AI Blog

Complexities of deep learning-based undersampled MR image reconstruction

Constant Richard Noordman April 2024

Recent advances in AI have led to deep learning-based MR undersampled image reconstruction methods showing more speed-ups compared to traditional algorithms. MR undersampling is an excellent way to reduce scan time but can negatively impact image quality. Our literature review aims to inform a broader audience about this complex topic. This highly multidisciplinary science requires the informed input of many

Unleashing the power of data in radiology: A look ahead

Matthias Fink April 2024

Peering into the future of radiology, we find ourselves at an exciting crossroads. The past year has seen language-based foundation models disrupt the status quo, offering a tantalising glimpse into new possibilities for data accessibility. Yet we still face a huge challenge: a wealth of valuable data remains locked away in free-text reports. But what if we could unlock this

Predicting tertiary lymphoid structures status of ICC patients using CT radiomics

Insights into Imaging April 2024

The authors of this study used preoperative CT radiomics in order to predict the tertiary lymphoid structures (TLSs) status and recurrence-free survival (RFS) of intrahepatic cholangiocarcinoma (ICC) patients. Enhanced CT images from a total of 116 ICC patients were included when using the radiomics model. The study results showed that the radiomics nomogram displayed better performance in predicting TLSs than

Ready for testing artificial intelligence in radiology clinical practice

Benjamin Bender April 2024

In the near future, I believe AI support systems will play a crucial role in the daily practice of radiologic reading. Radiologists are faced with an ever-increasing number of examinations and it remains vital to identify urgent cases as quickly as possible. An initial certified support system on the market has reported interesting performance data that proved the positive effect

Reproducibility of radiomics quality score: an intra- and inter-rater reliability study

Tugba Akinci D’Antonoli March 2024

The rapidly evolving field of radiomics research holds the potential to revolutionize medicine by transforming diagnostic images into quantifiable data. Assessing the quality of radiomics research is challenging and requires reliable tools for standardization. Our results, published in European Radiology, have revealed some room for improvement regarding the reproducibility of the widely used Radiomics Quality Score (RQS). We recruited multiple

MRI-based radiomics models show promise in clinical decision-making in spinal metastases patients

Insights into Imaging March 2024

The aim of this study was to extract radiomics features from MRI using various machine learning algorithms which would then be integrated with clinical features to build response prediction models for spinal metastases patients who were undergoing stereotactic body radiotherapy (SBRT). The authors found that the MRI-based radiomics models showed valuable predictive capability for treatment outcomes regarding spinal metastases patients

Implementing AI in breast imaging: challenges to turn the gadget into gain

Katja Pinker March 2024

In healthcare, the implementation of artificial intelligence (AI) is rapidly gaining momentum with breast imaging being no exception, or rather a poster child case. Numerous clinical indications intuitively lend themselves to AI enhancement. While the adoption of broad AI in clinical breast imaging practice has been more or less a silent revolution – it is already widely used for invite

New radiomics model to predict the Leibovich risk groups for ccRCC patients

Insights into Imaging March 2024

This study developed and validated a triphasic CT-based radiomics model, which incorporated radiomics features and significant clinical factors, for preoperative risk stratification of patients with localized clear cell renal cell carcinoma (ccRCC). The model showed a favorable performance in preoperatively predicting the Leibovich low-risk and intermediate-high-risk groups in localized ccRCC patients. The authors determined that this model can be used

Radiomics in the evaluation of ovarian masses

Insights into Imaging February 2024

This systematic review looked at the literature reporting the application of radiomics to imaging techniques in ovarian lesion patients. The authors found that radiomics showed promising results and great potential as a clinical diagnostic tool in patients with ovarian masses when it comes to improving lesion stratification, treatment selection, and outcome prediction. However, much larger and more diverse patient cohorts

Impact of signal intensity normalization of MRI on the generalizability of radiomic-based prediction of molecular glioma subtypes

Martha Foltyn-Dumitru, Philipp Vollmuth February 2024

With the help of radiomics, standard medical images can be transformed into detailed, high-dimensional data sets that go beyond what the eye can see. The typical workflow of radiomic projects involves a series of sequential processes, including image registration, intensity normalization, and segmentation of the region of interest. While there is a general agreement on the essential steps, consensus on

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

Latest posts