Breaking News
February 23, 2019 - AHA News: Why Are Black Women at Higher Risk of Dying From Pregnancy Complications?
February 23, 2019 - NIMH » Anxiety Disorders
February 23, 2019 - Autistic people urgently need access to tailored mental health support
February 23, 2019 - Newly designed molecule could benefit people with Friedrich’s Ataxia
February 23, 2019 - Chinese CRISPR twins may have better cognition and memory
February 23, 2019 - Study finds new genetic clues associated with asthma in African ancestry populations
February 23, 2019 - Fetal signaling pathways may offer future opportunities to treat lung damage
February 23, 2019 - Early-stage osteoarthritis drug wins prestigious innovation award
February 23, 2019 - Researchers report positive findings with dasotraline for ADHD in children ages 6-12
February 23, 2019 - News study reanalyzes the effects of noncaloric sweeteners on gut microbiota
February 23, 2019 - New device allows scientists to reproduce blow effects on the heart in lab
February 23, 2019 - Holy herb identified as a potential treatment for Alzheimer’s disease
February 23, 2019 - New technology platform digitally counts growth factors in single cells
February 23, 2019 - Surgery and other treatments offer viable options for adult scoliosis
February 23, 2019 - Reduced antibody adaptability may make the elderly more vulnerable to influenza
February 23, 2019 - Neighborhood income, education associated with risk of disability progression in MS patients
February 23, 2019 - 2019 guidelines for management of patients with atrial fibrillation
February 23, 2019 - Surprise rheumatoid arthritis discovery points to new treatment for joint inflammation
February 23, 2019 - A just-right fix for a tiny heart
February 23, 2019 - UMass Amherst scientist explores role of citrus peel in decreasing gut inflammation
February 23, 2019 - Owlstone Medical and Shanghai Renji Hospital collaborate to initiate breath biopsy lung cancer trial
February 23, 2019 - AMSBIO’s comprehensive portfolio of knock-out cell lines and lysates
February 23, 2019 - New app reliably determines physicians’ skills in forming accurate, efficient diagnoses
February 23, 2019 - Peripheral nerve injury can trigger the onset and spread of ALS, shows study
February 23, 2019 - Researchers uncover mechanisms that prevent tooth replacement in mice
February 23, 2019 - Once-a-day capsule offers new way to reduce symptoms of chronic breathlessness
February 23, 2019 - FDA Adds Boxed Warning for Increased Risk of Death with Gout Medicine Uloric (febuxostat)
February 23, 2019 - Phone-based intervention aids rheumatoid arthritis care
February 23, 2019 - Opioid epidemic makes eastern inroads and targets African-Americans
February 23, 2019 - New identified biomarker predicts patients who might benefit from HER2-targeted agents
February 23, 2019 - Study offers new insights into mechanisms of changes in erythrocytes under stress
February 23, 2019 - Antipsychotic polypharmacy may be beneficial for schizophrenia patients
February 23, 2019 - Researchers investigate how marijuana and tobacco co-use affects quit attempts by smokers
February 23, 2019 - Patients with diabetes mellitus have high risk of stable ischemic heart disease
February 23, 2019 - Transparency on healthcare prices played key role in Arizona health system’s turnaround
February 23, 2019 - A comprehensive, multinational review of peppers around the world
February 23, 2019 - Study finds modest decrease in burnout among physicians
February 23, 2019 - A simple change can drastically reduce unnecessary tests for urinary tract infections
February 23, 2019 - Deep Learning-Enhanced Device Detects Diabetic Retinopathy
February 23, 2019 - Researchers discover new binding partner for amyloid precursor protein
February 23, 2019 - Modest decrease seen in burnout among physicians, researchers say | News Center
February 23, 2019 - Transplanting bone marrow of young mice into old mice prevents cognitive decline
February 23, 2019 - Mogrify to accelerate novel IP and cell therapies using $3.7m USD funding
February 23, 2019 - Johns Hopkins study describes cells that may help speed bone repair
February 23, 2019 - Scientists demonstrate influence of food odors on proteostasis
February 23, 2019 - Researchers unlock the secret behind reproduction of fish called ‘Mary’
February 23, 2019 - Acupuncture Could Help Ease Menopausal Symptoms
February 23, 2019 - Researchers use AI to detect early signs of Alzheimer’s
February 23, 2019 - On recovery, vulnerability and ritual: An exhibit in white | News Center
February 23, 2019 - Memory Stored in Unexpected Region of the Brain
February 23, 2019 - Several health experts worldwide gather at EUDONORGAN event
February 23, 2019 - Discovery of potent compound in native California shrub may lead to treatment for Alzheimer’s
February 22, 2019 - Researchers create new map of the brain’s own immune system
February 22, 2019 - ICHE’s reviews on surgical infections, unnecessary urine tests, and nurses’ role in antibiotic stewardship
February 22, 2019 - UK Research and Innovation invests £200 million to create new generation of AI leaders
February 22, 2019 - Takeda collaboration to boost fight against Alzheimer’s and other neurodegenerative diseases
February 22, 2019 - Heavy drinking may change DNA, leading to increased craving for alcohol
February 22, 2019 - U.S. opioid deaths jump fourfold in 20 years; epidemic shifts to Eastern states | News Center
February 22, 2019 - 5 Questions with William Turner on Diversity in Medicine
February 22, 2019 - HHS Finalizes Rule Seeking To Expel Planned Parenthood From Family Planning Program
February 22, 2019 - Researchers uncover biochemical pathway that may help identify drugs to treat Alzheimer’s
February 22, 2019 - Biologist uses new grant to find ways to eliminate schistosomiasis
February 22, 2019 - Bag-mask ventilation to help patients breathe during intubation prevents complications
February 22, 2019 - AbbVie Announces New Drug Application Accepted for Priority Review by FDA for Upadacitinib for Treatment of Moderate to Severe Rheumatoid Arthritis
February 22, 2019 - Nature versus nurture and addiction
February 22, 2019 - New website connects researchers with data experts, resources | News Center
February 22, 2019 - Today’s Concerns About Drug Prices Echo The Past
February 22, 2019 - CT and Doppler equipment have low accuracy in detecting cerebral vasospasm and ischemia
February 22, 2019 - Study finds out similarity in function between healthy retina cell and tumor cell
February 22, 2019 - CWRU awarded NIH grant to identify effective treatments for intimate partner violence
February 22, 2019 - Oncotype DX Not Cost-Effective for Low-Risk Breast Cancer
February 22, 2019 - Scientists discover new type of immune cells that are essential for forming heart valves
February 22, 2019 - Talk About Déjà Vu: Senators Set To Re-Enact Drug Price Hearing Of 60 Years Ago
February 22, 2019 - Genetic defect linked to pediatric liver disease identified
February 22, 2019 - New cellular atlas could provide a deeper insight into blinding diseases
February 22, 2019 - Growing number of cancer survivors, fewer providers point to challenge in meeting care needs
February 22, 2019 - Innovative compound offers a new therapeutic approach to treat multiple sclerosis
February 22, 2019 - $1.5 million grant to develop opioid treatment program for jail detainees
February 22, 2019 - FDA’s new proposed rule would update regulatory requirements for sunscreen products in the U.S
February 22, 2019 - Most Hip, Knee Replacements Last Decades, Study Finds
Researchers have trained a computer to analyze breast cancer images and classify tumors

Researchers have trained a computer to analyze breast cancer images and classify tumors

image_pdfDownload PDFimage_print

Using technology similar to the type that powers facial and speech recognition on a smartphone, researchers at the University of North Carolina Lineberger Comprehensive Cancer Center have trained a computer to analyze breast cancer images and then classify the tumors with high accuracy.

In a study published in the journal NPJ Breast Cancer, researchers reported they used a form of artificial intelligence called machine learning, or deep learning, to train a computer to identify certain features of breast cancer tumors from images. The computer also identified the tumor type based on complex molecular and genomic features, which a pathologist can’t yet identify from a picture alone. They believe this approach, while still in its early stages, could eventually lead to cost savings for the clinic and in breast cancer research.

“Your smartphone can interpret your speech, and find and identify faces in a photo,” said the study’s first author Heather D. Couture, a graduate research assistant in the UNC-Chapel Hill Department of Computer Science. “We’re using similar technology where we capture abstract properties in images, but we’re applying it to a totally different problem.”

For the study, the researchers used a set of 571 images of breast cancer tumors from the Carolina Breast Cancer Study to train the computer to classify tumors for grade, estrogen receptor status, PAM50 intrinsic subtype, histologic subtype, and risk of recurrence score. To do this, they created software that learned how to predict labels from images using a training set, so that new images could be processed in the same way.

They then used a different set of 288 images to test the computer’s ability to distinguish features of the tumor on its own, comparing the computer’s responses to findings of a pathologist for each tumor’s grade and subtype, and to separate tests for gene expression subtypes. They found the computer was able to distinguish low-intermediate versus high-grade tumors 82 percent of the time. When they had two pathologists review the tumor grade for the low-intermediate grade group, the pathologists agreed with each other about 89 percent of the time, which was slightly higher than the computer’s accuracy.

In addition, the computer identified estrogen receptor status, distinguished between ductal and lobular tumors, and determined whether each case had a high or low risk of recurrence high levels of accuracy. It also identified one of the molecular subtypes of breast cancers – the basal-like subtype – which is based on how genes within the tumor were expressed – with 77 percent accuracy.

“Using artificial intelligence, or machine learning, we were able to do a number of things that pathologists can do at a similar accuracy, but we were also able to do a thing or two that pathologists are not able to do today,” said UNC Lineberger’s Charles M. Perou, PhD, the May Goldman Shaw Distinguished Professor of Molecular Oncology, professor of genetics, and of pathology and laboratory medicine in the UNC School of Medicine. “This has a long way to go in terms of validation, but I think the accuracy is only going to get better as we acquire more images to train the computer with.”

The computer’s ability to identify the basal-like subtype was exciting to researchers, and could have applications in cancer research. They also believe the technology could have applications in communities that do not have pathology resources as well as in helping to validate pathologists’ findings.

“We were surprised that the computer was able to get a pretty high accuracy in estimating biomarker risk just from looking at the pictures,” said UNC Lineberger’s Melissa Troester, PhD, a professor in the UNC Gillings School of Global Public Health. “We spend thousands of dollars measuring those biomarkers using molecular tools, and this new method can take the image and get 80 percent accuracy or better at estimating the tumor phenotype or subtype. That was pretty amazing.”

Couture said deep learning technology has been used in a range of applications, including speech recognition and autonomous vehicles.

“Humans can look at one or two examples of something, and be able to generalize when they see other objects,” Couture said. “For example, chairs come in so many different forms, but we can recognize it as something we sit on. Computers have a much harder time generalizing from small amounts of data. But on other hand, if it you provide enough labeled data, they can learn concepts that are much more complex than humans can assess visually – such as identifying the basal-like subtype from an image alone.”

The unique aspect of their work, researchers said, was that they were able to use the technology to see features of the tumors that humans cannot. They want to figure out what the computer is seeing, as well as to study whether the technology could predict outcomes.

“The computer extracted a lot of information from the images,” Troester said. “We would like to test how well these features predict outcomes, and if we can use these features together with things like molecular data to do even better at giving patients a precise view of what their disease course looks like, and what treatments might be effective.”

Source:

https://unclineberger.org/news/scientists-trained-a-computer

Tagged with:

About author

Related Articles