Top

Published in:

Open Access 01-12-2024 | Original Article

NnU-Net versus mesh growing algorithm as a tool for the robust and timely segmentation of neurosurgical 3D images in contrast-enhanced T1 MRI scans

Authors: Mathijs de Boer, Tessa M. Kos, Tim Fick, Jesse A. M. van Doormaal, Elisa Colombo, Hugo J. Kuijf, Pierre A. J. T. Robe, Luca P. Regli, Lambertus W. Bartels, Tristan P. C. van Doormaal

Published in: Acta Neurochirurgica | Issue 1/2024

Abstract

Purpose

This study evaluates the nnU-Net for segmenting brain, skin, tumors, and ventricles in contrast-enhanced T1 (T1CE) images, benchmarking it against an established mesh growing algorithm (MGA).

Methods

We used 67 retrospectively collected annotated single-center T1CE brain scans for training models for brain, skin, tumor, and ventricle segmentation. An additional 32 scans from two centers were used test performance compared to that of the MGA. The performance was measured using the Dice-Sørensen coefficient (DSC), intersection over union (IoU), 95th percentile Hausdorff distance (HD95), and average symmetric surface distance (ASSD) metrics, with time to segment also compared.

Results

The nnU-Net models significantly outperformed the MGA (p < 0.0125) with a median brain segmentation DSC of 0.971 [95CI: 0.945–0.979], skin: 0.997 [95CI: 0.984–0.999], tumor: 0.926 [95CI: 0.508–0.968], and ventricles: 0.910 [95CI: 0.812–0.968]. Compared to the MGA’s median DSC for brain: 0.936 [95CI: 0.890, 0.958], skin: 0.991 [95CI: 0.964, 0.996], tumor: 0.723 [95CI: 0.000–0.926], and ventricles: 0.856 [95CI: 0.216–0.916]. NnU-Net performance between centers did not significantly differ except for the skin segmentations Additionally, the nnU-Net models were faster (mean: 1139 s [95CI: 685.0–1616]) than the MGA (mean: 2851 s [95CI: 1482–6246]).

Conclusions

The nnU-Net is a fast, reliable tool for creating automatic deep learning-based segmentation pipelines, reducing the need for extensive manual tuning and iteration. The models are able to achieve this performance despite a modestly sized training set. The ability to create high-quality segmentations in a short timespan can prove invaluable in neurosurgical settings.

Available only for authorised users

Balwant MK (2022) A Review on Convolutional neural networks for brain tumor segmentation: methods, datasets, libraries, and future directions. IRBM 43(6):521–537. https://doi.org/10.1016/j.irbm.2022.05.002CrossRef

Billot B, Greve DN, Puonti O, et al. SynthSeg: domain randomisation for segmentation of brain scans of any contrast and resolution. Published online January 4, 2023. http://arxiv.org/abs/2107.09559. Accessed January 27, 2023

Bounajem MT, Cameron B, Sorensen K et al (2023) Improved accuracy and lowered learning curve of ventricular targeting using augmented reality—phantom and cadaveric model testing. Neurosurgery 92(4):884–891. https://doi.org/10.1227/neu.0000000000002293CrossRefPubMed

Cabezas M, Oliver A, Lladó X, Freixenet J, Bach CM (2011) A review of atlas-based segmentation for magnetic resonance brain images. Comput Methods Programs Biomed 104(3):e158–e177. https://doi.org/10.1016/j.cmpb.2011.07.015CrossRefPubMed

Du G, Cao X, Liang J, Chen X, Zhan Y (2020) Medical image segmentation based on U-Net: a review. J Imaging Sci Technol. 64(2):20508–1–20508–20512. https://doi.org/10.2352/J.ImagingSci.Technol.2020.64.2.020508

Eck U, Stefan P, Laga H, Sandor C, Fallavollita P, Navab N (2016) Exploring visuo-haptic augmented reality user interfaces for stereo-tactic neurosurgery planning. In: Zheng G, Liao H, Jannin P, Cattin P, Lee SL, eds. Medical imaging and augmented reality. Vol 9805. Lecture Notes in Computer Science. Springer International Publishing:208–220. https://doi.org/10.1007/978-3-319-43775-0_19

Fick T, van Doormaal JAM, Tosic L et al (2021) Fully automatic brain tumor segmentation for 3D evaluation in augmented reality. Neurosurg Focus 51(2):E14. https://doi.org/10.3171/2021.5.FOCUS21200CrossRefPubMed

Ghaffari M, Sowmya A, Oliver R (2020) Automated brain tumor segmentation using multimodal brain scans: a survey based on models submitted to the BraTS 2012–2018 challenges. IEEE Rev Biomed Eng 13:156–168. https://doi.org/10.1109/RBME.2019.2946868CrossRefPubMed

He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Published online December 10, 2015. Accessed January 30, 2023. http://arxiv.org/abs/1512.03385

10.

Hesamian MH, Jia W, He X, Kennedy P (2019) Deep learning techniques for medical image segmentation: achievements and challenges. J Digit Imaging 32(4):582–596. https://doi.org/10.1007/s10278-019-00227-xCrossRefPubMedPubMedCentral

11.

Huo Y, Xu Z, Xiong Y et al (2019) 3D whole brain segmentation using spatially localized atlas network tiles. Neuroimage 194:105–119. https://doi.org/10.1016/j.neuroimage.2019.03.041CrossRefPubMed

12.

Incekara F, Smits M, Dirven C, Vincent A (2018) Clinical feasibility of a wearable mixed-reality device in neurosurgery. World Neurosurg 118:e422–e427. https://doi.org/10.1016/j.wneu.2018.06.208CrossRefPubMed

13.

Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH (2021) nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18(2):203–211. https://doi.org/10.1038/s41592-020-01008-zCrossRefPubMed

14.

Kärkkäinen M, Wilkman T, Mesimäki K, Snäll J (2018) Primary reconstruction of orbital fractures using patient-specific titanium milled implants: the Helsinki protocol. Br J Oral Maxillofac Surg 56(9):791–796. https://doi.org/10.1016/j.bjoms.2018.08.008CrossRefPubMed

15.

Karlsson A, Rosander J, Romu T et al (2015) Automatic and quantitative assessment of regional muscle volume by multi-atlas segmentation using whole-body water-fat MRI: automated muscle tissue quantification. J Magn Reson Imaging 41(6):1558–1569. https://doi.org/10.1002/jmri.24726CrossRefPubMed

16.

Kvarda P, Heisler L, Krähenbühl N et al (2021) 3D Assessment in posttraumatic ankle osteoarthritis. Foot Ankle Int 42(2):200–214. https://doi.org/10.1177/1071100720961315CrossRefPubMed

17.

Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM 60(6):84–90. https://doi.org/10.1145/3065386CrossRef

18.

Kos TM, Haaksman S, Van Doormaal TPC, Colombo E. Effect of intraoperative mixed reality use on non-surgical team members in the neurosurgical operating room: an explorative study. World Neurosurg. Published online September 2023:S1878875023012706. https://doi.org/10.1016/j.wneu.2023.09.031

19.

Li Y, Chen X, Wang N et al (2019) A wearable mixed-reality holographic computer for guiding external ventricular drain insertion at the bedside. J Neurosurg 131(5):1599–1606. https://doi.org/10.3171/2018.4.JNS18124CrossRef

20.

Liou TH, Chan WP, Pan LC, Lin PW, Chou P, Chen CH (2006) Fully automated large-scale assessment of visceral and subcutaneous abdominal adipose tissue by magnetic resonance imaging. Int J Obes 30(5):844–852. https://doi.org/10.1038/sj.ijo.0803216CrossRef

21.

Maier-Hein L, Reinke A, Godau P, et al. Metrics reloaded: pitfalls and recommendations for image analysis validation. Published online September 15, 2022. http://arxiv.org/abs/2206.01653. Accessed January 26, 2023

22.

Menze BH, Jakab A, Bauer S et al (2015) The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging 34(10):1993–2024. https://doi.org/10.1109/TMI.2014.2377694CrossRefPubMed

23.

Mårtensson G, Ferreira D, Granberg T et al (2020) The reliability of a deep learning model in clinical out-of-distribution MRI data: a multicohort study. Med Image Anal 66:101714. https://doi.org/10.1016/j.media.2020.101714CrossRefPubMed

24.

Norouzi A, Rahim MSM, Altameem A et al (2014) Medical image segmentation methods, algorithms, and applications. IETE Tech Rev 31(3):199–213. https://doi.org/10.1080/02564602.2014.906861CrossRef

25.

Olexa J, Cohen J, Alexander T, Brown C, Schwartzbauer G, Woodworth GF (2023) Expanding educational frontiers in neurosurgery: current and future uses of augmented reality. Neurosurgery 92(2):241–250. https://doi.org/10.1227/neu.0000000000002199CrossRefPubMed

26.

Pham DL, Xu C, Prince JL (2000) Current methods in medical image segmentation. Annu Rev Biomed Eng 2(1):315–337. https://doi.org/10.1146/annurev.bioeng.2.1.315CrossRefPubMed

27.

Pyötsiä K, Lehtinen V, Toivari M, Puolakkainen T, Lowery Wilson M, Snäll J (2021) Three-dimensional computer-aided analysis of 293 isolated blowout fractures — which radiological findings guide treatment decision? J Oral Maxillofac Surg 79(11):2306–2318. https://doi.org/10.1016/j.joms.2021.06.026CrossRefPubMed

28.

Qi Z, Li Y, Xu X et al (2021) Holographic mixed-reality neuronavigation with a head-mounted device: technical feasibility and clinical application. Neurosurg Focus 51(2):E22. https://doi.org/10.3171/2021.5.FOCUS21175CrossRefPubMed

29.

Reinke A, Tizabi MD, Sudre CH, et al. Common limitations of image processing metrics: a picture story. Published online July 7, 2022. http://arxiv.org/abs/2104.05642. Accessed January 26, 2023

30.

Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. Published online May 18, 2015. http://arxiv.org/abs/1505.04597. Accessed January 30, 2023

31.

Siddique N, Paheding S, Elkin CP, Devabhaktuni V (2021) U-Net and its variants for medical image segmentation: a review of theory and applications. IEEE Access 9:82031–82057. https://doi.org/10.1109/ACCESS.2021.3086020CrossRef

32.

Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. Published online April 10, 2015. http://arxiv.org/abs/1409.1556. Accessed January 30, 2023

33.

Sharma N, Ray A, Shukla K et al (2010) Automated medical image segmentation techniques. J Med Phys 35(1):3. https://doi.org/10.4103/0971-6203.58777CrossRefPubMedPubMedCentral

34.

Suojärvi N, Tampio J, Lindfors N, Waris E (2021) Computer-aided 3D analysis of anatomy and radiographic parameters of the distal radius. Clin Anat 34(4):574–580. https://doi.org/10.1002/ca.23615CrossRefPubMed

35.

van Doormaal JAM, Fick T, Ali M, Köllen M, van der Kuijp V, van Doormaal TPC (2021) Fully automatic adaptive meshing based segmentation of the ventricular system for augmented reality visualization and navigation. World Neurosurg 156:e9–e24. https://doi.org/10.1016/j.wneu.2021.07.099CrossRefPubMed

36.

Wang L, Xie C, Zeng N (2019) RP-Net: A 3D convolutional neural network for brain segmentation from magnetic resonance imaging. IEEE Access 7:39670–39679. https://doi.org/10.1109/ACCESS.2019.2906890CrossRef

37.

Wu J, Tang X (2021) Brain segmentation based on multi-atlas and diffeomorphism guided 3D fully convolutional network ensembles. Pattern Recognit 115:107904. https://doi.org/10.1016/j.patcog.2021.107904CrossRef

38.

Yamanakkanavar N, Choi JY, Lee B (2020) MRI Segmentation and classification of human brain using deep learning for diagnosis of Alzheimer’s disease: a survey. Sensors 20(11):3243. https://doi.org/10.3390/s20113243ADSCrossRefPubMedPubMedCentral

Title: NnU-Net versus mesh growing algorithm as a tool for the robust and timely segmentation of neurosurgical 3D images in contrast-enhanced T1 MRI scans
Authors: Mathijs de Boer
Tessa M. Kos
Tim Fick
Jesse A. M. van Doormaal
Elisa Colombo
Hugo J. Kuijf
Pierre A. J. T. Robe
Luca P. Regli
Lambertus W. Bartels
Tristan P. C. van Doormaal
Publication date: 01-12-2024
Publisher: Springer Vienna
Published in: Acta Neurochirurgica / Issue 1/2024
Print ISSN: 0001-6268
Electronic ISSN: 0942-0940
DOI: https://doi.org/10.1007/s00701-024-05973-8

Keynote webinar | Spotlight on medication adherence

Springer Medicine

NnU-Net versus mesh growing algorithm as a tool for the robust and timely segmentation of neurosurgical 3D images in contrast-enhanced T1 MRI scans

Abstract

Purpose

Methods

Results

Conclusions

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Purpose

Methods

Results

Conclusions

Please log in to get access to this content

Other articles of this Issue 1/2024

Clinical presentation and surgical outcomes of very large and giant pituitary adenomas: 80 cases in a cohort study of 306 patients with pituitary adenomas

Intra-operative extracorporeal irradiation of tumour-invaded craniotomy bone flap in meningioma: a case series

Coronal vertical fracture of vertebral body following minimally invasive lateral lumbar interbody fusion: risk factor analysis in consecutive case series

Obituary Ronald L. Hayes

A novel lateral myelotomy approach for the treatment of lateral or ventrolateral spinal gliomas

The diagnostic yield of inferior petrosal sinus sampling in Cushing syndrome in the era of ovine CRH shortage