A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Data

TL;DR

This paper introduces a unified deep learning framework for low-shot medical image segmentation that effectively handles extreme data scarcity by utilizing multimodal representations and adaptive mixture models, outperforming existing methods.

Contribution

The proposed framework uniquely combines distance metric learning with adaptive multimodal representations to improve low-shot segmentation in medical imaging, especially for rare diseases.

Findings

Achieves 81% Dice for brain tissue segmentation with a single training sample.

Outperforms standard DNN and registration-based methods in low-shot scenarios.

Effective in brain MRI and abdominal CT datasets.

Abstract

Medical image segmentation has achieved remarkable advancements using deep neural networks (DNNs). However, DNNs often need big amounts of data and annotations for training, both of which can be difficult and costly to obtain. In this work, we propose a unified framework for generalized low-shot (one- and few-shot) medical image segmentation based on distance metric learning (DML). Unlike most existing methods which only deal with the lack of annotations while assuming abundance of data, our framework works with extreme scarcity of both, which is ideal for rare diseases. Via DML, the framework learns a multimodal mixture representation for each category, and performs dense predictions based on cosine distances between the pixels' deep embeddings and the category representations. The multimodal representations effectively utilize the inter-subject similarities and intraclass variations to overcome overfitting due to extremely limited data. In addition, we propose adaptive mixing coefficients for the multimodal mixture distributions to adaptively emphasize the modes better suited to the current input. The representations are implicitly embedded as weights of the fc layer, such that the cosine distances can be computed efficiently via forward propagation. In our experiments on brain MRI and abdominal CT datasets, the proposed framework achieves superior performances for low-shot segmentation towards standard DNN-based (3D U-Net) and classical registration-based (ANTs) methods, e.g., achieving mean Dice coefficients of 81%/69% for brain tissue/abdominal multiorgan segmentation using a single training sample, as compared to 52%/31% and 72%/35% by the U-Net and ANTs, respectively.