Critical Abnormality Detection-VeriScout

Fully automatic brain CT emergency abnormality detection

Based on computer vision and deep learning technology, VeriScout^TM provides fully automatic real-time detection and triaging of cerebral haemorrhage cases. Veriscout™ has been approved by the TGA as a Class IIb medical device

Trained on nearly 40,000 clinical cases, VeriScout^TM uses artificial intelligence technology to efficiently detect brain haemorrhage in non-contrast head CT images in real time. The software thereby identifies patients with potentially critical abnormalities and triages these cases for priority reporting by radiologists. Heatmap ‘preview’ images provide radiologists with immediate insight into the decision reasoning of Veriscout’s underlying AI architecture. Veriscout’s performance for the detection of a variety of cerebral haemorrhage types has been validated by comparison with standard clinical review by expert radiologists, achieving a sensitivity of 93.17% and a specificity of 96.86%.  VeriScout^TM seamlessly integrates into existing PACS/RIS workflows with SNAC’s dedicated Torana Medical Imaging Gateway, ensuring no additional clinician burden.

For more information on Veriscout™ clinical validation, please see publications below:

Wang D, Wang C, Masters L, Barnett M. Masked multi-task network for case-level intracranial hemorrhage classification in brain ct volumes. InInternational Conference on Medical Image Computing and Computer-Assisted Intervention 2020 Sep 29 (pp. 145-154). Cham: Springer International Publishing.

Wang D, Jin R, Shieh CC, Ng AY, Pham H, Dugal T, Barnett M, Winoto L, Wang C, Barnett Y. Real world validation of an AI-based CT hemorrhage detection tool. Frontiers in Neurology.