IFSS-Net: Interactive Few-Shot Siamese Network for Faster Muscle Segmentation and Propagation in Volumetric Ultrasound

TL;DR

This paper introduces IFSS-Net, a novel deep Siamese network with bidirectional LSTM and a specialized loss for rapid, accurate muscle segmentation and propagation in 3D ultrasound, requiring minimal annotated data.

Contribution

It presents a new few-shot learning approach with a bidirectional LSTM and a decremental training strategy for efficient muscle segmentation in ultrasound.

Findings

Achieved over 95% Dice score in muscle segmentation.

Volumetric error around 1.6%.

Validated on 44 subjects with 61,600 images.

Abstract

We present an accurate, fast and efficient method for segmentation and muscle mask propagation in 3D freehand ultrasound data, towards accurate volume quantification. A deep Siamese 3D Encoder-Decoder network that captures the evolution of the muscle appearance and shape for contiguous slices is deployed. We uses it to propagate a reference mask annotated by a clinical expert. To handle longer changes of the muscle shape over the entire volume and to provide an accurate propagation, we devise a Bidirectional Long Short Term Memory module. Also, to train our model with a minimal amount of training samples, we propose a strategy combining learning from few annotated 2D ultrasound slices with sequential pseudo-labeling of the unannotated slices. We introduce a decremental update of the objective function to guide the model convergence in the absence of large amounts of annotated data. After training with a small number of volumes, the decremental update transitions from a weakly-supervised training to a few-shot setting. Finally, to handle the class-imbalance between foreground and background muscle pixels, we propose a parametric Tversky loss function that learns to adaptively penalize false positives and false negatives. We validate our approach for the segmentation, label propagation, and volume computation of the three low-limb muscles on a dataset of 61600 images from 44 subjects. We achieve a Dice score coefficient of over $95~\%$ and a volumetric error \textcolor{black}{of} $1.6035 \pm 0.587~\%$.