Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Document Type
- Journal article (2)
Language
- English (2)
Keywords
- CT angiography (1)
- aneurysmal subarachnoid hemorrhage (1)
- aneurysms (1)
- convolutional neural networks (1)
- deep learning (1)
- detector (1)
- peptide sensors (1)
- peri-implant disease (1)
- sensory chewing gums (1)
- tongue (1)
Institute
EU-Project number / Contract (GA) number
- 314911 (1)
Our ability of screening broad communities for clinically asymptomatic diseases critically drives population health. Sensory chewing gums are presented targeting the tongue as 24/7 detector allowing diagnosis by “anyone, anywhere, anytime”. The chewing gum contains peptide sensors consisting of a protease cleavable linker in between a bitter substance and a microparticle. Matrix metalloproteinases in the oral cavity, as upregulated in peri-implant disease, specifically target the protease cleavable linker while chewing the gum, thereby generating bitterness for detection by the tongue. The peptide sensors prove significant success in discriminating saliva collected from patients with peri-implant disease versus clinically asymptomatic volunteers. Superior outcome is demonstrated over commercially available protease-based tests in saliva. “Anyone, anywhere, anytime” diagnostics are within reach for oral inflammation. Expanding this platform technology to other diseases in the future features this diagnostic as a massive screening tool potentially maximizing impact on population health.
Purpose
To evaluate whether a deep learning model (DLM) could increase the detection sensitivity of radiologists for intracranial aneurysms on CT angiography (CTA) in aneurysmal subarachnoid hemorrhage (aSAH).
Methods
Three different DLMs were trained on CTA datasets of 68 aSAH patients with 79 aneurysms with their outputs being combined applying ensemble learning (DLM-Ens). The DLM-Ens was evaluated on an independent test set of 104 aSAH patients with 126 aneuryms (mean volume 129.2 ± 185.4 mm3, 13.0% at the posterior circulation), which were determined by two radiologists and one neurosurgeon in consensus using CTA and digital subtraction angiography scans. CTA scans of the test set were then presented to three blinded radiologists (reader 1: 13, reader 2: 4, and reader 3: 3 years of experience in diagnostic neuroradiology), who assessed them individually for aneurysms. Detection sensitivities for aneurysms of the readers with and without the assistance of the DLM were compared.
Results
In the test set, the detection sensitivity of the DLM-Ens (85.7%) was comparable to the radiologists (reader 1: 91.2%, reader 2: 86.5%, and reader 3: 86.5%; Fleiss κ of 0.502). DLM-assistance significantly increased the detection sensitivity (reader 1: 97.6%, reader 2: 97.6%,and reader 3: 96.0%; overall P=.024; Fleiss κ of 0.878), especially for secondary aneurysms (88.2% of the additional aneurysms provided by the DLM).
Conclusion
Deep learning significantly improved the detection sensitivity of radiologists for aneurysms in aSAH, especially for secondary aneurysms. It therefore represents a valuable adjunct for physicians to establish an accurate diagnosis in order to optimize patient treatment.