Deep Learning for Automated Ventricle and Periventricular Space Segmentation on CT and T1CE MRI in Neuro-Oncology Patients
Authors:
- Mart WubbelsMWMart Wubbels
- Marvin RibeiroMRMarvin Ribeiro
- Jelmer M. WolterinkJWJelmer M. Wolterink
- Wouter van ElmptWEWouter van Elmpt
- Inge CompterICInge Compter
- David HofstedeDHDavid Hofstede
- Nikolina E. BirimacNBNikolina E. Birimac
- Femke VaassenFVFemke Vaassen
- Kati PalmgrenKPKati Palmgren
- Hendrik H. G. HansenHHHendrik H. G. Hansen
- Hiska L. van der WeideHWHiska L. van der Weide
- Charlotte L. BrouwerCBCharlotte L. Brouwer
Open Access
Abstract
Purpose: This study aims to create a deep learning (DL) model capable of accurately delineating the ventricles, and by extension, the periventricular space (PVS), following the 2021 EPTN Neuro-Oncology Atlas guidelines on T1-weighted contrast-enhanced MRI scans (T1CE). The performance of this DL model was quantitatively and qualitatively compared with an off-the-shelf model. Materials and Methods: An nnU-Net was trained for ventricle segmentation using both CT and T1CE MRI images from 78 patients. Its performance was compared to that of a publicly available pretrained segmentation model, SynthSeg. The evaluation was conducted on both internal (N = 18) and external (n = 18) test sets, with each consisting of paired CT and T1CE MRI images and expert-delineated ground truths (GTs). Segmentation accuracy was assessed using the volumetric Dice Similarity Coefficient (DSC), 95th percentile Hausdorff distance (HD95), surface DSC, and added path length (APL). Additionally, a local evaluation of ventricle segmentations quantified differences between manual and automatic segmentations across both test sets. All segmentations were scored by radiotherapy technicians for clinical acceptability using a 4-point Likert scale. Results: The nnU-Net significantly outperformed the SynthSeg model on the internal test dataset in terms of median [range] DSC, 0.93 [0.86–0.95] vs. 0.85 [0.67–0.91], HD95, 0.9 [0.7–2.5] mm vs. 2.2 [1.7–4.8] mm, surface DSC, 0.97 [0.90–0.98] vs. 0.84 [0.70–0.89], and APL, 876 [407–1298] mm vs. 2809 [2311–3622] mm, all with p < 0.001. No significant differences in these metrics were found in the external test set. However clinical ratings favored nnU-Net segmentations on the internal and external test sets. In addition, the nnU-Net had higher clinical ratings than the GT delineation on the internal and external test set. Conclusions: The nnU-Net model outperformed the SynthSeg model on the internal dataset in both segmentation metrics and clinician ratings. While segmentation metrics showed no significant differences between the models on the external set, clinician ratings favored nnU-Net, suggesting enhanced clinical acceptability. This suggests that nnU-Net could contribute to more time-efficient and streamlined radiotherapy planning workflows.Keywords
Funding Information
- ZonMw (10070012010002)
This publication has 36 references indexed in Scilit:
- nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation2024
- Geometric and dosimetric analysis of CT- and MR-based automatic contouring for the EPTN contouring atlas in neuro-oncologyPhysica Medica, 2023
- Improved Segmentation of the Intracranial and Ventricular Volumes in Populations with Cerebrovascular Lesions and Atrophy Using 3D CNNsNeuroinformatics, 2021
- Late Contrast Enhancing Brain Lesions in Proton-Treated Patients With Low-Grade Glioma: Clinical Evidence for Increased Periventricular Sensitivity and Variable RBEInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2020
- Deep Learning-Based Delineation of Head and Neck Organs at Risk: Geometric and Dosimetric EvaluationInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2019
- Shortcomings of Ventricle Segmentation Using Deep Convolutional Networks2018
- Comparative evaluation of autocontouring in clinical practice: A practical method using the Turing testMedical Physics, 2018
- How to Exploit Weaknesses in Biomedical Challenge Design and Organization2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Object modelling by registration of multiple range imagesImage and Vision Computing, 1992