Zero-shot learning for automated segmentation of true and false lumen in type-B aortic dissection from CT angiography images

Congress:

ECR 2024

Poster Number:

C-14868

Type:

Scientific Exhibit

Keywords:

Artificial Intelligence, Cardiovascular system, CT, CT-Angiography, Segmentation, Dissection

Authors:

A. Manohar, D. Profit, B. Sandoval Valle, D. Mastrodicasa, G. Mistelbauer, K. Nieman, D. Fleischmann

DOI:

10.26044/ecr2024/C-14868

DOI-Link:

https://dx.doi.org/10.26044/ecr2024/C-14868

References

[1] C. A. Nienaber et al., “Aortic dissection,” Nat Rev Dis Primers, vol. 2, no. 1, Art. no. 1, Jul. 2016.

[2] I. A. Khan and C. K. Nair, “Clinical, Diagnostic, and Management Perspectives of Aortic Dissection,” Chest, vol. 122, no. 1, pp. 311–328, Jul. 2002.

[3] Y.-L. Qin, G. Deng, T.-X. Li, W. Wang, and G.-J. Teng, “Treatment of Acute Type-B Aortic Dissection: Thoracic Endovascular Aortic Repair or Medical Management Alone?,” JACC: Cardiovascular Interventions, vol. 6, no. 2, pp. 185–191, Feb. 2013.

[4] A. M. Sailer et al., “Computed Tomography Imaging Features in Acute Uncomplicated Stanford Type-B Aortic Dissection Predict Late Adverse Events,” Circulation: Cardiovascular Imaging, vol. 10, no. 4, p. e005709, Apr. 2017.

[5] L. D. Wobben et al., “Deep Learning-Based 3D Segmentation of True Lumen, False Lumen, and False Lumen Thrombosis in Type-B Aortic Dissection,” in 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Nov. 2021, pp. 3912–3915.

[6] L. D. Hahn et al., “CT-based True- and False-Lumen Segmentation in Type B Aortic Dissection Using Machine Learning,” Radiology: Cardiothoracic Imaging, vol. 2, no. 3, p. e190179, Jun. 2020.

[7] A. Kirillov et al., “Segment Anything.” arXiv, Apr. 05, 2023.

Fig 1: Overview of the segmentation procedure using Meta AI's Segment Anything Model...

Fig 2: Correlation between manual and Segment Anything Model (SAM) derived volume...