Scientists trained a computer to classify breast cancer tumors

 

Chapel Hill, NC (November 19, 2018) – 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.”

 

In addition to Couture, Perou and Troester, other authors included Lindsay A. Williams, Joseph Geradts, Sarah J. Nyante, Ebonee N. Butler, J.S. Marron, and Marc Niethammer.

The study was supported by the University Cancer Research Fund through UNC Lineberger, the National Cancer Institute, the Breast SPORE Program, the Breast Cancer Research Foundation, and Susan G. Komen. The Tesla K40 used for this research was donated by the NVIDIA Corp.

Conflict of interest: Perou is an equity stock holder and board member for BioClassifier LLC, and has filed patents on the PAM50 subtyping assay.

 


UNC Lineberger Comprehensive Cancer Center, 19.11.2018 (tB).

Schlagwörter: ,

MEDICAL NEWS

Inadequate sequencing of SARS-CoV-2 variants impedes global response to COVID-19
New meta-analysis finds cannabis may be linked to development of…
New guidance on how to diagnosis and manage osteoporosis in…
Starting the day off with chocolate could have unexpected benefits
Better mental health supports for nurses needed, study finds

SCHMERZ PAINCARE

Versorgung verbessern: Deutsche Gesellschaft für Schmerzmedizin fordert die Einführung des…
Pflegeexpertise im Fokus: Schmerzmanagement nach Operationen
Versorgung verbessern: Bundesweite Initiative der Deutschen Gesellschaft für Schmerzmedizin zu…
Jedes vierte Kind wünscht bessere Schmerzbehandlung
Lebensqualität von Patienten in der dauerhaften Schmerztherapie mit Opioiden verbessern

DIABETES

Bundestag berät über DMP Adipositas: DDG begrüßt dies als Teil…
Mit der Smartwatch Insulinbildung steuern
Verbände fordern bessere Ausbildung und Honorierung von Pflegekräften für Menschen…
Minimalinvasive Geräte warnen ungenügend vor Unterzuckerung
Typ-1-Diabetes und Hashimoto-Thyreoiditis treten häufig gemeinsam auf

ERNÄHRUNG

Wie eine Diät die Darmflora beeinflusst: Krankenhauskeim spielt wichtige Rolle…
DGEM plädiert für Screening und frühzeitige Aufbautherapie: Stationäre COVID-19-Patienten oft…
Führt eine vegane Ernährungsweise zu einer geringeren Knochengesundheit?
Regelmässiger Koffeinkonsum verändert Hirnstrukturen
Corona-Erkrankung: Fehl- und Mangelernährung sind unterschätze Risikofaktoren

ONKOLOGIE

Anti-Myelom-Therapie mit zusätzlich Daratumumab noch effektiver
Positive Ergebnisse beim fortgeschrittenen Prostatakarzinom: Phase-III-Studie zur Radioligandentherapie mit 177Lu-PSMA-617
Lymphom-News vom EHA2021 Virtual. Alle Berichte sind nun online verfügbar!
Deutsch-dänisches Interreg-Projekt: Grenzübergreifende Fortbildungskurse in der onkologischen Pflege
Sotorasib: Neues Medikament macht Lungenkrebs-Patienten Hoffnung

MULTIPLE SKLEROSE

NMOSD-Erkrankungen: Zulassung von Satralizumab zur Behandlung von Jugendlichen und Erwachsenen
Verzögerte Verfügbarkeit von Ofatumumab (Kesimpta®)
Neuer Biomarker bei Multipler Sklerose ermöglicht frühe Risikoeinschätzung und gezielte…
Multiple Sklerose beginnt oft lange vor der Diagnose
Goldstandard für Versorgung bei Multipler Sklerose

PARKINSON

Meilenstein in der Parkinson-Frühdiagnose
Parkinson-Erkrankte besonders stark von Covid-19 betroffen
Gangstörungen durch Kleinhirnschädigung beim atypischen Parkinson-Syndrom
Parkinson-Agenda 2030: Die kommenden 10 Jahre sind für die therapeutische…
Gemeinsam gegen Parkinson: bessere Therapie durch multidisziplinäre Versorgung