The diagnosis and surgical resection using Magnetic Resonance (MR) images in brain tumors is a challenging task to minimize the neurological defects after surgery owing to the non-linear nature of the size, shape, and textural variation. Radiologists, clinical experts, and brain surgeons examine brain MRI scans using the available methods, which are tedious, error-prone, time-consuming, and still exhibit positional accuracy up to 2–3 mm, which is very high in the case of brain cells. In this context, we propose an automated Ultra-Light Brain Tumor Detection (UL-BTD) system based on a novel Ultra-Light Deep Learning Architecture (UL-DLA) for deep features, integrated with highly distinctive textural features, extracted by Gray Level Co-occurrence Matrix (GLCM). It forms a Hybrid Feature Space (HFS), which is used for tumor detection using Support Vector Machine (SVM), culminating in high prediction accuracy and optimum false negatives with limited network size to fit within the average GPU resources of a modern PC system. The objective of this study is to categorize multi-class publicly available MRI brain tumor datasets with a minimum time thus real-time tumor detection can be carried out without compromising accuracy. Our proposed framework includes a sensitivity analysis of image size, One-versus-All and One-versus-One coding schemes with stringent efforts to assess the complexity and reliability performance of the proposed system with K-fold cross-validation as a part of the evaluation protocol. The best generalization achieved using SVM has an average detection rate of 99.23% (99.18%, 98.86%, and 99.67%), and F-measure of 0.99 (0.99, 0.98, and 0.99) for (glioma, meningioma, and pituitary tumors), respectively. Our results have been found to improve the state-of-the-art (97.30%) by 2%, indicating that the system exhibits capability for translation in modern hospitals during real-time surgical brain applications. The method needs 11.69 ms with an accuracy of 99.23% compared to 15 ms achieved by the state-of-the-art to earlier to detect tumors on a test image without any dedicated hardware providing a route for a desktop application in brain surgery.

/pdf/intelligent-ultra-light-deep-learning-model-for-multi-class-2h2pibat.pdf

Intelligent Ultra-Light Deep Learning Model for Multi-Class Brain Tumor Detection

Multifunctional nanotheranostics for near infrared optical imaging-guided treatment of brain tumors.

Surgery is essential in the treatment of high-grade gliomas (HGG) and gross total resection (GTR) is known to increase the overall survival and progression-free survival. Several studies have shown that fluorescence-guided surgery with 5-aminolevulinic acid (5-ALA) increases GTR considerably compared to white light surgery (65% vs. 36%). In recent years, sodium fluorescein (SF) has become an increasingly popular agent for fluorescence-guided surgery due to numerous utility benefits compared to 5-ALA, including lower cost, non-toxicity, easy administration during surgery and a wide indication range covering all contrast-enhancing lesions with disruption of the blood-brain barrier in the CNS. However, currently, SF is an off-label agent and the level of evidence for use in HGG surgery is inferior compared to 5-ALA. Here, we give an update and review the latest literature on fluorescence-guided surgery with 5-ALA and SF for brain tumors with emphasis on fluorescence-guided surgery in HGG and brain metastases. Further, we assess the advantages and disadvantages of both fluorophores and discuss their future perspectives. 

https://www.mdpi.com/2072-6694/14/3/617/pdf?version=1644221755

Effect of 5-Aminolevulinic Acid and Sodium Fluorescein on the Extent of Resection in High-Grade Gliomas and Brain Metastasis

Background: Glioblastoma (GBM) is the most common primary brain tumor. The extent of resection (EOR) has been claimed as one of the most important prognostic factors. Fluorescent dyes aid surgeons in detecting a tumor’s borders. 5-aminolevulinic acid (5-ALA) and sodium fluorescein (SF) are the most used. Only a few studies have directly compared these two fluorophores. Methods: A single center retrospective analysis of patients treated for GBM in the period between January 2018 and January 2021 was built to find any differences in terms of EOR, Karnofsky Performance Status (KPS), and overall survival (OS) on the use of 5-ALA, SF, or both. Results: Overall, 99 patients affected by isocitrate dehydrogenase (IDH) wild-type Glioblastoma were included. 5-ALA was administered to 40 patients, SF to 44, and both to 15. No statistically significant associations were identified between the fluorophore and EOR (p = 0.783) or postoperative KPS (p = 0.270). Survival analyses did not show a selective advantage for the use of a given fluorophore (p = 0.184), although there appears to be an advantageous trend associated with the concomitant use of both dyes, particularly after stratification by MGMT (p = 0.071). Conclusions: 5-Ala and SF are equally useful in achieving gross total resection of the enhancing tumor volume. The combination of both fluorophores could lead to an OS advantage.

/pdf/fluorescence-guided-surgery-in-glioblastoma-5-ala-sf-or-both-1gqh909f.pdf

Fluorescence-Guided Surgery in Glioblastoma: 5-ALA, SF or Both? Differences between Fluorescent Dyes in 99 Consecutive Cases

Targeting glioblastoma stem cells: The first step of photodynamic therapy

Fluorescence-guided surgery (FGS) allows surgeons to have improved visualization of tumor tissue in the operating room, enabling maximal safe resection of malignant brain tumors. Over the past two decades, multiple fluorescent agents have been studied for FGS, including 5-aminolevulinic acid (5-ALA), fluorescein sodium, and indocyanine green (ICG). Both non-targeted and targeted fluorescent agents are currently being used in clinical practice, as well as under investigation, for glioma visualization and resection. While the efficacy of intraoperative fluorescence in studied fluorophores has been well established in the literature, the effect of timing on fluorophore administration in glioma surgery has not been as well depicted. In the past year, recent studies of 5-ALA use have shown that intraoperative fluorescence may persist beyond the previously studied window used in prior multicenter trials. Additionally, the use of fluorophores for different brain tumor types is discussed in detail, including a discussion of choosing the right fluorophore based on tumor etiology. In the following review, the authors will describe the temporal nature of the various fluorophores used in glioma surgery, what remains uncertain in FGS, and provide a guide for using fluorescence as a surgical adjunct in brain tumor surgery.

/pdf/fluorescence-guided-surgery-a-review-on-timing-and-use-in-42ykfsmrpz.pdf

Manasa Rao

Papers

Fluorescence-Guided Surgery: A Review on Timing and Use in Brain Tumor Surgery.