TY - JOUR
T1 - Automated Peak Prominence-Based Iterative Dijkstra's Algorithm for Segmentation of B-Mode Echocardiograms
AU - Brindise, Melissa C.
AU - Meyers, Brett A.
AU - Kutty, Shelby
AU - Vlachos, Pavlos P.
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022/5/1
Y1 - 2022/5/1
N2 - We present a user-initialized, automated left ventricle (LV) segmentation method for use with echocardiograms (echo). The method uses an iterative Dijkstra's algorithm, strategic node selection, and novel cost matrix formulation based on intensity peak prominence and is termed the 'Prominence Iterative Dijkstra's' algorithm, or ProID. ProID is initialized with three user-input clicks per time-series scan. ProID was tested using artificial echos representing five different systems. Results showed accurate LV contours and volume estimations as compared to the ground-truth for all systems. Using the CAMUS dataset, we demonstrate ProID maintained similar Dice similarity scores (DSS) to other automated methods. ProID was then used to analyze a clinical cohort of 66 pediatric patients, including normal and diseased hearts. Output segmentations, LV volume, and ejection fraction were compared against manual segmentations from two expert readers. ProID maintained an average DSS of 0.93 when comparing against manual segmentation. Comparing the two expert readers, the manual segmentations maintained a DSS of 0.93 which increased to 0.95 when they used ProID. Thus, ProID reduced inter-operator variability across the expert readers. Overall, this work demonstrates ProID yields accurate boundaries across age groups, disease states, and echo platforms with low computational cost and no need for training data.
AB - We present a user-initialized, automated left ventricle (LV) segmentation method for use with echocardiograms (echo). The method uses an iterative Dijkstra's algorithm, strategic node selection, and novel cost matrix formulation based on intensity peak prominence and is termed the 'Prominence Iterative Dijkstra's' algorithm, or ProID. ProID is initialized with three user-input clicks per time-series scan. ProID was tested using artificial echos representing five different systems. Results showed accurate LV contours and volume estimations as compared to the ground-truth for all systems. Using the CAMUS dataset, we demonstrate ProID maintained similar Dice similarity scores (DSS) to other automated methods. ProID was then used to analyze a clinical cohort of 66 pediatric patients, including normal and diseased hearts. Output segmentations, LV volume, and ejection fraction were compared against manual segmentations from two expert readers. ProID maintained an average DSS of 0.93 when comparing against manual segmentation. Comparing the two expert readers, the manual segmentations maintained a DSS of 0.93 which increased to 0.95 when they used ProID. Thus, ProID reduced inter-operator variability across the expert readers. Overall, this work demonstrates ProID yields accurate boundaries across age groups, disease states, and echo platforms with low computational cost and no need for training data.
UR - http://www.scopus.com/inward/record.url?scp=85118553424&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85118553424&partnerID=8YFLogxK
U2 - 10.1109/TBME.2021.3123612
DO - 10.1109/TBME.2021.3123612
M3 - Article
C2 - 34714729
AN - SCOPUS:85118553424
SN - 0018-9294
VL - 69
SP - 1595
EP - 1607
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
IS - 5
ER -