SEP 27, 2016 02:22 PM PDT

Machine Outperforms Doctors at Diagnosing Brain Cancer

WRITTEN BY: Xuan Pham
“Come in, Mr. Smith. The computer is ready for your diagnosis now.” This could conceivably be in store for brain cancer patients in the future, as a new computer program shows nearly twice the accuracy of doctors at diagnosing the tumors.
 
Computer training and machine learning has come a long ways – machines have beat humans in Jeopardy!, chess, even Go. In August 2016, machine learning even helped to rekindle seemingly deadened nerves, giving paraplegics limb sensations they hadn’t felt in years. Now, Case Western Reserve researchers say their computer program can tell whether abnormal MRI scans are indicative of dead tissues (radiation necrosis) or the recurrence of brain cancer. And, impressively, the program can do this better than trained neuroradiologists.

MRI scans of patients with radiation necrosis (above) and cancer recurrence (below) are shown in the left column. | Image: Tiwari Lab
 
"One of the biggest challenges with the evaluation of brain tumor treatment is distinguishing between the confounding effects of radiation and cancer recurrence," said Pallavi Tiwari, assistant professor of biomedical engineering at Case Western Reserve and leader of the study. "On an MRI, they look very similar."
 
To better distinguish between radiation necrosis and cancer recurrence, the team trained a computer to read radiomic features from an image scan. These features include textures and densities that can’t be gleaned with the naked eye.
 
"What the algorithms see that the radiologists don't are the subtle differences in quantitative measurements of tumor heterogeneity and breakdown in microarchitecture on MRI, which are higher for tumor recurrence," said Tiwari.
 

The algorithm also takes into account the edge space of a mass. This can reveal important information about the identity of the mass. "If the edges all point to the same direction, the architecture is preserved," said Anant Madabhushi, professor at Case Western who is co-author on the study. "If they point in different directions, the architecture is disrupted -- the entropy, or disorder, and heterogeneity are higher."
 
In a head-to-head test, the team gave 15 MRI scans to 2 physicians and compared the results to that from the computer algorithm. The algorithm was able to correctly diagnose more cases (12 total) than either of the physicians (7 and 8 cases each).
 
While it may still be unreasonable to solely rely on a computer algorithm to read brain cancer scans, the team hopes this tool will augment the accuracy of diagnoses for patients. Importantly, the right diagnosis can eliminate unnecessary biopsies and other procedures that are both extremely stressful and costly. 

Additional source: Case Western Reserve University
About the Author
  • I am a human geneticist, passionate about telling stories to make science more engaging and approachable. Find more of my writing at the Hopkins BioMedical Odyssey blog and at TheGeneTwist.com.
You May Also Like
APR 25, 2018
Clinical & Molecular DX
APR 25, 2018
Why is dementia going unnoticed in hospitals?
A study in the UK showed that while the rate of diagnosis for dementia is improving, more than a third of all dementia patients still go undiagnosed. The n...
MAY 24, 2018
Neuroscience
MAY 24, 2018
Can Brain Fold Patterns Predict Psychosis?
While it's a famous slogan and not meant to be taken verbatim, in neuroscience, it's often true that "Image is everything." A recent stud...
JUN 23, 2018
Clinical & Molecular DX
JUN 23, 2018
Algorithm-Based Blood Test Diagnoses Autism
As a developmental disorder, autism spectrum disorders (ASD) can be diagnosed as early as 18 to 24 months of age, but often the diagnosis does not come unt...
JUN 29, 2018
Clinical & Molecular DX
JUN 29, 2018
TRAF7 Mutation Responsible for Mysterious Disorder
A multisystem developmental disorder with specific symptoms shared by seven patients had gone unexplained, but a new genetic sequencing study may provide a...
AUG 16, 2018
Clinical & Molecular DX
AUG 16, 2018
Bubbles and a blood test could detect brain tumors
Researchers have developed a proof-of-concept technique that allows them to detect brain tumor biomarkers with a simple blood test, rather than a complicat...
OCT 16, 2018
Microbiology
OCT 16, 2018
Simple Test Rapidly Diagnoses Antibiotic-resistant Infections
If we get a bacterial infection, doctors use antibiotics to treat it. But sometimes people are infected by pathogens that are resistant to drugs....
Loading Comments...