Breaking News
December 18, 2018 - Artificial intelligence and the future of medicine
December 18, 2018 - Montana State doctoral student receives grant for her work to improve neuroscience tool
December 18, 2018 - Early postpartum initiation of opioids associated with persistent use
December 18, 2018 - Russian scientists identify molecular ‘switch’ that could be target for treatment of allergic asthma
December 18, 2018 - Surgeons make more mistakes in the operating room during stressful moments, shows study
December 18, 2018 - Immune cells explode themselves to inform about the danger of invading bacteria
December 18, 2018 - Malnutrition in children with Crohn’s disease linked with increased risk of surgical complications
December 18, 2018 - FDA Approves Motegrity (prucalopride) for Adults with Chronic Idiopathic Constipation (CIC)
December 18, 2018 - The long and short of CDK12
December 18, 2018 - CMR Surgical partners with Nicholson Center to launch U.S.-based training program for Versius
December 18, 2018 - Findings reinforce guidelines for cautious use of antipsychotics in younger populations
December 18, 2018 - Study finds new strains of hepatitis C virus in sub-Saharan Africa
December 18, 2018 - New battery-free, implantable device aids weight loss
December 18, 2018 - Parental alcohol use disorder associated with offspring marital outcomes
December 18, 2018 - Novel Breast Imaging Technique Might Cut Unnecessary Biopsies
December 18, 2018 - What can a snowflake teach us about how cancer spreads in the body?
December 18, 2018 - Management of nausea and vomiting in pregnancy costs the NHS more than previously thought
December 18, 2018 - Green leafy vegetables may reduce risk of developing liver steatosis
December 18, 2018 - Veganism linked to nutrient deficiencies and malnutrition if not planned correctly
December 18, 2018 - Coming Soon: A Tiny Robot You Swallow to Help You Stay Healthy
December 18, 2018 - Modified malaria drug proven effective at inhibiting Ebola
December 18, 2018 - Study finds epigenetic differences in the brains of individuals with schizophrenia
December 18, 2018 - Fitness instructors’ motivational comments influence women’s body satisfaction
December 18, 2018 - Study focuses on modification of lipid nanoparticles for successful brain cell targeting
December 18, 2018 - New gut bacteria may be effective against obesity, metabolic and mental disorders
December 18, 2018 - New two-in-one powder aerosol to upgrade fight against deadly superbugs in lungs
December 18, 2018 - Biofilms feed with swirling flows
December 17, 2018 - Study identifies specific neurological changes related to traumatic brain injury
December 17, 2018 - New study confirms geographic bias in lung allocation for transplant
December 17, 2018 - Research focuses on optimization of solid lipid nanoparticle that encapsulates Vinorelbine bitartrate
December 17, 2018 - Carpal tunnel syndrome – Genetics Home Reference
December 17, 2018 - A novel insulin accelerant
December 17, 2018 - Tips for caring for patients with disabilities, from a mother and physician
December 17, 2018 - Menopause-related sexual, urinary problems tied to worse quality of life
December 17, 2018 - In-school nutrition programs among students limit increases in BMI, finds study
December 17, 2018 - Risk for Hospitalization for Heart Failure Greater With Diabetes
December 17, 2018 - Food assistance may help older adults adhere to diabetes meds
December 17, 2018 - Supporting a family’s goals during a difficult pregnancy
December 17, 2018 - Neurons with Good Housekeeping Are Protected from Alzheimer’s
December 17, 2018 - New approach to tumor analysis could improve prognosis for bowel cancer patients
December 17, 2018 - New ‘epigenetics-based’ cervical cancer test outperforms Pap smear and HPV tests
December 17, 2018 - Ten year follow-up after negative colonoscopy related to reduced risk of colorectal cancer
December 17, 2018 - CTF along with NTAP and Sage announce first-ever open data portal for neurofibromatosis
December 17, 2018 - Intimacy: The Elusive Fountain of Youth?
December 17, 2018 - Will saliva translate to a real diagnostic tool?
December 17, 2018 - DFG establishes nine new Research Units and one new Clinical Research Unit
December 17, 2018 - Assisted living’s breakneck growth leaves patient safety behind
December 17, 2018 - America’s teens report dramatic increase in their use of vaping devices in just one year
December 17, 2018 - Enlarged heart linked to a higher risk of dementia
December 17, 2018 - Prostate cancer detection using MRI now first-line investigation tool
December 17, 2018 - Loughborough academics part of new project investigating effectiveness of personalized breast cancer screening
December 17, 2018 - Adolescents who use cognitive reappraisal had better metabolic measures, shows study
December 17, 2018 - Probiotics may offer therapeutic benefits for biopolar patients
December 17, 2018 - Stealth BioTherapeutics Granted Fast Track Designation for Elamipretide for the Treatment of Dry Age-Related Macular Degeneration with Geographic Atrophy
December 17, 2018 - Studies reveal role of red meat in gut bacteria, heart disease development
December 17, 2018 - Eisai enters into agreement with Eurofarma for its anti-obesity agent lorcaserin
December 17, 2018 - Researchers use brain connectome to reassess neuroimaging findings of Alzheimer’s disease
December 17, 2018 - “Miracle” baby survives Ebola in Congo and rapid a new Ebola detection device
December 17, 2018 - Mechanisms behind neonatal diabetes uncovered
December 17, 2018 - AHF urges the WHO to expedite approval process for vaccine effective against Ebola
December 17, 2018 - Study finds misuse of benzodiazepines to be highest among young adults
December 17, 2018 - TGen receives PayPal grant to underwrite costs of genetic tests for children with rare disorders
December 17, 2018 - New research highlights why HIV-infected patients suffer higher rates of cancer
December 17, 2018 - Antibiotic-resistant bacteria could soon be targeted with Alzheimer’s drug
December 17, 2018 - Rutgers scientists take an important step in making diseased hearts heal themselves
December 17, 2018 - Tailored Feedback at CRC Screen Improves Lifestyle Behaviors
December 17, 2018 - Loss of two genes drives a deadly form of colorectal cancer, reveals a potential treatment
December 17, 2018 - How the Mediterranean Diet Can Help Women’s Hearts
December 17, 2018 - Sustained connections associated with symptoms of autism
December 17, 2018 - Concussion rates among young football players were higher than previously reported
December 17, 2018 - Cresco Labs granted approval to operate marijuana dispensary in Ohio
December 17, 2018 - Study provides insight into health risks facing new mothers
December 17, 2018 - AMSBIO expands Wnt signaling pathway product range to aid research
December 16, 2018 - Surgical treatment unnecessary for many prostate cancer patients
December 16, 2018 - Excess weight responsible for cancers globally finds report
December 16, 2018 - Regular sex associated with greater enjoyment of life in seniors
December 16, 2018 - Social stigma contributes to poor mental health in the autistic community
December 16, 2018 - Multidisciplinary team successfully performs complex surgery on patient suffering from enlarged skull
December 16, 2018 - Experts analyze data that can guide antidepressant discontinuation
December 16, 2018 - Menlo Therapeutics’ Successful Phase 2 Clinical Trial of Serlopitant Demonstrates Reduction of Pruritus Associated with Psoriasis
AI, doctors team up to improve, expedite diagnoses

AI, doctors team up to improve, expedite diagnoses

image_pdfDownload PDFimage_print

As the role of artificial intelligence in medicine continues to evolve, doctors and robots are often seen as pitted against each other. But two new studies suggest that it’s not man versus machine, it’s man and machine.

The research harnesses artificial intelligence to “read” medical images, from X-rays to more advanced scans such as magnetic resonance imaging, or MRI, scans. The ultimate goal is not to replace physicians, says co-senior author Matthew Lungren, PhD, it’s instead to provide all clinicians with tools to make faster, more accurate imaging diagnoses and treatment plans  — something that could one day benefit patients across the world.

A team of scientists led by Lungren, an assistant professor of radiology, and Andrew Ng, PhD, an adjunct professor of computer science, have devised two algorithms poised to do just that. One of the latest algorithms, which diagnoses knee injuries by automatically reading MRI scans, has already made its way into the hands of Stanford clinicians for preliminary testing.

The results were published today in PLOS Medicine. Graduate students Nicholas Bien and Pranav Rajpurkar are the first authors.

“One of the main goals of this paper is to figure out how doctors, both radiologists and non-radiologist clinicians, would work with algorithms that read medical scans,” said Lungren. “Does it make them better? Worse?”

So far, it’s one of the first studies to investigate how the physician-and-machine dynamic might work. The preliminary results show that the algorithm, called MRNet, not only performed at about the same level as radiologists on its own (although sometimes it performed just below depending on the MRI), it actually helped radiologists more accurately diagnose MRI scans of knee injuries.

“We developed MRNet for knee MRIs, but the same algorithm could also potentially classify other types of MRI,” said Bien. After the algorithm has been trained on a large dataset, it can generate predictions for a new MRI scan in a matter of seconds.”

MRNet was trained on a dataset of 1,370 MRI scans. Such image-based diagnostics comes down to pattern recognition, and in this case, the scientists trained the algorithm to recognize visual patterns associated with ligament and meniscal tears in the knee, as well as anything else that looks iffy. A panel of expert radiologists then sifted through a separate set of 120 knee MRIs to find a “ground truth,” for each scan, or diagnoses that the radiologists agreed was the right call. This set of images served to establish MRNet’s accuracy.

To answer if MRNet helped or hindered doctors diagnosing MRIs, a group of seven radiologists and two orthopedic surgeons took turns reading MRI scans with and without the algorithm. When reading the scans with the help of MRNet, they diagnosed fewer false positives (meaning they were less likely to say a patient had a serious knee injury, when they in fact were healthy) compared to their performance without the algorithm.

The results of the study, although still very early, are encouraging to physicians like Gary Fanton, MD, a clinical professor of orthopedic surgery at Stanford. He was one of the first doctors to give MRNet a try.

“As a clinician, having immediate and accurate data-driven information will allow us to make clinical decisions and mobilize a treatment plan with greater efficiency, especially in urgent care facilities or the emergency room,” Fanton said. “MRNet takes us closer to a more efficient, accurate and cost-effective means of delivering the most important first step in patient management — a diagnosis.”

Lungren and Ng likewise have plans to move another one of their diagnostic algorithms into the clinic to test how it fairs among doctors. The algorithm, called CheXNeXt, can simultaneously recognize 10 different pathologies from chest X-rays as well as radiologists; for one disease, it even outdid the experts.

It was featured in a recent video.

Lungren speaks to its potential in our release:

‘I could see [CheXNeXt] working in a few ways. [It] could triage the X-rays, sorting them into prioritized categories for doctors to review, like normal, abnormal or emergent,’ Lungren said. Or the algorithm could sit bedside with primary care doctors for on-demand consultation, he said.

In this case, Lungren said, the algorithm could step in to help confirm or cast doubt on a diagnosis.

Eventually, the scientists hope that algorithms like MRNet and CheXNeXt could stand alone, efficiently and effectively scanning for a wide range of diseases or injuries typically diagnosed through image-based medical exams. Such a feat could one day even be used as a sort of digital consultation for resource-deprived regions of the world that don’t typically have access to professional radiologists.

Photo by Kurt Hickman

Tagged with:

About author

Related Articles