MDNet: Multi-Decoder Network for Abdominal CT Organs Segmentation

TL;DR

This paper introduces MDNet, a multi-decoder neural network leveraging multi-scale features and previous mask predictions to improve the accuracy and robustness of abdominal organ segmentation in CT scans.

Contribution

The paper presents a novel multi-decoder architecture with iterative refinement and spatial attention, enhancing segmentation accuracy and interpretability over existing methods.

Findings

Achieved high dice similarity coefficients of 0.9013 and 0.9169 on LiTS and MSD spleen datasets.

Reduced Hausdorff distance to 3.79 and 2.26, indicating precise boundary delineation.

Demonstrated improved robustness and interpretability compared to baseline models.

Abstract

Accurate segmentation of organs from abdominal CT scans is essential for clinical applications such as diagnosis, treatment planning, and patient monitoring. To handle challenges of heterogeneity in organ shapes, sizes, and complex anatomical relationships, we propose a \textbf{\textit{\ac{MDNet}}}, an encoder-decoder network that uses the pre-trained \textit{MiT-B2} as the encoder and multiple different decoder networks. Each decoder network is connected to a different part of the encoder via a multi-scale feature enhancement dilated block. With each decoder, we increase the depth of the network iteratively and refine segmentation masks, enriching feature maps by integrating previous decoders' feature maps. To refine the feature map further, we also utilize the predicted masks from the previous decoder to the current decoder to provide spatial attention across foreground and background regions. MDNet effectively refines the segmentation mask with a high dice similarity coefficient (DSC) of 0.9013 and 0.9169 on the Liver Tumor segmentation (LiTS) and MSD Spleen datasets. Additionally, it reduces Hausdorff distance (HD) to 3.79 for the LiTS dataset and 2.26 for the spleen segmentation dataset, underscoring the precision of MDNet in capturing the complex contours. Moreover, \textit{\ac{MDNet}} is more interpretable and robust compared to the other baseline models.