Dice coefficients of the five deep learning models for the segmentation of OCT scan pathology using 5-fold cross-validation.

Dice coefficients of the five deep learning models for the segmentation of OCT scan pathology using 5-fold cross-validation.

<p>Dice coefficients of the five deep learning models for the segmentation of OCT scan pathology using 5-fold cross-validation.</p>

Saved in:

Bibliographic Details
Main Author:	Katherine Du (20448297) (author)
Other Authors:	Utkarsh Doshi (22521858) (author), Benjamin DiCenzo (22521861) (author), Jessica Jiang (8056742) (author), Ethan Wu (22521864) (author), Adarsh Gadari (20448309) (author), Sharat Chandra Vupparaboina (22521867) (author), Elham Sadeghi (14176245) (author), Sandeep Chandra Bollepalli (20448303) (author), José-Alain Sahel (19376) (author), Jay Chhablani (561257) (author), Kiran Kumar Vupparaboina (4919440) (author)
Published:	2025
Subjects:	Medicine Genetics Molecular Biology Neuroscience Physiology Immunology Biological Sciences not elsewhere classified Information Systems not elsewhere classified track retinal disease segment subretinal fluid pigment epithelial detachment help standardize interpretations evaluated using 5 automated report generation study explores using pearson correlation coefficient 81 ± 0 66 ± 0 manually annotated scans typical clinical settings net model remains net model performing 2 </ sup retinal oct scans labeled oct scans benchmarking diffusion models ground truth segmentations ground truth diffusion model clinical settings study demonstrates dice coefficient diffusion models 269 scans 224 scans 114 scans xlink "> vision impairment segmented areas nested u models display major causes limited number key challenge fold cross effective overall downstream analysis deep learning art architectures 11 ).
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Cannot write session to /tmp/vufind_sessions/sess_flgtqfsp20oa93ceq1ujrb8r8a