Risk stratification of thyroid malignancy by using the number of suspicious US features allows for a practical and convenient TIRADS.

The use of artificial intelligence in medicine is currently an issue of great interest, especially with regard to the diagnostic or predictive analysis of medical images. Adoption of an artificial intelligence tool in clinical practice requires careful confirmation of its clinical utility. Herein, the authors explain key methodology points involved in a clinical evaluation of artificial intelligence technology for use in medicine, especially high-dimensional or overparameterized diagnostic or predictive models in which artificial deep neural networks are used, mainly from the standpoints of clinical epidemiology and biostatistics. First, statistical methods for assessing the discrimination and calibration performances of a diagnostic or predictive model are summarized. Next, the effects of disease manifestation spectrum and disease prevalence on the performance results are explained, followed by a discussion of the difference between evaluating the performance with use of internal and external datasets, the importance of using an adequate external dataset obtained from a well-defined clinical cohort to avoid overestimating the clinical performance as a result of overfitting in high-dimensional or overparameterized classification model and spectrum bias, and the essentials for achieving a more robust clinical evaluation. Finally, the authors review the role of clinical trials and observational outcome studies for ultimate clinical verification of diagnostic or predictive artificial intelligence tools through patient outcomes, beyond performance metrics, and how to design such studies. RSNA, 2018.

No abstract

No abstract

Clinical prediction models are developed to calculate estimates of the probability of the presence/occurrence or future course of a particular prognostic or diagnostic outcome from multiple clinical or non-clinical parameters. Radiologic imaging techniques are being developed for accurate detection and early diagnosis of disease, which will eventually affect patient outcomes. Hence, results obtained by radiological means, especially diagnostic imaging, are frequently incorporated into a clinical prediction model as important predictive parameters, and the performance of the prediction model may improve in both diagnostic and prognostic settings. This article explains in a conceptual manner the overall process of developing and validating a clinical prediction model involving radiological parameters in relation to the study design and statistical methods. Collection of a raw dataset; selection of an appropriate statistical model; predictor selection; evaluation of model performance using a calibration plot, Hosmer-Lemeshow test and c-index; internal and external validation; comparison of different models using c-index, net reclassification improvement, and integrated discrimination improvement; and a method to create an easy-to-use prediction score system will be addressed. This article may serve as a practical methodological reference for clinical researchers.

Purpose To retrospectively analyze whether Prostate Imaging Reporting and Data System (PI-RADS) version 2 is helpful for the detection of clinically significant prostate cancer. Materials and Methods Institutional review board approved this retrospective study. A total of 425 patients with prostate cancer who had undergone magnetic resonance (MR) imaging and radical prostatectomy were included. Preoperative parameters such as prostate-specific antigen, biopsy Gleason score, greatest percentage of the core, percentage of the positive core number, and score at PI-RADS version 2 with MR imaging were investigated. Two independent readers performed PI-RADS scoring. Clinically significant prostate cancer was defined as follows: (a) Gleason score of 7 or greater, (b) tumor volume of 0.5 cm(3) or greater, or a (c) positive extracapsular extension or seminal vesicle invasion. The reference standard was based on review of surgical specimen. Logistic regression was conducted to determine which parameters are associated with the presence of clinically significant cancer. Interreader agreement (ie, score ≥4 or not) was investigated by using κ statistics. Results At univariate analysis, all of the preoperative parameters were significant for clinically significant prostate cancer (P < .05). However, multivariate analysis revealed that PI-RADS score was the only significant parameter for both readers (reader 1: odds ratio = 28.170, P = .002; reader 2: odds ratio = 5.474, P = .007). The interreader agreement was excellent for PI-RADS score of 4 or greater (weighted κ = 0.801; 95% confidence interval: 0.737, 0.865). Conclusion The use of PI-RADS version 2 may help preoperatively diagnose clinically significant prostate cancer. (©) RSNA, 2016.

Central lymph node metastasis in patients with PTMC was significantly associated with various clinicopathological factors, including larger tumor size (>5 mm), bilaterality, extracapsular invasion, and lateral LNM. When these features are detected on preoperative US, selective central compartment dissection may be helpful in patients diagnosed with PTMC.

No abstract