TY - GEN
T1 - Early Experiences with Crowdsourcing Airway Annotations in Chest CT
AU - Cheplygina, Veronika
AU - Perez-Rovira, Adria
AU - Kuo, Wieying
AU - Tiddens, Harm A.W.M.
AU - Bruijne, M de
PY - 2016
Y1 - 2016
N2 - Measuring airways in chest computed tomography (CT) images is important for characterizing diseases such as cystic fibrosis, yet very time-consuming to perform manually. Machine learning algorithms offer an alternative, but need large sets of annotated data to perform well. We investigate whether crowdsourcing can be used to gather airway annotations which can serve directly for measuring the airways, or as training data for the algorithms. We generate image slices at known locations of airways and request untrained crowd workers to outline the airway lumen and airway wall. Our results show that the workers are able to interpret the images, but that the instructions are too complex, leading to many unusable annotations. After excluding unusable annotations, quantitative results show medium to high correlations with expert measurements of the airways. Based on this positive experience, we describe a number of further research directions and provide insight into the challenges of crowdsourcing in medical images from the perspective of first-time users.
AB - Measuring airways in chest computed tomography (CT) images is important for characterizing diseases such as cystic fibrosis, yet very time-consuming to perform manually. Machine learning algorithms offer an alternative, but need large sets of annotated data to perform well. We investigate whether crowdsourcing can be used to gather airway annotations which can serve directly for measuring the airways, or as training data for the algorithms. We generate image slices at known locations of airways and request untrained crowd workers to outline the airway lumen and airway wall. Our results show that the workers are able to interpret the images, but that the instructions are too complex, leading to many unusable annotations. After excluding unusable annotations, quantitative results show medium to high correlations with expert measurements of the airways. Based on this positive experience, we describe a number of further research directions and provide insight into the challenges of crowdsourcing in medical images from the perspective of first-time users.
U2 - 10.1007/978-3-319-46976-8_22
DO - 10.1007/978-3-319-46976-8_22
M3 - Conference contribution
SN - 978-3-319-46975-1
T3 - Lecture Notes in Computer Science
SP - 209
EP - 2018
BT - Deep Learning and Data Labeling for Medical Applications
A2 - Carneiro, G.
A2 - Mateus, D.
A2 - Peter, L.
A2 - Bradley, A.
A2 - Tavares, J.M.R.S.
A2 - Belagiannis, V.
A2 - Papa, J.P.
A2 - Nascimento, J.C.
A2 - Loog, M.
A2 - Lu, Z.
A2 - Cardoso, J.S.
A2 - Cornebise, J.
PB - Springer
CY - Cham
T2 - First International Workshop, LABELS 2016, and Second International Workshop, DLMIA 2016
Y2 - 21 October 2016 through 21 October 2016
ER -