.png){kind=icon}
.png){kind=icon}
Return
DeepCilia: Automated, deep-learning based engine for precise ciliary beat frequency estimation
.png){kind=icon}
OA
AI
DOI：10.1016/j.bspc.2023.105808.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Technology advancements over recent decades have greatly impacted medical treatments and diagnostic methods. These advancements could be useful in nasal cytology, which is becoming increasingly critical in diagnosing nasal conditions. In this study we propose DeepCilia, a Ciliary beating frequency (CBF) decay estimation engine that autonomously detects ciliated strias using YOLOv8 to perform the detection task and is able to produce accurate estimations even for low FPS videos, by using the Short-Time Fourier Transform (STFT). DeepCilia achieves very good results with an average computation time below 2 s for each video in the dataset, and an RMSE of less than 1.5 Hz. These achievements make DeepCilia an ideal tool in the field of ciliary motility analysis to estimate the time of death in the context of forensics medicine.
Keywords:
Signal processing
Nasal cytology
CBF estimation
Object detection
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.9
Papers:
9.8K
Citations:
2.4W