Key result
Deep learning CT achieves ~82% segmentation accuracy with consistent aortic annulus sizing across measurement methods.
Why the study?
To explore the role of CT angiography information provided by a deep learning algorithm in the diagnosis and complications of congenital aortic valve disease and severe aortic valve stenosis.
Does a deep learning algorithm (TJ-2 fully convolutional network) applied to preoperative CT angiography accurately segment and measure the aortic annulus across different measurement methods in patients evaluated for TAVI?
Observational (n=120)
Blind method by two experienced doctors for image measurement
No
Does a deep learning algorithm (TJ-2 fully convolutional network) applied to preoperative CT angiography accurately segment and measure the aortic annulus across different measurement methods in patients evaluated for TAVI?
Deep learning-assisted CT angiography using a TJ-2 fully convolutional network provides accurate aortic root segmentation (82% accuracy) and reproducible annulus measurements across different geometric methods to aid preoperative TAVI planning.
Answers are grounded in this paper and cite their sources.
Supports deep learning CT angiography for reproducible annulus sizing in TAVI planning; extends segmentation research but leaves open prospective outcome validation.
This work was aimed to explore the role of CT angiography information provided by deep learning algorithm in the diagnosis and complications of the disease focusing on congenital aortic valve disease and severe aortic valve stenosis. 120 patients who underwent ultrasound cardiography for aortic stenosis and underwent transcatheter aortic valve implantation (TAVI) in hospital were selected as the research objects. Patients received CT examination of deep learning algorithm within one week. The measurement methods were long and short diameter method, area method, and perimeter method. The deep learning algorithm was used to measure the long and short diameter, area, and perimeter of the target area before CT image processing. The results showed that the average diameter of long and short diameter measurement was 95% CI (0.84, 0.92), the average diameter of perimeter measurement was 95% CI (0.68, 0.87), and the average diameter of area measurement was 95% CI (0.72, 0.91). Among the 52 patients, 35 cases were hypertension (67%), 13 cases were diabetes (25%), 6 cases were chronic renal insufficiency (Cr > 2 mg/dL) (11%) (2 cases were treated with hemodialysis, 3.8%), 11 patients had chronic pulmonary disease (21%), 9 patients had cerebrovascular disease (17.3%) and atrial flutter and atrial fibrillation. Deep learning can achieve excellent results in CT image processing, and it was of great significance for the diagnosis of TAVI patients, improving the success rate of treatment and the prognosis of patients.
No takes yet. Share an insight, caveat, or question.
Zheng et al. (2021) conducted an observational in Severe aortic valve stenosis and congenital aortic valve disease undergoing preoperative TAVI evaluation (n=120). Deep learning algorithm (TJ-2 fully convolutional network) for preoperative CT angiography image processing vs. Different CT measurement methods (long and short diameter method, perimeter method, and area method) was evaluated on Aortic annulus average diameter measured by three CT methods (long-short diameter, perimeter, and area) (95% CI 0.84-0.92, p=>0.05). Deep learning-based CT angiography achieved 82% segmentation accuracy and showed no significant difference in aortic annulus diameter across three measurement methods.
Synapse has enriched 10 related papers. Consider them for comparative context: