The CINA-CSpine AI software reportedly demonstrated a 90.3 percent sensitivity rate for cervical spine fractures in validation testing on more than 300 non-contrast CT scans.
The CINA-CSpine artificial intelligence (AI) software has garnered 510(k) clearance from the Food and Drug Administration (FDA) for the detection and triage of cervical spine fractures on computed tomography (CT) scans.
Facilitating timely treatment of cervical spine fractures, the CINA-CSpine software provides automated flagging of suspected acute fractures and subsequent alerts to reviewing radiologists, according to Avicenna.AI, the developer of the software.
In validation testing involving over 300 CT scans acquired from 36 scanner models and five different vendors, the company said the CINA-CSpine software demonstrated a 90.3 percent sensitivity rate and a 91.9 percent specificity rate for cervical spine fractures.
"These results demonstrate that our CINA-CSpine algorithm is capable of providing prompt and accurate findings that could positively guide physicians towards better assessments and improved patient outcomes," added Cyril Di Grandi, the co-founder and chief executive officer of Avicenna.ai.
Can AI Enhance CT Detection of Incidental Extrapulmonary Abnormalities and Prediction of Mortality?
September 18th 2024Emphasizing multi-structure segmentation and feature extraction from chest CT scans, an emerging AI model demonstrated an approximately 70 percent AUC for predicting significant incidental extrapulmonary findings as well as two-year and 10-year all-cause mortality.
Can Radiomics Enhance Differentiation of Intracranial Aneurysms on Computed Tomography Angiography?
September 17th 2024Radiomics models offered a pooled AUC of 86 percent for differentiating between ruptured and unruptured intracranial aneurysms, according to a recently published meta-analysis.
Can Radiomics and Autoencoders Enhance Real-Time Ultrasound Detection of Breast Cancer?
September 10th 2024Developed with breast ultrasound data from nearly 1,200 women, a model with mixed radiomic and autoencoder features had a 90 percent AUC for diagnosing breast cancer, according to new research.