AI Blog

How can we combat multicenter variability in MR radiomics? Validation of a correction procedure

European Radiology March 2021

In this study, the authors extended the ComBat approach to provide a harmonization procedure that is applicable to any radiomic feature. They achieve this by combining image standardization with ComBat realignment, thus demonstrating that this could efficiently remove the scanner/protocol effect while preserving the individual variations in phantom, brain, and prostate MR scans. Key points Radiomic feature values obtained using

The promising possibility of using AI in mammography screening

Kristina Lång March 2021

In two recent publications in European Radiology, we have addressed two, of several, challenges with mammography screening. Firstly, the vast majority of screen exams are normal, which is resource-demanding, especially in the double-reading setting; and secondly, we miss cancer that can be particularly aggressive, later appearing as interval cancer. To understand if artificial intelligence (AI) can identify normal exams, we

Minimizing acquisition-related radiomics variability by image resampling and batch effect correction to allow for large-scale data analysis

Raquel Perez-Lopez February 2021

Medical imaging encodes information of underlying tissues and can provide a comprehensive view of the entire body repeatedly throughout the course of disease. Therefore, medical imaging has been the foundation of disease detection and follow-up in clinical practice for decades. However, to date, observer-dependent evaluation of medical imaging has been a constraint for developing imaging biomarkers towards precision medicine. The

Differentiating the pathological subtypes of primary lung cancer for patients with brain metastases based on radiomics features from brain CT images

European Radiology February 2021

In this study, the aim of the authors was to investigate the feasibility and accuracy of differentiating the primary adenocarcinoma (AD) and squamous cell carcinoma (SCC) of non-small-cell lung cancer (NSCLC) for patients with brain metastases (BM) based on radiomics from brain contrast-enhanced computer tomography (CECT) images. Through this study, the authors discovered that brain CECT radiomics are promising in

Deep learning–based automated detection algorithm for active pulmonary tuberculosis on chest radiographs: diagnostic performance in systematic screening of asymptomatic individuals

Chang Min Park February 2021

Chest radiographs (CRs) have long been used as one of the screening tests for pulmonary tuberculosis (TB). However, the interpretation of a large number of CRs is time-consuming and labor-intensive. To overcome this difficulty, we developed the deep-learning-based automated detection (DLAD) for active pulmonary TB detection and performed out-of-sample testing in the consecutively collected 20.135 CRs from 19.686 servicepersons. As

Challenges and solutions for introducing artificial intelligence (AI) in daily clinical workflow

Elmar Kotter February 2021

We are living in the hype about artificial intelligence (AI) in radiology. Many publications have proven that AI is able to support image analysis with its excellent pattern recognition. It has the potential to augment the radiologist by helping to analyse the increasingly complex data we are confronted with in our daily work. However, to make AI happen in our

Simulated clinical deployment of fully automatic deep learning for clinical prostate MRI assessment

David Bonekamp January 2021

We use a previously validated artificial neural network to evaluate its performance in a much larger, subsequent, consecutive cohort. In the community, there exists a belief that with infinite training data, an AI system can theoretically be trained that has the ability to handle all possible data and thus be generalised to all environments. Applied to the prostate, this would

A decade of radiomics research: are images really data or just patterns in the noise?

Daniel Pinto dos Santos January 2021

Radiomics as a research topic in radiology is certainly a promising field. Over the last years, many publications have shown promising results, showing that image analysis using a radiomics approach could potentially help guide clinical decision making by allowing for accurate, non-invasive diagnosis and prognosis. However, despite the large number of publications, we see only little to no translation of

Radiologists with MRI-based radiomics aids to predict the pelvic lymph node metastasis in endometrial cancer: a multicenter study

European Radiology January 2021

The purpose of this study, performed between January 2014 and May 2019 across five different centers, was to construct an MRI radiomics model and help radiologists to improve the preoperative assessments of pelvic lymph node metastasis (PLNM) in endometrial cancer (EC). The authors were able to find that the MRI-based radiomics model could be used to assess the status of

Radiomics in predicting treatment response in non-small-cell lung cancer: current status, challenges and future perspectives

European Radiology January 2021

This literature review summarizes the current status and evaluates the scientific reporting quality of radiomics research in the prediction of treatment response in non-small-cell lung cancer (NSCLC). The authors performed this literature review through a comprehensive literature search using the PubMed database, screening a total of 178 articles for eligibility. Key points The included studies reported several promising radiomic markers

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

Latest posts