pulse sequences of 3D T1-weighed turbo spin-echo and 3D T2-weighed turbo spin-echo on a 1.5 T MRI simulator. The repeatability of radiomics feature acquisition was evaluated in terms of the intraclass correlation coefficient (ICC), whereas within-subject acquisition variability was evaluated in terms of the coefficient of variation (CV). The results showed that MRI radiomics features exhibited heterogeneous acquisition variability and uncertainty dependent on feature types, tissues, and pulse sequences. Only a small fraction of features showed excellent acquisition repeatability (ICC > 0.9) and low within-subject variability. Multiple MRI scans improved the accuracy and confidence of the identification of reliable features concerning MRI acquisition compared to simple test-retest repeated scans. This study contributes to the literature on the reliability of radiomics features with respect to MRI acquisition and the selection of reliable radiomics features for use in modeling in future HNC MRgRT applications.

Brain MRI Radiomics Analysis of School-Aged Children with Tetralogy of Fallot

Introduction

Radiomics could be potential imaging biomarkers by capturing and analyzing the features. Children and adolescents with CHD have worse neurodevelopmental and functional outcomes compared with their peers. Early diagnosis and intervention are the necessity to improve neurological outcomes in CHD patients.

Methods

School-aged TOF patients and their healthy peers were recruited for MRI and neurodevelopmental assessment. LASSO regression was used for dimension reduction. ROC curve graph showed the performance of the model.

Results

Six related features were finally selected for modeling. The final model AUC was 0.750. The radiomics features can be potential significant predictors for neurodevelopmental diagnoses.

Conclusion

The radiomics on the conventional MRI can help predict the neurodevelopment of school-aged children and provide parents with rehabilitation advice as early as possible.

Radiomics feature reliability assessed by intraclass correlation coefficient: a systematic review

Radiomics research is rapidly growing in recent years, but more concerns on radiomics reliability are also raised. This review attempts to update and overview the current status of radiomics reliability research in the ever expanding medical literature from the perspective of a single reliability metric of intraclass correlation coefficient (ICC). To conduct this systematic review, Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. After literature search and selection, a total of 481 radiomics studies using CT, PET, or MRI, covering a wide range of subject and disease types, were included for review. In these highly heterogeneous studies, feature reliability to image segmentation was much more investigated than reliability to other factors, such as image acquisition, reconstruction, post-processing, and feature quantification. The reported ICCs also suggested high radiomics feature reliability to image segmentation. Image acquisition was found to introduce much more feature variability than image segmentation, in particular for MRI, based on the reported ICC values. Image post-processing and feature quantification yielded different levels of radiomics reliability and might be used to mitigate image acquisition-induced variability. Some common flaws and pitfalls in ICC use were identified, and suggestions on better ICC use were given. Due to the extremely high study heterogeneities and possible risks of bias, the degree of radiomics feature reliability that has been achieved could not yet be safely synthesized or derived in this review. More future researches on radiomics reliability are warranted.