Attention-based CT Scan Interpolation for Lesion Segmentation of Colorectal Liver Metastases

TL;DR

This paper introduces an unsupervised attention-based interpolation model that generates intermediate CT slices to improve lesion segmentation accuracy in colorectal liver metastases, especially across varying slice thicknesses.

Contribution

The novel interpolation model leverages segmentation loss during training to enhance lesion-focused interpolation in CT scans, improving segmentation performance.

Findings

Increases Dice score in lesion segmentation.

Outperforms other interpolation methods in accuracy.

Produces consistent intermediate slices for better 3D segmentation.

Abstract

Small liver lesions common to colorectal liver metastases (CRLMs) are challenging for convolutional neural network (CNN) segmentation models, especially when we have a wide range of slice thicknesses in the computed tomography (CT) scans. Slice thickness of CT images may vary by clinical indication. For example, thinner slices are used for presurgical planning when fine anatomic details of small vessels are required. While keeping the effective radiation dose in patients as low as possible, various slice thicknesses are employed in CRLMs due to their limitations. However, differences in slice thickness across CTs lead to significant performance degradation in CT segmentation models based on CNNs. This paper proposes a novel unsupervised attention-based interpolation model to generate intermediate slices from consecutive triplet slices in CT scans. We integrate segmentation loss during the interpolation model's training to leverage segmentation labels in existing slices to generate middle ones. Unlike common interpolation techniques in CT volumes, our model highlights the regions of interest (liver and lesions) inside the abdominal CT scans in the interpolated slice. Moreover, our model's outputs are consistent with the original input slices while increasing the segmentation performance in two cutting-edge 3D segmentation pipelines. We tested the proposed model on the CRLM dataset to upsample subjects with thick slices and create isotropic volume for our segmentation model. The produced isotropic dataset increases the Dice score in the segmentation of lesions and outperforms other interpolation approaches in terms of interpolation metrics.