Third Ventricle Width Measurements Based on YOLO and Localized Intensity Features
Transcranial ultrasound (TCS) imaging can quantitatively measure third ventricle width (TVW) in Parkinson’s (PD) patients, helping physicians detect cognitive dysfunction in PD patients as early as possible. However, the transmitted unified TVW measurement has problems such as low efficie...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10623320/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Transcranial ultrasound (TCS) imaging can quantitatively measure third ventricle width (TVW) in Parkinson’s (PD) patients, helping physicians detect cognitive dysfunction in PD patients as early as possible. However, the transmitted unified TVW measurement has problems such as low efficiency and unstable measurement. For this reason, this paper proposes an automatic TVW measurement for TCS images. Firstly, to solve the problem of third ventricle detection in the complex background of TCS images, the YOLO-TV improvement model is proposed to improve the detection accuracy. The YOLO-TV model introduces a multi-head attention mechanism in the feature extraction network to enhance the network to extract feature at different scales. Meanwhile, a depth separable path aggregation module is used to improve the channel sensitivity of the feature fusion. Secondly, to solve the problem of third ventricle segmentation measurement, a third ventricle segmentation algorithm based on local intensity features is proposed, which realizes automatic segmentation measurement of third ventricle by calculating the local intensity features of the region and localization of the multi-angle projection method. The detection accuracy of the YOLO-TV model in the validation set reaches 98.50%, and the average measurement deviation between the automatic measurement results of the method proposed in this paper and the manual measurement results of the doctors is 0.089 mm, and the correlation coefficient between the two is 0.9643, which indicates that the method can be used to accurately measure the width of third ventricle. |
|---|---|
| ISSN: | 2169-3536 |