Metastatic liver tumour segmentation from discriminant Grassmannian manifolds

TL;DR

This paper introduces an unsupervised machine learning framework using discriminant Grassmannian manifolds for accurate segmentation of metastatic liver tumors in CT images, addressing challenges like noise and tissue variability.

Contribution

It presents a novel unsupervised segmentation method based on Grassmannian manifolds that learns tumor appearance relative to normal tissue, improving accuracy over existing techniques.

Findings

Achieved a mean Dice coefficient of 90.7% on clinical datasets.

Validated on 43 CT images with over 50 tumors.

Outperformed state-of-the-art segmentation methods.

Abstract

The early detection, diagnosis and monitoring of liver cancer progression can be achieved with the precise delineation of metastatic tumours. However, accurate automated segmentation remains challenging due to the presence of noise, inhomogeneity and the high appearance variability of malignant tissue. In this paper, we propose an unsupervised metastatic liver tumour segmentation framework using a machine learning approach based on discriminant Grassmannian manifolds which learns the appearance of tumours with respect to normal tissue. First, the framework learns within-class and between-class similarity distributions from a training set of images to discover the optimal manifold discrimination between normal and pathological tissue in the liver. Second, a conditional optimisation scheme computes nonlocal pairwise as well as pattern-based clique potentials from the manifold subspace to recognise regions with similar labelings and to incorporate global consistency in the segmentation process. The proposed framework was validated on a clinical database of 43 CT images from patients with metastatic liver cancer. Compared to state-of-the-art methods, our method achieves a better performance on two separate datasets of metastatic liver tumours from different clinical sites, yielding an overall mean Dice similarity coefficient of 90.7 +/- 2.4 in over 50 tumours with an average volume of 27.3 mm3.