News

AddToAny

Google+ Facebook Twitter Twitter

AI potential for breast cancer screening

A major new study shows that artificial intelligence (AI) is a promising tool for breast cancer detection in screening mammography programmes.

Mammograms acquired through population-based breast cancer screening programmes produce a significant workload for radiologists.

AI has been proposed as an automated second reader for mammograms that could help reduce this workload. The technology has shown encouraging results for cancer detection, but evidence related to its use in real screening settings is limited.

In the new study – the largest of its kind to date –Norwegian researchers compared the performance of a commercially available AI system with routine independent double reading.

The study drew from almost 123,000 examinations performed on more than 47,000 women at four facilities in BreastScreen Norway, the nation’s population-based screening programme.

The dataset included 752 cancers detected at screening and 205 interval cancers, or cancers detected between screening rounds.

The AI system predicted the risk of cancer on a scale from 1 to 10, with 1 representing the lowest risk and 10 the highest. A total of 87.6% of screen-detected and 44.9% of interval cancers had the highest AI score of 10.

bit.ly/3Do28tA

Image credit | iStock

Related Articles

Genetic method for identifying hundreds of disease agents

A new paper compares the pathogen-detecting ability of a next-generation sequencing (NGS) system — the Respiratory Pathogen Infectious Diseases/Antimicrobial Resistance Panel (RPIP) — with a previously studied NGS system and standard of care (SOC) diagnostic methods for samples obtained with bronchoalveolar lavage.

“Gene editing via CRISPR/cas9 can lead to cell toxicity and genome instability”

CRISPR/Cas9 is a commonly used, very precise, gene editing technique often known as “genetic scissors”.

AI and ecg heart trace to predict diabetes

An artificial intelligence (AI) algorithm, derived from the features of individual heartbeats recorded on an ECG (electrocardiogram), can accurately predict diabetes and pre-diabetes, suggests preliminary research.

An electrophoresis case study

Madihah Abbas, Specialist Biochemistry Team Manager at Christie Pathology Partnership, looks at result interpretation, comparing gel and capillary zone electrophoresis.

Top