KEVS: Enhancing Segmentation of Visceral Adipose Tissue in Pre-Cystectomy CT with Gaussian Kernel Density Estimation

2025-03-28

AI Summary

High inter-observer variability and scarcity of ground-truth visceral adipose tissue (VAT) masks in CT imaging hinder the development of deep learning–based VAT segmentation methods. Method: We propose the first fully automated, supervision-free VAT segmentation framework that eliminates reliance on annotated VAT masks. Our approach innovatively integrates Gaussian kernel density estimation (KDE) with a multi-organ semantic segmentation network to achieve scan-adaptive VAT localization and joint modeling of multi-tissue features; it further leverages an open-source CT-pretrained model to enhance generalizability. Contribution/Results: Evaluated on the UCLH-Cyst dataset (n=20), our method achieves a Dice coefficient of 0.892—improving upon the best prior deep learning and threshold-based methods by 4.80% and 6.02%, respectively—while significantly reducing inter-observer variability. This establishes a clinically viable, unsupervised paradigm for VAT quantification in pre-cystectomy assessment.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Kernel Methods
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Security and Privacy: Data transparency and provenance
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Purpose: The distribution of visceral adipose tissue (VAT) in cystectomy patients is indicative of the incidence of post-operative complications. Existing VAT segmentation methods for computed tomography (CT) employing intensity thresholding have limitations relating to inter-observer variability. Moreover, the difficulty in creating ground-truth masks limits the development of deep learning (DL) models for this task. This paper introduces a novel method for VAT prediction in pre-cystectomy CT, which is fully automated and does not require ground-truth VAT masks for training, overcoming aforementioned limitations. Methods: We introduce the Kernel density Enhanced VAT Segmentator ( KEVS), combining a DL semantic segmentation model, for multi-body feature prediction, with Gaussian kernel density estimation analysis of predicted subcutaneous adipose tissue to achieve accurate scan-specific predictions of VAT in the abdominal cavity. Uniquely for a DL pipeline, KEVS does not require ground-truth VAT masks. Results: We verify the ability of KEVS to accurately segment abdominal organs in unseen CT data and compare KEVS VAT segmentation predictions to existing state-of-the-art (SOTA) approaches in a dataset of 20 pre-cystectomy CT scans, collected from University College London Hospital (UCLH-Cyst), with expert ground-truth annotations. KEVS presents a 4.80% and 6.02% improvement in Dice Coefficient over the second best DL and thresholding-based VAT segmentation techniques respectively when evaluated on UCLH-Cyst. Conclusion: This research introduces KEVS; an automated, SOTA method for the prediction of VAT in pre-cystectomy CT which eliminates inter-observer variability and is trained entirely on open-source CT datasets which do not contain ground-truth VAT masks.

Problem

• Automates VAT segmentation in CT scans without ground-truth masks
• Reduces inter-observer variability in existing VAT segmentation methods
• Improves accuracy over current DL and thresholding-based techniques

Innovation

• DL model with Gaussian kernel density estimation
• No ground-truth VAT masks required
• Automated scan-specific VAT prediction