AI Blog

Using a multiple classifier system for lesion detection and classification in breast MRI analysis

European Radiology Experimental March 2019

In breast magnetic resonance imaging (MRI) analysis for lesion detection and classification, radiologists agree that both morphological and dynamic features are important to differentiate benign from malignant lesions. This study proposes a multiple classifier system (MCS) to classify breast lesions on dynamic contrast-enhanced MRI (DCE-MRI) combining morphological features and dynamic information. The data gained through testing showed that an MCS

Prediction of rupture risk in anterior communicating artery aneurysms

European Radiology February 2019

This article attempts to predict the rupture risk in anterior communicating artery (ACOM) aneurysms by using a two-layer feed-forward artificial neural network (ANN). To improve ANN efficiency, an adaptive synthetic (ADASYN) sampling approach was applied to generate more synthetic data for unruptured aneurysms. Based on the results, the conclusion is that this ANN presents good performance and offers a valuable

The Rise of Augmented Radiology as an enabler to achieve Precision Health

ECR 2019 AIX February 2019

The field of medical imaging has witnessed a revolution thanks to the digital transformation, innovation and availability of advanced clinical applications. New imaging techniques are helping radiologists, oncologists, and other diagnosticians with greater anatomical and clinical details, highlighting the need for fast access to imaging reports and results, evidence-based collaborative peer review and collaboration, and predictive intelligence. A pioneer in

Convolutional neural networks: an overview and application in radiology

Insights into Imaging February 2019

Numerous domains, including radiology, have shown interest in convolutional neural network (CNN) – a class of artificial neural networks that has become dominant in various computer vision tasks. It is designed to automatically and adaptively learn spatial hierarchies of features through backpropagation by using multiple building blocks, such as convolution layers, pooling layers, and fully connected layers. This review article

Treat artificial intelligence as disruptive technology

Melisande Rouger February 2019

Radiologists tend to be afraid of artificial intelligence (AI), but they should demystify it and take it for what it is, i.e. disruptive technology, according to Frank Lexa, a professor of radiology at the University of Arizona and an expert in medical leadership. “AI tools improve at the speed of light, and it’s unclear whether radiologists will keep on playing

Big data, artificial intelligence, and structured reporting

Daniel Pinto dos Santos February 2019

Imagine you wanted to teach a baby to differentiate a ball from a dog. How would you do that? Intuitively it would make sense to repeatedly point at them while naming each object accordingly. But how about, e.g. if instead of saying “dog” or “ball”, you would only name the specific breed of dog without using the word “dog”? Maybe

A survey of medical students’ attitude toward AI

European Radiology February 2019

The aim of this survey was to assess undergraduate medical students’ attitudes towards artificial intelligence (AI) in radiology and medicine. A web-based questionnaire consisting of various sections aiming to evaluate the students’ prior knowledge of AI in radiology and beyond was sent out to students at three major medical schools. The survey showed that undergraduate medical students do not worry

AI for CT Image Reconstruction – A Great Opportunity

Martin Willemink February 2019

It seems like everybody in the radiology field is now working with Artificial Intelligence (AI) in one way or another. Especially here in the Silicon Valley, the number of ventures that develop AI algorithms is increasing by the day. What are these newly developed algorithms focusing on? Most of them try to solve a specific problem, and they do that

Radiomics of liver MRI predict metastases in mice

European Radiology Experimental February 2019

This study aimed to investigate whether any texture features show a correlation with intrahepatic tumor growth before the metastasis is visible to the human eye. For the purposes of the study, eight mice were injected intraportally with syngeneic MC-38 colon cancer cells and two mice were injected with phosphate-buffered saline (sham controls). Magnetic resonance imaging (MRI) and texture analysis were

Comparing computer- and human-extracted imaging phenotypes

European Radiology Experimental February 2019

This retrospective study sought to investigate if computer-extracted magnetic resonance imaging (MRI) phenotypes of breast cancer could replicate human-extracted size and Breast Imaging-Reporting and Data System (BI-RADS) imaging phenotypes using MRI data from The Cancer Genome Atlas (TCGA) project of the National Cancer Institute. Upon obtaining the results, it was possible to conclude that quantitative radiomics of breast cancer may replicate human-extracted tumour size

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

Latest posts