TY - GEN

T1 - cRedAnno+

T2 - 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023

AU - Lu, Jiahao

AU - Yin, Chong

AU - Erleben, Kenny

AU - Nielsen, Michael Bachmann

AU - Darkner, Sune

N1 - Publisher Copyright: © 2023 IEEE.

PY - 2023

Y1 - 2023

N2 - Recently, attempts have been made to reduce annotation requirements in feature-based self-explanatory models for lung nodule diagnosis. As a representative, cRedAnno achieves competitive performance with considerably reduced annotation needs by introducing self-supervised contrastive learning to do unsupervised feature extraction. However, it exhibits unstable performance under scarce annotation conditions. To improve the accuracy and robustness of cRedAnno, we propose an annotation exploitation mechanism by conducting semi-supervised active learning with sparse seeding and training quenching in the learned semantically meaningful reasoning space, to jointly utilise the extracted features, annotations, and unlabelled data. The proposed approach achieves comparable or even higher malignancy prediction accuracy with 10x fewer annotations, meanwhile showing better robustness and nodule attribute prediction accuracy under the condition of 1% annotations. Our complete code is open-source available: https://github.com/diku-dk/credanno.

AB - Recently, attempts have been made to reduce annotation requirements in feature-based self-explanatory models for lung nodule diagnosis. As a representative, cRedAnno achieves competitive performance with considerably reduced annotation needs by introducing self-supervised contrastive learning to do unsupervised feature extraction. However, it exhibits unstable performance under scarce annotation conditions. To improve the accuracy and robustness of cRedAnno, we propose an annotation exploitation mechanism by conducting semi-supervised active learning with sparse seeding and training quenching in the learned semantically meaningful reasoning space, to jointly utilise the extracted features, annotations, and unlabelled data. The proposed approach achieves comparable or even higher malignancy prediction accuracy with 10x fewer annotations, meanwhile showing better robustness and nodule attribute prediction accuracy under the condition of 1% annotations. Our complete code is open-source available: https://github.com/diku-dk/credanno.

KW - Active learning

KW - Explainable AI

KW - Lung nodule diagnosis

KW - Self-explanatory model

KW - Semi-supervised learning

UR - http://www.scopus.com/inward/record.url?scp=85172125707&partnerID=8YFLogxK

U2 - 10.1109/ISBI53787.2023.10230720

DO - 10.1109/ISBI53787.2023.10230720

M3 - Article in proceedings

AN - SCOPUS:85172125707

T3 - Proceedings - International Symposium on Biomedical Imaging

BT - 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023

PB - IEEE Computer Society Press

Y2 - 18 April 2023 through 21 April 2023

ER -