Have you been diagnosed with a brain tumour? Order your free information pack.

Artificial Intelligence improves Brain tumour diagnosis

A new machine learning approach can classify gliomas, a common type of brain tumour, into low or high grades with almost 98% accuracy, researchers report in the journal IEEE Access.

Scientists in India and Japan, including from Kyoto University’s Institute for Integrated Cell-Material Sciences (iCeMS), developed this method to allow clinicians to choose the best treatment plan for their patients depending on the grade of their brain tumour.

The usual diagnosis method for gliomas is through MRI scans, which reconstruct a 3D imagine of scanned tissue and give valuable data about the tumour’s shape and texture.

Artificial intelligence algorithms have been helping extract this data for a long time. Medical oncologists have been using this approach, called radiomics, to improve patient diagnoses, however there is still room for improvement in accuracy.

That’s why iCeMS bioengineer Ganesh Pandian Namasivayam teamed up with data scientist Balasubramanian Raman to develop a machine learning approach that can classify gliomas into low or high grade with a massive 97.54% accuracy rate.

This is an important development for patients with brain tumours because the choice of treatment for gliomas largely depends on the glioma’s grading.

The team used a dataset from 210 MRI scans of people with high grade gliomas and another 75 with low grade gliomas. They developed a machine learning approach called CGHF, which stands for: computational decision support system for glioma classification using hybrid radiomics and stationary wavelet-based features.

The algorthims they chose to extract information about the brain tumours from the MRI scans accurately processed the data and classified the gliomas. They then tested their model on the rest of the MRI scans to assess its accuracy of 97.54%.

“Our method outperformed other state-of-the-art approaches for predicting glioma grades from brain MRI scans,” says Balasubramanian. “This is quite considerable.”

“We hope AI helps develop a semi-automatic or automatic machine predictive software model that can help doctors, radiologists, and other medical practitioners tailor the best approaches for their individual patients,” adds Ganesh.