Exploiting Scale-Variant Attention for Segmenting Small Medical Objects

TL;DR

This paper introduces SvANet, a novel attention-based network that effectively segments small medical objects by leveraging cross-scale features and vision transformers, significantly improving accuracy in challenging medical imaging tasks.

Contribution

The paper proposes a scale-variant attention network that combines cross-scale guidance, Monte Carlo attention, and vision transformers to enhance small object segmentation in medical images, addressing CNN limitations.

Findings

Achieved high mean Dice scores across multiple datasets for small medical objects.

Outperformed existing methods in segmenting objects occupying less than 1% of images.

Demonstrated robustness and superior accuracy in diverse medical imaging scenarios.

Abstract

Early detection and accurate diagnosis can predict the risk of malignant disease transformation, thereby increasing the probability of effective treatment. Identifying mild syndrome with small pathological regions serves as an ominous warning and is fundamental in the early diagnosis of diseases. While deep learning algorithms, particularly convolutional neural networks (CNNs), have shown promise in segmenting medical objects, analyzing small areas in medical images remains challenging. This difficulty arises due to information losses and compression defects from convolution and pooling operations in CNNs, which become more pronounced as the network deepens, especially for small medical objects. To address these challenges, we propose a novel scale-variant attention-based network (SvANet) for accurately segmenting small-scale objects in medical images. The SvANet consists of scale-variant attention, cross-scale guidance, Monte Carlo attention, and vision transformer, which incorporates cross-scale features and alleviates compression artifacts for enhancing the discrimination of small medical objects. Quantitative experimental results demonstrate the superior performance of SvANet, achieving 96.12%, 96.11%, 89.79%, 84.15%, 80.25%, 73.05%, and 72.58% in mean Dice coefficient for segmenting kidney tumors, skin lesions, hepatic tumors, polyps, surgical excision cells, retinal vasculatures, and sperms, which occupy less than 1% of the image areas in KiTS23, ISIC 2018, ATLAS, PolypGen, TissueNet, FIVES, and SpermHealth datasets, respectively.