Deep learning

News • Foreign body aspiration

AI spots hidden objects lodged in patients' airways on CT

In a CT scan of the lungs, accidentally inhaled objects can be extremely subtle and easy to miss, even for experienced clinicians. A new AI model acts as a “second set of eyes” to help detect…

News • Estimation of nodule malignancy risk

Lung cancer screening: AI to reduce false positives

Misinterpreting the malignancy risk of lung nodules often results in high false-positive rates, unnecessary follow-ups, increased patient anxiety and healthcare costs. A new study suggests that AI…

News • Breast cancer screening

Mammography: Hybrid reading to overcome AI overconfidence

Mammography image interpretation AI models are unreliable – but so are human readers. A new hybrid strategy could reduce radiologist workload by 38% without compromising diagnostic efficacy.

News • Nasopharyngeal carcinoma detection

Virtual MRI for contrast-free NPC tumour imaging

Gadolinium-based contrast agents enhance visibility but also pose a significant health risk. A new AI-powered virtual MRI imaging technique is designed to offer a safer diagnostic approach.

News • Microsatellite instability

Predicting tumor MSI status for precision cancer treatments

Microsatellite instability-high (MSI-H) tumors are associated with better clinical outcomes. A novel AI model for accurate MSI prediction could help battle gastric and colorectal cancers.

News • Multimodal AI for ventricular Arrhythmia Risk Stratification

Predicting sudden cardiac arrest with MAARS

Analyzing heart imaging and a full spectrum of medical records, a new AI tool can reveal previously hidden information about a patient’s heart health, including predictions of sudden cardiac arrest.

News • Deep learning model

AI detects fatty liver disease with chest X-rays

A research group at Osaka Metropolitan University developed an AI model that can detect the presence of hepatic steatosis (fatty liver disease) from chest X-ray images.

News • Diagnostic assistance

Pancreatic cancer: clinical deployment of AI system for early detection

Survival rates for pancreatic cancer rise drastically the earlier it is detected, but early-stage tumors are notoriously difficult to spot. A new AI-powered diagnostic system is set to improve this.

News • Deep learning-based assessment

AI ‘Sybil’ predicts lung cancer risk from single LDCT scan

A deep learning model was able to predict future lung cancer risk from a single low-dose chest CT (LDCT) scan, according to new research published at the ATS 2025 International Conference.

News • Breast cancer diagnosis

AI classifies mammography microcalcifications

A novel deep-learning approach automatically finds and classifies microcalcifications found in mammography images—bringing both accuracy and consistency to breast-cancer screening.

News • CT-based deep learning-driven tool

Liver cancer segmentation and detection with 'SALSA'

Results of a new retrospective study demonstrate the potential of a novel, CT-based deep learning-driven tool to enhance liver cancer diagnosis, treatment planning, and response evaluation.

News • Synthetic fibrosis distributions

AI generates ‘scarred hearts’ for better cardiac treatments

Researchers have developed an AI tool that creates synthetic yet medically accurate models of fibrotic heart tissue (heart scarring), aiding treatment planning for atrial fibrillation (AF) patients.

News • Sputum-free, rapid alternative for TB detection

POCT AI-guided lung ultrasound boosts tuberculosis diagnosis

Despite previous global declines, pulmonary tuberculosis (TB) is on the rise again. A new AI-powered lung ultrasound shows promise in improving diagnostic performance of TB.

News • Brain MRI analysis

AI tool tracks effectiveness of multiple sclerosis treatments

A new AI tool can extract key information from brain MRI scans of multiple sclerosis (MS) patients. This could be used to improve disease and treatment response monitoring.

News • Deep learning-based CVD risk prediction

Mammography and AI open a new window into heart health

New findings show how AI-assisted mammography may not only reveal breast cancer, but can also assess calcium buildup in the arteries within breast tissue—an indicator of cardiovascular health.

News • Imaging immunocompromised patients

Pneumonia diagnosis: deep learning takes the grain out of ultra-low dose CT

To reduce the radiation exposure for patients undergoing frequent CT scans for pneumonia diagnosis, deep learning-based denoising of ultra-low dose CT presents a viable alternative.

News • Deep and ensemble learning improve performance

New AI tool surpasses previous methods in colorectal cancer tissue analysis

Researchers developed an advanced AI tool for automatic analysis of colorectal cancer tissue slides. The new model outperformed all predecessors in the classification of tissue microscopy samples.

News • Deep learning tool shows promise

Long-term ECG: AI algorithm checks heart rhythm

Analysing long-term ECG recordings for signs of heart abnormalities such as arrhythmias is a time-consuming process. New research finds that AI is better suited for this task than humans.

News • Deep learning-based approach

3D body composition analysis for assessing health risks

Using 3D imaging and deep learning AI, researchers have developed a new way to accurately assess body fat and muscle distribution, which are crucial for understanding health risks.

News • Automated tumor detection and segmentation

Deep learning helps detect lung cancer on CT

A new deep learning model shows promise in detecting and segmenting lung tumors. The findings of the study could have important implications for lung cancer treatment.

Article • AI-assisted image analysis

More accuracy in brain tumour segmentation

Precise segmentation of anatomical structures greatly benefits cancer diagnosis. Using AI and deep learning methods, researchers are developing a high-precision 3D viewer software for medical image data.

News • Deep learning advances

New AI model for cell segmentation and classification

US researchers have developed a comprehensive deep learning AI model designed to more accurately identify and classify cells in high-content tissue images.

News • Ultrasound tool

AI 'guides' childbirth by tracking a baby's position

The journey of a baby through the birth canal can be fraught with obstacles and risks. A new AI-based tool to evaluate the head position of the baby could lead to fewer childbirth complications.

News • Improved image quality, reduced radiation dose

Benefits of deep learning reconstruction in paediatric imaging

Recent developments in deep learning techniques are enhancing clinical imaging quality and reducing radiation exposure for patients while also maintaining diagnostic accuracy. The latest AI (artificial intelligence) component to clinical imaging – referred to as deep learning reconstruction (DLR) – is having a particular benefit in paediatric imaging, according to Dr Samuel Brady from…

News • Real-time drug identification

Wrong meds? A wearable AI camera detects what's in a syringe or vial

A newly-developed wearable camera system is designed to detect potential errors in medication delivery by identifying contents of vials and syringes with the help of deep-learning AI.

139 show more articles