Automated Final Lesion Segmentation in Posterior Circulation Acute Ischemic Stroke Using Deep Learning.

Zoetmulder, Riaan; Konduri, Praneeta R; Obdeijn, Iris V; Gavves, Efstratios; IÅ¡gum, Ivana; Majoie, Charles B L M; Dippel, Diederik W J; Roos, Yvo B W E M; Goyal, Mayank; Mitchell, Peter J; Campbell, Bruce C V; Lopes, Demetrius K; Reimann, Gernot; Jovin, Tudor G; Saver, Jeffrey L; Muir, Keith W; White, Phil; Bracard, Serge; Chen, Bailiang; Brown, Scott; Schonewille, Wouter J; van der Hoeven, Erik; Puetz, Volker; Marquering, Henk A

Final lesion volume (FLV) is a surrogate outcome measure in anterior circulation stroke (ACS). In posterior circulation stroke (PCS), this relation is plausibly understudied due to a lack of methods that automatically quantify FLV. The applicability of deep learning approaches to PCS is limited due to its lower incidence compared to ACS. We evaluated strategies to develop a convolutional neural network (CNN) for PCS lesion segmentation by using image data from both ACS and PCS patients. We included follow-up non-contrast computed tomography scans of 1018 patients with ACS and 107 patients with PCS. To assess whether an ACS lesion segmentation generalizes to PCS, a CNN was trained on ACS data (ACS-CNN). Second, to evaluate the performance of only including PCS patients, a CNN was trained on PCS data. Third, to evaluate the performance when combining the datasets, a CNN was trained on both datasets. Finally, to evaluate the performance of transfer learning, the ACS-CNN was fine-tuned using PCS patients. The transfer learning strategy outperformed the other strategies in volume agreement with an intra-class correlation of 0.88 (95% CI: 0.83-0.92) vs. 0.55 to 0.83 and a lesion detection rate of 87% vs. 41-77 for the other strategies. Hence, transfer learning improved the FLV quantification and detection rate of PCS lesions compared to the other strategies.