Detecting the pulmonary trunk in CT scout views using deep learning

Abstract

For CT pulmonary angiograms, a scout view obtained in anterior–posterior projection is usually used for planning. For bolus tracking the radiographer manually locates a position in the CT scout view where the pulmonary trunk will be visible in an axial CT pre-scan. We automate the task of localizing the pulmonary trunk in CT scout views by deep learning methods. In 620 eligible CT scout views of 563 patients between March 2003 and February 2020 the region of the pulmonary trunk as well as an optimal slice (“reference standard”) for bolus tracking, in which the pulmonary trunk was clearly visible, was annotated and used to train a U-Net predicting the region of the pulmonary trunk in the CT scout view. The networks’ performance was subsequently evaluated on 239 CT scout views from 213 patients and was compared with the annotations of three radiographers. The network was able to localize the region of the pulmonary trunk with high accuracy, yielding an accuracy of 97.5% of localizing a slice in the region of the pulmonary trunk on the validation cohort. On average, the selected position had a distance of 5.3 mm from the reference standard. Compared to radiographers, using a non-inferiority test (one-sided, paired Wilcoxon rank-sum test) the network performed as well as each radiographer (P < 0.001 in all cases). Automated localization of the region of the pulmonary trunk in CT scout views is possible with high accuracy and is non-inferior to three radiographers.

Development and Validation of a Deep-Learning-Based Algorithm for Detecting and Classifying Metallic Implants in Abdominal and Spinal CT Topograms

“…As topograms are low-dose and low-resolution images, image quality is inferior to radiographs in detecting subtle objects. Some papers about automatic segmentation or detection of a certain part of the human anatomy have been published; however, there have been no studies on applying DLA to the detection of metallic implants in topograms [16,17]. As topograms are always obtained to localize and determine the range of CT scans, extracting useful information from topograms may help to perform CT examinations with more suitable parameters.…”

“…Topograms have also been used in the prediction of patient body weight or with deep learning algorithms (DLAs) in the reconstruction of three-dimensional images from two topograms for dose modulation [13][14][15]. Segmenting images of the specific organs in topograms using DLAs has also been a promising application [16,17]. However, the detection and classification of metallic implants based on topograms has not yet been studied.…”

A Systematic Collection of Medical Image Datasets for Deep Learning

“…The success of AI algorithms such as DL has led to their widespread use in several fields, including for med-ical image analysis. Researchers with different knowledge and background tackle image-based clinical tasks using computer vision tools to design automatic algorithms for different applications [11,12,12,260,261,262,263,264]. Though AI algorithms can successfully handle many tasks, several unsolved problems and challenges hinder the development of AI-based medical image analysis.…”

The Effect of Limiting the Scan Range of Computed Tomography Pulmonary Angiography (to Reduce Radiation Exposure) on the Detection of Pulmonary Embolism: A Systematic Review

“…Scan windows based on absolute measures and not easily identifiable anatomical landmarks are potentially problematic in clinical practice. Firstly, radiographers routinely use anatomical landmarks to determine the CTPA window [ 30 ]. Secondly, absolute measures may not be applicable to all population groups, as patients may have significant variations in anatomy and thorax length.…”