Automated Prostate Gland Segmentation in MRI Using nnU-Net

TL;DR

This paper presents a deep learning model based on nnU-Net v2 for automatic prostate gland segmentation in multiparametric MRI, achieving high accuracy and strong generalization across datasets.

Contribution

The study introduces a task-specific, multimodal deep learning approach for prostate segmentation that outperforms general-purpose tools and is ready for clinical deployment.

Findings

Achieved a mean Dice score of 0.96 in cross-validation.

Attained a Dice score of 0.82 on external validation, demonstrating good generalization.

Outperformed a general-purpose segmentation tool significantly.

Abstract

Accurate segmentation of the prostate gland in multiparametric MRI (mpMRI) is a fundamental step for a wide range of clinical and research applications, including image registration, volume estimation, and radiomic analysis. However, manual delineation is time-consuming and subject to inter-observer variability, while general-purpose segmentation tools often fail to provide sufficient accuracy for prostate-specific tasks. In this work, we propose a dedicated deep learning-based approach for automatic prostate gland segmentation using the nnU-Net v2 framework. The model leverages multimodal mpMRI data, including T2-weighted imaging, diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps, to exploit complementary tissue information. Training was performed on 981 cases from the PI-CAI dataset using whole-gland annotations, and model performance was assessed through 5-fold cross-validation and external validation on an independent cohort of 54 patients from Hospital La Fe. The proposed model achieved a mean Dice score of 0.96 +/- 0.00 in cross-validation and 0.82 on the external test set, demonstrating strong generalization despite domain shift. In comparison, a general-purpose approach (TotalSegmentator) showed substantially lower performance, with a Dice score of 0.15, primarily due to under-segmentation of the gland. These results highlight the importance of task-specific, multimodal segmentation strategies and demonstrate the potential of the proposed approach for reliable integration into clinical research workflows. To facilitate reproducibility and deployment, the model has been fully containerized and is available as a ready-to-use inference tool.