Machine learning applications to neuroimaging for glioma detection and classification: An artificial intelligence augmented systematic review

Deep CNNs for glioma grading on conventional MRIs: Performance analysis, challenges, and future directions

The increasing global incidence of glioma tumors has raised significant healthcare concerns due to their high mortality rates. Traditionally, tumor diagnosis relies on visual analysis of medical imaging and invasive biopsies for precise grading. As an alternative, computer-assisted methods, particularly deep convolutional neural networks (DCNNs), have gained traction. This research paper explores the recent advancements in DCNNs for glioma grading using brain magnetic resonance images (MRIs) from 2015 to 2023. The study evaluated various DCNN architectures and their performance, revealing remarkable results with models such as hybrid and ensemble based DCNNs achieving accuracy levels of up to 98.91%. However, challenges persisted in the form of limited datasets, lack of external validation, and variations in grading formulations across diverse literature sources. Addressing these challenges through expanding datasets, conducting external validation, and standardizing grading formulations can enhance the performance and reliability of DCNNs in glioma grading, thereby advancing brain tumor classification and extending its applications to other neurological disorders.

Effects of a comprehensive brain computed tomography deep learning model on radiologist detection accuracy

OBJECTIVES

Non-contrast computed tomography of the brain (NCCTB) is commonly used to detect intracranial pathology but is subject to interpretation errors. Machine learning can augment clinical decision-making and improve NCCTB scan interpretation. This retrospective detection accuracy study assessed the performance of radiologists assisted by a deep learning model and compared the standalone performance of the model with that of unassisted radiologists.

METHODS

A deep learning model was trained on 212,484 NCCTB scans drawn from a private radiology group in Australia. Scans from inpatient, outpatient, and emergency settings were included. Scan inclusion criteria were age ≥ 18 years and series slice thickness ≤ 1.5 mm. Thirty-two radiologists reviewed 2848 scans with and without the assistance of the deep learning system and rated their confidence in the presence of each finding using a 7-point scale. Differences in AUC and Matthews correlation coefficient (MCC) were calculated using a ground-truth gold standard.

RESULTS

The model demonstrated an average area under the receiver operating characteristic curve (AUC) of 0.93 across 144 NCCTB findings and significantly improved radiologist interpretation performance. Assisted and unassisted radiologists demonstrated an average AUC of 0.79 and 0.73 across 22 grouped parent findings and 0.72 and 0.68 across 189 child findings, respectively. When assisted by the model, radiologist AUC was significantly improved for 91 findings (158 findings were non-inferior), and reading time was significantly reduced.

CONCLUSIONS

The assistance of a comprehensive deep learning model significantly improved radiologist detection accuracy across a wide range of clinical findings and demonstrated the potential to improve NCCTB interpretation.

CLINICAL RELEVANCE STATEMENT

This study evaluated a comprehensive CT brain deep learning model, which performed strongly, improved the performance of radiologists, and reduced interpretation time. The model may reduce errors, improve efficiency, facilitate triage, and better enable the delivery of timely patient care.

KEY POINTS

• This study demonstrated that the use of a comprehensive deep learning system assisted radiologists in the detection of a wide range of abnormalities on non-contrast brain computed tomography scans. • The deep learning model demonstrated an average area under the receiver operating characteristic curve of 0.93 across 144 findings and significantly improved radiologist interpretation performance. • The assistance of the comprehensive deep learning model significantly reduced the time required for radiologists to interpret computed tomography scans of the brain.

Predicting Acoustic Hearing Preservation Following Cochlear Implant Surgery Using Machine Learning

OBJECTIVES

The aim of the study was to train and test supervised machine-learning classifiers to predict acoustic hearing preservation after CI using preoperative clinical data.

STUDY DESIGN

Retrospective predictive modeling study of prospectively collected single-institution CI dataset.

METHODS

One hundred and seventy-five patients from a REDCap database including 761 patients >18 years who underwent CI and had audiometric testing preoperatively and one month after surgery were included. The primary outcome variable was the lowest quartile change in acoustic hearing at one month after CI using various formulae (standard pure tone average, SPTA; low-frequency PTA, LFPTA). Analysis involved applying multivariate logistic regression to detect statistical associations and training and testing supervised learning classifiers. Classifier performance was assessed with numerous metrics including area under the receiver operating characteristic curve (AUC) and Matthews correlation coefficient (MCC).

RESULTS

Lowest quartile change (indicating hearing preservation) in SPTA was positively associated with a history of meningitis, preoperative LFPTA, and preoperative SPTA. Lowest quartile change in SPTA was negatively associated with sudden hearing loss, noise exposure, aural fullness, and abnormal anatomy. Lowest quartile change in LFPTA was positively associated with preoperative LFPTA. Lowest quartile change in LFPTA was negatively associated with tobacco use. Random forest demonstrated the highest mean classification performance on the validation dataset when predicting each of the outcome variables.

CONCLUSIONS

Machine learning demonstrated utility for predicting preservation of residual acoustic hearing in patients undergoing CI surgery, and the detected associations facilitated the interpretation of our machine-learning models. The models and statistical associations together may be used to facilitate improvements in shared clinical decision-making and patient outcomes.

LEVEL OF EVIDENCE

3 Laryngoscope, 134:926-936, 2024.

Time-to-event overall survival prediction in glioblastoma multiforme patients using magnetic resonance imaging radiomics

PURPOSE

Glioblastoma Multiforme (GBM) represents the predominant aggressive primary tumor of the brain with short overall survival (OS) time. We aim to assess the potential of radiomic features in predicting the time-to-event OS of patients with GBM using machine learning (ML) algorithms.

MATERIALS AND METHODS

One hundred nineteen patients with GBM, who had T1-weighted contrast-enhanced and T2-FLAIR MRI sequences, along with clinical data and survival time, were enrolled. Image preprocessing methods included 64 bin discretization, Laplacian of Gaussian (LOG) filters with three Sigma values and eight variations of Wavelet Transform. Images were then segmented, followed by the extraction of 1212 radiomic features. Seven feature selection (FS) methods and six time-to-event ML algorithms were utilized. The combination of preprocessing, FS, and ML algorithms (12 × 7 × 6 = 504 models) was evaluated by multivariate analysis.

RESULTS

Our multivariate analysis showed that the best prognostic FS/ML combinations are the Mutual Information (MI)/Cox Boost, MI/Generalized Linear Model Boosting (GLMB) and MI/Generalized Linear Model Network (GLMN), all of which were done via the LOG (Sigma = 1 mm) preprocessing method (C-index = 0.77). The LOG filter with Sigma = 1 mm preprocessing method, MI, GLMB and GLMN achieved significantly higher C-indices than other preprocessing, FS, and ML methods (all p values < 0.05, mean C-indices of 0.65, 0.70, and 0.64, respectively).

CONCLUSION

ML algorithms are capable of predicting the time-to-event OS of patients using MRI-based radiomic and clinical features. MRI-based radiomics analysis in combination with clinical variables might appear promising in assisting clinicians in the survival prediction of patients with GBM. Further research is needed to establish the applicability of radiomics in the management of GBM in the clinic.

Glioma Tumor Grading Using Radiomics on Conventional MRI: A Comparative Study of WHO 2021 and WHO 2016 Classification of Central Nervous Tumors

BACKGROUND

Glioma grading transformed in World Health Organization (WHO) 2021 CNS tumor classification, integrating molecular markers. However, the impact of this change on radiomics-based machine learning (ML) classifiers remains unexplored.

PURPOSE

To assess the performance of ML in classifying glioma tumor grades based on various WHO criteria.

STUDY TYPE

Retrospective.

SUBJECTS

A neuropathologist regraded gliomas of 237 patients into WHO 2016 and 2021 from 2007 criteria.

FIELD STRENGTH/SEQUENCE

Multicentric 0.5 to 3 Tesla; pre- and post-contrast T1-weighted, T2-weighted, and fluid-attenuated inversion recovery.

ASSESSMENT

Radiomic features were selected using random forest-recursive feature elimination. The synthetic minority over-sampling technique (SMOTE) was implemented for data augmentation. Stratified 10-fold cross-validation with and without SMOTE was used to evaluate 11 classifiers for 3-grade (2, 3, and 4; WHO 2016 and 2021) and 2-grade (low and high grade; WHO 2007 and 2021) classification. Additionally, we developed the models on data randomly divided into training and test sets (mixed-data analysis), or data divided based on the centers (independent-data analysis).

STATISTICAL TESTS

We assessed ML classifiers using sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC). Top performances were compared with a t-test and categorical data with the chi-square test using a significance level of P < 0.05.

RESULTS

In the mixed-data analysis, Stacking Classifier without SMOTE achieved the highest accuracy (0.86) and AUC (0.92) in 3-grade WHO 2021 grouping. The results of WHO 2021 were significantly better than WHO 2016 (P-value<0.0001). In the 2-grade analysis, ML achieved 1.00 in all metrics. In the independent-data analysis, ML classifiers showed strong discrimination between grade 2 and 4, despite lower performance metrics than the mixed analysis.

DATA CONCLUSION

ML algorithms performed better in glioma tumor grading based on WHO 2021 criteria. Nonetheless, the clinical use of ML classifiers needs further investigation.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

Untangling the web of glioblastoma treatment resistance using a multi-omic and multidisciplinary approach

Glioblastoma (GBM), the most common human brain tumor, has been notoriously resistant to treatment. As a result, the dismal overall survival of GBM patients has not changed over the past three decades. GBM has been stubbornly resistant to checkpoint inhibitor immunotherapies, which have been remarkably effective in the treatment of other tumors. It is clear that GBM resistance to therapy is multifactorial. Although therapeutic transport into brain tumors is inhibited by the blood brain barrier, there is evolving evidence that overcoming this barrier is not the predominant factor. GBMs generally have a low mutation burden, exist in an immunosuppressed environment and they are inherently resistant to immune stimulation, all of which contribute to treatment resistance. In this review, we evaluate the contribution of multi-omic approaches (genomic and metabolomic) along with analyzing immune cell populations and tumor biophysical characteristics to better understand and overcome GBM multifactorial resistance to treatment.

Brain tumor detection and screening using artificial intelligence techniques: Current trends and future perspectives

A brain tumor is an abnormal mass of tissue located inside the skull. In addition to putting pressure on the healthy parts of the brain, it can lead to significant health problems. Depending on the region of the brain tumor, it can cause a wide range of health issues. As malignant brain tumors grow rapidly, the mortality rate of individuals with this cancer can increase substantially with each passing week. Hence it is vital to detect these tumors early so that preventive measures can be taken at the initial stages. Computer-aided diagnostic (CAD) systems, in coordination with artificial intelligence (AI) techniques, have a vital role in the early detection of this disorder. In this review, we studied 124 research articles published from 2000 to 2022. Here, the challenges faced by CAD systems based on different modalities are highlighted along with the current requirements of this domain and future prospects in this area of research.

Artificial Intelligence in Neurosurgery: A State-of-the-Art Review from Past to Future

In recent years, there has been a significant surge in discussions surrounding artificial intelligence (AI), along with a corresponding increase in its practical applications in various facets of everyday life, including the medical industry. Notably, even in the highly specialized realm of neurosurgery, AI has been utilized for differential diagnosis, pre-operative evaluation, and improving surgical precision. Many of these applications have begun to mitigate risks of intraoperative and postoperative complications and post-operative care. This article aims to present an overview of the principal published papers on the significant themes of tumor, spine, epilepsy, and vascular issues, wherein AI has been applied to assess its potential applications within neurosurgery. The method involved identifying high-cited seminal papers using PubMed and Google Scholar, conducting a comprehensive review of various study types, and summarizing machine learning applications to enhance understanding among clinicians for future utilization. Recent studies demonstrate that machine learning (ML) holds significant potential in neuro-oncological care, spine surgery, epilepsy management, and other neurosurgical applications. ML techniques have proven effective in tumor identification, surgical outcomes prediction, seizure outcome prediction, aneurysm prediction, and more, highlighting its broad impact and potential in improving patient management and outcomes in neurosurgery. This review will encompass the current state of research, as well as predictions for the future of AI within neurosurgery.

Class imbalance should not throw you off balance: Choosing the right classifiers and performance metrics for brain decoding with imbalanced data

Machine learning (ML) is increasingly used in cognitive, computational and clinical neuroscience. The reliable and efficient application of ML requires a sound understanding of its subtleties and limitations. Training ML models on datasets with imbalanced classes is a particularly common problem, and it can have severe consequences if not adequately addressed. With the neuroscience ML user in mind, this paper provides a didactic assessment of the class imbalance problem and illustrates its impact through systematic manipulation of data imbalance ratios in (i) simulated data and (ii) brain data recorded with electroencephalography (EEG), magnetoencephalography (MEG) and functional magnetic resonance imaging (fMRI). Our results illustrate how the widely-used Accuracy (Acc) metric, which measures the overall proportion of successful predictions, yields misleadingly high performances, as class imbalance increases. Because Acc weights the per-class ratios of correct predictions proportionally to class size, it largely disregards the performance on the minority class. A binary classification model that learns to systematically vote for the majority class will yield an artificially high decoding accuracy that directly reflects the imbalance between the two classes, rather than any genuine generalizable ability to discriminate between them. We show that other evaluation metrics such as the Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC), and the less common Balanced Accuracy (BAcc) metric - defined as the arithmetic mean between sensitivity and specificity, provide more reliable performance evaluations for imbalanced data. Our findings also highlight the robustness of Random Forest (RF), and the benefits of using stratified cross-validation and hyperprameter optimization to tackle data imbalance. Critically, for neuroscience ML applications that seek to minimize overall classification error, we recommend the routine use of BAcc, which in the specific case of balanced data is equivalent to using standard Acc, and readily extends to multi-class settings. Importantly, we present a list of recommendations for dealing with imbalanced data, as well as open-source code to allow the neuroscience community to replicate and extend our observations and explore alternative approaches to coping with imbalanced data.

Tool-tissue force segmentation and pattern recognition for evaluating neurosurgical performance

Surgical data quantification and comprehension expose subtle patterns in tasks and performance. Enabling surgical devices with artificial intelligence provides surgeons with personalized and objective performance evaluation: a virtual surgical assist. Here we present machine learning models developed for analyzing surgical finesse using tool-tissue interaction force data in surgical dissection obtained from a sensorized bipolar forceps. Data modeling was performed using 50 neurosurgery procedures that involved elective surgical treatment for various intracranial pathologies. The data collection was conducted by 13 surgeons of varying experience levels using sensorized bipolar forceps, SmartForceps System. The machine learning algorithm constituted design and implementation for three primary purposes, i.e., force profile segmentation for obtaining active periods of tool utilization using T-U-Net, surgical skill classification into Expert and Novice, and surgical task recognition into two primary categories of Coagulation versus non-Coagulation using FTFIT deep learning architectures. The final report to surgeon was a dashboard containing recognized segments of force application categorized into skill and task classes along with performance metrics charts compared to expert level surgeons. Operating room data recording of > 161 h containing approximately 3.6 K periods of tool operation was utilized. The modeling resulted in Weighted F1-score = 0.95 and AUC = 0.99 for force profile segmentation using T-U-Net, Weighted F1-score = 0.71 and AUC = 0.81 for surgical skill classification, and Weighted F1-score = 0.82 and AUC = 0.89 for surgical task recognition using a subset of hand-crafted features augmented to FTFIT neural network. This study delivers a novel machine learning module in a cloud, enabling an end-to-end platform for intraoperative surgical performance monitoring and evaluation. Accessed through a secure application for professional connectivity, a paradigm for data-driven learning is established.

An online survival predictor in glioma patients using machine learning based on WHO CNS5 data

Background

The World Health Organization (WHO) CNS5 classification system highlights the significance of molecular biomarkers in providing meaningful prognostic and therapeutic information for gliomas. However, predicting individual patient survival remains challenging due to the lack of integrated quantitative assessment tools. In this study, we aimed to design a WHO CNS5-related risk signature to predict the overall survival (OS) rate of glioma patients using machine learning algorithms.

Methods

We extracted data from patients who underwent an operation for histopathologically confirmed glioma from our hospital database (2011-2022) and split them into a training and hold-out test set in a 7/3 ratio. We used biological markers related to WHO CNS5, clinical data (age, sex, and WHO grade), and prognosis follow-up information to identify prognostic factors and construct a predictive dynamic nomograph to predict the survival rate of glioma patients using 4 kinds machine learning algorithms (RF, SVM, XGB, and GLM).

Results

A total of 198 patients with complete WHO5 molecular data and follow-up information were included in the study. The median OS time of all patients was 29.77 [95% confidence interval (CI): 21.19-38.34] months. Age, FGFR2, IDH1, CDK4, CDK6, KIT, and CDKN2A were considered vital indicators related to the prognosis and OS time of glioma. To better predict the prognosis of glioma patients, we constructed a WHO5-related risk signature and nomogram. The AUC values of the ROC curves of the nomogram for predicting the 1, 3, and 5-year OS were 0.849, 0.835, and 0.821 in training set, and, 0.844, 0.943, and 0.959 in validation set. The calibration plot confirmed the reliability of the nomogram, and the c-index was 0.742 in training set and 0.775 in validation set. Additionally, our nomogram showed a superior net benefit across a broader scale of threshold probabilities in decision curve analysis. Therefore, we selected it as the backend for the online survival prediction tool (Glioma Survival Calculator, https://who5pumch.shinyapps.io/DynNomapp/), which can calculate the survival probability for a specific time of the patients.

Conclusion

An online prognosis predictor based on WHO5-related biomarkers was constructed. This therapeutically promising tool may increase the precision of forecast therapy outcomes and assess prognosis.

Emerging role of artificial intelligence in diagnosis, classification and clinical management of glioma

Glioma represents a dominant primary intracranial malignancy in the central nervous system. Artificial intelligence that mainly includes machine learning, and deep learning computational approaches, presents a unique opportunity to enhance clinical management of glioma through improving tumor segmentation, diagnosis, differentiation, grading, treatment, prediction of clinical outcomes (prognosis, and recurrence), molecular features, clinical classification, characterization of the tumor microenvironment, and drug discovery. A growing body of recent studies apply artificial intelligence-based models to disparate data sources of glioma, covering imaging modalities, digital pathology, high-throughput multi-omics data (especially emerging single-cell RNA sequencing and spatial transcriptome), etc. While these early findings are promising, future studies are required to normalize artificial intelligence-based models to improve the generalizability and interpretability of the results. Despite prominent issues, targeted clinical application of artificial intelligence approaches in glioma will facilitate the development of precision medicine of this field. If these challenges can be overcome, artificial intelligence has the potential to profoundly change the way patients with or at risk of glioma are provided with more rational care.

Artificial Intelligence for Neurosurgery : Current State and Future Directions

Artificial intelligence (AI) is a field of computer science that equips machines with human-like intelligence and enables them to learn, reason, and solve problems when presented with data in various formats. Neurosurgery is often at the forefront of innovative and disruptive technologies, which have similarly altered the course of acute and chronic diseases. In diagnostic imaging, such as X-rays, computed tomography, and magnetic resonance imaging, AI is used to analyze images. The use of robots in the field of neurosurgery is also increasing. In neurointensive care units, AI is used to analyze data and provide care to critically ill patients. Moreover, AI can be used to predict a patient's prognosis. Several AI applications have already been introduced in the field of neurosurgery, and many more are expected in the near future. Ultimately, it is our responsibility to keep pace with this evolution to provide meaningful outcomes and personalize each patient's care. Rather than blindly relying on AI in the future, neurosurgeons should gain a thorough understanding of it and use it to enhance their patient care.

Machine Learning Augmented Interpretation of Chest X-rays: A Systematic Review

Limitations of the chest X-ray (CXR) have resulted in attempts to create machine learning systems to assist clinicians and improve interpretation accuracy. An understanding of the capabilities and limitations of modern machine learning systems is necessary for clinicians as these tools begin to permeate practice. This systematic review aimed to provide an overview of machine learning applications designed to facilitate CXR interpretation. A systematic search strategy was executed to identify research into machine learning algorithms capable of detecting >2 radiographic findings on CXRs published between January 2020 and September 2022. Model details and study characteristics, including risk of bias and quality, were summarized. Initially, 2248 articles were retrieved, with 46 included in the final review. Published models demonstrated strong standalone performance and were typically as accurate, or more accurate, than radiologists or non-radiologist clinicians. Multiple studies demonstrated an improvement in the clinical finding classification performance of clinicians when models acted as a diagnostic assistance device. Device performance was compared with that of clinicians in 30% of studies, while effects on clinical perception and diagnosis were evaluated in 19%. Only one study was prospectively run. On average, 128,662 images were used to train and validate models. Most classified less than eight clinical findings, while the three most comprehensive models classified 54, 72, and 124 findings. This review suggests that machine learning devices designed to facilitate CXR interpretation perform strongly, improve the detection performance of clinicians, and improve the efficiency of radiology workflow. Several limitations were identified, and clinician involvement and expertise will be key to driving the safe implementation of quality CXR machine learning systems.

MRI-derived radiomics to guide post-operative management of glioblastoma: Implication for personalized radiation treatment volume delineation

Background

The glioblastoma's bad prognosis is primarily due to intra-tumor heterogeneity, demonstrated from several studies that collected molecular biology, cytogenetic data and more recently radiomic features for a better prognostic stratification. The GLIFA project (GLIoblastoma Feature Analysis) is a multicentric project planned to investigate the role of radiomic analysis in GB management, to verify if radiomic features in the tissue around the resection cavity may guide the radiation target volume delineation.

Materials and methods

We retrospectively analyze from three centers radiomic features extracted from 90 patients with total or near total resection, who completed the standard adjuvant treatment and for whom we had post-operative images available for features extraction. The Manual segmentation was performed on post gadolinium T1w MRI sequence by 2 radiation oncologists and reviewed by a neuroradiologist, both with at least 10 years of experience. The Regions of interest (ROI) considered for the analysis were: the surgical cavity ± post-surgical residual mass (CTV_cavity); the CTV a margin of 1.5 cm added to CTV_cavity and the volume resulting from subtracting the CTV_cavity from the CTV was defined as CTV_Ring. Radiomic analysis and modeling were conducted in RStudio. Z-score normalization was applied to each radiomic feature. A radiomic model was generated using features extracted from the Ring to perform a binary classification and predict the PFS at 6 months. A 3-fold cross-validation repeated five times was implemented for internal validation of the model.

Results

Two-hundred and seventy ROIs were contoured. The proposed radiomic model was given by the best fitting logistic regression model, and included the following 3 features: F_cm_merged.contrast, F_cm_merged.info.corr.2, F_rlm_merged.rlnu. A good agreement between model predicted probabilities and observed outcome probabilities was obtained (p-value of 0.49 by Hosmer and Lemeshow statistical test). The ROC curve of the model reported an AUC of 0.78 (95% CI: 0.68-0.88).

Conclusion

This is the first hypothesis-generating study which applies a radiomic analysis focusing on healthy tissue ring around the surgical cavity on post-operative MRI. This study provides a preliminary model for a decision support tool for a customization of the radiation target volume in GB patients in order to achieve a margin reduction strategy.

Machine Learning in the Classification of Pediatric Posterior Fossa Tumors: A Systematic Review

Background: Posterior fossa tumors (PFTs) are a morbid group of central nervous system tumors that most often present in childhood. While early diagnosis is critical to drive appropriate treatment, definitive diagnosis is currently only achievable through invasive tissue collection and histopathological analyses. Machine learning has been investigated as an alternative means of diagnosis. In this systematic review and meta-analysis, we evaluated the primary literature to identify all machine learning algorithms developed to classify and diagnose pediatric PFTs using imaging or molecular data. Methods: Of the 433 primary papers identified in PubMed, EMBASE, and Web of Science, 25 ultimately met the inclusion criteria. The included papers were extracted for algorithm architecture, study parameters, performance, strengths, and limitations. Results: The algorithms exhibited variable performance based on sample size, classifier(s) used, and individual tumor types being investigated. Ependymoma, medulloblastoma, and pilocytic astrocytoma were the most studied tumors with algorithm accuracies ranging from 37.5% to 94.5%. A minority of studies compared the developed algorithm to a trained neuroradiologist, with three imaging-based algorithms yielding superior performance. Common algorithm and study limitations included small sample sizes, uneven representation of individual tumor types, inconsistent performance reporting, and a lack of application in the clinical environment. Conclusions: Artificial intelligence has the potential to improve the speed and accuracy of diagnosis in this field if the right algorithm is applied to the right scenario. Work is needed to standardize outcome reporting and facilitate additional trials to allow for clinical uptake.

The White Matter Functional Abnormalities in Patients with Transient Ischemic Attack: A Reinforcement Learning Approach

Background

Transient ischemic attack (TIA) is a known risk factor for stroke. Abnormal alterations in the low-frequency range of the gray matter (GM) of the brain have been studied in patients with TIA. However, whether there are abnormal neural activities in the low-frequency range of the white matter (WM) in patients with TIA remains unknown. The current study applied two resting-state metrics to explore functional abnormalities in the low-frequency range of WM in patients with TIA. Furthermore, a reinforcement learning method was used to investigate whether altered WM function could be a diagnostic indicator of TIA.

Methods

We enrolled 48 patients with TIA and 41 age- and sex-matched healthy controls (HCs). Resting-state functional magnetic resonance imaging (rs-fMRI) and clinical/physiological/biochemical data were collected from each participant. We compared the group differences between patients with TIA and HCs in the low-frequency range of WM using two resting-state metrics: amplitude of low-frequency fluctuation (ALFF) and fractional ALFF (fALFF). The altered ALFF and fALFF values were defined as features of the reinforcement learning method involving a Q-learning algorithm.

Results

Compared with HCs, patients with TIA showed decreased ALFF in the right cingulate gyrus/right superior longitudinal fasciculus/left superior corona radiata and decreased fALFF in the right cerebral peduncle/right cingulate gyrus/middle cerebellar peduncle. Based on these two rs-fMRI metrics, an optimal Q-learning model was obtained with an accuracy of 82.02%, sensitivity of 85.42%, specificity of 78.05%, precision of 82.00%, and area under the curve (AUC) of 0.87.

Conclusion

The present study revealed abnormal WM functional alterations in the low-frequency range in patients with TIA. These results support the role of WM functional neural activity as a potential neuromarker in classifying patients with TIA and offer novel insights into the underlying mechanisms in patients with TIA from the perspective of WM function.

Convolutional Neural Network Techniques for Brain Tumor Classification (from 2015 to 2022): Review, Challenges, and Future Perspectives

Convolutional neural networks (CNNs) constitute a widely used deep learning approach that has frequently been applied to the problem of brain tumor diagnosis. Such techniques still face some critical challenges in moving towards clinic application. The main objective of this work is to present a comprehensive review of studies using CNN architectures to classify brain tumors using MR images with the aim of identifying useful strategies for and possible impediments in the development of this technology. Relevant articles were identified using a predefined, systematic procedure. For each article, data were extracted regarding training data, target problems, the network architecture, validation methods, and the reported quantitative performance criteria. The clinical relevance of the studies was then evaluated to identify limitations by considering the merits of convolutional neural networks and the remaining challenges that need to be solved to promote the clinical application and development of CNN algorithms. Finally, possible directions for future research are discussed for researchers in the biomedical and machine learning communities. A total of 83 studies were identified and reviewed. They differed in terms of the precise classification problem targeted and the strategies used to construct and train the chosen CNN. Consequently, the reported performance varied widely, with accuracies of 91.63–100% in differentiating meningiomas, gliomas, and pituitary tumors (26 articles) and of 60.0–99.46% in distinguishing low-grade from high-grade gliomas (13 articles). The review provides a survey of the state of the art in CNN-based deep learning methods for brain tumor classification. Many networks demonstrated good performance, and it is not evident that any specific methodological choice greatly outperforms the alternatives, especially given the inconsistencies in the reporting of validation methods, performance metrics, and training data encountered. Few studies have focused on clinical usability.

Comparing human milk macronutrients measured using analyzers based on mid-infrared spectroscopy and ultrasound and the application of machine learning in data fitting

OBJECTIVE

Fat, carbohydrates (mainly lactose) and protein in breast milk all provide indispensable benefits for the growth of newborns. The only source of nutrition in early infancy is breast milk, so the energy of breast milk is also crucial to the growth of infants. Some macronutrients composition in human breast milk varies greatly, which could affect its nutritional fulfillment to preterm infant needs. Therefore, rapid analysis of macronutrients (including lactose, fat and protein) and milk energy in breast milk is of clinical importance. This study compared the macronutrients results of a mid-infrared (MIR) analyzer and an ultrasound-based breast milk analyzer and unified the results by machine learning.

METHODS

This cross-sectional study included breastfeeding mothers aged 22-40 enrolled between November 2019 and February 2021. Breast milk samples (n = 546) were collected from 244 mothers (from Day 1 to Day 1086 postpartum). A MIR milk analyzer (BETTERREN Co., HMIR-05, SH, CHINA) and an ultrasonic milk analyzer (Honɡyanɡ Co,. HMA 3000, Hebei, CHINA) were used to determine the human milk macronutrient composition. A total of 465 samples completed the tests in both analyzers. The results of the ultrasonic method were mathematically converted using machine learning, while the Bland-Altman method was used to determine the limits of agreement (LOA) between the adjusted results of the ultrasonic method and MIR results.

RESULTS

The MIR and ultrasonic milk analyzer results were significantly different. The protein, fat, and energy determined using the MIR method were higher than those determined by the ultrasonic method, while lactose determined by the MIR method were lower (all p < 0.05). The consistency between the measured MIR and the adjusted ultrasound values was evaluated using the Bland-Altman analysis and the scatter diagram was generated to calculate the 95% LOA. After adjustments, 93.96% protein points (436 out of 465), 94.41% fat points (439 out of 465), 95.91% lactose points (446 out of 465) and 94.62% energy points (440 out of 465) were within the LOA range. The 95% LOA of protein, fat, lactose and energy were - 0.6 to 0.6 g/dl, -0.92 to 0.92 g/dl, -0.88 to 0.88 g/dl and - 40.2 to 40.4 kj/dl, respectively and clinically acceptable. The adjusted ultrasonic results were consistent with the MIR results, and LOA results were high (close to 95%).

CONCLUSIONS

While the results of the breast milk rapid analyzers using the two methods varied significantly, they could still be considered comparable after data adjustments using linear regression algorithm in machine learning. Machine learning methods can play a role in data fitting using different analyzers.

Research on Infant Health Diagnosis and Intelligence Development Based on Machine Learning and Health Information Statistics

Intelligent health diagnosis for young children aims at maintaining and promoting the healthy development of young children, aiming to make young children have a healthy state and provide a better future for their physical and mental health development. The biological basis of intelligence is the structure and function of human brain and the key to improve the intelligence level of infants is to improve the quality of brain development, especially the early development of brain. Based on machine learning and health information statistics, this paper studies the development of infant health diagnosis and intelligence, physical and mental health. Pre-process the sample data, and use the filtering method based on machine learning and health information statistics for feature screening. Compared with traditional statistical methods, machine learning and health information statistical methods can better obtain the hidden information in the big data of children's physical and mental health development, and have better learning ability and generalization ability. The machine learning theory is used to analyze and mine the infant's health diagnosis and intelligence development, establish a health state model, and intuitively show people the health status of their infant's physical and mental health development by means of data. Moreover, the accumulation of these big data is very important in the field of medical and health research driven by big data.

Gaps and Opportunities of Artificial Intelligence Applications for Pediatric Oncology in European Research: A Systematic Review of Reviews and a Bibliometric Analysis

The application of artificial intelligence (AI) systems is emerging in many fields in recent years, due to the increased computing power available at lower cost. Although its applications in various branches of medicine, such as pediatric oncology, are many and promising, its use is still in an embryonic stage. The aim of this paper is to provide an overview of the state of the art regarding the AI application in pediatric oncology, through a systematic review of systematic reviews, and to analyze current trends in Europe, through a bibliometric analysis of publications written by European authors. Among 330 records found, 25 were included in the systematic review. All papers have been published since 2017, demonstrating only recent attention to this field. The total number of studies included in the selected reviews was 674, with a third including an author with a European affiliation. In bibliometric analysis, 304 out of the 978 records found were included. Similarly, the number of publications began to dramatically increase from 2017. Most explored AI applications regard the use of diagnostic images, particularly radiomics, as well as the group of neoplasms most involved are the central nervous system tumors. No evidence was found regarding the use of AI for process mining, clinical pathway modeling, or computer interpreted guidelines to improve the healthcare process. No robust evidence is yet available in any of the domains investigated by systematic reviews. However, the scientific production in Europe is significant and consistent with the topics covered in systematic reviews at the global level. The use of AI in pediatric oncology is developing rapidly with promising results, but numerous gaps and challenges persist to validate its utilization in clinical practice. An important limitation is the need for large datasets for training algorithms, calling for international collaborative studies.

Machine Learning Tools for Image-Based Glioma Grading and the Quality of Their Reporting: Challenges and Opportunities

Technological innovation has enabled the development of machine learning (ML) tools that aim to improve the practice of radiologists. In the last decade, ML applications to neuro-oncology have expanded significantly, with the pre-operative prediction of glioma grade using medical imaging as a specific area of interest. We introduce the subject of ML models for glioma grade prediction by remarking upon the models reported in the literature as well as by describing their characteristic developmental workflow and widely used classifier algorithms. The challenges facing these models-including data sources, external validation, and glioma grade classification methods -are highlighted. We also discuss the quality of how these models are reported, explore the present and future of reporting guidelines and risk of bias tools, and provide suggestions for the reporting of prospective works. Finally, this review offers insights into next steps that the field of ML glioma grade prediction can take to facilitate clinical implementation.

Machine Learning Models for Classifying High- and Low-Grade Gliomas: A Systematic Review and Quality of Reporting Analysis

Objectives

To systematically review, assess the reporting quality of, and discuss improvement opportunities for studies describing machine learning (ML) models for glioma grade prediction.

Methods

This study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses of Diagnostic Test Accuracy (PRISMA-DTA) statement. A systematic search was performed in September 2020, and repeated in January 2021, on four databases: Embase, Medline, CENTRAL, and Web of Science Core Collection. Publications were screened in Covidence, and reporting quality was measured against the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) Statement. Descriptive statistics were calculated using GraphPad Prism 9.

Results

The search identified 11,727 candidate articles with 1,135 articles undergoing full text review and 85 included in analysis. 67 (79%) articles were published between 2018-2021. The mean prediction accuracy of the best performing model in each study was 0.89 ± 0.09. The most common algorithm for conventional machine learning studies was Support Vector Machine (mean accuracy: 0.90 ± 0.07) and for deep learning studies was Convolutional Neural Network (mean accuracy: 0.91 ± 0.10). Only one study used both a large training dataset (n>200) and external validation (accuracy: 0.72) for their model. The mean adherence rate to TRIPOD was 44.5% ± 11.1%, with poor reporting adherence for model performance (0%), abstracts (0%), and titles (0%).

Conclusions

The application of ML to glioma grade prediction has grown substantially, with ML model studies reporting high predictive accuracies but lacking essential metrics and characteristics for assessing model performance. Several domains, including generalizability and reproducibility, warrant further attention to enable translation into clinical practice.

Systematic Review Registration

PROSPERO, identifier CRD42020209938.

Transfer Learning Approaches for Neuroimaging Analysis: A Scoping Review

Deep learning algorithms have been moderately successful in diagnoses of diseases by analyzing medical images especially through neuroimaging that is rich in annotated data. Transfer learning methods have demonstrated strong performance in tackling annotated data. It utilizes and transfers knowledge learned from a source domain to target domain even when the dataset is small. There are multiple approaches to transfer learning that result in a range of performance estimates in diagnosis, detection, and classification of clinical problems. Therefore, in this paper, we reviewed transfer learning approaches, their design attributes, and their applications to neuroimaging problems. We reviewed two main literature databases and included the most relevant studies using predefined inclusion criteria. Among 50 reviewed studies, more than half of them are on transfer learning for Alzheimer's disease. Brain mapping and brain tumor detection were second and third most discussed research problems, respectively. The most common source dataset for transfer learning was ImageNet, which is not a neuroimaging dataset. This suggests that the majority of studies preferred pre-trained models instead of training their own model on a neuroimaging dataset. Although, about one third of studies designed their own architecture, most studies used existing Convolutional Neural Network architectures. Magnetic Resonance Imaging was the most common imaging modality. In almost all studies, transfer learning contributed to better performance in diagnosis, classification, segmentation of different neuroimaging diseases and problems, than methods without transfer learning. Among different transfer learning approaches, fine-tuning all convolutional and fully-connected layers approach and freezing convolutional layers and fine-tuning fully-connected layers approach demonstrated superior performance in terms of accuracy. These recent transfer learning approaches not only show great performance but also require less computational resources and time.

Treatment Response and Prognosis Evaluation in High-Grade Glioma: An Imaging Review Based on MRI

In recent years, the development of advanced magnetic resonance imaging (MRI) technology and machine learning (ML) have created new tools for evaluating treatment response and prognosis of patients with high-grade gliomas (HGG); however, patient prognosis has not improved significantly. This is mainly due to the heterogeneity between and within HGG tumors, resulting in standard treatment methods not benefitting all patients. Moreover, the survival of patients with HGG is not only related to tumor cells, but also to noncancer cells in the tumor microenvironment (TME). Therefore, during preoperative diagnosis and follow-up treatment of patients with HGG, noninvasive imaging markers are needed to characterize intratumoral heterogeneity, and then to evaluate treatment response and predict prognosis, timeously adjust treatment strategies, and achieve individualized diagnosis and treatment. In this review, we summarize the research progress of conventional MRI, advanced MRI technology, and ML in evaluation of treatment response and prognosis of patients with HGG. We further discuss the significance of the TME in the prognosis of HGG patients, associate imaging features with the TME, indirectly reflecting the heterogeneity within the tumor, and shifting treatment strategies from tumor cells alone to systemic therapy of the TME, which may be a major development direction in the future. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY STAGE: 4.

AI-Driven Image Analysis in Central Nervous System Tumors-Traditional Machine Learning, Deep Learning and Hybrid Models

The interpretation of imaging in medicine in general and in oncology specifically remains problematic due to several limitations which include the need to incorporate detailed clinical history, patient and disease-specific history, clinical exam features, previous and ongoing treatment, and account for the dependency on reproducible human interpretation of multiple factors with incomplete data linkage. To standardize reporting, minimize bias, expedite management, and improve outcomes, the use of Artificial Intelligence (AI) has gained significant prominence in imaging analysis. In oncology, AI methods have as a result been explored in most cancer types with ongoing progress in employing AI towards imaging for oncology treatment, assessing treatment response, and understanding and communicating prognosis. Challenges remain with limited available data sets, variability in imaging changes over time augmented by a growing heterogeneity in analysis approaches. We review the imaging analysis workflow and examine how hand-crafted features also referred to as traditional Machine Learning (ML), Deep Learning (DL) approaches, and hybrid analyses, are being employed in AI-driven imaging analysis in central nervous system tumors. ML, DL, and hybrid approaches coexist, and their combination may produce superior results although data in this space is as yet novel, and conclusions and pitfalls have yet to be fully explored. We note the growing technical complexities that may become increasingly separated from the clinic and enforce the acute need for clinician engagement to guide progress and ensure that conclusions derived from AI-driven imaging analysis reflect that same level of scrutiny lent to other avenues of clinical research.

[Machine learning for resting state fMRI-based preoperative mapping: comparison with task-based fMRI and direct cortical stimulation]

OBJECTIVE

To develop a system for preoperative prediction of individual activations of motor and speech areas in patients with brain gliomas using resting state fMRI (rsfMRI), task-based fMRI (tb-fMRI), direct cortical stimulation and machine learning methods.

MATERIAL AND METHODS

Thirty-three patients with gliomas (19 females and 14 males aged 19 - 540) underwent DCS-assisted resection of tumor (19 ones with lesion of motor zones and 14 patients with lesions of speech areas). Awake craniotomy was performed in 14 cases. Preoperative mapping was performed according to special MRI protocol (T1, tb-fMRI, rs-fMRI).

Machine learning system was built on open source data from The Human Connectome Project. MR data of 200 healthy subjects from this database were used for system pre-training. Further, this system was trained on the data of our patients with gliomas.

RESULTS

In DCS, we obtained 332 stimulations including 173 with positive response. According to comparison of functional activations between rs-fMRI and tb-fMRI, there were more positive DCS responses predicted by rs-fMRI (132 vs 112). Non-response stimulation sites (negative) prevailed in tb-fMRI activations (69 vs 44).

CONCLUSION

The developed method with machine learning based on resting state fMRI showed greater sensitivity compared to classical task-based fMRI after verification with DCS: 0.72 versus 0.66 (p<0.05) for identifying the speech zones and 0.79 versus 0.62 (p<0.05) for motor areas.

[Artificial intelligence technologies in clinical neurooncology]

Neurooncology in the 21st century is a complex discipline integrating achievements of fundamental and applied neurosciences. Complex processes and data in clinical neurooncology determine the necessity for advanced methods of mathematical modeling and predictive analytics to obtain new scientific knowledge. Such methods are currently being developed in computer science (artificial intelligence). This review is devoted to potential and range of possible applications of artificial intelligence technologies in neurooncology with a special emphasis on glial tumors. Our conclusions may be valid for other areas of clinical medicine.

[Structured reporting and artificial intelligence]

BACKGROUND

There are a multitude of application possibilities of artificial intelligence (AI) and structured reporting (SR) in radiology. The number of scientific publications have continuously increased for many years. There is an extensive portfolio of available AI algorithms for, e.g. automatic detection and preselection of pathologic patterns in images or for facilitating the reporting workflows. Even machines already use AI algorithms for improvement of operating comfort.

METHOD

The use of SR is essential especially for the extraction of automatically evaluable semantic data from radiology results reports. Regarding eligibility in certification processes, the use of SR is mandatory for the accreditation of the German Cancer Society as an oncological center or outside Germany, such as the European Cancer Center.

RESULTS

The data from SR can be automatically evaluated for the purpose of patient care, research and educational purposes and quality assurance. Lack of information and a high degree of variability often hamper the extraction of valid information from free-text reports using neurolinguistic programming (NLP). Against the background of supervised training, AI algorithms or k‑nearest neighbors (KNN) require a considerable amount of validated data. The semantic data from SR can also be processed by AI and used for training.

CONCLUSION

The AI and SR are separate entities within the field of radiology with mutual dependencies and significant added value. Both have a high potential for profound upcoming changes and further developments in radiology.

A State-of-Art-Review on Machine-Learning Based Methods for PV

In the current era, Artificial Intelligence (AI) is becoming increasingly pervasive with applications in several applicative fields effectively changing our daily life. In this scenario, machine learning (ML), a subset of AI techniques, provides machines with the ability to programmatically learn from data to model a system while adapting to new situations as they learn more by data they are ingesting (on-line training). During the last several years, many papers have been published concerning ML applications in the field of solar systems. This paper presents the state of the art ML models applied in solar energy’s forecasting field i.e., for solar irradiance and power production forecasting (both point and interval or probabilistic forecasting), electricity price forecasting and energy demand forecasting. Other applications of ML into the photovoltaic (PV) field taken into account are the modelling of PV modules, PV design parameter extraction, tracking the maximum power point (MPP), PV systems efficiency optimization, PV/Thermal (PV/T) and Concentrating PV (CPV) system design parameters’ optimization and efficiency improvement, anomaly detection and energy management of PV’s storage systems. While many review papers already exist in this regard, they are usually focused only on one specific topic, while in this paper are gathered all the most relevant applications of ML for solar systems in many different fields. The paper gives an overview of the most recent and promising applications of machine learning used in the field of photovoltaic systems.

Clinical outcomes associated with robotic and computer-navigated total knee arthroplasty: a machine learning-augmented systematic review

BACKGROUND

Robotic (RTKA) and computer-navigated total knee arthroplasty (CNTKA) are increasingly replacing manual techniques in orthopaedic surgery. This systematic review compared clinical outcomes associated with RTKA and CNTKA and investigated the utility of natural language processing (NLP) for the literature synthesis.

METHODS

A comprehensive search strategy was implemented. Results of included studies were combined and analysed. A transfer learning approach was applied to train deep NLP classifiers (BERT, RoBERTa and XLNet), with cross-validation, to partially automate the systematic review process.

RESULTS

52 studies were included, comprising 5,067 RTKA and 2,108 CNTKA. Complication rates were 0-22% and 0-16% and surgical time was 70-116 and 77-102 min for RTKA and CNTKA, respectively. Technical failures were more commonly associated with RTKA (8%) than CNTKA (2-4%). Patient satisfaction was equivalent (94%). RTKA was associated with a higher likelihood of achieving target alignment, less femoral notching, shorter operative time and shorter length of stay. NLP models demonstrated moderate performance (AUC = 0.65-0.68).

CONCLUSIONS

RTKA and CNTKA appear to be associated with similarly positive clinical outcomes. Further work is required to determine whether the two techniques differ significantly with regard to specific outcome measures. NLP shows promise for facilitating the systematic review process.