Efficiently obtaining a reliable coronary artery centerline from computed tomography angiography data is relevant in clinical practice. Whereas numerous methods have been presented for this purpose, up to now no standardized evaluation methodology has been published to reliably evaluate and compare the performance of the existing or newly developed coronary artery centerline extraction algorithms. This paper describes a standardized evaluation methodology and reference database for the quantitative evaluation of coronary artery centerline extraction algorithms. The contribution of this work is fourfold: 1) a method is described to create a consensus centerline with multiple observers, 2) well-defined measures are presented for the evaluation of coronary artery centerline extraction algorithms, 3) a database containing thirty-two cardiac CTA datasets with corresponding reference standard is described and made available, and 4) thirteen coronary artery centerline extraction algorithms, implemented by different research groups, are quantitatively evaluated and compared. The presented evaluation framework is made available to the medical imaging community for benchmarking existing or newly developed coronary centerline extraction algorithms.

Brain Metastases (BM) complicate 20-40% of cancer cases. BM lesions can present as punctate (1 mm) foci, requiring high-precision Magnetic Resonance Imaging (MRI) in order to prevent inadequate or delayed BM treatment. However, BM lesion detection remains challenging partly due to their structural similarities to normal structures (e.g., vasculature). We propose a BMdetection framework using a single-sequence gadoliniumenhanced T1-weighted 3D MRI dataset. The framework focuses on detection of smaller (< 15 mm) BM lesions and consists of: (1) candidate-selection stage, using Laplacian of Gaussian approach for highlighting parts of a MRI volume holding higher BM occurrence probabilities, and (2) detection stage that iteratively processes cropped region-of-interest volumes centered by candidates using a custom-built 3D convolutional neural network ("CropNet"). Data is augmented extensively during training via a pipeline consisting of random gamma correction and elastic deformation stages; the framework thereby maintains its invariance for a plausible range of BM shape and intensity representations. This approach is tested using five-fold cross-validation on 217 datasets from 158 patients, with training and testing groups randomized per patient to eliminate learning bias. The BM database included lesions with a mean diameter of ~5.4 mm and a mean volume of ~160 mm 3 . For 90% BM-detection sensitivity, the framework produced on average 9.12 falsepositive BM detections per patient (standard deviation of 3.49); for 85% sensitivity, the average number of falsepositives declined to 5.85. Comparative analysis showed that the framework produces comparable BM-detection accuracy with the state-of-art approaches validated for significantly larger lesions.Index Terms-magnetic resonance imaging, brain metastases, convolutional neural networks, deep learning, scale-space representations, computer-aided detection, medical image analysis.

Abstract. Delayed Enhancement MR is an imaging technique by which nonviable (dead) myocardial tissues appear with increased signal intensity. The extent of non-viable tissue in the left ventricle (LV) of the heart is a direct indicator of patient survival rate. In this paper we propose a two-stage method for quantifying the extent of non-viable tissue. First, we segment the myocardium in the DEMR images. Then, we classify the myocardial pixels as corresponding to viable or non-viable tissue. Segmentation of the myocardium is challenging because we cannot reliably predict its intensity characteristics. Worse, it may be impossible to distinguish the infracted tissues from the ventricular blood pool. Therefore, we make use of MR Cine images acquired in the same session (in which the myocardium has a more predictable appearance) in order to create a prior model of the myocardial borders. Using image features in the DEMR images and this prior we are able to segment the myocardium consistently. In the second stage of processing, we employ a Support Vector Machine to distinguish viable from non-viable pixels based on training from an expert.

This report represents a roadmap for integrating Artificial Intelligence (AI)-based image analysis algorithms into existing Radiology workflows such that: (1) radiologists can significantly benefit from enhanced automation in various imaging tasks due to AI; and (2) radiologists' feedback is utilized to further improve the AI application. This is achieved by establishing three maturity levels where: (1) research enables the visualization of AI-based results/annotations by radiologists without generating new patient records; (2) production allows the AI-based system to generate results stored in an institution's Picture Archiving and Communication System; and (3) feedback equips radiologists with tools for editing the AI inference results for periodic retraining of the deployed AI systems, thereby allowing the continuous organic improvement of AI-based radiology-workflow solutions. A case study (i.e., detection of brain metastases with T1-weighted contrast-enhanced 3D MRI) illustrates the deployment details of a particular AI-based application according to the aforementioned maturity levels. It is shown that the given AI application significantly improves with the feedback coming from radiologists; the number of incorrectly detected brain metastases (false positives) reduces from 14.2 to 9.12 per patient with the number of subsequently annotated datasets increasing from 93 to 217 as a result of radiologist adjudication.