English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

A brain tumour is an exponential proliferation of cancerous tissues in the brain. The capacity to accurately segregate and categorise tumours is consequential for later prognosis and therapy planning. Patients with brain tumours must plan their surgery based on their survival prognostication. By combining 3D radiomics parameters, such as shape, geometry, wavelet features and clinical information, a radionics-based overall survival (OS) prediction approach was developed. For the survival prediction, 858 radiomics characteristics were obtained from each of the 325 segmented tumour volumes and then determined 4,875 effective features using univariate selection, the Pearson correlation and an ensemble of the two aforementioned feature selection methods. Finally, to predict the overall survival of the patient, nine machine learning models were developed. An accuracy of 73.8 percent was achieved in predicting the survival of short-survivors and long-survivors while using the Pearson correlation feature selection methods with XGBoosting and soft voting classifiers, respectively. Furthermore, a 70.6 percent accuracy was obtained while using the Pearson correlation method combined with the random forest, gradient boosting, and AdaBoost classifiers. The experimental results demonstrate that the proposed strategy for predicting the survival of gliomas is efficient and effective.

Brain tumour segmentation and survival prognostication using 3D radiomics features and machine learning algorithms