Designed to assist clinicians with non-contrast brain CT scans, this solution aids in identifying up to 130 finding.
Designed to assist clinicians with non-contrast brain CT scans, this solution aids in identifying up to 130 finding
Non-contrast CT (DICOM)
Indication of presence of finding, segmentation overlay, confidence and threshold score/bar
The Annalise Enterprise CTB system achieved high diagnostic accuracy, with a specificity of 93.1% (95% CI, 89.1%–96.6%) for detecting mass effect in thick slices and a sensitivity of 90.0% (95% CI, 84.0%–96.0%) for vasogenic edema in thick slices. Across all measures, the model showed an AUC of at least 0.980, validating its precision in identifying these critical conditions CTB system improved radiologists' performance by increasing their AUC from 0.73 to 0.79 when assisted by the AI, reducing interpretation times by 26.5 seconds on average.
The AI achieved a sensitivity of 96.6% (95% CI, 94.9%–98.2%) and a specificity of 89.8% (95% CI, 84.7%–94.2%) for detecting mass effect in thin-slice images, and a sensitivity of 90.2% (95% CI, 82.0%–96.7%) with a specificity of 93.5% (95% CI, 88.9%–97.2%) for vasogenic edema in thin slices
By reducing the interpretation time by 26.5 seconds per scan and improving diagnostic accuracy, the AI system helps decrease the likelihood of delayed treatments, which can lower overall healthcare costs, especially in emergency settings
Newbury-Chaet, I., Mercaldo, S.F., Chin, J.K., et al. (2024). Evaluation of an Artificial Intelligence Model for Identification of Mass Effect and Vasogenic Edema on CT of the Head. American Journal of Neuroradiology. DOI: 10.3174/ajnr.A8358Buchlak, Q.D., Tang, C.H.M., Seah, J.C.Y., et al. (2024). Effects of a Comprehensive Brain Computed Tomography Deep Learning Model on Radiologist Detection Accuracy. European Radiology, 34, pp. 810-822. DOI: 10.1007/s00330-023-10074-8
