Automated segmentation and quantification of the healthy and diseased aorta in CT angiographies using a dedicated deep learning approach.

OBJECTIVES: To develop and validate a deep learning-based algorithm for segmenting and quantifying the physiological and diseased aorta in computed tomography angiographies. METHODS: CTA exams of the aorta of 191 patients (68.1 ± 14 years, 128 male), performed between 2015 and 2018, were retrospectively identified from our imaging archive and manually segmented by two investigators. A 3D U-Net model was trained on the data, which was divided into a training, a validation, and a test group at a ratio of 7:1:2. Cases in the test group (n = 41) were evaluated to compare manual and automatic segmentations. Dice similarity coefficient (DSC), mean surface distance (MSD), and Hausdorff surface distance (HSD) were extracted. Maximum diameter, effective diameter, and area were quantified and compared between both segmentations at eight anatomical landmarks, and at the maximum area of an aneurysms if present (n = 14). Statistics included error calculation, intraclass correlation coefficient, and Bland-Altman analysis. RESULTS: A DSC of 0.95 [0.94; 0.95] and an MSD of 0.76 [0.06; 0.99] indicated close agreement between segmentations. HSD was 8.00 [4.47; 10.00]. The largest absolute errors were found in the ascending aorta with 0.8 ± 1.5 mm for maximum diameter and at the coeliac trunk with - 30.0 ± 81.6 mm2 for area. Results for absolute errors in aneurysms were - 0.5 ± 2.3 mm for maximum diameter, 0.3 ± 1.6 mm for effective diameter, and 64.9 ± 114.9 mm2 for area. ICC showed excellent agreement (> 0.9; p < 0.05) between quantitative measurements. CONCLUSIONS: Automated segmentation of the aorta on CTA data using a deep learning algorithm is feasible and allows for accurate quantification of the aortic lumen even if the vascular architecture is altered by disease. KEY POINTS: • A deep learning-based algorithm can automatically segment the aorta, mostly within acceptable margins of error, even if the vascular architecture is altered by disease. • Quantifications performed in the segmentations were mostly within clinically acceptable limits, even in pathologically altered segments of the aorta.

Cooperative AI training for cardiothoracic segmentation in computed tomography: An iterative multi-center annotation approach.

PURPOSE: Radiological reporting is transitioning to quantitative analysis, requiring large-scale multi-center validation of biomarkers. A major prerequisite and bottleneck for this task is the voxelwise annotation of image data, which is time-consuming for large cohorts. In this study, we propose an iterative training workflow to support and facilitate such segmentation tasks, specifically for high-resolution thoracic CT data. METHODS: Our study included 132 thoracic CT scans from clinical practice, annotated by 13 radiologists. In three iterative training experiments, we aimed to improve and accelerate segmentation of the heart and mediastinum. Each experiment started with manual segmentation of 5-25 CT scans, which served as training data for a nnU-Net. Further iterations incorporated AI pre-segmentation and human correction to improve accuracy, accelerate the annotation process, and reduce human involvement over time. RESULTS: Results showed consistent improvement in AI model quality with each iteration. Resampled datasets improved the Dice similarity coefficients for both the heart (DCS 0.91 [0.88; 0.92]) and the mediastinum (DCS 0.95 [0.94; 0.95]). Our AI models reduced human interaction time by 50 % for heart and 70 % for mediastinum segmentation in the most potent iteration. A model trained on only five datasets achieved satisfactory results (DCS > 0.90). CONCLUSIONS: The iterative training workflow provides an efficient method for training AI-based segmentation models in multi-center studies, improving accuracy over time and simultaneously reducing human intervention. Future work will explore the use of fewer initial datasets and additional pre-processing methods to enhance model quality.

New vessel analysis tool for morphometric quantification and visualization of vessels in CT and MR imaging data sets.

Image processing algorithms and a prototypical research software tool have been developed for visualization and quantitative analysis of vessels in data sets from computed tomography and magnetic resonance imaging. The software is based on a sequence of processing steps, which are as follows: (a) vessel segmentation based on a region growing algorithm, (b) interactive "premasking" to optionally exclude interfering structures close to the vessels of interest, (c) distance transform-based skeletonization, (d) multiplanar reformation orthogonal to the vessel path, (e) identification of the lumen boundary on the orthogonal cross-section images, and (f) morphometric measurements. The development of the algorithmic components and the application user interface has been carried out in close cooperation with clinical users to achieve a high degree of usability and flexible support of work flow. The software has been successfully applied to the intracranial arteries, carotid arteries, and abdominal and thoracic aorta, as well as the renal, coronary, and peripheral arteries.

Remifentanil-induced tolerance, withdrawal or hyperalgesia in infants: a randomized controlled trial. RAPIP trial: remifentanil-based analgesia and sedation of paediatric intensive care patients.

BACKGROUND: Short-acting opioids like remifentanil are suspected of an increased risk for tolerance, withdrawal and opioid-induced hyperalgesia (OIH). These potential adverse effects have never been investigated in neonates. OBJECTIVES: To compare remifentanil and fentanyl concerning the incidence of tolerance, withdrawal and OIH. METHODS: 23 mechanically ventilated infants received up to 96 h either a remifentanil- or fentanyl-based analgesia and sedation regimen with low-dose midazolam. We compared the required opioid doses and the number of opioid dose adjustments. Following extubation, withdrawal symptoms were assessed by a modification of the Finnegan score. OIH was evaluated by the CHIPPS scale and by testing the threshold of the flexion withdrawal reflex with calibrated von Frey filaments. RESULTS: Remifentanil had to be increased by 24% and fentanyl by 47% to keep the infants adequately sedated during mechanical ventilation. Following extubation, infants revealed no pronounced opioid withdrawal and low average Finnegan scores in both groups. Only 1 infant of the fentanyl group and 1 infant of the remifentanil group required methadone for treatment of withdrawal symptoms. Infants also revealed no signs of OIH and low CHIPPS scores in both groups. The median threshold of the flexion withdrawal reflex was 4.5 g (IQR = 2.3) in the fentanyl group and 2.7 g (IQR = 3.3) in the remifentanil group (p = 0.312), which is within the physiologic range of healthy infants. CONCLUSIONS: Remifentanil does not seem to be associated with an increased risk for tolerance, withdrawal or OIH.