Analysis of machine learning algorithms in brain tumour prediction

The tumour is fundamentally an excessive development of dangerous cells in any part of the body, while a tumour in a brain is an unreasonable development of cancerous cells in the brain. Brain tumour can be either benign or malignant. The benign brain tumour has structural consistency and does not include active (cancer) cells, but the malignant brain tumour has no structure consistency and includes active cells. The primary concern is to segment, detect, and extract the infected tumour area from magnetic resonance images (MRI) which are being performed by radiologists or medical experts, and their accuracy is totally dependent on their experience only. Thus, it becomes very essential to overcome these limitations by the use of artificial intelligence. The current paper uses various machine learning algorithms as well as their features to design a structure to predict brain tumour at an early phase by using different classifiers and comparing their respective accuracy parameters.

A Customisable Cell Line Model of Glioblastoma

<p><b>Glioblastoma is an extremely malignant brain tumour with one of the lowest survival rates of all cancers. Current treatments do very little to alter this prognosis. Research into new therapies and the biology of glioblastoma has made scarce progress over the past decades. This is partly due to the combination of the tumour’s heterogeneity, and the inability of the current animal models to accurately depict this. This project was a pilot study into the development and characterisation of a novel cell line model of glioblastoma, which could be transplanted into immune competent mice, in order to study the disease.</b></p> <p>An immortalised C57BL/6 astrocyte cell line, with an EGFP transgene, was used as the base to add glioblastoma specific mutations. To produce a ‘classical-like’ glioblastoma model, a knockout in Pten was induced, onto which two separate lines the human oncogenes, EGFRVIII and RAS V12, were stably expressed. ‘Secondary-like’ models were created with a knockout of P53, and the stable transfection of IDH1R132H.</p> <p>The ‘classical-like’ cell lines were assessed for how well they mimicked a classical glioblastoma. The Pten knockout cell line showed an increased proliferative and metabolic rate compared with the astrocytes and a significant increase in clonogenicity. The addition of RAS V12 to the cells showed an increased migratory capacity; and the Pten + EGFRVIII cell line had a tendency towards an increased proliferation. The ‘secondary-like’ cell lines were assessed for their survival-related phenotypes. The P53 cell line showed a decreased proliferative rate, but with an increased metabolic rate and clonogenic ability. The introduction of the IDH1 mutant protein resulted in a decreased rate of G2 arrest in response to ionising radiation.</p> <p>These cell lines recapitulated what is seen in human glioblastoma tumours and show potential as a transplantation model. Future research will investigate the tumorigenicity of these cell lines.</p>

A Customisable Cell Line Model of Glioblastoma

<p><b>Glioblastoma is an extremely malignant brain tumour with one of the lowest survival rates of all cancers. Current treatments do very little to alter this prognosis. Research into new therapies and the biology of glioblastoma has made scarce progress over the past decades. This is partly due to the combination of the tumour’s heterogeneity, and the inability of the current animal models to accurately depict this. This project was a pilot study into the development and characterisation of a novel cell line model of glioblastoma, which could be transplanted into immune competent mice, in order to study the disease.</b></p> <p>An immortalised C57BL/6 astrocyte cell line, with an EGFP transgene, was used as the base to add glioblastoma specific mutations. To produce a ‘classical-like’ glioblastoma model, a knockout in Pten was induced, onto which two separate lines the human oncogenes, EGFRVIII and RAS V12, were stably expressed. ‘Secondary-like’ models were created with a knockout of P53, and the stable transfection of IDH1R132H.</p> <p>The ‘classical-like’ cell lines were assessed for how well they mimicked a classical glioblastoma. The Pten knockout cell line showed an increased proliferative and metabolic rate compared with the astrocytes and a significant increase in clonogenicity. The addition of RAS V12 to the cells showed an increased migratory capacity; and the Pten + EGFRVIII cell line had a tendency towards an increased proliferation. The ‘secondary-like’ cell lines were assessed for their survival-related phenotypes. The P53 cell line showed a decreased proliferative rate, but with an increased metabolic rate and clonogenic ability. The introduction of the IDH1 mutant protein resulted in a decreased rate of G2 arrest in response to ionising radiation.</p> <p>These cell lines recapitulated what is seen in human glioblastoma tumours and show potential as a transplantation model. Future research will investigate the tumorigenicity of these cell lines.</p>

Calcium Signalling in Medulloblastoma: An In Silico Analysis of the Expression of Calcium Regulating Genes in Patient Samples

Dysregulation in calcium signalling is implicated in several cancer-associated processes, including cell proliferation, migration, invasion and therapy resistance. Modulators of specific calcium-regulating proteins have been proposed as promising future therapeutic agents for some cancers. Alterations in calcium signalling have been extensively studied in some cancers; however, this area of research is highly underexplored in medulloblastoma (MB), the most common paediatric malignant brain tumour. Current MB treatment modalities are not completely effective and can result in several long-lasting mental complications. Hence, new treatment strategies are needed. In this study, we sought to probe the landscape of calcium signalling regulators to uncover those most likely to be involved in MB tumours. We investigated the expression of calcium signalling regulator genes in MB patients using publicly available datasets. We stratified the expression level of these genes with MB molecular subgroups, tumour metastasis and patient survival to uncover correlations with clinical features. Of particular interest was CACNA1 genes, in which we were able to show a developmentally-driven change in expression within the cerebellum, MB’s tissue of origin, highlighting a potential influence on tumour incidence. This study lays a platform for future investigations into molecular regulators of calcium signalling in MB formation and progression.

Association Between Psychiatric Comorbidities and Mortality in Epilepsy

ABSTRACTObjective:To explore the impact of psychiatric comorbidities on all-cause mortality in adults with epilepsy from a cohort of patients admitted for video-electroencephalogram monitoring (VEM) over two decades.Methods:A retrospective medical records audit was conducted on 2709 adults admitted for VEM and diagnosed with epilepsy at three Victorian comprehensive epilepsy programs from 1995-2015. 1805 patients were identified in whom the record of a clinical evaluation by a neuropsychiatrist was available, excluding 27 patients who died from a malignant brain tumour known at the time of VEM admission. Epilepsy and lifetime psychiatric diagnoses were determined from consensus opinion of epileptologists and neuropsychiatrists involved in the care of each patient. Mortality and cause of death were determined by linkage to the Australian National Death Index and National Coronial Information System.Results:Compared to the general population, mortality was higher in people with epilepsy (PWE) with a psychiatric illness (standardised mortality ratio [SMR] 3.6) and without a psychiatric illness (SMR 2.5). PWE with a psychiatric illness had greater mortality compared to PWE without (hazards ratio 1.41, 95% confidence interval 1.02-1.97) after adjusting for age and sex. No single psychiatric disorder by itself conferred increased mortality in PWE. The distribution of causes of death remained similar between PWE with psychiatric comorbidities and those without.Conclusion:The presence of comorbid psychiatric disorders in adults with epilepsy is associated with increased mortality, highlighting the importance of identifying and treating psychiatric comorbidities in these patients.

Radiobiological Evaluation of Combined Gamma Knife Radiosurgery and Hyperthermia for Pediatric Neuro-Oncology

Combining radiotherapy (RT) with hyperthermia (HT) has been proven effective in the treatment of a wide range of tumours, but the combination of externally delivered, focused heat and stereotactic radiosurgery has never been investigated. We explore the potential of such treatment enhancement via radiobiological modelling, specifically via the linear-quadratic (LQ) model adapted to thermoradiotherapy through modulating the radiosensitivity of temperature-dependent parameters. We extend this well-established model by incorporating oxygenation effects. To illustrate the methodology, we present a clinically relevant application in pediatric oncology, which is novel in two ways. First, it deals with medulloblastoma, the most common malignant brain tumour in children, a type of brain tumour not previously reported in the literature of thermoradiotherapy studies. Second, it makes use of the Gamma Knife for the radiotherapy part, thereby being the first of its kind in this context. Quantitative metrics like the biologically effective dose (BED) and the tumour control probability (TCP) are used to assess the efficacy of the combined plan.

EMBR-10. INOSITOL TREATMENT INHIBITS MEDULLOBLASTOMA THROUGH SUPPRESSION OF EPIGENETIC-DRIVEN METABOLIC ADAPTATION

Medulloblastoma (MB) is the most common paediatric malignant brain tumour and is classified into four distinct molecular subgroups (WNT, SHH, G3 and G4), each of them further subdivided into subtypes with different prognosis and responses to therapy. Deregulation of chromatin modifier genes plays an essential role in MB, particularly in the G4 subgroup, the least understood of all subgroups, despite being the most common and associated with poor prognosis. A BMI1High; CHD7Low molecular signature identifies patients with poor survival within this subgroup. We show that BMI1High; CHD7Low mediates a novel epigenetic regulation of inositol metabolism in both G4 MB cells and patients. These tumours display hyperactivation of the AKT/mTOR pathway which leads to energetic rewiring characterized by enhanced glycolytic capacity and reduced mitochondrial function. We demonstrate that inositol administration counteracts this metabolic alteration, impairs MB proliferation in vitro and significantly extends survival in an in vivo pre-clinical model. Moreover, inositol synergises with cisplatin, a chemotherapy agent currently used in MB treatment, enhancing its therapeutic effect in vivo. Importantly, cerebellar neural stem cells bearing the BMI1High; CHD7Low signature do not show metabolic adaptation and are thus resistant to inositol treatment, highlighting a fundamental difference between normal and neoplastic metabolism in the developing cerebellum. In summary, we have identified an actionable vulnerability in a pre-clinical setting modelling a molecularly defined group of MB patients, the translational value of which can now be explored in signature-matched clinical trials in MB.

Laparoscopic gynaecological surgery in the context of maintaining normal intracranial pressure

A nulliparous patient in her early 20s was referred to a fertility specialist for fertility preservation, before commencing chemo–radiation therapy for a recently diagnosed malignant brain tumour. Two weeks prior, she had presented with seizures and undergone emergency craniotomy and tumour resection. Taking into consideration of the tight time frame and her comorbidities, several measures were undertaken to minimise the potential increase in intracranial pressure that may lead to cerebral oedema during laparoscopy. Preoperatively, the anaesthetist administered 8 mg dexamethasone as prophylaxis. Intraoperatively, the degree of head-down tilt was minimised to 10, which was just adequate to displace bowel cranially for visualisation of pelvic structures. Finally, a shorter operative time was achieved by ensuring the most senior surgeon performed the operation, and the procedure itself was altered from the standard approach of ovarian harvesting to unilateral oophorectomy. The patient made a quick recovery and was discharged home day 1 postoperatively.

Inositol treatment inhibits medulloblastoma through suppression of epigenetic-driven metabolic adaptation

Deregulation of chromatin modifiers plays an essential role in the pathogenesis of medulloblastoma, the most common paediatric malignant brain tumour. Here, we identify a BMI1-dependent sensitivity to deregulation of inositol metabolism in a proportion of medulloblastoma. We demonstrate mTOR pathway activation and metabolic adaptation specifically in medulloblastoma of the molecular subgroup G4 characterised by a BMI1High;CHD7Low signature and show this can be counteracted by IP6 treatment. Finally, we demonstrate that IP6 synergises with cisplatin to enhance its cytotoxicity in vitro and extends survival in a pre-clinical BMI1High;CHD7Low xenograft model.