TY - JOUR
T1 - Ensemble of deep convolutional neural networks for classification of Early Barrett's Neoplasia Using Volumetric laser endomicroscopy
AU - Fonollà, Roger
AU - Scheeve, Thom
AU - Struyvenberg, Maarten R.
AU - Curvers, Wouter L.
AU - de Groof, Albert J.
AU - van der Sommen, Fons
AU - Schoon, Erik J.
AU - Bergman, Jacques J. G. H. M.
AU - de With, Peter H. N.
PY - 2019
Y1 - 2019
N2 - Barrett's esopaghagus (BE) is a known precursor of esophageal adenocarcinoma (EAC). Patients with BE undergo regular surveillance to early detect stages of EAC. Volumetric laser endomicroscopy (VLE) is a novel technology incorporating a second-generation form of optical coherence tomography and is capable of imaging the inner tissue layers of the esophagus over a 6 cm length scan. However, interpretation of full VLE scans is still a challenge for human observers. In this work, we train an ensemble of deep convolutional neural networks to detect neoplasia in 45 BE patients, using a dataset of images acquired with VLE in a multi-center study. We achieve an area under the receiver operating characteristic curve (AUC) of 0.96 on the unseen test dataset and we compare our results with previous work done with VLE analysis, where only AUC of 0.90 was achieved via cross-validation on 18 BE patients. Our method for detecting neoplasia in BE patients facilitates future advances on patient treatment and provides clinicians with new assisting solutions to process and better understand VLE data.
AB - Barrett's esopaghagus (BE) is a known precursor of esophageal adenocarcinoma (EAC). Patients with BE undergo regular surveillance to early detect stages of EAC. Volumetric laser endomicroscopy (VLE) is a novel technology incorporating a second-generation form of optical coherence tomography and is capable of imaging the inner tissue layers of the esophagus over a 6 cm length scan. However, interpretation of full VLE scans is still a challenge for human observers. In this work, we train an ensemble of deep convolutional neural networks to detect neoplasia in 45 BE patients, using a dataset of images acquired with VLE in a multi-center study. We achieve an area under the receiver operating characteristic curve (AUC) of 0.96 on the unseen test dataset and we compare our results with previous work done with VLE analysis, where only AUC of 0.90 was achieved via cross-validation on 18 BE patients. Our method for detecting neoplasia in BE patients facilitates future advances on patient treatment and provides clinicians with new assisting solutions to process and better understand VLE data.
KW - Barrett's esophagus
KW - Classification
KW - Deep learning
KW - Esophageal adenocarcinoma
KW - Glands
KW - Machine learning
KW - Optical coherence tomography
KW - Volumetric laser endomicroscopy
UR - http://www.scopus.com/inward/record.url?scp=85067258319&partnerID=8YFLogxK
U2 - https://doi.org/10.3390/app9112183
DO - https://doi.org/10.3390/app9112183
M3 - Article
SN - 2076-3417
VL - 9
JO - Applied Sciences (Switzerland)
JF - Applied Sciences (Switzerland)
IS - 11
M1 - 2183
ER -