cRedAnno+: Annotation Exploitation In Self-Explanatory Lung Nodule Diagnosis
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
cRedAnno+ : Annotation Exploitation In Self-Explanatory Lung Nodule Diagnosis. / Lu, Jiahao; Yin, Chong; Erleben, Kenny; Nielsen, Michael Bachmann; Darkner, Sune.
2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023. IEEE Computer Society Press, 2023. (Proceedings - International Symposium on Biomedical Imaging, Vol. 2023-April).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
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 -
ID: 369560241