November 18, 2026
Health news, explained with evidence
LIVE
Understanding and Addressing Love Handles Through Lifestyle Changes Ciele Releases New Woolmark-Certified Merino Winter Running Apparel Preventive Services Task Force Resumes Meetings Under New Leadership Blood-Based Genetic Signature May Predict CAR T-Cell Therapy Success in Lymphoma Ultraprocessed Diets May Impact Brain Reward Systems in Younger Adults Addressing Body Image and the Reality of Gluteal Anatomy Migraine and Smoking Linked to Increased Early Stroke Risk in Women CBD Oil Found Ineffective for Managing Behavioral Issues in Youths with Intellectual Disabilities Expert Advice on Hydration Gear Sparks Debate Among Recreational Runners A Structured Approach to Beginning a Strength and Cardio Routine Understanding and Addressing Love Handles Through Lifestyle Changes Ciele Releases New Woolmark-Certified Merino Winter Running Apparel Preventive Services Task Force Resumes Meetings Under New Leadership Blood-Based Genetic Signature May Predict CAR T-Cell Therapy Success in Lymphoma Ultraprocessed Diets May Impact Brain Reward Systems in Younger Adults Addressing Body Image and the Reality of Gluteal Anatomy Migraine and Smoking Linked to Increased Early Stroke Risk in Women CBD Oil Found Ineffective for Managing Behavioral Issues in Youths with Intellectual Disabilities Expert Advice on Hydration Gear Sparks Debate Among Recreational Runners A Structured Approach to Beginning a Strength and Cardio Routine

Deep Learning and Single-Element Ultrasound Show Promise in Breast Mass Detection

🥗 Nutrition 1 min read 👁 3

Researchers have demonstrated a proof-of-concept method using deep learning analysis on echo signals from a single piezoelectric element to help detect breast masses.

🥗Nutrition

Key points

  • Tested deep learning on single-element ultrasound echo signals
  • Evaluated data from 200 patients with breast lesions
  • Achieved high region-level accuracy in early validation tests

A team of investigators has explored whether deep learning analysis of echo signals gathered from a single-element ultrasound sensor could successfully differentiate normal breast tissue from regions containing a mass. Published in Nature Health Sciences, the prospective proof-of-concept study evaluated data gathered from 200 patients scheduled for breast surgery between October 2022 and January 2024. The cohort included 192 malignant lesions alongside eight benign or borderline lesions.

By employing self-supervised pre-training on public ultrasound images rather than standard ImageNet initialization, the models achieved higher region-level area under the curve metrics, reaching up to 96.3% with a Vision Transformer architecture. The study authors note that the research remains at an early, exploratory stage. Additional validation involving women without known breast lesions is strictly necessary before this technology can be considered for clinical screening or diagnostic applications.

What to know: While the findings suggest artificial intelligence may eventually enhance portable ultrasound techniques, readers should consult a qualified healthcare provider for any personal medical evaluations or diagnostic decisions regarding breast health.

Source Nature Health Sciences — nature.com/articles/s41598-026-78663-3 ↗

Contact the newsroom

Got a tip, a proposal or a partnership question? Write to us and we will reply shortly.