deep learning

Latest posts

Impact of deep learning reconstruction on radiation dose reduction and cancer risk in CT examinations

Takeshi Nakaura April 2025

Deep‑learning reconstruction (DLR) shifts CT image formation from a hardware‑limited process to a data‑driven one. In our real‑world cohort of >10,000 body scans, we observed a 45% fall in effective dose and a halving of lifetime attributable cancer risk without sacrificing diagnostic confidence. The message is simple: When the image quality can be algorithmically recovered, radiologists are no longer forced to

Impact of uncertainty quantification through conformal prediction on volume assessment from DL-based MRI prostate segmentation

Insights into Imaging March 2025

This study aimed to evaluate the uncertainty of a deep learning (DL)-based prostate segmentation algorithm using conformal prediction (CP) and its impact on prostate volume (PV) calculation in patients at risk of prostate cancer (PC). The study involved 377 patients’ 3-Tesla T2-weighted scans. By applying CP at an 85% confidence level, unreliable pixel segmentations of the DL model were flagged,

This blur detection model could provide instantaneous feedback to technicians

European Radiology Experimental March 2025

This study developed a model to automatically detect blurred areas in mammograms, which can affect diagnostic accuracy. Using a retrospective dataset consisting of 152 mammograms from three vendors, expert radiologists outlined blurred regions. Normalized Wiener spectra (nWS) were extracted and processed through a convolutional neural network (CNN) to classify images as either blurred or sharp. The model showed an AUROC

CNNs perform automated staging of cardiac iron overload from multiecho MR sequences

European Radiology February 2025

This new European Radiology study aimed to develop a deep-learning model for classifying myocardial iron overload (MIO) using magnitude T2* multi-echo MR images from 496 thalassemia major patients. Two 2D convolutional neural networks (CNN), MS-HippoNet (multi-slice) and SS-HippoNet (single-slice), were trained using 5-fold cross-validation. The model showed strong performance with a multi-class accuracy of 0.885 and 0.836 on test sets,

Deep learning in diagnostic imaging of spondyloarthropathies

Mahmud Omar February 2025

Our recent systematic review observed that deep learning models for spondyloarthropathies (SpA) hold remarkable promise—not just for identifying subtle radiographic or MRI findings, but also for harnessing massive datasets to detect early, even preclinical, disease features. These techniques can parse millions of pixel-level patterns, potentially flagging nuanced changes that may precede clinical symptoms. Such a capability could fundamentally shift SpA

Multi-scene model shows success for precise preoperative and intraoperative segmentation of acute VCFs

Insights into Imaging February 2025

This study aimed to develop a multi-scene model, Positioning and Focus Network (PFNet), for automatically segmenting acute vertebral compression fractures (VCFs) from spine radiographs. Conducted across five hospitals from 2016 to 2019, the study included both acute VCF patients and healthy controls. PFNet was trained with radiographs from Hospitals A and B, and tested on datasets from Hospitals A-E. The

Deep learning and compressed sensing for reconstruction of 3D knee MRI

European Radiology Experimental December 2024

This study explores combining compressed sensing (CS) and artificial intelligence (AI), particularly deep learning (DL), to accelerate three-dimensional (3D) magnetic resonance imaging (MRI) of the knee. Twenty healthy volunteers were examined using a 3-T scanner with a fat-saturated 3D proton density sequence at various acceleration levels. Two reconstruction methods were compared: conventional CS and a new DL-based algorithm (CS-AI). Two

Deep learning-based algorithm vs. Virtual monoenergetic imaging and orthopedic metal artifact reduction

European Radiology Experimental October 2024

This study compared the image quality, metal artifacts, and diagnostic confidence of conventional CT images of unilateral total hip arthroplasty patients (THA) with deep learning-based metal artifact reduction (DL-MAR) to conventional CT and 130-keV monoenergetic images with and without orthopedic metal artifact reduction (O-MAR). They found that DL-MAR showed not only higher image quality but also diagnostic confidence and superior

Automatic segmentation of fat metaplasia on sacroiliac joint MRI using deep learning

Insights into Imaging September 2024

The authors of this study developed a deep learning model used for segmenting fat metaplasia (FM) on sacroiliac joint (SIJ) MRI with the additional aim of utilizing the deep learning model to classify axial spondyloarthritis (axSpA) and non-axSpA. They were able to conclude that the deep learning model could automatically and accurately segment FM on SIJ MRI, helping to increase

AI applied to MRI reliably detects the presence of meniscus tears

European Radiology August 2024

It is known that meniscus tears are difficult to diagnose on knee MRIs. Therefore, this study reviews and compares the accuracy of convolutional neural networks (CNNs). The authors assessed databases including PubMed, MEDLINE, EMBASE, and Cochrane, finding eleven articles to include in the final review, consisting of over 13,000 patients and over 57,000 images. They concluded that CNN is accurate

Impact of deep learning reconstruction on radiation dose reduction and cancer risk in CT examinations

Takeshi Nakaura April 2025

Impact of uncertainty quantification through conformal prediction on volume assessment from DL-based MRI prostate segmentation

Insights into Imaging March 2025

Welcome to the blog on Artificial Intelligence of
the European Society of Radiology

Latest posts

Impact of deep learning reconstruction on radiation dose reduction and cancer risk in CT examinations

Impact of uncertainty quantification through conformal prediction on volume assessment from DL-based MRI prostate segmentation

This blur detection model could provide instantaneous feedback to technicians

CNNs perform automated staging of cardiac iron overload from multiecho MR sequences

Deep learning in diagnostic imaging of spondyloarthropathies

Multi-scene model shows success for precise preoperative and intraoperative segmentation of acute VCFs

Deep learning and compressed sensing for reconstruction of 3D knee MRI

Deep learning-based algorithm vs. Virtual monoenergetic imaging and orthopedic metal artifact reduction

Automatic segmentation of fat metaplasia on sacroiliac joint MRI using deep learning

AI applied to MRI reliably detects the presence of meniscus tears

Impact of deep learning reconstruction on radiation dose reduction and cancer risk in CT examinations

Impact of uncertainty quantification through conformal prediction on volume assessment from DL-based MRI prostate segmentation

This blur detection model could provide instantaneous feedback to technicians

CNNs perform automated staging of cardiac iron overload from multiecho MR sequences

Deep learning in diagnostic imaging of spondyloarthropathies

Multi-scene model shows success for precise preoperative and intraoperative segmentation of acute VCFs

Deep learning and compressed sensing for reconstruction of 3D knee MRI

Deep learning-based algorithm vs. Virtual monoenergetic imaging and orthopedic metal artifact reduction

Automatic segmentation of fat metaplasia on sacroiliac joint MRI using deep learning

AI applied to MRI reliably detects the presence of meniscus tears

Check out our different membership options.

Membership

Free membership

ESR Friends

Footnotes:

deep learning

Welcome to the blog on Artificial Intelligence ofthe European Society of Radiology

Latest posts

Become A Member Today!

Check out our different membership options.

Membership

Free membership

ESR Friends

Footnotes:

Welcome to the blog on Artificial Intelligence of
the European Society of Radiology