Artificial Intelligence for Cardiothoracic Imaging: Overview of Current and Emerging Applications.

Artificial intelligence algorithms can learn by assimilating information from large datasets in order to decipher complex associations, identify previously undiscovered pathophysiological states, and construct prediction models. There has been tremendous interest and increased incorporation of artificial intelligence into various industries, including healthcare. As a result, there has been an exponential rise in the number of research articles and industry participants producing models intended for a variety of applications in medical imaging, which can be challenging to navigate for radiologists. In thoracic imaging, multiple applications are being evaluated for chest radiography and computed tomography and include applications for lung nodule evaluation and cancer imaging, quantifying diffuse lung disorders, and cardiac imaging, to name a few. This review aims to provide an overview of current clinical AI models, focusing on the most common clinical applications of AI in cardiothoracic imaging.

Validation of the Dominant Sequence Paradigm and Role of Dynamic Contrast-enhanced Imaging in PI-RADS Version 2.

Purpose To validate the dominant pulse sequence paradigm and limited role of dynamic contrast material-enhanced magnetic resonance (MR) imaging in the Prostate Imaging Reporting and Data System (PI-RADS) version 2 for prostate multiparametric MR imaging by using data from a multireader study. Materials and Methods This HIPAA-compliant retrospective interpretation of prospectively acquired data was approved by the local ethics committee. Patients were treatment-naïve with endorectal coil 3-T multiparametric MR imaging. A total of 163 patients were evaluated, 110 with prostatectomy after multiparametric MR imaging and 53 with negative multiparametric MR imaging and systematic biopsy findings. Nine radiologists participated in this study and interpreted images in 58 patients, on average (range, 56-60 patients). Lesions were detected with PI-RADS version 2 and were compared with whole-mount prostatectomy findings. Probability of cancer detection for overall, T2-weighted, and diffusion-weighted (DW) imaging PI-RADS scores was calculated in the peripheral zone (PZ) and transition zone (TZ) by using generalized estimating equations. To determine dominant pulse sequence and benefit of dynamic contrast-enhanced (DCE) imaging, odds ratios (ORs) were calculated as the ratio of odds of cancer of two consecutive scores by logistic regression. Results A total of 654 lesions (420 in the PZ) were detected. The probability of cancer detection for PI-RADS category 2, 3, 4, and 5 lesions was 15.7%, 33.1%, 70.5%, and 90.7%, respectively. DW imaging outperformed T2-weighted imaging in the PZ (OR, 3.49 vs 2.45; P = .008). T2-weighted imaging performed better but did not clearly outperform DW imaging in the TZ (OR, 4.79 vs 3.77; P = .494). Lesions classified as PI-RADS category 3 at DW MR imaging and as positive at DCE imaging in the PZ showed a higher probability of cancer detection than did DCE-negative PI-RADS category 3 lesions (67.8% vs 40.0%, P = .02). The addition of DCE imaging to DW imaging in the PZ was beneficial (OR, 2.0; P = .027), with an increase in the probability of cancer detection of 15.7%, 16.0%, and 9.2% for PI-RADS category 2, 3, and 4 lesions, respectively. Conclusion DW imaging outperforms T2-weighted imaging in the PZ; T2-weighted imaging did not show a significant difference when compared with DW imaging in the TZ by PI-RADS version 2 criteria. The addition of DCE imaging to DW imaging scores in the PZ yields meaningful improvements in probability of cancer detection. © RSNA, 2017 An earlier incorrect version of this article appeared online. This article was corrected on July 27, 2017. Online supplemental material is available for this article.

Prostate Cancer: The European Society of Urogenital Radiology Prostate Imaging Reporting and Data System Criteria for Predicting Extraprostatic Extension by Using 3-T Multiparametric MR Imaging.

PURPOSE: To retrospectively assess the use of the European Society of Urogenital Radiology (ESUR) Prostate Imaging Reporting and Data System (PI-RADS) criteria and 3-T multiparametric magnetic resonance (MR) imaging for detection of extraprostatic extension (EPE) of prostate cancer. MATERIALS AND METHODS: The institutional review board approval requirement was waived. Consecutive patients with prostate cancer (n = 133) underwent 3-T multiparametric MR imaging before prostatectomy. Lesions were assessed by using ESUR/PI-RADS criteria for T2-weighted, diffusion-weighted, and dynamic contrast material-enhanced imaging, and by using the sum of these scores. Zonal dominant parameters corresponding to the score of diffusion-weighted imaging for peripheral zone lesions and to T2-weighted imaging scores for transitional zone lesions were calculated. In addition, the presence of EPE in each patient was evaluated on the basis of subjective multiparametric MR imaging features. Histopathologic examination of whole-mount radical prostatectomy specimens was used as the reference standard. Sensitivity, specificity, positive predictive, and negative predictive values; likelihood ratios; and areas under the receiver operating characteristic curve were calculated for each parameter on the basis of its usefulness for prediction of EPE. RESULTS: EPE was found in 60 of 133 (45%) patients. Receiver operating characteristic curve analysis for the prediction of EPE revealed an area under the curve of 0.72 for T2-weighted, 0.67 for diffusion-weighted, and 0.64 for dynamic contrast-enhanced imaging; 0.74 for the dominant parameter; and 0.74 for the sum of the PI-RADS scores, and a score of 5 was defined as the best threshold for the individual parameters, with a score greater than or equal to 13 as the threshold for the sum of the PI-RADS scores. By applying these thresholds, sensitivity, negative predictive value, and negative likelihood ratio (ruling out EPE) were 77%, 77%, and 0.36, respectively, and specificity, positive predictive value, and positive likelihood ratio (ruling in EPE) were 64%, 64%, and 2.15, respectively, for the dominant parameter. Feature analysis showed an area under the curve of 0.72; sensitivity, negative predictive value, and negative likelihood ratio of 63%, 72%, and 0.56, respectively, and specificity, positive predictive value, and positive likelihood ratio of 78%, 70%, and 3.77, respectively. CONCLUSION: ESUR/PI-RADS criteria showed moderate overall accuracy for use in the prediction of EPE, and these results were similar to those of multiparametric MR imaging assessment of features in this study sample.

PET/CT and vascular disease: current concepts.

Since its introduction in 2001, positron emission tomography associated to computed tomography (PET/CT) has been established as a standard tool in cancer evaluation. Being a multimodality imaging method, it combines in a single session the sensitivity granted by PET for detection of molecular targets within the picomolar range, with an underlying submilimetric resolution inherent to CT, that can precisely localize the PET findings. In this last decade, there have been new insights regarding the pathophysiology of atherosclerosis, particularly about plaque rupture and vascular remodeling. This has increased the interest for research on PET/CT in vascular diseases as a potential new diagnostic tool, since some PET molecular targets could identify diseases before the manifestation of gross anatomic features. In this review, we will describe the current applications of PET/CT in vascular diseases, emphasizing its usefulness in the settings of vasculitis, aneurysms, vascular graft infection, aortic dissection, and atherosclerosis/plaque vulnerability. Although not being properly peripheral vascular conditions, ischemic cardiovascular disease and cerebrovascular disease will be briefly addressed as well, due to their widespread prevalence and importance.