TY - JOUR
T1 - Multi-stage domain-specific pretraining for improved detection and localization of Barrett's neoplasia: A comprehensive clinically validated study
AU - van der Putten, Joost
AU - de Groof, Jeroen
AU - Struyvenberg, Maarten
AU - Boers, Tim
AU - Fockens, Kiki
AU - Curvers, Wouter
AU - Schoon, Erik
AU - Bergman, Jacques
AU - van der Sommen, Fons
AU - de With, Peter H. N.
PY - 2020/7/1
Y1 - 2020/7/1
N2 - Patients suffering from Barrett's Esophagus (BE) are at an increased risk of developing esophageal adenocarcinoma and early detection is crucial for a good prognosis. To aid the endoscopists with the early detection for this preliminary stage of esophageal cancer, this work concentrates on the development and extensive evaluation of a state-of-the-art computer-aided classification and localization algorithm for dysplastic lesions in BE. To this end, we have employed a large-scale endoscopic data set, consisting of 494,355 images, in combination with a novel semi-supervised learning algorithm to pretrain several instances of the proposed neural network architecture. Next, several Barrett-specific data sets that are increasingly closer to the target domain with significantly more data compared to other related work, were used in a multi-stage transfer learning strategy. Additionally, the algorithm was evaluated on two prospectively gathered external test sets and compared against 53 medical professionals. Finally, the model was also evaluated in a live setting without interfering with the current biopsy protocol. Results from the performed experiments show that the proposed model improves on the state-of-the-art on all measured metrics. More specifically, compared to the best performing state-of-the-art model, the specificity is improved by more than 20% points while simultaneously preserving high sensitivity and reducing the false positive rate substantially. Our algorithm yields similar scores on the localization metrics, where the intersection of all experts is correctly indicated in approximately 92% of the cases. Furthermore, the live pilot study shows great performance in a clinical setting with a patient level accuracy, sensitivity, and specificity of 90%. Finally, the proposed algorithm outperforms each individual medical expert by at least 5% and the average assessor by more than 10% over all assessor groups with respect to accuracy.
AB - Patients suffering from Barrett's Esophagus (BE) are at an increased risk of developing esophageal adenocarcinoma and early detection is crucial for a good prognosis. To aid the endoscopists with the early detection for this preliminary stage of esophageal cancer, this work concentrates on the development and extensive evaluation of a state-of-the-art computer-aided classification and localization algorithm for dysplastic lesions in BE. To this end, we have employed a large-scale endoscopic data set, consisting of 494,355 images, in combination with a novel semi-supervised learning algorithm to pretrain several instances of the proposed neural network architecture. Next, several Barrett-specific data sets that are increasingly closer to the target domain with significantly more data compared to other related work, were used in a multi-stage transfer learning strategy. Additionally, the algorithm was evaluated on two prospectively gathered external test sets and compared against 53 medical professionals. Finally, the model was also evaluated in a live setting without interfering with the current biopsy protocol. Results from the performed experiments show that the proposed model improves on the state-of-the-art on all measured metrics. More specifically, compared to the best performing state-of-the-art model, the specificity is improved by more than 20% points while simultaneously preserving high sensitivity and reducing the false positive rate substantially. Our algorithm yields similar scores on the localization metrics, where the intersection of all experts is correctly indicated in approximately 92% of the cases. Furthermore, the live pilot study shows great performance in a clinical setting with a patient level accuracy, sensitivity, and specificity of 90%. Finally, the proposed algorithm outperforms each individual medical expert by at least 5% and the average assessor by more than 10% over all assessor groups with respect to accuracy.
KW - Barrett's Esophagus
KW - Clinical validation
KW - Computer-aided detection
KW - Deep learning
UR - http://www.scopus.com/inward/record.url?scp=85086821562&partnerID=8YFLogxK
U2 - https://doi.org/10.1016/j.artmed.2020.101914
DO - https://doi.org/10.1016/j.artmed.2020.101914
M3 - Article
C2 - 32828453
SN - 0933-3657
VL - 107
JO - Artificial Intelligence in Medicine
JF - Artificial Intelligence in Medicine
M1 - 101914
ER -