Segmentation of Prostate Tumour Volumes from PET Images is a Different Ball Game

TL;DR

This paper introduces a novel intensity threshold-based normalization technique for PET image segmentation of prostate tumours, significantly improving U-Net model performance across multiple datasets and tracers.

Contribution

The authors propose a new custom-feature-clipping normalization method tailored for PET images, enhancing the accuracy of prostate tumour segmentation with deep learning models.

Findings

U-Net models perform better with the proposed normalization.

The clipping technique reduces outliers and improves segmentation quality.

Results are consistent across different tracers and datasets.

Abstract

Accurate segmentation of prostate tumours from PET images presents a formidable challenge in medical image analysis. Despite considerable work and improvement in delineating organs from CT and MR modalities, the existing standards do not transfer well and produce quality results in PET related tasks. Particularly, contemporary methods fail to accurately consider the intensity-based scaling applied by the physicians during manual annotation of tumour contours. In this paper, we observe that the prostate-localised uptake threshold ranges are beneficial for suppressing outliers. Therefore, we utilize the intensity threshold values, to implement a new custom-feature-clipping normalisation technique. We evaluate multiple, established U-Net variants under different normalisation schemes, using the nnU-Net framework. All models were trained and tested on multiple datasets, obtained with two radioactive tracers: [68-Ga]Ga-PSMA-11 and [18-F]PSMA-1007. Our results show that the U-Net models achieve much better performance when the PET scans are preprocessed with our novel clipping technique.