Emerging Applications of Artificial Intelligence in Neuro-Oncology

Development and Evaluation of Automated Artificial Intelligence-Based Brain Tumor Response Assessment in Patients with Glioblastoma

This project aimed to develop and evaluate an automated, AI-based, volumetric brain tumor MRI response assessment algorithm on a large cohort of patients treated at a high-volume brain tumor center. We retrospectively analyzed data from 634 patients treated for glioblastoma at a single brain tumor center over a 5-year period (2017-2021). The mean age was 56 ± 13 years. 372/634 (59%) patients were male, and 262/634 (41%) patients were female. Study data consisted of 3,403 brain MRI exams and corresponding standardized, radiologist-based brain tumor response assessments (BT-RADS). An artificial intelligence (AI)-based brain tumor response assessment (AI-VTRA) algorithm was developed using automated, volumetric tumor segmentation. AI-VTRA results were evaluated for agreement with radiologist-based response assessments and ability to stratify patients by overall survival. Metrics were computed to assess the agreement using BT-RADS as the ground-truth, fixed-time point survival analysis was conducted to evaluate the survival stratification, and associated P-values were calculated. For all BT-RADS categories, AI-VTRA showed moderate agreement with radiologist response assessments (F1 = 0.587-0.755). Kaplan-Meier survival analysis revealed statistically worse overall fixed time point survival for patients assessed as image worsening equivalent to RANO progression by human alone compared to by AI alone (log-rank P = .007). Cox proportional hazard model analysis showed a disadvantage to AI-based assessments for overall survival prediction (P = .012). In summary, our proposed AI-VTRA, following BT-RADS criteria, yielded moderate agreement for replicating human response assessments and slightly worse stratification by overall survival.

Differentiation of Glioblastoma and Solitary Brain Metastasis Using Brain-Tumor Interface Radiomics Features Based on MR Images: A Multicenter Study

RATIONALE AND OBJECTIVES

Glioblastoma (GBM) and solitary brain metastasis (SBM) exhibit similar radiomics features on magnetic resonance imaging (MRI), yet their treatment strategies and prognoses significantly differ. Therefore, accurate differentiation between these two types of tumors is crucial for clinical decision-making. This study aims to establish and validate an efficient diagnostic model based on the radiomic features of the T1-weighted contrast-enhanced (T1CE) sequence in the 10 mm brain-tumor interface region to achieve precise differentiation between GBM and SBM.

METHODS

This study retrospectively collected contrast-enhanced T1-weighted imaging data from 226 GBM patients and 206 SBM patients at three centers between January 2010 and October 2024. Samples from centers 1 and 2 were used as the training set, while samples from center 3 were used as the test set. Two observers manually delineated the tumor edges on the T1CE images layer by layer to obtain the Region of Interest (ROI) covering the entire tumor volume. A 10 mm brain-to-tumor interface (BTI) was extracted using Python code. Radiomic features were extracted from the 10 mm BTI region, followed by feature selection and model construction. Finally, SHAP (SHapley Additive exPlanations) was used to visualize the model. Three radiologists with 2, 6, and 18 years of diagnostic experience independently evaluated the test set samples without knowing the patient information or pathology results, establishing three diagnostic models. The DeLong test was used to compare these models with the radiomic model.

RESULTS

Ultimately, ten radiomic features were used for modeling. The model established using the logistic regression (LR) algorithm had an AUC of 0.893 on the training set and 0.808 on the test set. The AUCs of the three radiologists with different diagnostic experiences on the test set were 0.699, 0.740, and 0.789, respectively, all lower than that of the radiomic model. The DeLong test showed that ModelBTI performed significantly better than Doctor 1 (p<0.05) in the test set, but there was no statistically significant difference in performance between ModelBTI and Doctors 2 and 3.

CONCLUSION

The radiomic model constructed based on the 10 mm brain-tumor interface can effectively differentiate between GBM and SBM, capturing tumor heterogeneity from a new perspective, thereby significantly improving diagnostic performance and providing assistance for clinical diagnosis.

DATA AVAILABILITY STATEMENT

The original contributions presented in the study are included in the article/Supplemental material, further inquiries can be directed to the corresponding authors.

A multicenter study of neurofibromatosis type 1 utilizing deep learning for whole body tumor identification

Deep-learning models have shown promise in differentiating between benign and malignant lesions. Previous studies have primarily focused on specific anatomical regions, overlooking tumors occurring throughout the body with highly heterogeneous whole-body backgrounds. Using neurofibromatosis type 1 (NF1) as an example, this study developed highly accurate MRI-based deep-learning models for the early automated screening of malignant peripheral nerve sheath tumors (MPNSTs) against complex whole-body background. In a Chinese seven-center cohort, data from 347 subjects were analyzed. Our one-step model incorporated normal tissue/organ labels to provide contextual information, offering a solution for tumors with complex backgrounds. To address privacy concerns, we utilized a lightweight deep neural network suitable for hospital deployment. The final model achieved an accuracy of 85.71% for MPNST diagnosis in the validation cohort and 84.75% accuracy in the independent test set, outperforming another classic two-step model. This success suggests potential for AI models in screening other whole-body primary/metastatic tumors.

Current state and promise of user-centered design to harness explainable AI in clinical decision-support systems for patients with CNS tumors

In neuro-oncology, MR imaging is crucial for obtaining detailed brain images to identify neoplasms, plan treatment, guide surgical intervention, and monitor the tumor's response. Recent AI advances in neuroimaging have promising applications in neuro-oncology, including guiding clinical decisions and improving patient management. However, the lack of clarity on how AI arrives at predictions has hindered its clinical translation. Explainable AI (XAI) methods aim to improve trustworthiness and informativeness, but their success depends on considering end-users' (clinicians') specific context and preferences. User-Centered Design (UCD) prioritizes user needs in an iterative design process, involving users throughout, providing an opportunity to design XAI systems tailored to clinical neuro-oncology. This review focuses on the intersection of MR imaging interpretation for neuro-oncology patient management, explainable AI for clinical decision support, and user-centered design. We provide a resource that organizes the necessary concepts, including design and evaluation, clinical translation, user experience and efficiency enhancement, and AI for improved clinical outcomes in neuro-oncology patient management. We discuss the importance of multi-disciplinary skills and user-centered design in creating successful neuro-oncology AI systems. We also discuss how explainable AI tools, embedded in a human-centered decision-making process and different from fully automated solutions, can potentially enhance clinician performance. Following UCD principles to build trust, minimize errors and bias, and create adaptable software has the promise of meeting the needs and expectations of healthcare professionals.

The Spatial Distribution of Brain Metastasis Is Determined by the Heterogeneity of the Brain Microenvironment

It is now understood that brain metastases do not occur randomly but have distinct spatial patterns depending on the origin of the cancer. According to the "seed and soil" hypothesis, the final colonization of metastatic cells is the result of their adaptation to the altered environment. To investigate the most favorable microenvironment for brain metastasis, we analyzed neuroimaging data from 177 patients with breast cancer brain metastasis and 548 patients with lung cancer brain metastasis to create a replicable probabilistic map of metastatic locations. Additionally, we used population-based data from open repositories to generate brain atlases of diverse microenvironment features, including gene expression, functional connectivity, glucose metabolism, and neurotransmitter transporters/receptors. We then compared the spatial correlation between brain metastasis frequency and these features, after which we constructed a general linear model to identify the most significant variables that contributed to tumor location predilection. Our findings revealed that brain metastases from breast cancer and lung cancer had distinct radiographic characteristics and distribution patterns. Breast cancer tended to metastasize in brain regions with decreased expression of genes associated with immunity and metabolism and reduced levels of connectomic hubness and glucose metabolism. In contrast, lung cancer had a higher probability of metastasizing in regions with active metabolism. Moreover, neurotransmitter systems play various roles in determining tumor location. These results provide new insights into the adaptation of metastatic cells to the brain microenvironment and illustrate how factors on diverse biological scales can affect the colonization of brain metastases.

Robotics and Artificial Intelligence in Minimally Invasive Spine Surgery: A Bibliometric and Visualization Analysis

OBJECTIVE

This study aims to highlight the trends in the minimally invasive spine surgery (MISS) research field from the bibliometrics perspective.

METHODS

The articles and reviews from 2002 to 2022 were manually retrieved from Scopus based on predefined inclusion criteria. A total of 296 articles for robotics and 13 articles for AI were included in the final analysis. All publication records were imported and analyzed in Microsoft Excel and VOSviewer.

RESULTS

An increase in the number of publications per year was observed in the last five years. For robotics, the United States published the largest number of articles (161), but the Netherlands had the highest total citations (1216). Beijing Jishuitan Hospital, China, was the most prolific institution. For journals, World Neurosurgery had the most publications (31), while Spine journal was the most impactful (average citation index = 86.6). Wang T.Y was the author with the most published articles (5). For AI, the United States had the greatest number of publications (10) and the highest citations (229). Global Spine Journal had the most publications (3), while Spine had the most citations (112). Kim J.S. was the most cited author (102). Recent keywords mainly focused on techniques and prognoses using these modalities in MISS. There were relatively fewer collaborations among countries.

CONCLUSIONS

An increasing trend in publications regarding robotics and AI use reflects the recent MISS technique advancements. Our findings can provide useful information to identify potential research fronts in the coming years. Enhanced collaboration on an international level should be pursued.

Medical image foundation models in assisting diagnosis of brain tumors: a pilot study

OBJECTIVES

To build self-supervised foundation models for multicontrast MRI of the whole brain and evaluate their efficacy in assisting diagnosis of brain tumors.

METHODS

In this retrospective study, foundation models were developed using 57,621 enhanced head MRI scans through self-supervised learning with a pretext task of cross-contrast context restoration with two different content dropout schemes. Downstream classifiers were constructed based on the pretrained foundation models and fine-tuned for brain tumor detection, discrimination, and molecular status prediction. Metrics including accuracy, sensitivity, specificity, and area under the ROC curve (AUC) were used to evaluate the performance. Convolutional neural networks trained exclusively on downstream task data were employed for comparative analysis.

RESULTS

The pretrained foundation models demonstrated their ability to extract effective representations from multicontrast whole-brain volumes. The best classifiers, endowed with pretrained weights, showed remarkable performance with accuracies of 94.9, 92.3, and 80.4%, and corresponding AUC values of 0.981, 0.972, and 0.852 on independent test datasets in brain tumor detection, discrimination, and molecular status prediction, respectively. The classifiers with pretrained weights outperformed the convolutional classifiers trained from scratch by approximately 10% in terms of accuracy and AUC across all tasks. The saliency regions in the correctly predicted cases are mainly clustered around the tumors. Classifiers derived from the two dropout schemes differed significantly only in the detection of brain tumors.

CONCLUSIONS

Foundation models obtained from self-supervised learning have demonstrated encouraging potential for scalability and interpretability in downstream brain tumor-related tasks and hold promise for extension to neurological diseases with diffusely distributed lesions.

CLINICAL RELEVANCE STATEMENT

The application of our proposed method to the prediction of key molecular status in gliomas is expected to improve treatment planning and patient outcomes. Additionally, the foundation model we developed could serve as a cornerstone for advancing AI applications in the diagnosis of brain-related diseases.

Role of artificial intelligence in gastrointestinal surgery

Artificial intelligence is rapidly evolving and its application is increasing day-by-day in the medical field. The application of artificial intelligence is also valuable in gastrointestinal diseases, by calculating various scoring systems, evaluating radiological images, preoperative and intraoperative assistance, processing pathological slides, prognosticating, and in treatment responses. This field has a promising future and can have an impact on many management algorithms. In this minireview, we aimed to determine the basics of artificial intelligence, the role that artificial intelligence may play in gastrointestinal surgeries and malignancies, and the limitations thereof.

Glioblastoma and Solitary Brain Metastasis: Differentiation by Integrating Demographic-MRI and Deep-Learning Radiomics Signatures

BACKGROUND

Studies have shown that deep-learning radiomics (DLR) could help differentiate glioblastoma (GBM) from solitary brain metastasis (SBM), but whether integrating demographic-MRI and DLR features can more accurately distinguish GBM from SBM remains uncertain.

PURPOSE

To construct and validate a demographic-MRI deep-learning radiomics nomogram (DDLRN) integrating demographic-MRI and DLR signatures to differentiate GBM from SBM preoperatively.

STUDY TYPE

Retrospective.

POPULATION

Two hundred and thirty-five patients with GBM (N = 115) or SBM (N = 120), randomly divided into a training cohort (90 GBM and 98 SBM) and a validation cohort (25 GBM and 22 SBM).

FIELD STRENGTH/SEQUENCE

Axial T2-weighted fast spin-echo sequence (T2WI), T2-weighted fluid-attenuated inversion recovery sequence (T2-FLAIR), and contrast-enhanced T1-weighted spin-echo sequence (CE-T1WI) using 1.5-T and 3.0-T scanners.

ASSESSMENT

The demographic-MRI signature was constructed with seven imaging features ("pool sign," "irregular ring sign," "regular ring sign," "intratumoral vessel sign," the ratio of the area of peritumoral edema to the enhanced tumor, the ratio of the lesion area on T2-FLAIR to CE-T1WI, and the tumor location) and demographic factors (age and sex). Based on multiparametric MRI, radiomics and deep-learning (DL) models, DLR signature, and DDLRN were developed and validated.

STATISTICAL TESTS

The Mann-Whitney U test, Pearson test, least absolute shrinkage and selection operator, and support vector machine algorithm were applied for feature selection and construction of radiomics and DL models.

RESULTS

DDLRN showed the best performance in differentiating GBM from SBM with area under the curves (AUCs) of 0.999 and 0.947 in the training and validation cohorts, respectively. Additionally, the DLR signature (AUC = 0.938) outperformed the radiomics and DL models, and the demographic-MRI signature (AUC = 0.775) was comparable to the T2-FLAIR radiomics and DL models in the validation cohort (AUC = 0.762 and 0.749, respectively).

DATA CONCLUSION

DDLRN integrating demographic-MRI and DLR signatures showed excellent performance in differentiating GBM from SBM.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

Differentiation of glioblastoma from solitary brain metastasis using deep ensembles: Empirical estimation of uncertainty for clinical reliability

BACKGROUND AND OBJECTIVES

To develop a clinically reliable deep learning model to differentiate glioblastoma (GBM) from solitary brain metastasis (SBM) by providing predictive uncertainty estimates and interpretability.

METHODS

A total of 469 patients (300 GBM, 169 SBM) were enrolled in the institutional training set. Deep ensembles based on DenseNet121 were trained on multiparametric MRI. The model performance was validated in the external test set consisting of 143 patients (101 GBM, 42 SBM). Entropy values for each input were evaluated for uncertainty measurement; based on entropy values, the datasets were split to high- and low-uncertainty groups. In addition, entropy values of out-of-distribution (OOD) data from unknown class (257 patients with meningioma) were compared to assess uncertainty estimates of the model. The model interpretability was further evaluated by localization accuracy of the model.

RESULTS

On external test set, the area under the curve (AUC), accuracy, sensitivity and specificity of the deep ensembles were 0.83 (95 % confidence interval [CI] 0.76-0.90), 76.2 %, 54.8 % and 85.2 %, respectively. The performance was higher in the low-uncertainty group than in the high-uncertainty group, with AUCs of 0.91 (95 % CI 0.83-0.98) and 0.58 (95 % CI 0.44-0.71), indicating that assessment of uncertainty with entropy values ascertained reliable prediction in the low-uncertainty group. Further, deep ensembles classified a high proportion (90.7 %) of predictions on OOD data to be uncertain, showing robustness in dataset shift. Interpretability evaluated by localization accuracy provided further reliability in the "low-uncertainty and high-localization accuracy" subgroup, with an AUC of 0.98 (95 % CI 0.95-1.00).

CONCLUSIONS

Empirical assessment of uncertainty and interpretability in deep ensembles provides evidence for the robustness of prediction, offering a clinically reliable model in differentiating GBM from SBM.

Training and Comparison of nnU-Net and DeepMedic Methods for Autosegmentation of Pediatric Brain Tumors

BACKGROUND AND PURPOSE

Tumor segmentation is essential in surgical and treatment planning and response assessment and monitoring in pediatric brain tumors, the leading cause of cancer-related death among children. However, manual segmentation is time-consuming and has high interoperator variability, underscoring the need for more efficient methods. After training, we compared 2 deep-learning-based 3D segmentation models, DeepMedic and nnU-Net, with pediatric-specific multi-institutional brain tumor data based on multiparametric MR images.

MATERIALS AND METHODS

Multiparametric preoperative MR imaging scans of 339 pediatric patients (n = 293 internal and n = 46 external cohorts) with a variety of tumor subtypes were preprocessed and manually segmented into 4 tumor subregions, ie, enhancing tumor, nonenhancing tumor, cystic components, and peritumoral edema. After training, performances of the 2 models on internal and external test sets were evaluated with reference to ground truth manual segmentations. Additionally, concordance was assessed by comparing the volume of the subregions as a percentage of the whole tumor between model predictions and ground truth segmentations using the Pearson or Spearman correlation coefficients and the Bland-Altman method.

RESULTS

The mean Dice score for nnU-Net internal test set was 0.9 (SD, 0.07) (median, 0.94) for whole tumor; 0.77 (SD, 0.29) for enhancing tumor; 0.66 (SD, 0.32) for nonenhancing tumor; 0.71 (SD, 0.33) for cystic components, and 0.71 (SD, 0.40) for peritumoral edema, respectively. For DeepMedic, the mean Dice scores were 0.82 (SD, 0.16) for whole tumor; 0.66 (SD, 0.32) for enhancing tumor; 0.48 (SD, 0.27) for nonenhancing tumor; 0.48 (SD, 0.36) for cystic components, and 0.19 (SD, 0.33) for peritumoral edema, respectively. Dice scores were significantly higher for nnU-Net (P ≤ .01). Correlation coefficients for tumor subregion percentage volumes were higher (0.98 versus 0.91 for enhancing tumor, 0.97 versus 0.75 for nonenhancing tumor, 0.98 versus 0.80 for cystic components, 0.95 versus 0.33 for peritumoral edema in the internal test set). Bland-Altman plots were better for nnU-Net compared with DeepMedic. External validation of the trained nnU-Net model on the multi-institutional Brain Tumor Segmentation Challenge in Pediatrics (BraTS-PEDs) 2023 data set revealed high generalization capability in the segmentation of whole tumor, tumor core (a combination of enhancing tumor, nonenhancing tumor, and cystic components), and enhancing tumor with mean Dice scores of 0.87 (SD, 0.13) (median, 0.91), 0.83 (SD, 0.18) (median, 0.89), and 0.48 (SD, 0.38) (median, 0.58), respectively.

CONCLUSIONS

The pediatric-specific data-trained nnU-Net model is superior to DeepMedic for whole tumor and subregion segmentation of pediatric brain tumors.

Artificial Intelligence and Multiple Sclerosis

In this paper, we analyse the different advances in artificial intelligence (AI) approaches in multiple sclerosis (MS). AI applications in MS range across investigation of disease pathogenesis, diagnosis, treatment, and prognosis. A subset of AI, Machine learning (ML) models analyse various data sources, including magnetic resonance imaging (MRI), genetic, and clinical data, to distinguish MS from other conditions, predict disease progression, and personalize treatment strategies. Additionally, AI models have been extensively applied to lesion segmentation, identification of biomarkers, and prediction of outcomes, disease monitoring, and management. Despite the big promises of AI solutions, model interpretability and transparency remain critical for gaining clinician and patient trust in these methods. The future of AI in MS holds potential for open data initiatives that could feed ML models and increasing generalizability, the implementation of federated learning solutions for training the models addressing data sharing issues, and generative AI approaches to address challenges in model interpretability, and transparency. In conclusion, AI presents an opportunity to advance our understanding and management of MS. AI promises to aid clinicians in MS diagnosis and prognosis improving patient outcomes and quality of life, however ensuring the interpretability and transparency of AI-generated results is going to be key for facilitating the integration of AI into clinical practice.

Machine-Learning and Radiomics-Based Preoperative Prediction of Ki-67 Expression in Glioma Using MRI Data

BACKGROUND

Gliomas are the most common primary brain tumours and constitute approximately half of all malignant glioblastomas. Unfortunately, patients diagnosed with malignant glioblastomas typically survive for less than a year. In light of this circumstance, genotyping is an effective means of categorising gliomas. The Ki67 proliferation index, a widely used marker of cellular proliferation in clinical contexts, has demonstrated potential for predicting tumour classification and prognosis. In particular, magnetic resonance imaging (MRI) plays a vital role in the diagnosis of brain tumours. Using MRI to extract glioma-related features and construct a machine learning model offers a viable avenue to classify and predict the level of Ki67 expression.

METHODS

This study retrospectively collected MRI data and postoperative immunohistochemical results from 613 glioma patients from the First Affliated Hospital of Nanjing Medical University. Subsequently, we performed registration and skull stripping on the four MRI modalities: T1-weighted (T1), T2-weighted (T2), T1-weighted with contrast enhancement (T1CE), and Fluid Attenuated Inversion Recovery (FLAIR). Each modality's segmentation yielded three distinct tumour regions. Following segmentation, a comprehensive set of features encompassing texture, first-order, and shape attributes were extracted from these delineated regions. Feature selection was conducted using the least absolute shrinkage and selection operator (LASSO) algorithm with subsequent sorting to identify the most important features. These selected features were further analysed using correlation analysis to finalise the selection for machine learning model development. Eight models: logistic regression (LR), naive bayes, decision tree, gradient boosting tree, and support vector classification (SVM), random forest (RF), XGBoost, and LightGBM were used to objectively classify Ki67 expression.

RESULTS

In total, 613 patients were enroled in the study, and 24,455 radiomic features were extracted from each patient's MRI. These features were eventually reduced to 36 after LASSO screening, RF importance ranking, and correlation analysis. Among all the tested machine learning models, LR and linear SVM exhibited superior performance. LR achieved the highest area under the curve score of 0.912 ± 0.036, while linear SVM obtained the top accuracy with a score of 0.884 ± 0.031.

CONCLUSION

This study introduced a novel approach for classifying Ki67 expression levels using MRI, which has been proven to be highly effective. With the LR model at its core, our method demonstrated its potential in signalling a promising avenue for future research. This innovative approach of predicting Ki67 expression based on MRI features not only enhances our understanding of cell activity but also represents a significant leap forward in brain glioma research. This underscores the potential of integrating machine learning with medical imaging to aid in the diagnosis and prognosis of complex diseases.

Research Progress of Artificial Intelligence in the Grading and Classification of Meningiomas

A meningioma is a common primary central nervous system tumor. The histological features of meningiomas vary significantly depending on the grade and subtype, leading to differences in treatment and prognosis. Therefore, early diagnosis, grading, and typing of meningiomas are crucial for developing comprehensive and individualized diagnosis and treatment plans. The advancement of artificial intelligence (AI) in medical imaging, particularly radiomics and deep learning (DL), has contributed to the increasing research on meningioma grading and classification. These techniques are fast and accurate, involve fully automated learning, are non-invasive and objective, enable the efficient and non-invasive prediction of meningioma grades and classifications, and provide valuable assistance in clinical treatment and prognosis. This article provides a summary and analysis of the research progress in radiomics and DL for meningioma grading and classification. It also highlights the existing research findings, limitations, and suggestions for future improvement, aiming to facilitate the future application of AI in the diagnosis and treatment of meningioma.

Radiomics using multiparametric magnetic resonance imaging to predict postoperative visual outcomes of patients with pituitary adenoma

BACKGROUND

Preoperative prediction of visual outcomes following pituitary adenoma surgery is challenging yet crucial for clinical decision-making. We aimed to develop models using radiomics from multiparametric MRI to predict postoperative visual outcomes.

METHODS

A cohort of 152 patients with pituitary adenoma was retrospectively enrolled and divided into recovery and non-recovery groups based on visual examinations performed six months after surgery. Radiomic features of the optic chiasm were extracted from preoperative T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and contrast-enhanced T1-weighted imaging (T1CE). Predictive models were constructed using the least absolute shrinkage and selection operator wrapped with a support vector machine through five-fold cross-validation in the development cohort and evaluated in an independent test cohort. Model performance was evaluated using the area under the curve (AUC), accuracy, sensitivity, and specificity.

RESULTS

Four models were established based on radiomic features selected from individual or combined sequences. The AUC values of the models based on T1WI, T2WI and T1CE were 0.784, 0.724, 0.822 in the development cohort, and 0.767, 0.763, 0.794 in the independent test cohort. The multiparametric model demonstrated superior performance among the four models, with AUC of 0.851, accuracy of 0.832. sensitivity of 0.700, specificity of 0.910 in the development cohort, and AUC of 0.847, accuracy of 0.800, sensitivity of 0.882 and specificity of 0.750 in the independent test cohort.

CONCLUSION

The multiparametric model utilizing radiomics of optic chiasm outperformed single-sequence models in predicting postoperative visual recovery in patients with pituitary adenoma, serving as a novel approach for enhancing personalized treatment strategies.

Recent Outcomes and Challenges of Artificial Intelligence, Machine Learning, and Deep Learning in Neurosurgery

Neurosurgeons receive extensive technical training, which equips them with the knowledge and skills to specialise in various fields and manage the massive amounts of information and decision-making required throughout the various stages of neurosurgery, including preoperative, intraoperative, and postoperative care and recovery. Over the past few years, artificial intelligence (AI) has become more useful in neurosurgery. AI has the potential to improve patient outcomes by augmenting the capabilities of neurosurgeons and ultimately improving diagnostic and prognostic outcomes as well as decision-making during surgical procedures. By incorporating AI into both interventional and non-interventional therapies, neurosurgeons may provide the best care for their patients. AI, machine learning (ML), and deep learning (DL) have made significant progress in the field of neurosurgery. These cutting-edge methods have enhanced patient outcomes, reduced complications, and improved surgical planning.

Role of artificial intelligence in brain tumour imaging

Artificial intelligence (AI) is a rapidly evolving field with many neuro-oncology applications. In this review, we discuss how AI can assist in brain tumour imaging, focusing on machine learning (ML) and deep learning (DL) techniques. We describe how AI can help in lesion detection, differential diagnosis, anatomic segmentation, molecular marker identification, prognostication, and pseudo-progression evaluation. We also cover AI applications in non-glioma brain tumours, such as brain metastasis, posterior fossa, and pituitary tumours. We highlight the challenges and limitations of AI implementation in radiology, such as data quality, standardization, and integration. Based on the findings in the aforementioned areas, we conclude that AI can potentially improve the diagnosis and treatment of brain tumours and provide a path towards personalized medicine and better patient outcomes.

Uses of artificial intelligence in glioma: A systematic review

Glioma is the most prevalent type of primary brain tumor in adults. The use of artificial intelligence (AI) in glioma is increasing and has exhibited promising results. The present study performed a systematic review of the applications of AI in glioma as regards diagnosis, grading, prediction of genotype, progression and treatment response using different databases. The aim of the present study was to demonstrate the trends (main directions) of the recent applications of AI within the field of glioma, and to highlight emerging challenges in integrating AI within clinical practice. A search in four databases (Scopus, PubMed, Wiley and Google Scholar) yielded a total of 42 articles specifically using AI in glioma and glioblastoma. The articles were retrieved and reviewed, and the data were summarized and analyzed. The majority of the articles were from the USA (n=18) followed by China (n=11). The number of articles increased by year reaching the maximum number in 2022. The majority of the articles studied glioma as opposed to glioblastoma. In terms of grading, the majority of the articles were about both low-grade glioma (LGG) and high-grade glioma (HGG) (n=23), followed by HGG/glioblastoma (n=13). Additionally, three articles were about LGG only; two articles did not specify the grade. It was found that one article had the highest sample size among the other studies, reaching 897 samples. Despite the limitations and challenges that face AI, the use of AI in glioma has increased in recent years with promising results, with a variety of applications ranging from diagnosis, grading, prognosis prediction, and reaching to treatment and post-operative care.

The University of California San Francisco Adult Longitudinal Post-Treatment Diffuse Glioma MRI Dataset

Supplemental material is available for this article.

The Current Diagnostic Performance of MRI-Based Radiomics for Glioma Grading: A Meta-Analysis

BACKGROUND

Multiple radiomics models have been proposed for grading glioma using different algorithms, features, and sequences of magnetic resonance imaging. The research seeks to assess the present overall performance of radiomics for grading glioma.

METHODS

A systematic literature review of the databases Ovid MEDLINE PubMed, and Ovid EMBASE for publications published on radiomics for glioma grading between 2012 and 2023 was performed. The systematic review was carried out following the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analysis.

RESULTS

In the meta-analysis, a total of 7654 patients from 40 articles, were assessed. R-package mada was used for modeling the joint estimates of specificity (SPE) and sensitivity (SEN). Pooled event rates across studies were performed with a random-effects meta-analysis. The heterogeneity of SPE and SEN were based on the χ2 test. Overall values for SPE and SEN in the differentiation between high-grade gliomas (HGGs) and low-grade gliomas (LGGs) were 84% and 91%, respectively. With regards to the discrimination between World Health Organization (WHO) grade 4 and WHO grade 3, the overall SPE was 81% and the SEN was 89%. The modern non-linear classifiers showed a better trend, whereas textural features tend to be the best-performing (29%) and the most used.

CONCLUSIONS

Our findings confirm that present radiomics' diagnostic performance for glioma grading is superior in terms of SEN and SPE for the HGGs vs. LGGs discrimination task when compared to the WHO grade 4 vs. 3 task.

AI-based classification of three common malignant tumors in neuro-oncology: A multi-institutional comparison of machine learning and deep learning methods

PURPOSE

To determine if machine learning (ML) or deep learning (DL) pipelines perform better in AI-based three-class classification of glioblastoma (GBM), intracranial metastatic disease (IMD) and primary CNS lymphoma (PCNSL).

METHODOLOGY

Retrospective analysis included 502 cases for training (208 GBM, 67 PCNSL and 227 IMD), with external validation on 86 cases (27:27:32). Multiparametric MRI images (T1W, T2W, FLAIR, DWI and T1-CE) were co-registered, resampled, denoised and intensity normalized, followed by semiautomatic 3D segmentation of the enhancing tumor (ET) and peritumoral region (PTR). Model performance was assessed using several ML pipelines and 3D-convolutional neural networks (3D-CNN) using sequence specific masks, as well as combination of masks. All pipelines were trained and evaluated with 5-fold nested cross-validation on internal data followed by external validation using multi-class AUC.

RESULTS

Two ML models achieved similar performance on test set, one using T2-ET and T2-PTR masks (AUC: 0.885, 95% CI: [0.816, 0.935] and another using T1-CE-ET and FLAIR-PTR mask (AUC: 0.878, CI: [0.804, 0.930]). The best performing DL models achieved an AUC of 0.854, (CI [0.774, 0.914]) on external data using T1-CE-ET and T2-PTR masks, followed by model derived from T1-CE-ET, ADC-ET and FLAIR-PTR masks (AUC: 0.851, CI [0.772, 0.909]).

CONCLUSION

Both ML and DL derived pipelines achieved similar performance. T1-CE mask was used in three of the top four overall models. Additionally, all four models had some mask derived from PTR, either T2WI or FLAIR.

Tinnitus classification based on resting-state functional connectivity using a convolutional neural network architecture

OBJECTIVES

Many studies have investigated aberrant functional connectivity (FC) using resting-state functional MRI (rs-fMRI) in subjective tinnitus patients. However, no studies have verified the efficacy of resting-state FC as a diagnostic imaging marker. We established a convolutional neural network (CNN) model based on rs-fMRI FC to distinguish tinnitus patients from healthy controls, providing guidance and fast diagnostic tools for the clinical diagnosis of subjective tinnitus.

METHODS

A CNN architecture was trained on rs-fMRI data from 100 tinnitus patients and 100 healthy controls using an asymmetric convolutional layer. Additionally, a traditional machine learning model and a transfer learning model were included for comparison with the CNN, and each of the three models was tested on three different brain atlases.

RESULTS

Of the three models, the CNN model outperformed the other two models with the highest area under the curve, especially on the Dos_160 atlas (AUC = 0.944). Meanwhile, the model with the best classification performance highlights the crucial role of the default mode network, salience network, and sensorimotor network in distinguishing between normal controls and patients with subjective tinnitus.

CONCLUSION

Our CNN model could appropriately tackle the diagnosis of tinnitus patients using rs-fMRI and confirmed the diagnostic value of FC as measured by rs-fMRI.

Artificial intelligence in lung cancer screening: Detection, classification, prediction, and prognosis

BACKGROUND

The exceptional capabilities of artificial intelligence (AI) in extracting image information and processing complex models have led to its recognition across various medical fields. With the continuous evolution of AI technologies based on deep learning, particularly the advent of convolutional neural networks (CNNs), AI presents an expanded horizon of applications in lung cancer screening, including lung segmentation, nodule detection, false-positive reduction, nodule classification, and prognosis.

METHODOLOGY

This review initially analyzes the current status of AI technologies. It then explores the applications of AI in lung cancer screening, including lung segmentation, nodule detection, and classification, and assesses the potential of AI in enhancing the sensitivity of nodule detection and reducing false-positive rates. Finally, it addresses the challenges and future directions of AI in lung cancer screening.

RESULTS

AI holds substantial prospects in lung cancer screening. It demonstrates significant potential in improving nodule detection sensitivity, reducing false-positive rates, and classifying nodules, while also showing value in predicting nodule growth and pathological/genetic typing.

CONCLUSIONS

AI offers a promising supportive approach to lung cancer screening, presenting considerable potential in enhancing nodule detection sensitivity, reducing false-positive rates, and classifying nodules. However, the universality and interpretability of AI results need further enhancement. Future research should focus on the large-scale validation of new deep learning-based algorithms and multi-center studies to improve the efficacy of AI in lung cancer screening.

Tumour Size and Overall Survival in a Cohort of Patients with Unifocal Glioblastoma: A Uni- and Multivariable Prognostic Modelling and Resampling Study

Published models inconsistently associate glioblastoma size with overall survival (OS). This study aimed to investigate the prognostic effect of tumour size in a large cohort of patients diagnosed with GBM and interrogate how sample size and non-linear transformations may impact on the likelihood of finding a prognostic effect. In total, 279 patients with a IDH-wildtype unifocal WHO grade 4 GBM between 2014 and 2020 from a retrospective cohort were included. Uni-/multivariable association between core volume, whole volume (CV and WV), and diameter with OS was assessed with (1) Cox proportional hazard models +/- log transformation and (2) resampling with 1,000,000 repetitions and varying sample size to identify the percentage of models, which showed a significant effect of tumour size. Models adjusted for operation type and a diameter model adjusted for all clinical variables remained significant (p = 0.03). Multivariable resampling increased the significant effects (p < 0.05) of all size variables as sample size increased. Log transformation also had a large effect on the chances of a prognostic effect of WV. For models adjusted for operation type, 19.5% of WV vs. 26.3% log-WV (n = 50) and 69.9% WV and 89.9% log-WV (n = 279) were significant. In this large well-curated cohort, multivariable modelling and resampling suggest tumour volume is prognostic at larger sample sizes and with log transformation for WV.

Diffusion-weighted imaging-based radiomics model using automatic machine learning to differentiate cerebral cystic metastases from brain abscesses

OBJECTIVES

To develop a radiomics model based on diffusion-weighted imaging (DWI) utilizing automated machine learning method to differentiate cerebral cystic metastases from brain abscesses.

MATERIALS AND METHODS

A total of 186 patients with cerebral cystic metastases (n = 98) and brain abscesses (n = 88) from two clinical institutions were retrospectively included. The datasets (129 from institution A) were randomly portioned into separate 75% training and 25% internal testing sets. Radiomics features were extracted from DWI images using two subregions of the lesion (cystic core and solid wall). A thorough image preprocessing method was applied to DWI images to ensure the robustness of radiomics features before feature extraction. Then the Tree-based Pipeline Optimization Tool (TPOT) was utilized to search for the best optimized machine learning pipeline, using a fivefold cross-validation in the training set. The external test set (57 from institution B) was used to evaluate the model's performance.

RESULTS

Seven distinct TPOT models were optimized to distinguish between cerebral cystic metastases and abscesses either based on different features combination or using wavelet transform. The optimal model demonstrated an AUC of 1.00, an accuracy of 0.97, sensitivity of 1.00, and specificity of 0.93 in the internal test set, based on the combination of cystic core and solid wall radiomics signature using wavelet transform. In the external test set, this model reached 1.00 AUC, 0.96 accuracy, 1.00 sensitivity, and 0.93 specificity.

CONCLUSION

The DWI-based radiomics model established by TPOT exhibits a promising predictive capacity in distinguishing cerebral cystic metastases from abscesses.

Artificial intelligence-based MRI radiomics and radiogenomics in glioma

The specific genetic subtypes that gliomas exhibit result in variable clinical courses and the need to involve multidisciplinary teams of neurologists, epileptologists, neurooncologists and neurosurgeons. Currently, the diagnosis of gliomas pivots mainly around the preliminary radiological findings and the subsequent definitive surgical diagnosis (via surgical sampling). Radiomics and radiogenomics present a potential to precisely diagnose and predict survival and treatment responses, via morphological, textural, and functional features derived from MRI data, as well as genomic data. In spite of their advantages, it is still lacking standardized processes of feature extraction and analysis methodology among different research groups, which have made external validations infeasible. Radiomics and radiogenomics can be used to better understand the genomic basis of gliomas, such as tumor spatial heterogeneity, treatment response, molecular classifications and tumor microenvironment immune infiltration. These novel techniques have also been used to predict histological features, grade or even overall survival in gliomas. In this review, workflows of radiomics and radiogenomics are elucidated, with recent research on machine learning or artificial intelligence in glioma.

Artificial Intelligence Imaging for Predicting High-risk Molecular Markers of Gliomas

Gliomas, the most prevalent primary malignant tumors of the central nervous system, present significant challenges in diagnosis and prognosis. The fifth edition of the World Health Organization Classification of Tumors of the Central Nervous System (WHO CNS5) published in 2021, has emphasized the role of high-risk molecular markers in gliomas. These markers are crucial for enhancing glioma grading and influencing survival and prognosis. Noninvasive prediction of these high-risk molecular markers is vital. Genetic testing after biopsy, the current standard for determining molecular type, is invasive and time-consuming. Magnetic resonance imaging (MRI) offers a non-invasive alternative, providing structural and functional insights into gliomas. Advanced MRI methods can potentially reflect the pathological characteristics associated with glioma molecular markers; however, they struggle to fully represent gliomas' high heterogeneity. Artificial intelligence (AI) imaging, capable of processing vast medical image datasets, can extract critical molecular information. AI imaging thus emerges as a noninvasive and efficient method for identifying high-risk molecular markers in gliomas, a recent focus of research. This review presents a comprehensive analysis of AI imaging's role in predicting glioma high-risk molecular markers, highlighting challenges and future directions.

A large open access dataset of brain metastasis 3D segmentations on MRI with clinical and imaging information

Resection and whole brain radiotherapy (WBRT) are standard treatments for brain metastases (BM) but are associated with cognitive side effects. Stereotactic radiosurgery (SRS) uses a targeted approach with less side effects than WBRT. SRS requires precise identification and delineation of BM. While artificial intelligence (AI) algorithms have been developed for this, their clinical adoption is limited due to poor model performance in the clinical setting. The limitations of algorithms are often due to the quality of datasets used for training the AI network. The purpose of this study was to create a large, heterogenous, annotated BM dataset for training and validation of AI models. We present a BM dataset of 200 patients with pretreatment T1, T1 post-contrast, T2, and FLAIR MR images. The dataset includes contrast-enhancing and necrotic 3D segmentations on T1 post-contrast and peritumoral edema 3D segmentations on FLAIR. Our dataset contains 975 contrast-enhancing lesions, many of which are sub centimeter, along with clinical and imaging information. We used a streamlined approach to database-building through a PACS-integrated segmentation workflow.

A subregion-based RadioFusionOmics model discriminates between grade 4 astrocytoma and glioblastoma on multisequence MRI

PURPOSE

To explore a subregion-based RadioFusionOmics (RFO) model for discrimination between adult-type grade 4 astrocytoma and glioblastoma according to the 2021 WHO CNS5 classification.

METHODS

329 patients (40 grade 4 astrocytomas and 289 glioblastomas) with histologic diagnosis was retrospectively collected from our local institution and The Cancer Imaging Archive (TCIA). The volumes of interests (VOIs) were obtained from four multiparametric MRI sequences (T1WI, T1WI + C, T2WI, T2-FLAIR) using (1) manual segmentation of the non-enhanced tumor (nET), enhanced tumor (ET), and peritumoral edema (pTE), and (2) K-means clustering of four habitats (H1: high T1WI + C, high T2-FLAIR; (2) H2: high T1WI + C, low T2-FLAIR; (3) H3: low T1WI + C, high T2-FLAIR; and (4) H4: low T1WI + C, low T2-FLAIR). The optimal VOI and best MRI sequence combination were determined. The performance of the RFO model was evaluated using the area under the precision-recall curve (AUPRC) and the best signatures were identified.

RESULTS

The two best VOIs were manual VOI3 (putative peritumoral edema) and clustering H34 (low T1WI + C, high T2-FLAIR (H3) combined with low T1WI + C and low T2-FLAIR (H4)). Features fused from four MRI sequences ([Formula: see text]) outperformed those from either a single sequence or other sequence combinations. The RFO model that was trained using fused features [Formula: see text] achieved the AUPRC of 0.972 (VOI3) and 0.976 (H34) in the primary cohort (p = 0.905), and 0.971 (VOI3) and 0.974 (H34) in the testing cohort (p = 0.402).

CONCLUSION

The performance of subregions defined by clustering was comparable to that of subregions that were manually defined. Fusion of features from the edematous subregions of multiple MRI sequences by the RFO model resulted in differentiation between grade 4 astrocytoma and glioblastoma.

A clinically relevant computed tomography (CT) radiomics strategy for intracranial rodent brain tumour monitoring

Here, we establish a CT-radiomics based method for application in invasive, orthotopic rodent brain tumour models. Twenty four NOD/SCID mice were implanted with U87R-Luc2 GBM cells and longitudinally imaged via contrast enhanced (CE-CT) imaging. Pyradiomics was employed to extract CT-radiomic features from the tumour-implanted hemisphere and non-tumour-implanted hemisphere of acquired CT-scans. Inter-correlated features were removed (Spearman correlation > 0.85) and remaining features underwent predictive analysis (recursive feature elimination or Boruta algorithm). An area under the curve of the receiver operating characteristic curve was implemented to evaluate radiomic features for their capacity to predict defined outcomes. Firstly, we identified a subset of radiomic features which distinguish the tumour-implanted hemisphere and non- tumour-implanted hemisphere (i.e, tumour presence from normal tissue). Secondly, we successfully translate preclinical CT-radiomic pipelines to GBM patient CT scans (n = 10), identifying similar trends in tumour-specific feature intensities (E.g. 'glszm Zone Entropy'), thereby suggesting a mouse-to-human species conservation (a conservation of radiomic features across species). Thirdly, comparison of features across timepoints identify features which support preclinical tumour detection earlier than is possible by visual assessment of CT scans. This work establishes robust, preclinical CT-radiomic pipelines and describes the application of CE-CT for in-depth orthotopic brain tumour monitoring. Overall we provide evidence for the role of pre-clinical 'discovery' radiomics in the neuro-oncology space.

Artificial Intelligence Analysis Using MRI and PET Imaging in Gliomas: A Narrative Review

The lack of early detection and a high rate of recurrence/progression after surgery are defined as the most common causes of a very poor prognosis of Gliomas. The developments of quantification systems with special regards to artificial intelligence (AI) on medical images (CT, MRI, PET) are under evaluation in the clinical and research context in view of several applications providing different information related to the reconstruction of imaging, the segmentation of tissues acquired, the selection of features, and the proper data analyses. Different approaches of AI have been proposed as the machine and deep learning, which utilize artificial neural networks inspired by neuronal architectures. In addition, new systems have been developed using AI techniques to offer suggestions or make decisions in medical diagnosis, emulating the judgment of radiologist experts. The potential clinical role of AI focuses on the prediction of disease progression in more aggressive forms in gliomas, differential diagnosis (pseudoprogression vs. proper progression), and the follow-up of aggressive gliomas. This narrative Review will focus on the available applications of AI in brain tumor diagnosis, mainly related to malignant gliomas, with particular attention to the postoperative application of MRI and PET imaging, considering the current state of technical approach and the evaluation after treatment (including surgery, radiotherapy/chemotherapy, and prognostic stratification).

Prediction of MGMT promotor methylation status in glioblastoma by contrast-enhanced T1-weighted intensity image

Background

The study aims to explore MRI phenotypes that predict glioblastoma's (GBM) methylation status of the promoter region of MGMT gene (pMGMT) by qualitatively assessing contrast-enhanced T1-weighted intensity images.

Methods

A total of 193 histologically and molecularly confirmed GBMs at the Kansai Network for Molecular Diagnosis of Central Nervous Tumors (KANSAI) were used as an exploratory cohort. From the Cancer Imaging Archive/Cancer Genome Atlas (TCGA) 93 patients were used as validation cohorts. "Thickened structure" was defined as the solid tumor component presenting circumferential extension or occupying >50% of the tumor volume. "Methylated contrast phenotype" was defined as indistinct enhancing circumferential border, heterogenous enhancement, or nodular enhancement. Inter-rater agreement was assessed, followed by an investigation of the relationship between radiological findings and pMGMT methylation status.

Results

Fleiss's Kappa coefficient for "Thickened structure" was 0.68 for the exploratory and 0.55 for the validation cohort, and for "Methylated contrast phenotype," 0.30 and 0.39, respectively. The imaging feature, the presence of "Thickened structure" and absence of "Methylated contrast phenotype," was significantly predictive of pMGMT unmethylation both for the exploratory (p = .015, odds ratio = 2.44) and for the validation cohort (p = .006, odds ratio = 7.83). The sensitivities and specificities of the imaging feature, the presence of "Thickened structure," and the absence of "Methylated contrast phenotype" for predicting pMGMT unmethylation were 0.29 and 0.86 for the exploratory and 0.25 and 0.96 for the validation cohort.

Conclusions

The present study showed that qualitative assessment of contrast-enhanced T1-weighted intensity images helps predict GBM's pMGMT methylation status.

Biomedical Big Data Technologies, Applications, and Challenges for Precision Medicine: A Review

The explosive growth of biomedical Big Data presents both significant opportunities and challenges in the realm of knowledge discovery and translational applications within precision medicine. Efficient management, analysis, and interpretation of big data can pave the way for groundbreaking advancements in precision medicine. However, the unprecedented strides in the automated collection of large-scale molecular and clinical data have also introduced formidable challenges in terms of data analysis and interpretation, necessitating the development of novel computational approaches. Some potential challenges include the curse of dimensionality, data heterogeneity, missing data, class imbalance, and scalability issues. This overview article focuses on the recent progress and breakthroughs in the application of big data within precision medicine. Key aspects are summarized, including content, data sources, technologies, tools, challenges, and existing gaps. Nine fields-Datawarehouse and data management, electronic medical record, biomedical imaging informatics, Artificial intelligence-aided surgical design and surgery optimization, omics data, health monitoring data, knowledge graph, public health informatics, and security and privacy-are discussed.

Utility of machine learning for identifying stapes fixation on ultra-high-resolution CT

PURPOSE

Imaging diagnosis of stapes fixation (SF) is challenging owing to a lack of definite evidence. We developed a comprehensive machine learning (ML) model to identify SF on ultra-high-resolution CT.

MATERIALS AND METHODS

We retrospectively enrolled 109 participants (143 ears) and divided them into the training set (115 ears) and test set (28 ears). Stapes mobility (SF or non-SF) was determined by surgical inspection. In the ML analysis, rectangular regions of interest were placed on consecutive axial slices in the training set. Radiomic features were extracted and fed into the training session. The test set was analyzed using 7 ML models (support vector machine, k nearest neighbor, decision tree, random forest, extra trees, eXtreme Gradient Boosting, and Light Gradient Boosting Machine) and by 2 dedicated neuroradiologists. Diagnostic performance (sensitivity, specificity and accuracy, with surgical findings as the reference) was compared between the radiologists and the optimal ML model by using the McNemar test.

RESULTS

The mean age of the participants was 42.3 ± 17.5 years. The Light Gradient Boosting Machine (LightGBM) model showed the highest sensitivity (0.83), specificity (0.81), accuracy (0.82) and area under the curve (0.88) for detecting SF among the 7 ML models. The neuroradiologists achieved good sensitivities (0.75 and 0.67), moderate-to-good specificities (0.63 and 0.56) and good accuracies (0.68 and 0.61). This model showed no statistical differences with the neuroradiologists (P values 0.289-1.000).

CONCLUSIONS

Compared to the neuroradiologists, the LightGBM model achieved competitive diagnostic performance in identifying SF, and has the potential to be a supportive tool in clinical practice.

Automated Determination of the H3 K27-Altered Status in Spinal Cord Diffuse Midline Glioma by Radiomics Based on T2-Weighted MR Images

BACKGROUND AND PURPOSE

Conventional MR imaging is not sufficient to discern the H3 K27-altered status of spinal cord diffuse midline glioma. This study aimed to develop a radiomics-based model based on preoperative T2WI to determine the H3 K27-altered status of spinal cord diffuse midline glioma.

MATERIALS AND METHODS

Ninety-seven patients with confirmed spinal cord diffuse midline gliomas were retrospectively recruited and randomly assigned to the training (n = 67) and test (n = 30) sets. One hundred seven radiomics features were initially extracted from automatically-segmented tumors on T2WI, then 11 features selected by the Pearson correlation coefficient and the Kruskal-Wallis test were used to train and test a logistic regression model for predicting the H3 K27-altered status. Sensitivity analysis was performed using additional random splits of the training and test sets, as well as applying other classifiers for comparison. The performance of the model was evaluated through its accuracy, sensitivity, specificity, and area under the curve. Finally, a prospective set including 28 patients with spinal cord diffuse midline gliomas was used to validate the logistic regression model independently.

RESULTS

The logistic regression model accurately predicted the H3 K27-altered status with accuracies of 0.833 and 0.786, sensitivities of 0.813 and 0.750, specificities of 0.857 and 0.833, and areas under the curve of 0.839 and 0.818 in the test and prospective sets, respectively. Sensitivity analysis confirmed the robustness of the model, with predictive accuracies of 0.767-0.833.

CONCLUSIONS

Radiomics signatures based on preoperative T2WI could accurately predict the H3 K27-altered status of spinal cord diffuse midline glioma, providing potential benefits for clinical management.

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.

Advances in diffuse glial tumors diagnosis

In recent decades, there have been significant advances in the diagnosis of diffuse gliomas, driven by the integration of novel technologies. These advancements have deepened our understanding of tumor oncogenesis, enabling a more refined stratification of the biological behavior of these neoplasms. This progress culminated in the fifth edition of the WHO classification of central nervous system (CNS) tumors in 2021. This comprehensive review article aims to elucidate these advances within a multidisciplinary framework, contextualized within the backdrop of the new classification. This article will explore morphologic pathology and molecular/genetics techniques (immunohistochemistry, genetic sequencing, and methylation profiling), which are pivotal in diagnosis, besides the correlation of structural neuroimaging radiophenotypes to pathology and genetics. It briefly reviews the usefulness of tractography and functional neuroimaging in surgical planning. Additionally, the article addresses the value of other functional imaging techniques such as perfusion MRI, spectroscopy, and nuclear medicine in distinguishing tumor progression from treatment-related changes. Furthermore, it discusses the advantages of evolving diagnostic techniques in classifying these tumors, as well as their limitations in terms of availability and utilization. Moreover, the expanding domains of data processing, artificial intelligence, radiomics, and radiogenomics hold great promise and may soon exert a substantial influence on glioma diagnosis. These innovative technologies have the potential to revolutionize our approach to these tumors. Ultimately, this review underscores the fundamental importance of multidisciplinary collaboration in employing recent diagnostic advancements, thereby hoping to translate them into improved quality of life and extended survival for glioma patients.

Artificial intelligence in neuroimaging of brain tumors: reality or still promise?

PURPOSE OF REVIEW

To provide an updated overview of artificial intelligence (AI) applications in neuro-oncologic imaging and discuss current barriers to wider clinical adoption.

RECENT FINDINGS

A wide variety of AI applications in neuro-oncologic imaging have been developed and researched, spanning tasks from pretreatment brain tumor classification and segmentation, preoperative planning, radiogenomics, prognostication and survival prediction, posttreatment surveillance, and differentiating between pseudoprogression and true disease progression. While earlier studies were largely based on data from a single institution, more recent studies have demonstrated that the performance of these algorithms are also effective on external data from other institutions. Nevertheless, most of these algorithms have yet to see widespread clinical adoption, given the lack of prospective studies demonstrating their efficacy and the logistical difficulties involved in clinical implementation.

SUMMARY

While there has been significant progress in AI and neuro-oncologic imaging, clinical utility remains to be demonstrated. The next wave of progress in this area will be driven by prospective studies measuring outcomes relevant to clinical practice and go beyond retrospective studies which primarily aim to demonstrate high performance.

Polygenic Risk Score for Cardiovascular Diseases in Artificial Intelligence Paradigm: A Review

Cardiovascular disease (CVD) related mortality and morbidity heavily strain society. The relationship between external risk factors and our genetics have not been well established. It is widely acknowledged that environmental influence and individual behaviours play a significant role in CVD vulnerability, leading to the development of polygenic risk scores (PRS). We employed the PRISMA search method to locate pertinent research and literature to extensively review artificial intelligence (AI)-based PRS models for CVD risk prediction. Furthermore, we analyzed and compared conventional vs. AI-based solutions for PRS. We summarized the recent advances in our understanding of the use of AI-based PRS for risk prediction of CVD. Our study proposes three hypotheses: i) Multiple genetic variations and risk factors can be incorporated into AI-based PRS to improve the accuracy of CVD risk predicting. ii) AI-based PRS for CVD circumvents the drawbacks of conventional PRS calculators by incorporating a larger variety of genetic and non-genetic components, allowing for more precise and individualised risk estimations. iii) Using AI approaches, it is possible to significantly reduce the dimensionality of huge genomic datasets, resulting in more accurate and effective disease risk prediction models. Our study highlighted that the AI-PRS model outperformed traditional PRS calculators in predicting CVD risk. Furthermore, using AI-based methods to calculate PRS may increase the precision of risk predictions for CVD and have significant ramifications for individualized prevention and treatment plans.

Feature pyramid network-based computer-aided detection and monitoring treatment response of brain metastases on contrast-enhanced MRI

AIM

To investigate the value of feature pyramid network (FPN)-based computer-aided detection (CAD) of brain metastases (BMs) before and after non-surgical treatment, and to evaluate its performance in monitoring treatment response of BM on contrast-enhanced (CE) magnetic resonance imaging (MRI).

MATERIAL AND METHODS

Eighty-five cancer patients newly diagnosed with BM who had undergone initial and follow-up three-dimensional (3D) CE MRI at Liaocheng People's Hospital were included retrospectively in this study. Manual detection (MD) was performed by reviewer 1. Computer-aided detection (CAD) was performed by reviewer 2 using uAI Discover-BMs software. The treatment response was assessed by the two reviewers for each patient separately. A paired chi-square test was used to compare the differences in the detection of BM between MD and CAD. Agreement between MD and CAD in monitoring treatment response was assessed by kappa test.

RESULTS

The sensitivities of MD and CAD on initial 3D CE MRI were 78.65% and 99.13%, respectively. The sensitivities of MD and CAD on follow-up 3D CE MRI were 76.32% and 98.24%, respectively. There was a very good agreement between Reviewer 1 and Reviewer 2 in evaluating the treatment response of BM.

CONCLUSION

FPN-based CAD has a higher sensitivity of close to 100% and lower false negatives (FNs) for BM detection, compared to MD. Although CAD had a few shortcomings in reflecting changes of BMs after treatment, it had high performance in monitoring treatment response of BM on CE MRI.

Prediction of the mean transit time using machine learning models based on radiomics features from digital subtraction angiography in moyamoya disease or moyamoya syndrome-a development and validation model study

Background

Digital subtraction angiography (DSA) is an important technique for diagnosis of moyamoya disease (MMD) or moyamoya syndrome (MMS), and computed tomography perfusion (CTP) is essential for assessing intracranial blood supply. The aim of this study was to assess whether radiomics features based on images of DSA could predict the mean transit time (MTT; outcome of CTP) using machine learning models.

Methods

The DSA images and MTT values of adult patients with MMD or MMS, according to the diagnostic guidelines for MMD, as well as control cases, were retrospectively collected in the Guangdong Provincial People's Hospital between January 2018 and December 2020. A total of 93 features were extracted from the images of each case through 3-dimensional (3D) slicer. After features preprocessing and filtering, 3-4 features were selected by the least absolute shrinkage and selection operator (LASSO) regression algorithm. Prediction models were established using random forest (RF) and support vector machine (SVM) for MTT values. Single-factor receiver operating characteristic (ROC) curve analysis and partial-dependence (PD) profiles were conducted to investigate selected features and prediction models.

Results

Our results showed that prediction models based on RF models had the best performance in frontal lobe {area under the curve (AUC) [95% confidence interval (CI)] =1.000 (1.000-1.000)], parietal lobe [AUC (95% CI) =1.000 (1.000-1.000)], and basal ganglia/thalamus [AUC (95% CI) =0.922 (0.797-1.000)] in the test set, whereas the SVM model performed the best in the temporal lobe [AUC (95% CI) =0.962 (0.876-1.000)] in the test set. The AUC values in the test set were greater than 0.9. The PD profiles showed good robustness and consistency.

Conclusions

Prediction models based on radiomics features extracted from DSA images demonstrate excellent performance in predicting MTT in patients with MMD or MMS, which may provide guidance for future clinical practice.

A Large Open Access Dataset of Brain Metastasis 3D Segmentations with Clinical and Imaging Feature Information

Resection and whole brain radiotherapy (WBRT) are the standards of care for the treatment of patients with brain metastases (BM) but are often associated with cognitive side effects. Stereotactic radiosurgery (SRS) involves a more targeted treatment approach and has been shown to avoid the side effects associated with WBRT. However, SRS requires precise identification and delineation of BM. While many AI algorithms have been developed for this purpose, their clinical adoption has been limited due to poor model performance in the clinical setting. Major reasons for non-generalizable algorithms are the limitations in the datasets used for training the AI network. The purpose of this study was to create a large, heterogenous, annotated BM dataset for training and validation of AI models to improve generalizability. We present a BM dataset of 200 patients with pretreatment T1, T1 post-contrast, T2, and FLAIR MR images. The dataset includes contrast-enhancing and necrotic 3D segmentations on T1 post-contrast and whole tumor (including peritumoral edema) 3D segmentations on FLAIR. Our dataset contains 975 contrast-enhancing lesions, many of which are sub centimeter, along with clinical and imaging feature information. We used a streamlined approach to database-building leveraging a PACS-integrated segmentation workflow.

Current state of radiomics in pediatric neuro-oncology practice: a systematic review

BACKGROUND

Radiomics is the process of converting radiological images into high-dimensional data that may be used to create machine learning models capable of predicting clinical outcomes, such as disease progression, treatment response and survival. Pediatric central nervous system (CNS) tumors differ from adult CNS tumors in terms of their tissue morphology, molecular subtype and textural features. We set out to appraise the current impact of this technology in clinical pediatric neuro-oncology practice.

OBJECTIVES

The aims of the study were to assess radiomics' current impact and potential utility in pediatric neuro-oncology practice; to evaluate the accuracy of radiomics-based machine learning models and compare this to the current standard which is stereotactic brain biopsy; and finally, to identify the current limitations of radiomics applications in pediatric neuro-oncology.

MATERIALS AND METHODS

Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) standards, a systematic review of the literature was carried out with protocol number CRD42022372485 in the prospective register of systematic reviews (PROSPERO). We performed a systematic literature search via PubMed, Embase, Web of Science and Google Scholar. Studies involving CNS tumors, studies that utilized radiomics and studies involving pediatric patients (age<18 years) were included. Several parameters were collected including imaging modality, sample size, image segmentation technique, machine learning model used, tumor type, radiomics utility, model accuracy, radiomics quality score and reported limitations.

RESULTS

The study included a total of 17 articles that underwent full-text review, after excluding duplicates, conference abstracts and studies that did not meet the inclusion criteria. The most commonly used machine learning models were support vector machines (n=7) and random forests (n=6), with an area under the curve (AUC) range of 0.60-0.94. The included studies investigated several pediatric CNS tumors, with ependymoma and medulloblastoma being the most frequently studied. Radiomics was primarily used for lesion identification, molecular subtyping, survival prognostication and metastasis prediction in pediatric neuro-oncology. The low sample size of studies was a commonly reported limitation.

CONCLUSION

The current state of radiomics in pediatric neuro-oncology is promising, in terms of distinguishing between tumor types; however, its utility in response assessment requires further evaluation which, given the relatively low number of pediatric tumors, calls for multicenter collaboration.

Deep learning-based reconstruction for canine brain magnetic resonance imaging could improve image quality while reducing scan time

Optimal magnetic resonance imaging (MRI) quality and shorter scan time are challenging to achieve in veterinary practices. Recently, deep learning-based reconstruction (DLR) has been proposed for ideal image quality. We hypothesized that DLR-based MRI will improve brain imaging quality and reduce scan time. This prospective, methods comparison study compared the MR image denoising performances of DLR and conventional methods, with the aim of reducing scan time and improving canine brain image quality. Transverse T2-weighted and fluid-attenuated inversion recovery (FLAIR) sequences of the brain were performed in 12 clinically healthy beagle dogs. Different numbers of excitations (NEX) were used to obtain the image groups NEX4, NEX2, and NEX1. DLR was applied to NEX2 and NEX1 to obtain NEX2DL and NEX1DL . The scan times were recorded, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated for quantitative analysis. Five blinded veterinarians assessed the overall quality, contrast, and perceived SNR on four-point Likert scales. Quantitative and qualitative values were compared among the five groups. Compared with NEX4, NEX2 and NEX1 reduced scan time by 50% and 75%, respectively. The mean SNR and CNR of NEX2DL and NEX1DL were significantly superior to those of NEX4, NEX2, and NEX1 (P < 0.05). In all image quality indices, DLR-applied images for both T2-weighted and FLAIR images were significantly higher than NEX4 and NEX2DL had significantly better quality than NEX1DL for FLAIR (P < 0.05). Findings indicated that DLR reduced scan time and improved image quality compared with conventional MRI images in a sample of clinically healthy beagles.

Artificial Intelligence in Neuroradiology: A Review of Current Topics and Competition Challenges

There is an expanding body of literature that describes the application of deep learning and other machine learning and artificial intelligence methods with potential relevance to neuroradiology practice. In this article, we performed a literature review to identify recent developments on the topics of artificial intelligence in neuroradiology, with particular emphasis on large datasets and large-scale algorithm assessments, such as those used in imaging AI competition challenges. Numerous applications relevant to ischemic stroke, intracranial hemorrhage, brain tumors, demyelinating disease, and neurodegenerative/neurocognitive disorders were discussed. The potential applications of these methods to spinal fractures, scoliosis grading, head and neck oncology, and vascular imaging were also reviewed. The AI applications examined perform a variety of tasks, including localization, segmentation, longitudinal monitoring, diagnostic classification, and prognostication. While research on this topic is ongoing, several applications have been cleared for clinical use and have the potential to augment the accuracy or efficiency of neuroradiologists.

Predicting glioblastoma molecular subtypes and prognosis with a multimodal model integrating convolutional neural network, radiomics, and semantics

OBJECTIVE

The aim of this study was to build a convolutional neural network (CNN)-based prediction model of glioblastoma (GBM) molecular subtype diagnosis and prognosis with multimodal features.

METHODS

In total, 222 GBM patients were included in the training set from Sun Yat-sen University Cancer Center (SYSUCC) and 107 GBM patients were included in the validation set from SYSUCC, Xuanwu Hospital Capital Medical University, and the First Hospital of Jilin University. The multimodal model was trained with MR images (pre- and postcontrast T1-weighted images and T2-weighted images), corresponding MRI impression, and clinical patient information. First, the original images were segmented using the Multimodal Brain Tumor Image Segmentation Benchmark toolkit. Convolutional features were extracted using 3D residual deep neural network (ResNet50) and convolutional 3D (C3D). Radiomic features were extracted using pyradiomics. Report texts were converted to word embedding using word2vec. These three types of features were then integrated to train neural networks. Accuracy, precision, recall, and F1-score were used to evaluate the model performance.

RESULTS

The C3D-based model yielded the highest accuracy of 91.11% in the prediction of IDH1 mutation status. Importantly, the addition of semantics improved precision by 11.21% and recall in MGMT promoter methylation status prediction by 14.28%. The areas under the receiver operating characteristic curves of the C3D-based model in the IDH1, ATRX, MGMT, and 1-year prognosis groups were 0.976, 0.953, 0.955, and 0.976, respectively. In external validation, the C3D-based model showed significant improvement in accuracy in the IDH1, ATRX, MGMT, and 1-year prognosis groups, which were 88.30%, 76.67%, 85.71%, and 85.71%, respectively (compared with 3D ResNet50: 83.51%, 66.67%, 82.14%, and 70.79%, respectively).

CONCLUSIONS

The authors propose a novel multimodal model integrating C3D, radiomics, and semantics, which had a great performance in predicting IDH1, ATRX, and MGMT molecular subtypes and the 1-year prognosis of GBM.

Advanced Magnetic Resonance Imaging in the Evaluation of Treated Glioblastoma: A Pictorial Essay

MRI plays a key role in the evaluation of post-treatment changes, both in the immediate post-operative period and during follow-up. There are many different treatment's lines and many different neuroradiological findings according to the treatment chosen and the clinical timepoint at which MRI is performed. Structural MRI is often insufficient to correctly interpret and define treatment-related changes. For that, advanced MRI modalities, including perfusion and permeability imaging, diffusion tensor imaging, and magnetic resonance spectroscopy, are increasingly utilized in clinical practice to characterize treatment effects more comprehensively. This article aims to provide an overview of the role of advanced MRI modalities in the evaluation of treated glioblastomas. For a didactic purpose, we choose to divide the treatment history in three main timepoints: post-surgery, during Stupp (first-line treatment) and at recurrence (second-line treatment). For each, a brief introduction, a temporal subdivision (when useful) or a specific drug-related paragraph were provided. Finally, the current trends and application of radiomics and artificial intelligence (AI) in the evaluation of treated GB have been outlined.