Precise Liver Tumor Segmentation in CT Using a Hybrid Deep Learning-Radiomics Framework

TL;DR

This paper introduces a hybrid deep learning and radiomics framework for precise 3D liver tumor segmentation in CT scans, addressing challenges like low contrast and boundary ambiguity to improve accuracy and consistency.

Contribution

It combines a cascaded U-Net, radiomics features, and a 3D CNN refinement in a novel hybrid approach for improved liver tumor segmentation.

Findings

Achieved accurate liver and tumor segmentation in CT images.

Effectively reduced false positives using radiomics-based classification.

Enhanced boundary delineation with CNN-based contour smoothing.

Abstract

Accurate three-dimensional delineation of liver tumors on contrast-enhanced CT is a prerequisite for treatment planning, navigation and response assessment, yet manual contouring is slow, observer-dependent and difficult to standardise across centres. Automatic segmentation is complicated by low lesion-parenchyma contrast, blurred or incomplete boundaries, heterogeneous enhancement patterns, and confounding structures such as vessels and adjacent organs. We propose a hybrid framework that couples an attention-enhanced cascaded U-Net with handcrafted radiomics and voxel-wise 3D CNN refinement for joint liver and liver-tumor segmentation. First, a 2.5D two-stage network with a densely connected encoder, sub-pixel convolution decoders and multi-scale attention gates produces initial liver and tumor probability maps from short stacks of axial slices. Inter-slice temporal consistency is then enforced by a simple three-slice refinement rule along the cranio-caudal direction, which restores thin and tiny lesions while suppressing isolated noise. Next, 728 radiomic descriptors spanning intensity, texture, shape, boundary and wavelet feature groups are extracted from candidate lesions and reduced to 20 stable, highly informative features via multi-strategy feature selection; a random forest classifier uses these features to reject false-positive regions. Finally, a compact 3D patch-based CNN derived from AlexNet operates in a narrow band around the tumor boundary to perform voxel-level relabelling and contour smoothing.