AJR. American journal of roentgenology
-
AJR Am J Roentgenol · Feb 2019
Artificial Intelligence for Breast MRI in 2008-2018: A Systematic Mapping Review.
The purpose of this study is to review literature from the past decade on applications of artificial intelligence (AI) to breast MRI. ⋯ Interest in the application of advanced AI methods to breast MRI is growing worldwide. Although this growth is encouraging, the current performance of AI applications in breast MRI means that such applications are still far from being incorporated into clinical practice.
-
AJR Am J Roentgenol · Jan 2019
ReviewPeering Into the Black Box of Artificial Intelligence: Evaluation Metrics of Machine Learning Methods.
Machine learning (ML) and artificial intelligence (AI) are rapidly becoming the most talked about and controversial topics in radiology and medicine. Over the past few years, the numbers of ML- or AI-focused studies in the literature have increased almost exponentially, and ML has become a hot topic at academic and industry conferences. However, despite the increased awareness of ML as a tool, many medical professionals have a poor understanding of how ML works and how to critically appraise studies and tools that are presented to us. Thus, we present a brief overview of ML, explain the metrics used in ML and how to interpret them, and explain some of the technical jargon associated with the field so that readers with a medical background and basic knowledge of statistics can feel more comfortable when examining ML applications. ⋯ Attention to sample size, overfitting, underfitting, cross validation, as well as a broad knowledge of the metrics of machine learning, can help those with little or no technical knowledge begin to assess machine learning studies. However, transparency in methods and sharing of algorithms is vital to allow clinicians to assess these tools themselves.
-
AJR Am J Roentgenol · Aug 2018
Meta AnalysisDiagnostic Performance of Monoexponential DWI Versus Diffusion Kurtosis Imaging in Prostate Cancer: A Systematic Review and Meta-Analysis.
We aimed to compare the diagnostic performance of monoexponential DWI and diffusion kurtosis imaging (DKI) for the detection of prostate cancer (PCa). ⋯ Monoexponential DWI and DKI showed comparable diagnostic accuracies for PCa. DKI is a potentially helpful method for the diagnosis of PCa. Therefore, on the basis of current evidence, we do not recommend including DKI in routine clinical assessment of PCa for the moment.
-
AJR Am J Roentgenol · Jul 2018
Meta AnalysisJOURNAL CLUB: Extracolonic Findings at CT Colonography: Systematic Review and Meta-Analysis.
The purpose of this study was to perform a systematic review and meta-analysis of published studies on CT colonography (CTC) in which extracolonic findings were assessed. ⋯ With use of the more robust C-RADS classification, potentially important extracolonic findings at CTC occur in less than 3% of cohorts without symptoms. For all extracolonic findings, the rate of suggested or recommended additional workup is approximately 8% but decreases to 4% for potentially important extracolonic findings.
-
The field of cognitive science has provided important insights into mental processes underlying the interpretation of imaging examinations. Despite these insights, diagnostic error remains a major obstacle in the goal to improve quality in radiology. In this article, we describe several types of cognitive bias that lead to diagnostic errors in imaging and discuss approaches to mitigate cognitive biases and diagnostic error. ⋯ Radiologists rely on heuristic principles to reduce complex tasks of assessing probabilities and predicting values into simpler judgmental operations. These mental shortcuts allow rapid problem solving based on assumptions and past experiences. Heuristics used in the interpretation of imaging studies are generally helpful but can sometimes result in cognitive biases that lead to significant errors. An understanding of the causes of cognitive biases can lead to the development of educational content and systematic improvements that mitigate errors and improve the quality of care provided by radiologists.