Diagnosis Of Brain Tumors Research Articles

Brain magnetic resonance image (MRI) segmentation using multimodal optimization

AbstractOne of the highly focused areas in the medical science community is segmenting tumors from brain magnetic resonance imaging (MRI). The diagnosis of malignant tumors at an early stage is necessary to provide treatment for patients. The patient’s prognosis will improve if it is detected early. Medical experts use a manual method of segmentation when making a diagnosis of brain tumors. This study proposes a new approach to simplify and automate this process. In recent research, multi-level segmentation has been widely used in medical image analysis, and the effectiveness and precision of the segmentation method are directly tied to the number of segments used. However, choosing the appropriate number of segments is often left up to the user and is challenging for many segmentation algorithms. The proposed method is a modified version of the 3D Histogram-based segmentation method, which can automatically determine an appropriate number of segments. The general algorithm contains three main steps: The first step is to use a Gaussian filter to smooth the 3D RGB histogram of an image. This eliminates unreliable and non-dominating histogram peaks that are too close together. Next, a multimodal particle swarm optimization method identifies the histogram’s peaks. In the end, pixels are placed in the cluster that best fits their characteristics based on the non-Euclidean distance. The proposed algorithm has been applied to a Cancer Imaging Archive (TCIA) and brain MRI Images for brain Tumor detection dataset. The results of the proposed method are compared with those of three clustering methods: FCM, FCM_FWCW, and FCM_FW. In the comparative analysis of the three algorithms across various MRI slices. Our algorithm consistently demonstrates superior performance. It achieves the top mean rank in all three metrics, indicating its robustness and effectiveness in clustering. The proposed method is effective in experiments, proving its capacity to find the proper clusters.

Optimal extreme learning machine for diagnosing brain tumor based on modified sailfish optimizer

This study proposes a hierarchical automated methodology for detecting brain tumors in Magnetic Resonance Imaging (MRI), focusing on preprocessing images to improve quality and eliminate artifacts or noise. A modified Extreme Learning Machine is then used to diagnose brain tumors that are integrated with the Modified Sailfish optimizer to enhance its performance. The Modified Sailfish optimizer is a metaheuristic algorithm known for efficiently navigating optimization landscapes and enhancing convergence speed. Experiments were conducted using the “Whole Brain Atlas (WBA)” database, which contains annotated MRI images. The results showed superior efficiency in accurately detecting brain tumors from MRI images, demonstrating the potential of the method in enhancing accuracy and efficiency. The proposed method utilizes hierarchical methodology, preprocessing techniques, and optimization of the Extreme Learning Machine with the Modified Sailfish optimizer to improve accuracy rates and decrease the time needed for brain tumor diagnosis. The proposed method outperformed other methods in terms of accuracy, recall, specificity, precision, and F1 score in medical imaging diagnosis. It achieved the highest accuracy at 93.95 %, with End/End and CNN attaining high values of 89.24 % and 93.17 %, respectively. The method also achieved a perfect score of 100 % in recall, 91.38 % in specificity, and 75.64 % in F1 score. However, it is crucial to consider factors like computational complexity, dataset characteristics, and generalizability before evaluating the effectiveness of the method in medical imaging diagnosis. This approach has the potential to make substantial contributions to medical imaging and aid healthcare professionals in making prompt and precise treatment decisions for brain tumors.

Design of Terahertz Refractive Index-Based Spiral Hollow-Core Photonic Crystal Biosensor Using Enhanced Probabilistic Pyramid Neural Networks for Brain Tumor Detection

Cancer diagnosis is difficult and costly due to the complexity of the brain. Photonic technology-based biosensors show potential for identifying malignant tissues, including brain tumors, but they are often costly, time-consuming, and computationally difficult. To address these challenges, we propose an enhanced probabilistic pyramid neural networks (EPPNN)-based hollow-core photonic crystal fiber (PCF) biosensor with terahertz refractive index (THzBio-ECPPN) for detection of cancerous brain tumors. The approach is divided into two stages: biosensor design and brain tumor detection. Initially, PCF geometry with suspended cladding and a spiral-shaped hollow-core in the terahertz (THz) band is proposed. The PCF biosensors’ characteristics are then calculated using the EPPNN model. The EPPNN model’s hyperparameters are modified using the circle-inspired optimization algorithm to maximize accuracy and minimize effective mode loss. The proposed biosensor is then used to identify brain tumors. Experimental evaluations utilizing MATLAB show that the suggested strategy surpasses earlier methods, with a higher sensitivity (98%). The sensor has exceptional performance characteristics, such as a high figure of merit of 1.25–1.35 RI range and sensitivity of 50000 nm RIU−1, indicating its potential for precise detection of changes in refractive index. This combination of photonic crystal structures and neural networks has enormous potential for improving cancerous tumor accuracy to 99.92%, precision to 99.23%, specificity to 99.73%,and sensitivity to 99.36% of brain tumor diagnosis.

Brain Tumor Segmentation Based on α‐Expansion Graph Cut

ABSTRACTIn recent years, there has been an increased interest in using image processing, computer vision, and machine learning in biological and medical imaging research. One area of this interest is the diagnosis of brain tumors, which is considered a difficult and time‐consuming task traditionally performed manually. In this study, we present a method for tumor detection from magnetic resonance images (MRI) using a well‐known graph‐based algorithm, the Boykov–Kolmogorov algorithm, and the α‐expansion method. This approach involves pre‐processing the MRIs, representing the image positions as nodes, and calculations of the weights between edges as differences in intensity. The problem is formulated as an energy minimization problem and is solved by finding the 0,1 score for the image. Post‐processing is also performed to enhance the overall segmentation. The proposed method is easy to implement and shows high accuracy, precision, and efficiency in the results. We believe that this approach will bring significant benefits to scientists and healthcare researchers in qualitative research and can be applied to various imaging modalities for future research.

Histopathologic and molecular profile of gliomas diagnosed in Lagos, Nigeria

Abstract Background The optimal diagnosis and management of patients with brain tumors currently uses the 2021 WHO integrated diagnosis of histomorphologic and molecular features. However, neuro-oncology practice in resource-limited settings usually relies solely on histomorphology. This study aimed to classify glioma cases diagnosed in the Department of Anatomic and Molecular Pathology, Lagos University Teaching Hospital, using the 2021 WHO CNS tumor classification. Methods Fifty-six brain tumors from 55 patients diagnosed with glioma between 2013 and 2021 were reevaluated for morphologic diagnosis. Molecular features were determined from formalin-fixed paraffin-embedded (FFPE) tissue using immunohistochemistry (IHC) for IDH1-R132H, ATRX, BRAF-V600E, p53, Ki67, and H3-K27M, OncoScan chromosomal microarray for copy number, targeted next generation sequencing for mutation and fusion and methylation array profiling. Results Of 55 central nervous system tumors, 3 were excluded from histomorphologic reevaluation for not being of glial or neuroepithelial origin. Of the remaining 52 patients, the median age was 20.5 years (range: 1 to 60 years), 38(73%) were males and 14(27%) were females. Seventy-one percent of the gliomas evaluated provided adequate DNA from archival FFPE tissue blocks. After applying the 2021 WHO diagnostic criteria the initial morphologic diagnosis changed for 35% (18/52) of cases. Diagnoses of 5 (9.6%) gliomas were upgraded, and 7 (14%) were downgraded. Conclusions This study shows that the incorporation of molecular testing can considerably improve brain tumor diagnoses in Nigeria. Furthermore, this study highlights the diagnostic challenges in resource-limited settings and what is at stake in the global disparities of brain tumor diagnosis.

Developing a classification system for brain tumors using the ResNet152V2 CNN model architecture

According to The American Cancer Society, in 2021 there were 24,530 cases of brain and nervous system tumors. The National Cancer Institute reports that there are approximately 4.4 new cases of brain tumors per 100,000 men and women per year. Brain tumors can be detected using magnetic resonance imaging (MRI), a scanning tool that uses a magnetic field and a computer to record brain images and is able to provide clear visualization of differences in soft tissue such as white matter and gray matter. However, this cannot be done optimally because it still relies on manual analysis, so it cannot classify brain tumor types on larger datasets with the potential for error and a low level of accuracy. To accurately determine the type of brain tumor, a better classification method is needed. The aim of this study is to determine the accuracy of brain tumor calcification using the deep learning model. In this study, the classification of brain tumor types was carried out using the ResNet152V2 convolutional neural network (CNN) model which has a depth of 152 layers. The dataset used in this study was 7,023 MRI images of brain tumors consisting of 1,645 meningiomas, 1,621 gliomas, 1,757 pituitary and 2,000 normal. Research results show an accuracy value of 94.44%, so it can be concluded that the ResNet152V2 model performs well in classifying brain tumor images and can be used as a medium for physicians to more accurately diagnose brain tumor patients more accurately.

QOL-40. FAMILY MENTAL HEALTH SCREENING EARLY AFTER A DIAGNOSIS OF PEDIATRIC BRAIN TUMOR

Abstract INTRODUCTION A new diagnosis of a brain tumor in a child has significant emotional consequences for every member of the family. Despite this, early phases of oncologic care rarely provide formal mental health screening. METHODS In 2021, we implemented a mental health screening protocol for patients with a newly diagnosed brain tumor admitted to our pediatric intensive care unit (PICU) at the time of diagnosis, and their parents. Screening instruments were selected based on previous validation and relevance to both a brain tumor diagnosis and PICU admission. Parents were contacted by our team shortly after their child’s diagnosis and completed the screening within a month via an online interface. Parent proxy reports for children were used when necessary. Scores were shared with the family and neuro-oncology team. When indicated, supportive counseling and care coordination were offered. RESULTS Since 2021, 97 new brain tumor patients have met criteria for mental health screening. Of these, 72 patient and parent dyads were provided the screening protocol, and 31 fully completed the screening (mean patient age 7.3 yrs; 81% white; 58% male). Of the families that completed the evaluation, most parents (83%) reported their child’s diagnosis negatively impacted their health-related quality of life (HRQL), while 75% of children themselves reported a lower HRQL than population norms. Nearly half of children (44%) self-reported having symptoms outside of normal range for anger, anxiety or depression and 33% had abnormal scores for pain interference with their daily lives. More than half (65%) of families reported lower family functioning than population norms. CONCLUSION Families of children with a new diagnosis of brain tumor are at risk for impaired mental health and quality of life early after diagnosis. A systematic approach to assess and address these concerns early after diagnosis is needed.

Adaptive Detection and Classification of Brain Tumour Images Based on Photoacoustic Imaging

A new imaging technique called photoacoustic imaging (PAI) combines the advantages of ultrasound imaging and optical absorption to provide structural and functional details of tissues. It has broad application prospects in the accurate diagnosis and treatment monitoring of brain tumours. However, the existing photoacoustic image classification algorithms cannot effectively distinguish benign tumours from malignant tumours. To address this problem, the YoLov8-MedSAM model is proposed in this research to provide precise and adaptable brain tumour identification and detection segmentation. Additionally, it employs convolutional neural networks (CNNs) to classify and identify tumours in order to distinguish between benign and malignant variations in PAI. The experimental results show that the method proposed in this study not only effectively detects and segments brain tumours of various shapes and sizes but also increases the accuracy of brain tumour classification to 97.02%. The method provides richer and more valuable diagnostic information to the clinic and effectively optimizes the diagnosis and treatment strategy of brain tumours.

QOL-19. THE SIBLING TOOLKIT: DEVELOPMENT OF A PSYCHOLOGICALLY-INFORMED TOOLKIT TO SUPPORT SIBLINGS OF CHILDHOOD CNS TUMOUR PATIENTS WITH LIMITED ACCESS TO FORMAL SERVICES

Abstract BACKGROUND There is a recognised gap in service provision addressing the psychological and social needs of siblings of children with a diagnosis of brain tumour. In the absence of funding to provide direct psychological service provision for siblings, a project development group was established to identify and advance alternative methods of delivering support. METHODS Funding for a two year sibling-needs project was sourced from UK child brain tumour charity Tom’s Trust and led by the Neuro-Oncology psychology service at the Great North Children’s Hospital (Newcastle, UK). A development group was established of clinical psychologists and neuropsychologists representing nine UK hospital Trusts and one former school teacher. Following a comprehensive priorities exercise a toolkit was developed to support siblings of children with brain tumours. Significant further stakeholder involvement, including input from the regional Young People’s Advisory Group, resulted in positive revision to the initial draft. RESULTS A 39 page toolkit was produced for the use of any adult involved in the sibling’s life. This psychologically-informed toolkit provides guidance and support for a caring but potentially uninformed adult, such as a teacher, community leader, or member of the wider family, to be able to offer support to siblings. Guidance is included to help the adult talk about cancer, know what common issues siblings face, and to think about how to safely and appropriately undertake supportive work with this age group. The kit is associated with a website link, allowing toolkit users to download worksheets and resources for use with the sibling. CONCLUSIONS Early feedback on the published toolkit is highly positive, suggesting that the toolkit is considered ‘comprehensive’, ‘accessible’, and ‘practical’. We believe that this toolkit offers the potential to bridge some of the gap in service provision to siblings of a child with brain tumour.

NURS-18. GERMINOMA PATIENTS – MORE PRONE TO PSYCHIATRIC DISORDERS, ALLERGIES, AND WEIGHT PROBLEMS? AN INSTITUTIONAL REVIEW

Abstract BACKGROUND Germinoma are the most frequent type of intracranial germ cell tumour. Within nursing clinical practice an increased prevalence of psychiatric manifestations, allergies, and weight gain throughout treatment and into survivorship within the germinoma population has been observed. There is only limited literature about these problems available. METHODS A retrospective review of clinical presentation, psychiatric co-morbidity, therapeutic course, and follow-up of 27 Germinoma patients (6.2-17 years) diagnosed and treated at a tertiary care center from 2008-2021 was performed. In addition, the presence and occurrence of allergies and weight changes throughout their therapy was reviewed. RESULTS Nearly half of the Germinoma patients (n=11) (suprasellar, pineal, basal ganglia) were diagnosed with pre-existing psychiatric co-morbidity (anxiety, depression, mood disorder and eating disorder) as per DSM-5 criteria, more commonly verified after their brain tumour diagnosis and persistent beyond treatment. Three of 27 (11%) patients indicated allergies (medication, food) at diagnosis. Seventeen of the 27 (63%) patients presented with allergies throughout their therapy (medication, tape, cleaning products, blood products). Six (35%) of those patients developed anaphylactic reaction to Etoposide and/or blood products. Eight of the patients (suprasellar & pineal) were found to have a significant weight gain throughout their treatment and two (pineal & suprasellar) were found to have significant weight loss, the rest of the cohort remained stable. The impact of tumour location (suprasellar, pineal) on the specific problems is ongoing. CONCLUSION The findings of this retrospective review could guide clinical practice. The potential higher incidence of psychiatric disorders should prompt practitioners to upfront screening and throughout therapy to ensure adequate support. Allergy prevalence in pediatrics is variable but an allergy occurrence of 35% is elevated in comparison to the general population and therefore increased awareness of allergies within this population is important for the bedside nurse. Lastly, early involvement of dieticians to aid in weight management seems crucial.

IMG-18. DIFFERENTIAL DIAGNOSIS OF POSTERIOR FOSSA TUMORS USING RADIOMICS; A FIRST-LINE DIAGNOSTIC STEP REQUIRED FOR DOWNSTREAM ANALYSES

Abstract BACKGROUND Accurate radiographic diagnosis of pediatric brain tumors (PBTs) that originate in the brainstem and posterior fossa, including medulloblastoma (MB), pilocytic astrocytoma (PA), ependymoma (EPN), atypical teratoid/rhabdoid tumor (ATRT), and diffuse intrinsic pontine glioma (DIPG), is crucial for optimizing surgical approaches and enhancing neoadjuvant therapies. Existing research on the radiographic differential diagnosis of posterior fossa tumors has limitations, including small sample sizes, lack of inclusion of certain histologies especially rarer tumors such as ATRTs, and incomplete analysis of the whole tumor, including peritumoral edema. In this study, we aimed to perform a comprehensive analysis using radiomics and machine learning to differentiate among the common posterior fossa and brainstem tumors. METHODS We employed 927 radiomic features extracted from whole tumor regions within treatment-naïve, standard multiparametric MRI sequences (pre-/post-contrast T1-weighted, T2-weighted, FLAIR) of 264 patients (106 MBs, 78 PAs, 28 EPNs, 27 ATRTs, and 25 DIPGs), collected from the Children’s Brain Tumor Network (CBTN). We adopted a one-versus-rest classification strategy, employing Support Vector Machines combined with the Least Absolute Shrinkage and Selection Operator (LASSO) for feature selection, and implementing nested cross-validation for robustness. RESULTS The performances of the classifiers were evaluated using the Area Under the Receiver Operating Characteristic Curve, yielding values of 0.84 for MBs, 0.84 for PAs, 0.70 for EPNs, 0.75 for ATRTs, and 0.71 for DIPGs. CONCLUSIONS Our method effectively differentiates between various tumor types in the posterior fossa and brainstem, paving the path towards the development of comprehensive diagnostic and prognostic AI tools for pre-treatment histological diagnosis of these tumors. These AI tools can lead to more tailored, risk-adjusted treatments for PBTs, reducing morbidities and improving patient outcomes. Based on our promising initial results, we will expand our dataset to include more samples and incorporate rarer tumor types, as well as piloting in different molecular subclassifications.

QOL-35. ANALYSIS ON THE EVOLUTIONARY PATTERN OF COGNITIVE FUNCTIONS IN CHILDREN ON FOLLOW-UP FOR BRAIN TUMORS

Abstract BACKGROUND Long-term cognitive sequelae of paediatric brain tumors are of increasing interest. The role of histology and surgery remains still unclear. Our study aimed to evaluate children cognitive functioning before and after brain tumors surgery, and at the end of additional treatments. METHODS New diagnoses of paediatric primary brain tumors were prospectively assessed. Neurocognitive evaluations were performed at diagnosis (T0), within 7-10 days from surgery (T1) and 12-18 months after the end of treatments (T2). Language, learning and memory, attention, executive functions, visuo-constructional and sensorimotor skills were evaluated at T0 and T1, Intelligent Quotient (IQ) was explored at T0 and T2. RESULTS Twenty-five patients (M:F=15:10, mean age 10.9±3.4 years) were enrolled between January 2019 and December 2022. In comparison to normal values (>7.0), at baseline patients showed major deficits in narrative memory (6.6±3.7, p<0.001) and visuo-spatial memory (copy design tasks: general 6.8±3.9, p<0.001, specific 6.2±3.3, p<0.001, motor 5.2±3.2, p<0.001). At T1 assessment, significant deficits remained in narrative memory (6.2±3.3, p<0.001) and visual-motor coordination (copy design tasks: specific 5.9±3.0, p<0.001 and motor 4.8±4.3 p<0.001); attention and visual-constructional abilities significantly improved (p=0.04 and p=0.001). On the visual construction test, children with high-grade histology scored lower than the low-grade group (Rey- Osterrieth complex figure-copy 5.1±4.4 vs 11.0±4.3; p=0.019). At T2 evaluation children showed persistent deficits in visuo-spatial processing and a possible decline in IQ scores, with lower scores compared with T0 (93 vs 100, p=0.05). CONCLUSIONS Children with brain tumors may present several neuropsychological impairments at diagnosis, particularly those with high-grade diseases. Surgery may have a positive effect on the recovery of some cognitive functions. However, cognitive decline may worsen over time. Baseline and periodic neurocognitive evaluations should be encouraged to identify functional difficulties and to develop a tailored treatment approach for the patient.

PATH-11. FEASIBILITY OF BRAIN TUMOR CLASSIFICATION BY ENZYMATIC DNA METHYLATION SEQUENCING ANALYSIS OF CELL-FREE DNA OBTAINED FROM CEREBROSPINAL FLUID

Abstract BACKGROUND Array-based DNA methylation profiling is the gold standard for molecular classification of brain tumors. However, it relies on significant amount of input DNA extracted from surgical tissue, thus limiting its use for tumors where biopsy is challenging or limited in quantity. Cell-free tumor DNA (cfDNA) in cerebrospinal fluid (CSF) presents alternative opportunities for brain tumor diagnosis and disease monitoring following treatment. Novel enzymatic DNA methylation sequencing (EM-seq) methods may allow us to overcome input DNA limitations and accurately quantify methylation from cfDNA. METHODS We performed methylation sequencing using the NEBNext EM-seq kit on cfDNA from archival CSF samples collected from three brain tumor patients with confirmed histopathological diagnoses. Variable amounts of input cfDNA (0.1ng-10ng) were tested. We utilized the methylseq pipeline for data processing. For tumor classification, data was limited to CpG sites overlapping the MethylationEPIC array before analysis using MNP-Flex, a modified platform-agnostic version of the Heidelberg methylation classifier RESULTS Using the EM-seq method, genomic coverage for 10 and 1ng input DNA samples (average: 46x and 26x, respectively) was sufficient for generating global methylation profiles. Samples with 0.1ng input showed an average coverage of only 5.32x due to high levels of read duplication. However, methylation levels for CpG sites with at least 5x coverage were highly correlated across varying input DNA amounts, suggesting that lower input cfDNA could still be used for tumor classification based on relevant CpG sites. CONCLUSIONS Using the MNP-Flex classifier, which was originally trained with methylation array data from tumor tissue, we successfully predicted brain tumor types (both high-grade glioma and medulloblastoma) with cfDNA methylation data down to only 0.1ng of input cfDNA, matching diagnosis based on tissue methylation and histopathology in this pilot study. Further classification of additional tumor types using CSF cfDNA is required to confirm the clinical utility of this platform.

NURS-07. A NEEDS ASSESSMENT OF THE BRAIN TUMOR EDUCATION AND THERAPY (BEAT) GROUP AT WASHINGTON UNIVERSITY SCHOOL OF MEDICINE IN ST. LOUIS

Abstract BACKGROUND The Brain Tumor Education and Therapy (BEAT) group extends support to patients and families with pediatric brain tumor diagnoses. Social Work and healthcare providers typically meet with families quarterly to provide psychosocial support and address their educational needs. To better understand the factors that may impact participation and engagement, we sought to evaluate the opinions of current patients and their families. METHODS Both caregivers and adolescent patients, aged 16 years or older, were invited to participate in a 25-question survey. The survey assessed current sources of support, preferred meeting format, as well as educational and psychosocial needs. Additionally, the survey included questions about the patient’s diagnosis, treatment, and side effects experienced. RESULTS Over six weeks, 28 surveys were completed. Almost all respondents reported receiving support from family (93%) and friends (78%), while a smaller percentage (21%) sought support from families with similar diagnoses. Nearly half (46%) of respondents follow online or social media groups. When it comes to receiving support, 47% preferred online sessions (social media or virtual meetings), compared to in-person meetings (16%) or a combination of online and in-person (24%). Most respondents (85%) reported educational needs related to the late effects of therapy, while 69% cited concerns about friendships and socialization, and 57% on transitioning to young adulthood. Sixty-two percent request resources for emotional and psychosocial support. Respondents prefer (87%) healthcare professional-led sessions. CONCLUSION Our findings highlight an ongoing demand for healthcare professionals to provide psychosocial support and education to families of brain tumor patients. However, the preference is shifting towards virtual attendance of these meetings. In response, we intend to introduce a virtual support group and educational sessions, complemented by informative videos and handouts available on our hospital website or social media platforms. Subsequent studies will focus on family satisfaction with changes to the program.

Robust brain tumor classification by fusion of deep learning and channel-wise attention mode approach

Diagnosing brain tumors is a complex and time-consuming process that relies heavily on radiologists’ expertise and interpretive skills. However, the advent of deep learning methodologies has revolutionized the field, offering more accurate and efficient assessments. Attention-based models have emerged as promising tools, focusing on salient features within complex medical imaging data. However, the precise impact of different attention mechanisms, such as channel-wise, spatial, or combined attention within the Channel-wise Attention Mode (CWAM), for brain tumor classification remains relatively unexplored. This study aims to address this gap by leveraging the power of ResNet101 coupled with CWAM (ResNet101-CWAM) for brain tumor classification. The results show that ResNet101-CWAM surpassed conventional deep learning classification methods like ConvNet, achieving exceptional performance metrics of 99.83% accuracy, 99.21% recall, 99.01% precision, 99.27% F1-score and 99.16% AUC on the same dataset. This enhanced capability holds significant implications for clinical decision-making, as accurate and efficient brain tumor classification is crucial for guiding treatment strategies and improving patient outcomes. Integrating ResNet101-CWAM into existing brain classification software platforms is a crucial step towards enhancing diagnostic accuracy and streamlining clinical workflows for physicians.

11C-methionine in the diagnostics and management of glioblastoma patients with rapid early progression: nonrandomized, open label, prospective clinical trial (GlioMET)

BackgroundGlioblastoma (GBM) is the most common and aggressive primary brain cancer. The treatment of GBM consists of a combination of surgery and subsequent oncological therapy, i.e., radiotherapy, chemotherapy, or their combination. If postoperative oncological therapy involves irradiation, magnetic resonance imaging (MRI) is used for radiotherapy treatment planning. Unfortunately, in some cases, a very early worsening (progression) or return (recurrence) of the disease is observed several weeks after the surgery and is called rapid early progression (REP). Radiotherapy planning is currently based on MRI for target volumes definitions in many radiotherapy facilities. However, patients with REP may benefit from targeting radiotherapy with other imaging modalities. The purpose of the presented clinical trial is to evaluate the utility of 11C-methionine in optimizing radiotherapy for glioblastoma patients with REP.MethodsThis study is a nonrandomized, open-label, parallel-setting, prospective, monocentric clinical trial. The main aim of this study was to refine the diagnosis in patients with GBM with REP and to optimize subsequent radiotherapy planning.Glioblastoma patients who develop REP within approximately 6 weeks after surgery will undergo 11C-methionine positron emission tomography (PET/CT) examinations. Target volumes for radiotherapy are defined using both standard planning T1-weighted contrast-enhanced MRI and PET/CT. The primary outcome is progression-free survival defined using RANO criteria and compared to a historical cohort with REP treated without PET/CT optimization of radiotherapy.DiscussionPET is one of the most modern methods of molecular imaging. 11C-Methionine is an example of a radiolabelled (carbon 11) amino acid commonly used in the diagnosis of brain tumors and in the evaluation of response to treatment. Optimized radiotherapy may also have the potential to cover those regions with a high risk of subsequent progression, which would not be identified using standard-of-care MRI for radiotherapy planning. This is one of the first study focused on radiotherapy optimization for subgroup of patinets with REP.Trial RegistrationNCT05608395, registered on 8.11.2022 in clinicaltrials.gov; EudraCT Number: 2020–000640-64, registered on 26.5.2020 in clinicaltrialsregister.eu. Protocol ID: MOU-2020–01, version 3.2, date 18.09.2020.

CNN-Based Segmentation and Detection of Brain Tumors MRI Images: A Review

In order to provide effective therapy and enhance patient outcomes, it is essential to diagnose brain tumors as early as possible and with high accuracy. Due to the fact that it provides very specific anatomical information, magnetic resonance imaging (MRI) is an extremely important tool for diagnosing brain tumors. The manual segmentation and identification of brain tumors from MRI images, on the other hand, would take a significant amount of time and are prone to human mistake. The use of convolutional neural networks, often known as CNNs, has become more popular as a resource for automating certain activities. The purpose of this review article is to investigate the current developments in CNN-based methods for the segmentation and identification of brain tumors in magnetic resonance imaging (MRI) images. We describe the most significant difficulties that are connected with the analysis of brain tumors using MRI, investigate the different CNN designs that are used for this purpose, and evaluate the performance metrics of these architectures. The purpose of this study is to offer a complete overview of the present state-of-the-art in CNN-based brain tumor analysis of MRI data, emphasizing both the promise and limits of this method.

Glial fibrillary acidic protein, neurofilament light, matrix metalloprotease 3 and fatty acid binding protein 4 as non-invasive brain tumor biomarkers

BackgroundGliomas are aggressive malignant tumors, with poor prognosis. There is an unmet need for the discovery of new, non-invasive biomarkers for differential diagnosis, prognosis, and management of brain tumors. Our objective is to validate four plasma biomarkers – glial fibrillary acidic protein (GFAP), neurofilament light (NEFL), matrix metalloprotease 3 (MMP3) and fatty acid binding protein 4 (FABP4) – and compare them with established brain tumor molecular markers and survival.MethodsOur cohort consisted of patients with benign and malignant brain tumors (GBM = 77, Astrocytomas = 26, Oligodendrogliomas = 23, Secondary tumors = 35, Meningiomas = 70, Schwannomas = 15, Pituitary adenomas = 15, Normal individuals = 30). For measurements, we used ultrasensitive electrochemiluminescence multiplexed immunoassays.ResultsHigh plasma GFAP concentration was associated with GBM, low GFAP and high FABP4 were associated with meningiomas, and low GFAP and low FABP4 were associated with astrocytomas and oligodendrogliomas. NEFL was associated with progression of disease. Several prognostic genetic alterations were significantly associated with all plasma biomarker levels. We found no independent associations between plasma GFAP, NEFL, FABP4 and MMP3, and overall survival. The candidate biomarkers could not reliably discriminate GBM from primary or secondary CNS lymphomas.ConclusionsGFAP, NEFL, FABP4 and MMP3 are useful for differential diagnosis and prognosis, and are associated with molecular changes in gliomas.

Deep and Machine Learning Algorithms for Diagnosing Brain Cancer and Tumors

In the rapidly evolving field of medical diagnostics, the integration of deep learning (DL) and machine learning (ML) technologies has dramatically advanced the accuracy and efficiency of brain cancer and tumor diagnosis using magnetic resonance imaging (MRI). This review explores the transformative impact of these technologies, highlighting their role in enhancing tumor detection, classification, and early diagnosis interventions. DL and ML algorithms have significantly improved the analysis of complex imaging data, enabling more precise and faster diagnostic decisions, which are crucial for effective patient management and treatment planning. This review encompasses a broad spectrum of studies that illustrate the capabilities of these computational techniques in handling large datasets, learning intricate patterns, and achieving a high diagnostic performance. By delving into various algorithmic approaches and their clinical implications, this study underscores the importance of continued advancements and the integration of AI technologies in the field of oncology, aiming to foster better patient outcomes through innovative diagnostic tools.

Enhancing brain tumor classification in MRI scans with a multi-layer customized convolutional neural network approach.

The necessity of prompt and accurate brain tumor diagnosis is unquestionable for optimizing treatment strategies and patient prognoses. Traditional reliance on Magnetic Resonance Imaging (MRI) analysis, contingent upon expert interpretation, grapples with challenges such as time-intensive processes and susceptibility to human error. This research presents a novel Convolutional Neural Network (CNN) architecture designed to enhance the accuracy and efficiency of brain tumor detection in MRI scans. The dataset used in the study comprises 7,023 brain MRI images from figshare, SARTAJ, and Br35H, categorized into glioma, meningioma, no tumor, and pituitary classes, with a CNN-based multi-task classification model employed for tumor detection, classification, and location identification. Our methodology focused on multi-task classification using a single CNN model for various brain MRI classification tasks, including tumor detection, classification based on grade and type, and tumor location identification. The proposed CNN model incorporates advanced feature extraction capabilities and deep learning optimization techniques, culminating in a groundbreaking paradigm shift in automated brain MRI analysis. With an exceptional tumor classification accuracy of 99%, our method surpasses current methodologies, demonstrating the remarkable potential of deep learning in medical applications. This study represents a significant advancement in the early detection and treatment planning of brain tumors, offering a more efficient and accurate alternative to traditional MRI analysis methods.