BRAIN AND SPINAL CORD TUMORS

Epidemiology and etiology of brain cancer in Africa: A systematic review

BACKGROUND

Cancer is a significant threat to public health and a leading cause of morbidity across the globe. Of all cancers, brain cancer can be particularly catastrophic as treatment often fails to achieve the desired degree of effectiveness and diagnosis remains associated with a high mortality rate. Africa, as a continent with resource-limited countries, needs to allocate the necessary proper healthcare infrastructure to significantly reduce cancer rates and improve patient survival. In addition, the relative paucity of data within this field in Africa makes effective management a challenge.

OBJECTIVE

This review is aimed at elucidating the currently available evidence base with regard to the epidemiology and etiology of brain cancer within resource-limited African countries. This review hopes to bring to the attention of the wider clinical community the growing burden of brain cancer within Africa and to encourage future research into this field of research.

METHODS

The available literature for this Systematic Review was searched on two bibliographic databases, PubMed and Scopus, using an individually verified, prespecified approach. In addition, the Global Cancer Observatory and Global Burden of Disease databases were also utilized. Studies reporting on the epidemiology, etiology, and impact of brain cancer in Africa were suitable for inclusion. The level of evidence of the included studies was considered as per the Centre for Evidence-Based Medicine recommendations.

RESULTS

Out of the four databases searched, 3848 articles were initially screened rigorously, filtered into 54 articles, and finally assessed qualitatively and quantitatively. We have demonstrated a poor survival rate and lack of proper funds/resources necessary to report, identify, and treat cases, as well as the dearth of comprehensive research on the subject of brain cancer that has become a challenging healthcare concern in many African developing nations. Also, because of the gradual improvement in healthcare facilities and the increasing population within many countries in Africa, the number of patients with central nervous system and intracranial tumors is rising specifically in the elder population. In addition, the population in West Africa is at a higher risk of HIV-related malignancies due to the high prevalence of HIV in West Africa. The burden of brain cancer in Africa is increasing in comparison with the developed parts of the world in which it is decreasing. Moreover, the mismanagement of cancers in Africa leads to higher morbidity and mortality and decreased quality of life.

CONCLUSION

This study addresses the burden of brain cancer as a major public health crisis in Africa. Improved treatment modalities and access to screening are required to better address the burden of this disease. Therefore, there is a clear need for more substantial and comprehensive research on etiology, epidemiology, and treatment of brain cancer within Africa to understand its epidemiological distribution and provide a means for managing and reducing the associated morbidity and mortality.

Grading of gliomas using transfer learning on MRI images

OBJECTIVE

Despite the critical role of Magnetic Resonance Imaging (MRI) in the diagnosis of brain tumours, there are still many pitfalls in the exact grading of them, in particular, gliomas. In this regard, it was aimed to examine the potential of Transfer Learning (TL) and Machine Learning (ML) algorithms in the accurate grading of gliomas on MRI images.

MATERIALS AND METHODS

Dataset has included four types of axial MRI images of glioma brain tumours with grades I-IV: T1-weighted, T2-weighted, FLAIR, and T1-weighted Contrast-Enhanced (T1-CE). Images were resized, normalized, and randomly split into training, validation, and test sets. ImageNet pre-trained Convolutional Neural Networks (CNNs) were utilized for feature extraction and classification, using Adam and SGD optimizers. Logistic Regression (LR) and Support Vector Machine (SVM) methods were also implemented for classification instead of Fully Connected (FC) layers taking advantage of features extracted by each CNN.

RESULTS

Evaluation metrics were computed to find the model with the best performance, and the highest overall accuracy of 99.38% was achieved for the model containing an SVM classifier and features extracted by pre-trained VGG-16.

DISCUSSION

It was demonstrated that developing Computer-aided Diagnosis (CAD) systems using pre-trained CNNs and classification algorithms is a functional approach to automatically specify the grade of glioma brain tumours in MRI images. Using these models is an excellent alternative to invasive methods and helps doctors diagnose more accurately before treatment.