No abstract

Objectives Treatment and outcomes of acute stroke have been revolutionised by mechanical thrombectomy. Deep learning has shown great promise in diagnostics but applications in video and interventional radiology lag behind. We aimed to develop a model that takes as input digital subtraction angiography (DSA) videos and classifies the video according to (1) the presence of large vessel occlusion (LVO), (2) the location of the occlusion, and (3) the efficacy of reperfusion. Methods All patients who underwent DSA for anterior circulation acute ischaemic stroke between 2012 and 2019 were included. Consecutive normal studies were included to balance classes. An external validation (EV) dataset was collected from another institution. The trained model was also used on DSA videos post mechanical thrombectomy to assess thrombectomy efficacy. Results In total, 1024 videos comprising 287 patients were included (44 for EV). Occlusion identification was achieved with 100% sensitivity and 91.67% specificity (EV 91.30% and 81.82%). Accuracy of location classification was 71% for ICA, 84% for M1, and 78% for M2 occlusions (EV 73, 25, and 50%). For post-thrombectomy DSA (n = 194), the model identified successful reperfusion with 100%, 88%, and 35% for ICA, M1, and M2 occlusion (EV 89, 88, and 60%). The model could also perform classification of post-intervention videos as mTICI < 3 with an AUC of 0.71. Conclusions Our model can successfully identify normal DSA studies from those with LVO and classify thrombectomy outcome and solve a clinical radiology problem with two temporal elements (dynamic video and pre and post intervention). Key Points • DEEP MOVEMENT represents a novel application of a model applied to acute stroke imaging to handle two types of temporal complexity, dynamic video and pre and post intervention. • The model takes as an input digital subtraction angiograms of the anterior cerebral circulation and classifies according to (1) the presence or absence of large vessel occlusion, (2) the location of the occlusion, and (3) the efficacy of thrombectomy. • Potential clinical utility lies in providing decision support via rapid interpretation (pre thrombectomy) and automated objective gradation of thrombectomy outcomes (post thrombectomy).

Removing the antiscatter grid during FPCT imaging of the temporal bones is a simple and effective way to reduce radiation exposure while maintaining diagnostic image quality for the evaluation of SSCD.

No abstract

PURPOSE: To evaluate the impact of craniospinal irradiation (CSI) dose and molecular sub-type on medulloblastoma relapse rates. METHODS: 115 medulloblastoma patients were treated with 18-≥ 36 Gy CSI. Molecular subtyping data was done by nanostring assay [WNT, SHH, and Group 3/4 non-WNT/non-SHH (NWNS)]. A CSI dose schema based on prognostic implications of molecular subtype was devised: ≥36 Gy for M+ or Group 3;≤18 Gy for non-disseminated WNT; 23.4 Gy all others. Relapse rates were assessed and correlated with CSI dose. RESULTS: After excluding patients with incomplete data, the final cohort included 36 subjects with median age 8.7 years (range 3.3 -16.9) and median follow-up 4.1 years (0.2-3.7). Molecular subtypes were as follows: 2-WNT, 6-SHH, 28-NWNS. CSI dose was 18 Gy(11 cases), 23.4 Gy(9), and ≥36 Gy(16). CSI dose was divergent from the proposed schema in 18 cases (14-lower, 4-higher). There were 14 relapses (by molecular subtype: 0-WNT, 1-SHH, 13-NWNS; by histology: 8-classic, 5-LC/A, 1-EN), with median time to relapse 18.5 months (0.43-62). Seven of 14 tumors treated to a lower dose relapsed (1 SHH; 6 NWNS); only 1 (NWNS) of 4 patients with higher divergent dose relapsed. Six of 18 patients treated to similar dose relapsed; all were NWNS, and 4/6 had M3 disease. Eleven of 14 patients who relapsed died. CONCLUSION: Molecular subtyping may help avoid under-treating some NWNS tumors but innovative strategies for metastatic NWNS are needed. We confirm that histological subtypes may hold some predictive value as 5/7 LC/A relapsed and no desmoplastic tumors relapsed. In this small sample, no WNT relapse occurred and only 1 SHH relapsed, suggesting that dose de-escalation can be cautiously explored for these subtypes. Future research directions include applying an MRI imagebased algorithm to subtype the entire cohort, and combining molecular data with other institutions to examine relapse patterns by subtype.