ECONet: Efficient Convolutional Online Likelihood Network for Scribble-based Interactive Segmentation

{, }

1) Motivation, Objectives and Related Works:

Motivation:

Automatic segmentation of lung lesions associated with COVID-19 in CT images requires large amount of annotated volumes. Annotations mandate expert knowledge and are timeintensive 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.

Objectives:

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× and requiring 9000 lesser scribblesbased labelled voxels. Due to the online learning aspect, our approach adapts quickly to user input, resulting in high quality segmentation labels.

Related Works:

COVID-19

COVID-19 causes pneumonia-like symptoms, adversely affecting respiratory systems in some patients. In their response to the disease, clinicians have used Computed Tomography (CT) imaging to assess the amount of lung damage and disease progression by localizing lung lesions (Roth et al., 2021; Revel et al., 2021; Rubin et al., 2020). This has been essential in providing relevant treatment for COVID-19 patients with severe conditions and has resulted in acquisition of large number of CT volumes from COVID-19 patients (Roth et al., 2021; Tsai et al., 2021; Wang et al., 2020; Revel et al., 2021). Deep learning-based automatic lung lesion segmentation methods may ease burden on clinicians, however, these methods require large amounts of manually labelled data (Wang et al., 2020; Gonzalez et al., 2021; Tilborghs et al., 2020; Chassagnon et al., 2020). Labelling CT volumes for lung lesion is a time-intensive task which requires expert knowledge, putting further strain on clinicians’ workload. In addition, future variants of novel coronaviruses may result in variations in lesion pathologies (McLaren et al., 2020). In such cases, automatic segmentation methods that are trained on existing datasets may fail. To address this, rapid labelling of relevant data is needed to augment existing dataset with new labelled volumes

Contribution:

2) Methodology:

Method 1:

Method 2:

3) Experimental Results:

Dataset:

Metrics:

Experimental Results:

Ablations:

References:

Page updated

Google Sites

Report abuse

About Me: