News | Analytics Software | October 25, 2016

Computer Program Beats Physicians at Brain Cancer Diagnoses

New research could speed identification of recurrent tumors, eliminate costly and risky brain biopsies

Case Western Reserve University study, machine learning, MRI, brain cancer diagnoses, radiomics

MRI scans of patients with radiation necrosis (above) and cancer recurrence (below) are shown in the left column. Close-ups in the center column show the regions are indistinguishable on routine scans. Radiomic descriptors unearth subtle differences showing radiation necrosis, in the upper right panel, has less heterogeneity, shown in blue, compared to cancer recurrence, in the lower right, which has a much higher degree of heterogeneity, shown in red. Credit: Pallavi Tiwari

October 25, 2016 — Computer programs have defeated humans in Jeopardy!, chess and Go. Now a program developed at Case Western Reserve University has outperformed physicians on a more serious matter.

The program was nearly twice as accurate as two neuroradiologists in determining whether abnormal tissue seen on magnetic resonance images (MRI) were dead brain cells caused by radiation, called radiation necrosis, or if brain cancer had returned.

The direct comparison is part of a feasibility study published in the American Journal of Neuroradiology.

“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.”

But treatments for radiation necrosis and cancer recurrence are far different. Quick identification can help speed prognosis, therapy and improve patient outcomes, the researchers say.

With further confirmation of its accuracy, radiologists using their expertise and the program may eliminate unnecessary and costly biopsies, Tiwari said. Brain biopsies are currently the only definitive test but are highly invasive and risky, causing considerable morbidity and mortality.

To develop the program, the researchers employed machine learning algorithms in conjunction with radiomics, the term used for features extracted from images using computer algorithms. The engineers, scientists and physicians trained the computer to identify radiomic features that discriminate between brain cancer and radiation necrosis, using routine follow-up MRI scans from 43 patients. The images were all from University Hospitals Case Medical Center.

The team then developed algorithms to find the most discriminating radiomic features — in this case, textures that can’t be seen by simply eyeballing the images.

“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, who was appointed to the Department of Biomedical Engineering by the Case Western Reserve School of Medicine.

More specifically, while the physicians use the intensity of pixels on MRI scans as a guide, the computer looks at the edges of each pixel, explained Anant Madabhushi, F. Alex Nason professor II of biomedical engineering at Case Western Reserve, and study co-author.

“If the edges all point to the same direction, the architecture is preserved,” said Madabhushi, who also directs the Center of Computational Imaging and Personalized Diagnostics at CWRU. “If they point in different directions, the architecture is disrupted — the entropy, or disorder, and heterogeneity are higher. “

In the direct comparison, two physicians and the computer program analyzed MRI scans from 15 patients from University of Texas Southwest Medical Center. One neuroradiologist diagnosed seven patients correctly, and the second physician correctly diagnosed eight patients. The computer program was correct on 12 of the 15.

Tiwari and Madabhushi do not expect the computer program would be used alone, but as a decision support to assist neuroradiologists in improving their confidence in identifying a suspicious lesion as radiation necrosis or cancer recurrence.

Next, the researchers are seeking to validate the algorithms’ accuracy using a much larger collection of images from across different sites.

For more information: www.ajnr.org

Related Content

Older Biologic Age Linked to Elevated Breast Cancer Risk
News | Women's Health | March 19, 2019
Biologic age, a DNA-based estimate of a person’s age, is associated with future development of breast cancer, according...
Gregory W. Albers, M.D., Receives Distinguished Clinical Research Achievement Award for Stroke Research
News | Stroke | March 19, 2019
iSchemaView announced the company’s co-founder Gregory Albers, M.D., has received the Distinguished Clinical Research...
HeartFlow Analysis Successfully Stratifies Heart Disease Patients at One Year
News | CT Angiography (CTA) | March 19, 2019
Late-breaking results confirm the HeartFlow FFRct (fractional flow reserve computed tomography) Analysis enables...
DrChrono and 3D4Medical Partner to Bring 3-D Interactive Modeling to Physician Practices
News | Advanced Visualization | March 18, 2019
DrChrono Inc. and 3D4Medical have teamed up so practices across the United States can access 3-D interactive modeling...
PET Scans Show Biomarkers Could Spare Some Breast Cancer Patients from Chemotherapy
News | PET Imaging | March 18, 2019
A new study positron emission tomography (PET) scans has identified a biomarker that may accurately predict which...
SyncVision iFR Co-registration from Philips Healthcare maps iFR pressure readings onto angiogram.

SyncVision iFR Co-registration from Philips Healthcare maps iFR pressure readings onto angiogram. Results from an international study presented at #ACC19 show that pressure readings in coronary arteries may identify locations of stenoses remaining after cardiac cath interventions.

Feature | Cardiac Imaging | March 18, 2019 | By Greg Freiherr
As many as one in four patients who undergo cath lab interventions can benefit from a technology that identifies the
Non-Contrast MRI Effective in Monitoring MS Patients
News | Neuro Imaging | March 18, 2019
Brain magnetic resonance imaging (MRI) without contrast agent is just as effective as the contrast-enhanced approach...
Jennifer N. A. Silva, M.D., a pediatric cardiologist at Washington University School of Medicine in Saint Louis, Mo., describes “mixed reality” at ACC19 Future Hub.

Jennifer N. A. Silva, M.D., a pediatric cardiologist at Washington University School of Medicine in Saint Louis, Mo., describes “mixed reality” at ACC19 Future Hub.

Feature | Cardiac Imaging | March 17, 2019 | By Greg Freiherr
Virtual reality (VR) and its less immersive kin, augmented reality (AR), are gaining traction in some medical applica
WVU cardiology chief Partho Sengupta, M.D., describes at ACC 2019 how artificial intelligence already helps cardiologists in echocardiography.

WVU cardiology chief Partho Sengupta, M.D., describes at ACC 2019 how artificial intelligence already helps cardiologists in echocardiography. Photo by Greg Freiherr

Feature | Cardiac Imaging | March 16, 2019 | By Greg Freiherr
Machine learning is already having an enormous impact on cardiology, automatically calculating measurements in echoca
New MRI Sensor Can Image Activity Deep Within the Brain
News | Magnetic Resonance Imaging (MRI) | March 15, 2019
Calcium is a critical signaling molecule for most cells, and it is especially important in neurons. Imaging calcium in...