Attention-Gated Networks for Improving Ultrasound Scan Plane Detection
This addresses a domain-specific problem for clinicians in fetal ultrasound screening, offering an incremental improvement through a novel attention mechanism.
The paper tackles the problem of automated scan plane detection in fetal ultrasound, which is challenging due to poor image quality, by applying an attention-gated network. The result shows that the method improves overall performance, reduces false positives, and provides efficient object localization, with significant gains especially when the base network has low capacity.
In this work, we apply an attention-gated network to real-time automated scan plane detection for fetal ultrasound screening. Scan plane detection in fetal ultrasound is a challenging problem due the poor image quality resulting in low interpretability for both clinicians and automated algorithms. To solve this, we propose incorporating self-gated soft-attention mechanisms. A soft-attention mechanism generates a gating signal that is end-to-end trainable, which allows the network to contextualise local information useful for prediction. The proposed attention mechanism is generic and it can be easily incorporated into any existing classification architectures, while only requiring a few additional parameters. We show that, when the base network has a high capacity, the incorporated attention mechanism can provide efficient object localisation while improving the overall performance. When the base network has a low capacity, the method greatly outperforms the baseline approach and significantly reduces false positives. Lastly, the generated attention maps allow us to understand the model's reasoning process, which can also be used for weakly supervised object localisation.