Towards clinical translation of deep-learning based classification of DSA image sequences for stroke treatment

Abstract

In the event of stroke, a catheter-guided procedure (thrombectomy) is used to remove blood clots. Feasibility of machine learning based automatic classifications for thrombus detection on digital substraction angiography (DSA) sequences has been demonstrated. It was however not used live in the clinic, yet. We present an open-source tool for automatic thrombus classification and test it on three selected clinical cases regarding functionality and classification runtime. With our trained model all large vessel occlusions in the M1 segment were correctly classified. One small remaining M3 thrombus was not detected. Runtime was in the range from 1 to 10 seconds depending on the used hardware. We conclude that our open-source software tool enables clinical staff to classify DSA sequences in (close to) realtime and can be used for further studies in clinics.