Publications by authors named "J K Udupa"
Background: Increased epicardial adipose tissue (EAT) has adverse effects in cardiovascular diseases, independent of BMI. Estrogen levels may affect EAT accumulation. Little is known about the predictors and potential impact of EAT in pulmonary arterial hypertension (PAH).
View Article and Find Full Text PDFArticle Synopsis
- The study focuses on using dynamic magnetic resonance imaging (dMRI) to analyze diaphragm motion in patients with thoracic insufficiency syndrome (TIS), providing insights into the severity of respiratory disorders without exposing patients to radiation.
- The paper outlines a three-step approach to segment the left and right hemi-diaphragm from dMRI images, overcoming challenges like low resolution and motion blur by employing advanced deep learning techniques for accurate recognition and delineation.
- Results showed a mean-Hausdorff distance of approximately 3 mm for diaphragm delineation and a positional error of about 3 mm in identifying the mid-sagittal plane, validated using 100 test images of TIS patients.
Purpose: Vision Transformers recently achieved a competitive performance compared with CNNs due to their excellent capability of learning global representation. However, there are two major challenges when applying them to 3D image segmentation: i) Because of the large size of 3D medical images, comprehensive global information is hard to capture due to the enormous computational costs. ii) Insufficient local inductive bias in Transformers affects the ability to segment detailed features such as ambiguous and subtly defined boundaries.
View Article and Find Full Text PDFArticle Synopsis
- The study aimed to evaluate a new MRI technique to assess lung aeration in children, especially focusing on those with thoracic insufficiency syndrome (TIS).
- Researchers used standardized signal intensity (sSI) measurements from MRI scans of both healthy children and TIS patients to determine lung function pre- and post-surgery.
- Results indicated that the MRI method can detect lung aeration changes, showing a general decrease in lung sSI after surgery, although the changes were not statistically significant.
Anatomic attention regions via optimal anatomy modeling and recognition for DL-based image segmentation.
Proc SPIE Int Soc Opt Eng
February 2024
Organ segmentation is a crucial task in various medical imaging applications. Many deep learning models have been developed to do this, but they are slow and require a lot of computational resources. To solve this problem, attention mechanisms are used which can locate important objects of interest within medical images, allowing the model to segment them accurately even when there is noise or artifact.
View Article and Find Full Text PDF