SWIN-SFTNet : Spatial Feature Expansion and Aggregation using Swin Transformer For Whole Breast micro-mass segmentation

TL;DR

This paper introduces Swin-SFTNet, a transformer-based U-net architecture with novel spatial feature expansion and aggregation, significantly improving micro-mass segmentation accuracy in breast mammography datasets.

Contribution

It proposes a novel SFEA block and embedding loss for better global and local feature integration, outperforming existing methods in breast micro-mass segmentation.

Findings

Achieved 3.10% higher dice score on CBIS-DDSM dataset.

Improved segmentation accuracy on InBreast dataset by 3.81%.

Outperformed state-of-the-art architectures in micro-mass segmentation.

Abstract

Incorporating various mass shapes and sizes in training deep learning architectures has made breast mass segmentation challenging. Moreover, manual segmentation of masses of irregular shapes is time-consuming and error-prone. Though Deep Neural Network has shown outstanding performance in breast mass segmentation, it fails in segmenting micro-masses. In this paper, we propose a novel U-net-shaped transformer-based architecture, called Swin-SFTNet, that outperforms state-of-the-art architectures in breast mammography-based micro-mass segmentation. Firstly to capture the global context, we designed a novel Spatial Feature Expansion and Aggregation Block(SFEA) that transforms sequential linear patches into a structured spatial feature. Next, we combine it with the local linear features extracted by the swin transformer block to improve overall accuracy. We also incorporate a novel embedding loss that calculates similarities between linear feature embeddings of the encoder and decoder blocks. With this approach, we achieve higher segmentation dice over the state-of-the-art by 3.10% on CBIS-DDSM, 3.81% on InBreast, and 3.13% on CBIS pre-trained model on the InBreast test data set.