Clinical Publications

Find out more about Avicenna.AI’s Clinical Publications and clinical studies.

Validation of a Deep Learning tool for automatic intracranial hemorrhage detection and classification

Soun J, Quenet S, Chang P, Chow DS.
This study demonstrates that deep learning-based tools may be generalizable despite heterogenous hospital systems and vendors. Limitations of the tool include missing small volume ICH, particularly in the presence of noise, motion, or streak artifacts. Regardless, the validation of this robust tool has implications for widespread clinical use given the different settings from which the cases were obtained. This tool could help radiologists with triage in the acute setting.
Click Here

Validation of a Deep Learning Tool in the Detection of Intracerebral Hemorrhage and Large Vessel Occlusion

McLouth J, Elstrott S, Chaibi Y, Quenet S, Chang P, D Chow DS, Soun J.
Deep learning tools can be effective in the detection of both ICH and LVO across a wide variety of hospital systems. While some limitations were identified, specifically in the detection of small ICH and distal M2 In occlusion, this study highlights a deep learning tool that can assist radiologists in the detection of emergent findings in a variety of practice settings.
Click Here

Validation of a Deep Learning Tool for Automatic Aortic Dissection Detection

McLouth J, Elstrott S, Soun J, Chang P, Chow DS, Di Grandi C, Quenet S, Ayobi A, Chaibi Y.
This deep learning-based tool is generalizable and able to detect AD throughout a variety of hospital systems. Four false positives (FP), including two within aortic aneurysms, suggest that FPs can sometimes be triggered by findings already of interest to the radiologist. While there were five false negatives(FN), these all occurred in Type B dissections, which are often medically managed versus surgical management with Type A dissections. Additionally, these FNs primarily occurred in complicated cases that even prompted disagreement among the radiologists. Regardless, the robustness of this tool has implications for widespread clinical use which could help radiologists with AD triage for ultimately life-saving interventions.
Click Here

Validation of a Deep Learning Tool in the Detection of Intracranial Hemorrhage and Large Vessel Occlusion

McLouth J, Elstrott S, Chaibi Y, Quenet S, Chang P, Chow D, Soun J.
Deep learning tools can be effective in the detection of both ICH and LVO across a wide variety of hospital systems. While some limitations were identified, specifically in the detection of small ICH and distal M2 occlusion, this study highlights a deep learning tool that can assist radiologists in the detection of emergent findings in a variety of practice settings.
Click Here

Assessment of an Artificial Intelligence Algorithm for Detection of Intracranial Hemorrhage

Rava RA, Seymour SE, LaQue ME, Peterson BA
Canon's AUTOStroke Solution ICH detection algorithm was able to accurately detect intraparenchymal, intraventricular, subdural, and subarachnoid hemorrhages in addition to accurately determine when an ICH was not present. Having this automated ICH detection method could drastically improve treatment times for patients with ICH.
Click Here

Artificial Intelligence and Acute Stroke Imaging

Soun JE, Chow DS, Nagamine M, Takhtawala RS, Filippi CG, Yu W, Chang PD
Prompt detection and treatment of acute cerebrovascular disease is critical to reduce morbidity and mortality. The current application of AI in this field has allowed for vast opportunities to improve treatment selection and clinical outcomes by aiding in all parts of the diagnostic and treatment pathway, including detection, triage, and outcome prediction. Future studies validating AI techniques are needed to allow for more widespread use in various practice environments.
Click Here

Validation of an Artificial Intelligence Driven Large Vessel Occlusion Detection Algorithm for Acute Ischemic Stroke Patients

Rava RA, Peterson BA, Seymour SE, Snyder KV, Mokin M, Waqas M, Hoi Y, Davies JM, Levy EI, Siddiqui AH, Ionita CN
Canon’s AUTOStroke Solution LVO application was able to accurately identify ICA and M1 MCA occlusions in addition to nearly perfectly rule-out when an LVO was not present. M2 MCA occlusion detection needs further improvement based on the sensitivity results displayed by the LVO detection algorithm. Furthermore, having an automated method integrated with the onsite CT system provided a rapid stroke solution for comprehensive stroke centers.
Click Here

Partner with us!

We have built innovative technologies that change how AI is used. Partner with us, and let’s improve radiology together.

[zcwp id = 3]