ECONet: Efficient Convolutional Online Likelihood Network for Scribble-based Interactive Segmentation
This work addresses the time-intensive and expert-dependent annotation problem for medical imaging researchers and clinicians, offering an incremental improvement in interactive segmentation for COVID-19 lung lesion analysis.
The paper tackles the challenge of efficiently annotating lung lesions in COVID-19 CT images by proposing ECONet, an online convolutional network that learns from scribble-based user interactions, achieving a 16% higher Dice score, 3x faster execution, and requiring 9000 fewer labelled voxels compared to state-of-the-art methods.
Automatic segmentation of lung lesions associated with COVID-19 in CT images requires large amount of annotated volumes. Annotations mandate expert knowledge and are time-intensive to obtain through fully manual segmentation methods. Additionally, lung lesions have large inter-patient variations, with some pathologies having similar visual appearance as healthy lung tissues. This poses a challenge when applying existing semi-automatic interactive segmentation techniques for data labelling. To address these challenges, we propose an efficient convolutional neural networks (CNNs) that can be learned online while the annotator provides scribble-based interaction. To accelerate learning from only the samples labelled through user-interactions, a patch-based approach is used for training the network. Moreover, we use weighted cross-entropy loss to address the class imbalance that may result from user-interactions. During online inference, the learned network is applied to the whole input volume using a fully convolutional approach. We compare our proposed method with state-of-the-art using synthetic scribbles and show that it outperforms existing methods on the task of annotating lung lesions associated with COVID-19, achieving 16% higher Dice score while reducing execution time by 3$\times$ and requiring 9000 lesser scribbles-based labelled voxels. Due to the online learning aspect, our approach adapts quickly to user input, resulting in high quality segmentation labels. Source code for ECONet is available at: https://github.com/masadcv/ECONet-MONAILabel.