Deep Learning Model Classifies Brain Tumors with Single MRI Scan

A team of researchers at Washington University School of Medicine have developed a deep learning model that is capable of classifying a brain tumor as one of six common types using a single 3D MRI scan, according to a study published in Radiology: Artificial Intelligence.

"This is the first study to address the most common intracranial tumors and to directly determine the tumor class or the absence of tumor from a 3D MRI volume," said Satrajit Chakrabarty, M.S., a doctoral student under the direction of Aristeidis Sotiras, Ph.D., and Daniel Marcus, Ph.D., in Mallinckrodt Institute of Radiology's Computational Imaging Lab at Washington University School of Medicine in St. Louis, Missouri.

The six most common intracranial tumor types are high-grade glioma, low-grade glioma, brain metastases, meningioma, pituitary adenoma and acoustic neuroma. Each was documented through histopathology, which requires surgically removing tissue from the site of a suspected cancer and examining it under a microscope.

According to Chakrabarty, machine and deep learning approaches using MRI data could potentially automate the detection and classification of brain tumors.

"Non-invasive MRI may be used as a complement, or in some cases, as an alternative to histopathologic examination," he said.

To build their machine learning model, called a convolutional neural network, Chakrabarty and researchers from Mallinckrodt Institute of Radiology developed a large, multi-institutional dataset of intracranial 3D MRI scans from four publicly available sources. In addition to the institution’s own internal data, the team obtained pre-operative, post-contrast T1-weighted MRI scans from the Brain Tumor Image Segmentation, The Cancer Genome Atlas Glioblastoma Multiforme, and The Cancer Genome Atlas Low Grade Glioma.

The researchers divided a total of 2,105 scans into three subsets of data: 1,396 for training, 361 for internal testing and 348 for external testing. The first set of MRI scans was used to train the convolutional neural network to discriminate between healthy scans and scans with tumors, and to classify tumors by type. The researchers evaluated the performance of the model using data from both the internal and external MRI scans.

Using the internal testing data, the model achieved an accuracy of 93.35% (337 of 361) across seven imaging classes (a healthy class and six tumor classes). Sensitivities ranged from 91% to 100%, and positive predictive value - or the probability that patients with a positive screening test truly have the disease - ranged from 85% to 100%. Negative predictive values - or the probability that patients with a negative screening test truly don't have the disease - ranged from 98% to 100% across all classes. Network attention overlapped with the tumor areas for all tumor types.

For the external test dataset, which included only two tumor types (high-grade glioma and low-grade glioma), the model had an accuracy of 91.95%.

"These results suggest that deep learning is a promising approach for automated classification and evaluation of brain tumors," Chakrabarty said. "The model achieved high accuracy on a heterogeneous dataset and showed excellent generalization capabilities on unseen testing data."

Chakrabarty said the 3D deep learning model comes closer to the goal of an end-to-end, automated workflow by improving upon existing 2D approaches, which require radiologists to manually delineate, or characterize, the tumor area on an MRI scan before machine processing. The convolutional neural network eliminates the tedious and labor-intensive step of tumor segmentation prior to classification.

Dr. Sotiras, a co-developer of the model, said it can be extended to other brain tumor types or neurological disorders, potentially providing a pathway to augment much of the neuroradiology workflow.

"This network is the first step toward developing an artificial intelligence-augmented radiology workflow that can support image interpretation by providing quantitative information and statistics," Chakrabarty added.

Satrajit Chakrabarty, Aristeidis Sotiras, Mikhail Milchenko, Pamela LaMontagne, Michael Hileman, Daniel Marcus.
MRI-based Identification and Classification of Major Intracranial Tumor Types Using a 3D Convolutional Neural Network: A Retrospective Multi-Institutional Analysis.
Radiology: Artificial Intelligence, 2021. doi 10.1148/ryai.2021200301

Most Popular Now

Digital Health Webinar

14 September 2021, Webinar. The digital healthcare ecosystem is evolving with rapid speed. Technologies such as AI, robotics, telemedicine, and precision medicine are a mix of challenges and opportunities...

Using AI for Early Detection and Treatme…

Artificial intelligence (AI) will fundamentally change medicine and healthcare: Diagnostic patient data, e.g. from ECG, EEG or X-ray images, can be analyzed with the help of machine learning, so that...

Waiting Times for Medical Admissions Red…

Clinicians at Bolton NHS Foundation Trust have dramatically reduced patient waiting times, decreased hospital length of stay and improved patient safety after developing an electronic acute medical list solution to manage patient referrals.  The configuration was initially set-up to track referrals and admissions...

AI Algorithm Solves Structural Biology C…

Determining the 3D shapes of biological molecules is one of the hardest problems in modern biology and medical discovery. Companies and research institutions often spend millions of dollars to determine...

Novel AI Blood Testing Technology can ID…

A novel artificial intelligence blood testing technology developed by researchers at the Johns Hopkins Kimmel Cancer Center was found to detect over 90% of lung cancers in samples from nearly...

Accenture HealthTech Innovation Challeng…

Accenture (NYSE: ACN) has named eight companies as finalists in the Accenture HealthTech Innovation Challenge, which brings together leading-edge startups with prominent health companies to tackle some of North America's...

Clinerion Patent for Technology Underpin…

The new Clinerion patent underpins any medical EHR database infrastructure that incorporates a hybrid model of cloud-and-local server node installations at individual hospitals, as well as any method for search...

Data MATRIX Introduces an AI-Operated Pa…

Data MATRIX, a sole Real-World Evidence solutions provider in Russia, has presented a predictive analytics tool for estimating patient survival based on Real-World Data. An important feature of the presented tool for...

Researchers Use AI to Predict which COVI…

Researchers at Case Western Reserve University have developed an online tool to help medical staff quickly determine which COVID-19 patients will need help breathing with a ventilator. The tool, developed through...

A Game Changer: Virtual Reality Reduces …

It isn’t a matter of one needle puncture. Many children coming through the doors of Children's Hospital Los Angeles are seen for chronic conditions and often require frequent visits. Painful...

Bittium Expands Its Minority Holdings in…

Bittium Biosignals Ltd, a subsidiary of Bittium Corporation, and British ECG service provider, Technomed Limited, have today signed an agreement under which Bittium will purchase a 25 percent stake in...

Scientists Develop AI to Predict the Suc…

A study in which machine-learning models were trained to assess over 1 million companies has shown that artificial intelligence (AI) can accurately determine whether a startup firm will fail or...