Deep Learning from Label Proportions for Emphysema Quantification

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedings

We propose an end-to-end deep learning method that learns to estimate emphysema extent from proportions of the diseased tissue. These proportions were visually estimated by experts using a standard grading system, in which grades correspond to intervals (label example: 1–5% of diseased tissue). The proposed architecture encodes the knowledge that the labels represent a volumetric proportion. A custom loss is designed to learn with intervals. Thus, during training, our network learns to segment the diseased tissue such that its proportions fit the ground truth intervals. Our architecture and loss combined improve the performance substantially (8% ICC) compared to a more conventional regression network. We outperform traditional lung densitometry and two recently published methods for emphysema quantification by a large margin (at least 7% AUC and 15% ICC), and achieve near-human-level performance. Moreover, our method generates emphysema segmentations that predict the spatial distribution of emphysema at human level.

OriginalsprogEngelsk
TitelMedical Image Computing and Computer Assisted Intervention – MICCAI 2018 : 21st International Conference, 2018, Proceedings Part II
RedaktørerAlejandro F. Frangi, Julia A. Schnabel, Christos Davatzikos, Carlos Alberola-López, Gabor Fichtinger
ForlagSpringer
Publikationsdato2018
Sider768-776
ISBN (Trykt)9783030009335
DOI
StatusUdgivet - 2018
Begivenhed21st International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2018 - Granada, Spanien
Varighed: 16 sep. 201820 sep. 2018

Konference

Konference21st International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2018
LandSpanien
ByGranada
Periode16/09/201820/09/2018
NavnLecture notes in computer science
Vol/bind11071
ISSN0302-9743

ID: 203944440