FocusNet++: Attentive Aggregated Transformations for Efficient and Accurate Medical Image Segmentation
This work addresses efficient and accurate segmentation for medical imaging, but it appears incremental as it builds on existing methods like attention and group convolutions.
The paper tackled medical image segmentation by proposing a new residual block with group attention and a hybrid loss, achieving state-of-the-art results on ISIC 2018 melanoma and cell nuclei datasets with fewer parameters and FLOPs.
We propose a new residual block for convolutional neural networks and demonstrate its state-of-the-art performance in medical image segmentation. We combine attention mechanisms with group convolutions to create our group attention mechanism, which forms the fundamental building block of our network, FocusNet++. We employ a hybrid loss based on balanced cross entropy, Tversky loss and the adaptive logarithmic loss to enhance the performance along with fast convergence. Our results show that FocusNet++ achieves state-of-the-art results across various benchmark metrics for the ISIC 2018 melanoma segmentation and the cell nuclei segmentation datasets with fewer parameters and FLOPs.