KLO-Net: A Dynamic K-NN Attention U-Net with CSP Encoder for Efficient Prostate Gland Segmentation from MRI
This work addresses efficiency bottlenecks for clinical deployment of prostate gland segmentation from MRI, though it appears incremental as it builds on existing U-Net and attention mechanisms.
The paper tackled the problem of computational load and memory footprint in real-time prostate MRI segmentation by proposing KLO-Net, a dynamic K-NN attention U-Net with CSP encoder, achieving improved efficiency and segmentation accuracy on public datasets like PROMISE12 and PROSTATEx.
Real-time deployment of prostate MRI segmentation on clinical workstations is often bottlenecked by computational load and memory footprint. Deep learning-based prostate gland segmentation approaches remain challenging due to anatomical variability. To bridge this efficiency gap while still maintaining reliable segmentation accuracy, we propose KLO-Net, a dynamic K-Nearest Neighbor attention U-Net with Cross Stage Partial, i.e., CSP, encoder for efficient prostate gland segmentation from MRI scan. Unlike the regular K-NN attention mechanism, the proposed dynamic K-NN attention mechanism allows the model to adaptively determine the number of attention connections for each spatial location within a slice. In addition, CSP blocks address the computational load to reduce memory consumption. To evaluate the model's performance, comprehensive experiments and ablation studies are conducted on two public datasets, i.e., PROMISE12 and PROSTATEx, to validate the proposed architecture. The detailed comparative analysis demonstrates the model's advantage in computational efficiency and segmentation quality.