TY - JOUR
T1 - Probing perfection
T2 - The relentless art of meddling for pulmonary airway segmentation from HRCT via a human-AI collaboration based active learning method
AU - Wang, Shiyi
AU - Nan, Yang
AU - Zhang, Sheng
AU - Felder, Federico
AU - Xing, Xiaodan
AU - Fang, Yingying
AU - Del Ser, Javier
AU - Walsh, Simon L.F.
AU - Yang, Guang
N1 - Publisher Copyright:
© 2024 The Authors
PY - 2024/8
Y1 - 2024/8
N2 - In the realm of pulmonary tracheal segmentation, the scarcity of annotated data stands as a prevalent pain point in most medical segmentation endeavors. Concurrently, most Deep Learning (DL) methodologies employed in this domain invariably grapple with other dual challenges: the inherent opacity of ‘black box’ models and the ongoing pursuit of performance enhancement. In response to these intertwined challenges, the core concept of our Human-Computer Interaction (HCI) based learning models (RS_UNet, LC_UNet, UUNet and WD_UNet) hinge on the versatile combination of diverse query strategies and an array of deep learning models. We train four HCI models based on the initial training dataset and sequentially repeat the following steps 1–4: (1) Query Strategy: Our proposed HCI models selects those samples which contribute the most additional representative information when labeled in each iteration of the query strategy (showing the names and sequence numbers of the samples to be annotated). Additionally, in this phase, the model selects the unlabeled samples with the greatest predictive disparity by calculating the Wasserstein Distance, Least Confidence, Entropy Sampling, and Random Sampling. (2) Central line correction: The selected samples in previous stage are then used for domain expert correction of the system-generated tracheal central lines in each training round. (3) Update training dataset: When domain experts are involved in each epoch of the DL model's training iterations, they update the training dataset with greater precision after each epoch, thereby enhancing the trustworthiness of the ‘black box’ DL model and improving the performance of models. (4) Model training: Proposed HCI model is trained using the updated training dataset and an enhanced version of existing UNet. Experimental results validate the effectiveness of this Human-Computer Interaction-based approaches, demonstrating that our proposed WD-UNet, LC-UNet, UUNet, RS-UNet achieve comparable or even superior performance than the state-of-the-art DL models, such as WD-UNet with only 15 %–35 % of the training data, leading to substantial reductions (65 %–85 % reduction of annotation effort) in physician annotation time.
AB - In the realm of pulmonary tracheal segmentation, the scarcity of annotated data stands as a prevalent pain point in most medical segmentation endeavors. Concurrently, most Deep Learning (DL) methodologies employed in this domain invariably grapple with other dual challenges: the inherent opacity of ‘black box’ models and the ongoing pursuit of performance enhancement. In response to these intertwined challenges, the core concept of our Human-Computer Interaction (HCI) based learning models (RS_UNet, LC_UNet, UUNet and WD_UNet) hinge on the versatile combination of diverse query strategies and an array of deep learning models. We train four HCI models based on the initial training dataset and sequentially repeat the following steps 1–4: (1) Query Strategy: Our proposed HCI models selects those samples which contribute the most additional representative information when labeled in each iteration of the query strategy (showing the names and sequence numbers of the samples to be annotated). Additionally, in this phase, the model selects the unlabeled samples with the greatest predictive disparity by calculating the Wasserstein Distance, Least Confidence, Entropy Sampling, and Random Sampling. (2) Central line correction: The selected samples in previous stage are then used for domain expert correction of the system-generated tracheal central lines in each training round. (3) Update training dataset: When domain experts are involved in each epoch of the DL model's training iterations, they update the training dataset with greater precision after each epoch, thereby enhancing the trustworthiness of the ‘black box’ DL model and improving the performance of models. (4) Model training: Proposed HCI model is trained using the updated training dataset and an enhanced version of existing UNet. Experimental results validate the effectiveness of this Human-Computer Interaction-based approaches, demonstrating that our proposed WD-UNet, LC-UNet, UUNet, RS-UNet achieve comparable or even superior performance than the state-of-the-art DL models, such as WD-UNet with only 15 %–35 % of the training data, leading to substantial reductions (65 %–85 % reduction of annotation effort) in physician annotation time.
KW - Airway segmentation
KW - Deep Learning
KW - Human-centric AI
KW - Query strategy
UR - http://www.scopus.com/inward/record.url?scp=85199253225&partnerID=8YFLogxK
U2 - 10.1016/j.artmed.2024.102930
DO - 10.1016/j.artmed.2024.102930
M3 - Article
AN - SCOPUS:85199253225
SN - 0933-3657
VL - 154
JO - Artificial Intelligence in Medicine
JF - Artificial Intelligence in Medicine
M1 - 102930
ER -