TY - JOUR
T1 - GANDALF
T2 - Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification
AU - Mahapatra, Dwarikanath
AU - Bozorgtabar, Behzad
AU - Ge, Zongyuan
AU - Reyes, Mauricio
N1 - Funding Information:
This work was supported by the Swiss National Foundation grant number 212939 , and Innosuisse grant number 31274.1 .
Publisher Copyright:
© 2024 Elsevier B.V.
PY - 2024/4
Y1 - 2024/4
N2 - Informative sample selection in an active learning (AL) setting helps a machine learning system attain optimum performance with minimum labeled samples, thus reducing annotation costs and boosting performance of computer-aided diagnosis systems in the presence of limited labeled data. Another effective technique to enlarge datasets in a small labeled data regime is data augmentation. An intuitive active learning approach thus consists of combining informative sample selection and data augmentation to leverage their respective advantages and improve the performance of AL systems. In this paper, we propose a novel approach called GANDALF (Graph-based TrANsformer and Data Augmentation Active Learning Framework) to combine sample selection and data augmentation in a multi-label setting. Conventional sample selection approaches in AL have mostly focused on the single-label setting where a sample has only one disease label. These approaches do not perform optimally when a sample can have multiple disease labels (e.g., in chest X-ray images). We improve upon state-of-the-art multi-label active learning techniques by representing disease labels as graph nodes and use graph attention transformers (GAT) to learn more effective inter-label relationships. We identify the most informative samples by aggregating GAT representations. Subsequently, we generate transformations of these informative samples by sampling from a learned latent space. From these generated samples, we identify informative samples via a novel multi-label informativeness score, which beyond the state of the art, ensures that (i) generated samples are not redundant with respect to the training data and (ii) make important contributions to the training stage. We apply our method to two public chest X-ray datasets, as well as breast, dermatology, retina and kidney tissue microscopy MedMNIST datasets, and report improved results over state-of-the-art multi-label AL techniques in terms of model performance, learning rates, and robustness.
AB - Informative sample selection in an active learning (AL) setting helps a machine learning system attain optimum performance with minimum labeled samples, thus reducing annotation costs and boosting performance of computer-aided diagnosis systems in the presence of limited labeled data. Another effective technique to enlarge datasets in a small labeled data regime is data augmentation. An intuitive active learning approach thus consists of combining informative sample selection and data augmentation to leverage their respective advantages and improve the performance of AL systems. In this paper, we propose a novel approach called GANDALF (Graph-based TrANsformer and Data Augmentation Active Learning Framework) to combine sample selection and data augmentation in a multi-label setting. Conventional sample selection approaches in AL have mostly focused on the single-label setting where a sample has only one disease label. These approaches do not perform optimally when a sample can have multiple disease labels (e.g., in chest X-ray images). We improve upon state-of-the-art multi-label active learning techniques by representing disease labels as graph nodes and use graph attention transformers (GAT) to learn more effective inter-label relationships. We identify the most informative samples by aggregating GAT representations. Subsequently, we generate transformations of these informative samples by sampling from a learned latent space. From these generated samples, we identify informative samples via a novel multi-label informativeness score, which beyond the state of the art, ensures that (i) generated samples are not redundant with respect to the training data and (ii) make important contributions to the training stage. We apply our method to two public chest X-ray datasets, as well as breast, dermatology, retina and kidney tissue microscopy MedMNIST datasets, and report improved results over state-of-the-art multi-label AL techniques in terms of model performance, learning rates, and robustness.
KW - Active learning
KW - Data augmentation
KW - Informative samples
KW - Multi-label
UR - http://www.scopus.com/inward/record.url?scp=85182876131&partnerID=8YFLogxK
U2 - 10.1016/j.media.2023.103075
DO - 10.1016/j.media.2023.103075
M3 - Article
C2 - 38199069
AN - SCOPUS:85182876131
SN - 1361-8423
VL - 93
JO - Medical Image Analysis
JF - Medical Image Analysis
M1 - 103075
ER -