Deep Attentive Features for Prostate Segmentation in 3D Transrectal Ultrasound
Statistiche
3D ResNeXt [46] as the feature extraction layers.
Dice Similarity Coefficient (Dice) of 0.90.
Jaccard Index of 0.82.
Conformity Coefficient (CC) of 0.78.
Average Distance of Boundaries (ADB) of 3.32 voxels.
Precision of 0.90.
Recall of 0.91.
Citazioni
"Automatic prostate segmentation in transrectal ultrasound (TRUS) images is of essential importance for image-guided prostate interventions and treatment planning."
"Our attention module utilizes the attention mechanism to selectively leverage the multi-level features integrated from different layers to refine the features at each individual layer."
"Our method attains satisfactory segmentation performance on challenging 3D TRUS volumes."
"The proposed attention mechanism is a general strategy to aggregate multi-level deep features and has the potential to be used for other medical image segmentation tasks."