AI Blog

The latest developments in radiomics and AI may help against prostate cancer

European Radiology Experimental September 2022

The authors of this systematic review explored the currently available literature on artificial intelligence (AI) and radiomics applied to molecular imaging of prostate cancer. Due to the great promise that nuclear medicine holds regarding improving the quality of life for prostate cancer patients, this study looks at the myriad areas in which AI and radiomics can positively be applied to

Deep learning detection of ACL tear on knee MRI

European Radiology September 2022

The purpose of this study was to develop a deep-learning algorithm for tear detection in the anterior cruciate ligament (ACL), subsequently comparing its accuracy using two external datasets. The authors were able to conclude that their algorithm was capable of showing high performance in the detection of ACL tears. Key points An algorithm for detecting anterior cruciate ligament ruptures was

Applications of machine learning for imaging-driven diagnosis of musculoskeletal malignancies

European Radiology September 2022

Due to the rare nature of musculoskeletal malignancies and the lack of imaging data associated with this cancer, the authors of this study aimed to investigate whether machine learning (ML) is already having an impact on imaging-driven diagnosis of musculoskeletal malignancies. The authors concluded that because of the limited amounts of data and no established large-scale networks between multiple national

Metadata Models: The position of the AI for Health Imaging (AI4HI) network

European Radiology Experimental September 2022

Due to the enormous amount of imaging data that is becoming available, there is a wide range of possible improvements that can be provided by artificial intelligence (AI) algorithms in clinical care covering diagnosis and decision support. Therefore, it is crucial how we proceed in managing and handling this data, e.g. medical images, and to define which metadata must be

Radiomic assessment of oesophageal adenocarcinoma

Insights into Imaging August 2022

The use of radiomic models offers a possible way to improve oesophageal adenocarcinoma assessment through quantitative image analysis, but model selection becomes complicated due to the myriad available predictors as well as the uncertainty of their relevance and reproducibility. Therefore, the aim of this study was to review recent research in order to facilitate precedent-based model selection for prospective validation

Possible strategies for use of AI in screen-reading of mammograms

Marthe Larsen August 2022

After publishing the overall performance results of an AI system in Radiology (Artificial Intelligence Evaluation of 122,969 Mammography Examinations from a Population-based Screening Program), we explored different possible strategies for using AI in the screen-reading of mammograms. We presented estimated cancer detection rates for 11 different possible ways of implementing AI mammography screening. However, with different thresholds for selecting cases

Non-invasive prediction of microsatellite instability in colorectal cancer

European Radiology August 2022

The goal of this study was to establish a CT-based radiomics signature in order to predict microsatellite instability (MSI) status in patients with colorectal cancer (CRC). Through data from 837 CRC patients from two hospitals who underwent preoperative enhanced CT and had available MSI status data, the authors were able to build a robust radiomics signature for the identification of

The potential of texture analysis for breast density classification

European Radiology Experimental August 2022

Breast cancer continues to be the most commonly diagnosed cancer among women with over 2 million new cases per year worldwide. One important independent risk factor for developing breast cancer is breast density (BD). Epidemiological studies show that women with dense tissue may have an increased risk of developing breast cancer by 2-6 times when compared to women with less

How well does a 3D convolutional neural network perform in detecting hypoperfusion?

European Radiology Experimental July 2022

Due to the life-threatening nature of chronic pulmonary embolism (CPE) and how easily it can be misdiagnosed on computed tomography, the authors of this study investigated a three-dimensional convolutional neural network (CNN) algorithm for detecting hypoperfusion in CPE from computed tomography pulmonary angiography (CTPA). This study demonstrated the feasibility of a deep learning algorithm for detecting hypoperfusion in CPE from

Bone Strain Index predicts fragility fracture in osteoporotic women

European Radiology Experimental July 2022

The authors of this study used an artificial intelligence-based model in order to predict fragility fractures in postmenopausal women. Through a sample of 174 postmenopausal women, they found a high performance of an artificial neural network (ANN) analysis in predicting the occurrence of vertebral fractures (VFs) and also discovered that femoral bone strain index (BSI) appears helpful in identifying patients

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

Latest posts