This thesis investigates the use of Convolutional Neural Networks (CNNs) toperform semantic segmentation of feet during endovascular surgery in patientswith Critical Limb Threatening Ischemia (CLTI). It is currently being investigatedwhether objective assessment of perfusion can aid surgeons during endovascularsurgery. By segmenting feet, it is possible to perform automatic analysis of perfusion data which could give information about the impact of the surgery in specificRegions of Interest (ROIs). The CNN was developed in Python with a U-net architecture which has shownto be state of the art when it comes to medical image segmentation. An imageset containing approximately 78 000 images of feet and their ground truth segmentation was manually created from 11 videos taken during surgery, and onevideo taken on three healthy test subjects. All videos were captured with a MultiExposure Laser Speckle Contrast Imaging (MELSCI) camera developed by Hultman et al. [1]. The best performing CNN was an ensemble model consisting of10 sub-models, each trained with different sets of training data. An ROI tracking algorithm was developed based on the Unet output, by takingadvantage of the simplicity of edge detection in binary images. The algorithmconverts images into point clouds and calculates a transformation between twopoint clouds with the use of the Iterative Closest Point (ICP) algorithm. The resultis a system that perform automatic tracking of manually selected ROIs whichenables continuous measurement of perfusion in the ROIs during endovascularsurgery.

Purpose: To evaluate the use of the GoBack-catheter (Upstream Peripheral Technologies) in complex revascularizations in lower limb arteries. Materials and Methods: In this retrospective single-center study, the results of the first 100 consecutive patients including 101 limb-revascularizations, performed between May 2018 and July 2020 with the study device, were analyzed. In all cases, guidewire-crossing failed, and all lesions were chronic total occlusions (CTO), either de novo, reocclusions, or in-stent reocclusions. Successful crossing was defined as passing the CTO using the study device. Patency at discharge and after 30 days was defined as less than 50% restenosis on duplex sonography, without target lesion revascularization. Results: Median lesion length was 24 cm and 38 patients (37.6%) had a calcium grading according to the peripheral arterial calcium scoring system (PACSS) of 4 or 5. In 20.8% of patients, an occluded stent was treated. CTOs involved the femoropopliteal segment in 91.1%, iliac arteries in 5.9%, and tibial arteries in 7.9%. The GoBackcatheter was employed for entering into or crossing through parts or the full length of a CTO or an occluded stent as well as for re-entering into the true lumen after subintimal crossing. The device was used via contralateral and ipsilateral antegrade as well as retrograde access with an overall technical success rate of 92.1%. In 3 patients minor bleeding occurred at the crossing or re-entry site, which were managed conservatively. Thirty-day adverse limb events comprised minor amputations in 4 patients (4.0%), 1 major amputation (1.0%), and reocclusions in 7 limbs (6.9%). Conclusion: The new GoBack-catheter offers versatile endovascular applicability for complex CTO recanalization in a broad range of peripheral vascular interventions with a high technical success and low complication rate.