Application of Machine Learning for Classification of Brain Tumors: A Systematic Review and Meta-Analysis.

BACKGROUND: Classifying brain tumors accurately is crucial for treatment and prognosis. Machine learning (ML) shows great promise in improving tumor classification accuracy. This study evaluates ML algorithms for differentiating various brain tumor types. METHODS: A systematic review and meta-analysis were conducted, searching PubMed, Embase, and Web of Science up to March 14, 2023. Studies that only investigated image segmentation accuracy or brain tumor detection instead of classification were excluded. We extracted binary diagnostic accuracy data, constructing contingency tables to derive sensitivity and specificity. RESULTS: Fifty-one studies were included. The pooled area under the curve for glioblastoma versus lymphoma and low-grade versus high-grade gliomas were 0.99 (95% confidence interval [CI]: 0.98-1.00) and 0.89, respectively. The pooled sensitivity and specificity for benign versus malignant tumors were 0.90 (95% CI: 0.85-0.93) and 0.93 (95% CI: 0.90-0.95), respectively. The pooled sensitivity and specificity for low-grade versus high-grade gliomas were 0.99 (95% CI: 0.97-1.00) and 0.94, (95% CI: 0.79-0.99), respectively. Primary versus metastatic tumor identification yields sensitivity and specificity of 0.89, (95% CI: 0.83-0.93) and 0.87 (95% CI: 0.82-0.91), correspondingly. The differentiation of gliomas from pituitary tumors yielded the highest results among primary brain tumor classifications: sensitivity of 0.99 (95% CI: 0.99-1.00) and specificity of 0.99 (95% CI: 0.98-1.00). CONCLUSIONS: ML demonstrated excellent performance in classifying brain tumor images, with near-maximum area under the curves, sensitivity, and specificity.

Assessing the Capabilities of Transcranial Magnetic Stimulation (TMS) to Aid in the Removal of Brain Tumors Affecting the Motor Cortex: A Systematic Review.

Introduction: The brain tumor is frequently related to severe motor impairment and impacts the quality of life. The corticospinal tract can sometimes be affected depending on the type and size of the neoplasm, so different tools can evaluate motor function and connections. It is essential to organize surgical procedures and plan the approach. Functional motor status is mapped before, during, and after surgery. Studying corticospinal tract status can help map the functional areas, predict postoperative outcomes, and help the decision, reducing neurological deficits, aiming to preserve functional networks, using the concepts of white matters localization and fibbers connections. Nowadays, there are new techniques that provide functional information regarding the motor cortex, such as transcranial magnetic stimulation (TMS), direct cortical stimulation (DCS), and navigated TMS (nTMS). These tools can be used to plan a customized surgical strategy and the role of motor evoked potentials (MEPs) is well described during intra-operative, using intraoperative neuromonitoring. MEPs can help to localize primary motor areas and delineate the cut-off point of resection in real-time, using direct stimulation. In the post-operative, the MEP has increased your function as a predictive marker of permanent or transitory neurological lesion marker. Methods: Systematic review performed in MEDLINE via PUBMED, EMBASE, and SCOPUS databases regarding the post-operative assessment of MEP in patients with brain tumors. The search strategy included the following terms: (("Evoked Potentials, Motor"[Mesh]) AND "Neoplasms"[Mesh]) AND "Transcranial Magnetic Stimulation"[Mesh] AND "Brain Tumor"[Mesh]), the analysis followed the PRISMA guidelines for systematic reviews, the review spanned until 06/04/2021, inclusion criteria were studies presenting confirmed diagnosis of brain tumor (primary or metastatic), patients >18 y/o, using TMS, Navigated TMS, and/or Evoked Potentials as tools in preoperative planning or at the intra-operative helping the evaluation of the neurological status of the motor cortex, articles published in peer-reviewed journals, and written in English or Portuguese. Results: A total of 38 studies were selected for this review, of which 14 investigated the potential of nTMS to predict the occurrence of motor deficits, while 25 of the articles investigated the capabilities of the nTMS technique in performing pre/intraoperative neuro mapping of the motor cortex. Conclusion: Further studies regarding motor function assessment are needed and standardized protocols for MEPs also need to be defined.