Simultaneous reconstruction of multiple stiff wires from a single X-ray projection for endovascular aortic repair

Deep Learning-Based Intraoperative Stent Graft Segmentation on Completion Digital Subtraction Angiography During Endovascular Aneurysm Repair

PURPOSE

Modern endovascular hybrid operating rooms generate large amounts of medical images during a procedure, which are currently mostly assessed by eye. In this paper, we present fully automatic segmentation of the stent graft on the completion digital subtraction angiography during endovascular aneurysm repair, utilizing a deep learning network.

TECHNIQUE

Completion digital subtraction angiographies (cDSAs) of 47 patients treated for an infrarenal aortic aneurysm using EVAR were collected retrospectively. A two-dimensional convolutional neural network (CNN) with a U-Net architecture was trained for segmentation of the stent graft from the completion angiographies. The cross-validation resulted in an average Dice similarity score of 0.957 ± 0.041 and median of 0.968 (IQR: 0.950 - 0.976). The mean and median of the average surface distance are 1.266 ± 1.506 mm and 0.870 mm (IQR: 0.490 - 1.430), respectively.

CONCLUSION

We developed a fully automatic stent graft segmentation method based on the completion digital subtraction angiography during EVAR, utilizing a deep learning network. This can provide the platform for the development of intraoperative analytical applications in the endovascular hybrid operating room such as stent graft deployment accuracy, endoleak visualization, and image fusion correction.

Automated image fusion during endovascular aneurysm repair: a feasibility and accuracy study

PURPOSE

Image fusion merges preoperative computed tomography angiography (CTA) with live fluoroscopy during endovascular procedures to function as an overlay 3D roadmap. However, in most current systems, the registration between imaging modalities is performed manually by vertebral column matching which can be subjective, inaccurate and time consuming depending on experience. Our objective was to evaluate feasibility and accuracy of image-based automated 2D-3D image fusion between preoperative CTA and intraoperative fluoroscopy based on vertebral column matching.

METHODS

A single-center study with offline procedure data was conducted in 10 consecutive patients which had endovascular aortic repair in which we evaluated unreleased automated fusion software provided by Philips (Best, the Netherlands). Fluoroscopy and digital subtraction angiography images were collected after the procedures and the vertebral column was fused fully automatically. Primary endpoints were feasibility and accuracy of bone alignment (mm). Secondary endpoint was vascular alignment (mm) between the lowest renal artery orifices. Clinical non-inferiority was defined at a mismatch of < 1 mm.

RESULTS

In total, 87 automated measurements and 40 manual measurements were performed on vertebrae T12-L5 in all 10 patients. Manual correction was needed in 3 of the 10 patients due to incomplete visibility of the vertebral edges in the fluoroscopy image. Median difference between automated fusion and manual fusion was 0.1 mm for bone alignment (p = 0.94). The vascular alignment was 4.9 mm (0.7-17.5 mm) for manual and 5.5 mm (1.0-14.0 mm) for automated fusion. This did not improve, due to the presence of stiff wires and stent graft.

CONCLUSION

Automated image fusion was feasible when all vertebral edges were visible. Accuracy was non-inferior to manual image fusion regarding bone alignment. Future developments should focus on intraoperative image-based correction of vascular alignment.

A State-of-the-Art Review of Intra-Operative Imaging Modalities Used to Quality Assure Endovascular Aneurysm Repair

Endovascular aortic aneurysm repair (EVAR) is the preferred method for elective abdominal aortic aneurysm (AAA) repair. However, the success of this technique depends greatly on the technologies available. Intra-operative imaging is essential but can come with limitations. More complex interventions lead to longer operating times, fluoroscopy times, and greater contrast doses. A number of intra-operative imaging modalities to quality assure the success of EVAR have been developed. A systematic literature search was performed with separate searches conducted for each imaging modality in the study: computed tomography (CT), digital subtraction angiography (DSA), fusion, ultrasound, intra-operative positioning system (IOPS), and non-contrast imaging. CT was effective at detecting complications but commonly resulted in increased radiation and contrast dose. The effectiveness of DSA can be increased, and radiation exposure reduced, through the use of adjunctive technologies. We found that 2D-3D fusion was non-inferior to 3D-3D and led to reduced radiation and contrast dose. Non-contrast imaging occasionally led to higher doses of radiation. Ultrasound was particularly effective in the detection of type II endoleaks with reduced radiation and contrast use but was often operator dependent. Unfortunately, no papers made it past full text screening for IOPS. All of the imaging techniques discussed have advantages and disadvantages, and clinical context is relevant to guide imaging choice. Fusion and ultrasound in particular show promise for the future.