Deep Learning News and Research

RSS

Novel embedding-driven AI for adaptable brain control

Motor imagery (MI) is the mental process of imagining a specific limb movement, such as raising a hand or walking, without physically performing it. These imagined movements generate distinct patterns of brain activity that can be recorded using electroencephalography (EEG).

11 Mar 2026

AI and genetics reveal new insights into human language development

Learning French, reading the latest Andy Weir novel, hanging out with friends for St. Patrick's Day - language is central to all these everyday activities.

10 Mar 2026

Mapping the evolution of AI in organelle segmentation

In organelle imaging, segmentation aims to accurately delineate pixels or voxels corresponding to target organelles from background, noise, and other cellular structures in microscopy images, thereby generating masks suitable for quantitative analysis. Robust segmentation is foundational to downstream quantification, including morphological characterization, spatial distribution analysis, temporal trajectory tracking, and the detection of key biological events.

10 Mar 2026

AI model flags hidden breast cancers years before diagnosis in routine mammograms

Researchers evaluated four deep learning models using over 112,000 negative screening mammograms from the UK NHS to determine how well artificial intelligence could predict future breast cancers missed during routine screening. The MIT-developed Mirai model performed best, identifying about 27.5% of interval cancers within the top 4% of women flagged as highest risk.

9 Mar 2026

Virtual immunostaining method improves detection of vascular invasion in thyroid cancer

In a groundbreaking study published in BME Frontiers, researchers from the University of California, Los Angeles (UCLA), in collaboration with international partners, have developed a deep learning-based virtual multiplexed immunostaining (mIHC) method.

6 Mar 2026

AI system spots Parkinson’s signs in voice, walking and drawings

Combining gait, handwriting, and speech analysis, this AI framework enhances early Parkinson's disease detection, addressing clinical challenges effectively.

3 Mar 2026

AI cancer tools may be using visual shortcuts rather than true biology

New research warns that popular deep learning systems trained for cancer pathology may be relying on hidden shortcuts rather than genuine biological signals.

2 Mar 2026

Privacy-focused AI improves screening for rare endocrinological condition

An AI can accurately diagnose a rare endocrinological condition just by analyzing pictures of the back of the hand and the clenched fist.

27 Feb 2026

New AI-based approach detects fatty deposits inside coronary arteries using OCT images

Researchers have developed a new artificial intelligence-based approach for detecting fatty deposits inside coronary arteries using optical coherence tomography (OCT) images.

17 Feb 2026

CNN-based system improves lung nodule detection and classification

Lung cancer remains the leading cause of cancer-related mortality worldwide. Early detection of pulmonary nodules is crucial for timely diagnosis and effective treatment.

16 Feb 2026

New AI model eliminates false positives in food testing

Researchers have significantly enhanced an artificial intelligence tool used to rapidly detect bacterial contamination in food by eliminating misclassifications of food debris that looks like bacteria.

10 Feb 2026

AI stethoscope doubles detection of serious valve disease in primary care study

A prospective primary care study found that an AI-enabled digital stethoscope substantially improved sensitivity for detecting clinically significant valvular heart disease compared with standard auscultation. The technology identified more previously undiagnosed moderate-to-severe disease but showed reduced specificity, highlighting a trade-off between earlier detection and potential false positives.

8 Feb 2026

Bat viruses in Indochina Peninsula reveal viral diversity, PEDV origins, and spillover risks

Bats, critical reservoirs of viruses with significant cross-species spillover risks, have long been understudied in the Indochina Peninsula.

2 Feb 2026

Integrated Monte Carlo and deep learning improve radiotherapy QA

Led by Professor Fu Jin, the study addresses a critical challenge in radiation therapy: balancing the computational speed and accuracy of EPID-based dose verification.

31 Jan 2026

Diagnostic prognostic and therapeutic relevance of PIVKA-II in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) remains a leading cause of cancer-related mortality worldwide, particularly in regions with high hepatitis B virus prevalence.

24 Jan 2026

AI applied to abdominal imaging can help predict fall risk in adults

Artificial intelligence (AI) applied to abdominal imaging can help predict adults at higher risk of falling as early as middle age, a new Mayo Clinic study shows.

22 Jan 2026

AI predicts health outcomes for premature newborns from blood samples

An artificial intelligence-based tool can predict the medical trajectories of individual premature newborns from blood samples collected soon after they are born, a Stanford Medicine-led study has shown.

21 Jan 2026

More urban trees associated with fewer heart disease cases

A multi-institutional study led by the University of California, Davis, finds that living in urban areas with a higher percentage of visible trees is associated with a 4% decrease in cardiovascular disease.

21 Jan 2026

Digital twin technology guides personalized treatment for brain cancer patients

A new machine-learning-based approach to mapping real-time tumor metabolism in brain cancer patients, developed at the University of Michigan, could help doctors discover which treatment strategies are most likely to be effective against individual cases of glioma.

12 Jan 2026