FocusNet++: Attentive Aggregated Transformations for Efficient and Accurate Medical Image Segmentation

TL;DR

FocusNet++ introduces an attention-based residual block with hybrid loss for efficient, accurate medical image segmentation, achieving state-of-the-art results with fewer parameters.

Contribution

It presents a novel residual block combining attention mechanisms and group convolutions, along with a hybrid loss function, for improved medical image segmentation.

Findings

State-of-the-art performance on ISIC 2018 melanoma segmentation

Superior results on cell nuclei segmentation datasets

Fewer parameters and FLOPs compared to existing models

Abstract

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.