HistoSeg : Quick attention with multi-loss function for multi-structure segmentation in digital histology images

TL;DR

HistoSeg introduces a novel encoder-decoder network with quick attention and a multi-loss function, significantly improving multi-structure segmentation accuracy in digital histology images over existing methods.

Contribution

The paper presents a new neural network architecture combining a quick attention module and multi-loss function for better multi-scale boundary detection in histology image segmentation.

Findings

Achieved 1.99% higher accuracy on MoNuSeg dataset.

Achieved 7.15% higher accuracy on GlaS dataset.

Outperforms state-of-the-art networks in multi-structure segmentation.

Abstract

Medical image segmentation assists in computer-aided diagnosis, surgeries, and treatment. Digitize tissue slide images are used to analyze and segment glands, nuclei, and other biomarkers which are further used in computer-aided medical applications. To this end, many researchers developed different neural networks to perform segmentation on histological images, mostly these networks are based on encoder-decoder architecture and also utilize complex attention modules or transformers. However, these networks are less accurate to capture relevant local and global features with accurate boundary detection at multiple scales, therefore, we proposed an Encoder-Decoder Network, Quick Attention Module and a Multi Loss Function (combination of Binary Cross Entropy (BCE) Loss, Focal Loss & Dice Loss). We evaluate the generalization capability of our proposed network on two publicly available datasets for medical image segmentation MoNuSeg and GlaS and outperform the state-of-the-art networks with 1.99% improvement on the MoNuSeg dataset and 7.15% improvement on the GlaS dataset. Implementation Code is available at this link: https://bit.ly/HistoSeg