Fully automated guideline-compliant diameter measurements of the thoracic aorta on ECG-gated CT angiography using
Maurice Pradella1, Thomas Weikert1, Jonathan I Sperl2
1Department of Radiology, Clinic of Radiology & Nuclear Medicine, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland.
Insights
A new deep learning algorithm accurately measures thoracic aortic dimensions from CT angiography, achieving 87% coherence with radiologists and significantly reducing measurement time.
Area of Science:
- Cardiovascular Imaging
- Artificial Intelligence in Medicine
- Radiology
Background:
- Manual diameter measurements of thoracic aortic dilatation using CT angiography (CTA) are the gold standard but are time-consuming and prone to inter-reader variability.
- Accurate and efficient measurement is crucial for diagnosing thoracic aortic dilatation.
Purpose of the Study:
- To evaluate the accuracy and efficiency of a deep learning (DL) algorithm for measuring thoracic aorta dimensions compared to manual measurements by radiologists.
- To assess the impact of the DL algorithm on measurement time (MT).
Main Methods:
- Retrospective analysis of 405 ECG-gated CTA exams from 371 patients.
- A DL algorithm utilizing deep reinforcement learning for landmark detection and a convolutional neural network for lumen segmentation was employed.
- Measurements were performed according to AHA guidelines, and results were compared to manual centerline measurements by radiologists.
Main Results:
- The DL algorithm achieved 87.0% coherence with radiologist measurements in a clinical setting.
- Mean differences between DL and radiologist measurements were minimal (-0.45±5.52 mm at aortic sinus, -0.02±3.36 mm at ascending aorta).
- Discrepancies, primarily at the aortic root due to tilted measurement planes, were noted, but overall time saved per case was 3:10 minutes.
Conclusions:
- The DL algorithm provides coherent results comparable to radiologists for thoracic aorta measurements, with significant time savings.
- The algorithm assists radiologists in performing AHA-compliant measurements, improving efficiency by approximately 50% per case.
- Further refinement may be needed for measurements at the aortic root to address discrepancies.
Background:
Manually performed diameter measurements on ECG-gated CT-angiography (CTA) represent the gold standard for diagnosis of thoracic aortic dilatation. However, they are time-consuming and show high inter-reader variability. Therefore, we aimed to evaluate the accuracy of measurements of a deep learning-(DL)-algorithm in comparison to those of radiologists and evaluated measurement times (MT).
Methods:
We retrospectively analyzed 405 ECG-gated CTA exams of 371 consecutive patients with suspected aortic dilatation between May 2010 and June 2019. The DL-algorithm prototype detected aortic landmarks (deep reinforcement learning) and segmented the lumen of the thoracic aorta (multi-layer convolutional neural network). It performed measurements according to AHA-guidelines and created visual outputs. Manual measurements were performed by radiologists using centerline technique. Human performance variability (HPV), MT and DL-performance were analyzed in a research setting using a linear mixed model based on 21 randomly selected, repeatedly measured cases. DL-algorithm results were then evaluated in a clinical setting using matched differences. If the differences were within 5 mm for all locations, the cases was regarded as coherent; if there was a discrepancy >5 mm at least at one location (incl. missing values), the case was completely reviewed.
Results:
HPV ranged up to ±3.4 mm in repeated measurements under research conditions. In the clinical setting, 2,778/3,192 (87.0%) of DL-algorithm's measurements were coherent. Mean differences of paired measurements between DL-algorithm and radiologists at aortic sinus and ascending aorta were -0.45±5.52 and -0.02±3.36 mm. Detailed analysis revealed that measurements at the aortic root were over-/underestimated due to a tilted measurement plane. In total, calculated time saved by DL-algorithm was 3:10 minutes/case.
Conclusions:
The DL-algorithm provided coherent results to radiologists at almost 90% of measurement locations, while the majority of discrepent cases were located at the aortic root. In summary, the DL-algorithm assisted radiologists in performing AHA-compliant measurements by saving 50% of time per case.
More Related Videos
06:59Improved Registration of 3D CT Angiography with X-ray Fluoroscopy for Image Fusion During Transcatheter Aortic Valve Implantation
Published on: June 3, 2018
06:57Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection
Published on: September 22, 2023
Related Concept Videos
01:28Imaging Studies for Cardiovascular System V: CT
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT