Breaking News
December 10, 2018 - Scientists find answers to how cancer spreads
December 10, 2018 - Study explores why older people read more slowly
December 10, 2018 - Asbestos found in most NHS hospitals finds BBC inquiry
December 10, 2018 - Researchers use new technique to probe hydrogen bonds
December 10, 2018 - Music improves social communication in autistic children
December 10, 2018 - Some Brain Tumors May Respond to Immunotherapy, New Study Suggests
December 10, 2018 - Banning junk food ads to combat childhood obesity
December 10, 2018 - Skin Autofluorescence Predicts T2DM, Heart Disease, Mortality
December 10, 2018 - Largest autism sequencing study to date yields 102 genes associated with ASD
December 10, 2018 - Statins associated with low risk of side effects
December 10, 2018 - Study explores how schools address adolescent self-harming practices
December 10, 2018 - Pregnancy in adolescence linked to increased risks of complications in young mothers
December 10, 2018 - Risk Analysis publishes special issue on communicating about Zika virus
December 10, 2018 - Botox May Help Prevent Post-Op A-Fib
December 10, 2018 - African-American mothers rate boys higher for ADHD
December 10, 2018 - Graphic warning labels cancel out cigarettes’ appeal to young people
December 10, 2018 - Australian researchers to study gas inhalational anaesthetic and likelihood of cancer return
December 10, 2018 - Individual neurons located within the brain have implications for psychiatric diseases
December 10, 2018 - Researchers improve bariatric surgery scoring system to extend prediction time for diabetic remission
December 10, 2018 - HPV type 16 or 18 associated with cervical cancer risk in young women
December 10, 2018 - Cervical cancer risk is higher in women with positive HPV, but no cellular abnormalities
December 10, 2018 - Combo therapy not needed if low RA disease activity achieved
December 10, 2018 - Novel therapeutic targets based on biology of aging show promise for Alzheimer’s disease
December 10, 2018 - UC San Diego professor receives NCI Outstanding Investigator Award for cancer research
December 10, 2018 - Study evaluates placental mesenchymal stem cell sheets for myocardial repair and regeneration
December 10, 2018 - Blueprint Medicines Announces Updated Results from Ongoing EXPLORER Clinical Trial of Avapritinib Demonstrating Broad Clinical Activity and Significant Symptom Reductions in Patients with Systemic Mastocytosis
December 10, 2018 - Study clarifies ApoE4’s role in dementia
December 10, 2018 - Eating disorders now a top priority with Australian Government
December 10, 2018 - Neuronal activity in the brain allows prediction of risky or safe decisions
December 10, 2018 - FDA Alerts Health Care Professionals and Patients Not to Use Drug Products Intended to be Sterile from Promise Pharmacy
December 10, 2018 - Improving dementia care and treatment saves thousands of pounds in care homes
December 10, 2018 - Heroin-assisted treatment can offer benefits, reduce harms
December 10, 2018 - People covered by Michigan’s expanded Medicaid program report improvements in health, finds study
December 10, 2018 - Hazelnuts improve micronutrient levels in older adults
December 9, 2018 - History of Partner Violence Tied to Menopause Symptoms
December 9, 2018 - Clean Up Safely After a Disaster|Natural Disasters and Severe Weather
December 9, 2018 - Drug wholesalers drove fentanyl’s deadly rise, report concludes
December 9, 2018 - Deprescribing could help manage polypharmacy in older adults
December 9, 2018 - Retraction of article “Joy of cooking too much” from journal
December 9, 2018 - FDA Warns of Rare Stroke Risk With MS Drug Lemtrada (Alemtuzumab)
December 9, 2018 - Feds say heroin, fentanyl remain biggest drug threat to US
December 9, 2018 - Eliminating microglia can reverse some aspects of stress sensitization, study shows
December 9, 2018 - New genetic insight could help treat rare debilitating heart and lung condition
December 9, 2018 - MiRagen Therapeutics Announces Final Safety, Biodistribution and Clinical Efficacy Data From Phase 1 Cobomarsen Clinical Trial in Patients With Mycosis Fungoides
December 9, 2018 - Work with your doctor to weigh pros, cons of treatment options for hyperthyroidism
December 9, 2018 - CWRU researcher secures $14.6 million funding for genetic study into Alzheimer’s disease
December 9, 2018 - High intensity statin treatment and adherence could save more lives
December 9, 2018 - Surgery patients use only 1/4 of prescribed opioids, and prescription size matters
December 9, 2018 - AXT offers Phi Optics upgrade to QPI systems for inverted light microscopes
December 9, 2018 - New booklet could help improve conditions of young pupils with albinism
December 9, 2018 - Few Physicians Work in Practices That Use Telemedicine
December 9, 2018 - Older Adults and Oral Health
December 9, 2018 - Health utility values improve after septorhinoplasty
December 9, 2018 - New EU-funded project provides insight into how the brain develops
December 9, 2018 - Expanded use of tele-emergency services can help strengthen rural hospitals
December 9, 2018 - Infections in the Young May Be Tied to Risk for Mental Illness: Study
December 9, 2018 - Profile: Native Hawaiians and Pacific Islanders
December 9, 2018 - Snoring poses greater cardiac risk to women
December 9, 2018 - Researcher takes further steps in understanding how and why cute aggression occurs
December 9, 2018 - Researchers create new light-activated tools for controlling neurons
December 9, 2018 - Spinal cord injury disrupts the body’s internal clock, study shows
December 9, 2018 - Babies recognize nested structures similar to our grammar
December 9, 2018 - UT Austin researcher receives $2.5 million CZI grant for neurodegenerative disease research
December 9, 2018 - Sleep problems found to be prevalent and increasing among college students
December 9, 2018 - Study reveals why some children are susceptible to the effects of maltreatment
December 9, 2018 - Study investigates influence of different opioids on driving performance
December 9, 2018 - Jazz Pharmaceuticals Announces First Patient Enrolled in Phase 3 Clinical Trial Evaluating JZP-258 for the Treatment of Idiopathic Hypersomnia
December 9, 2018 - Eliminating microglia prevents heightened immune sensitivity after stress
December 9, 2018 - Boys with social difficulties are at greatest risk of early substance use
December 9, 2018 - ‘Wrong’ connective tissue cells linked to worse prognosis in breast cancer patients
December 8, 2018 - Chronic, refractory schizophrenia patients benefit from targeted cognitive training
December 8, 2018 - Advertising in kids’ apps more prevalent than parents may realize
December 8, 2018 - New way to trace the transmission histories of rare genetic diseases
December 8, 2018 - ASH: A+CHP Bests CHOP for Peripheral T-Cell Lymphoma
December 8, 2018 - Results of pediatric genomic epilepsy tests often reclassified
December 8, 2018 - New way of controlling HIV latency to completely eradicate the virus
December 8, 2018 - Phasefocus to showcase the Livecyte 2 at ASCB
December 8, 2018 - KHN’s ‘What the Health?’ Is health spending the next big political issue?
December 8, 2018 - Mussels take in microplastic pollution fibers and flush most of them out again
December 8, 2018 - AHA: How to Stop Smoking … for Good
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