Artificial Intelligence improves Brain tumor diagnosis

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 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: a computational decision support system for glioma classification using hybrid radionics and stationary wavelet-based features.

The algorithm 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.