Improving motion-mask segmentation in thoracic CT with multiplanar U-nets.
deep learning
segmentation
thoracic CT
Journal
Medical physics
ISSN: 2473-4209
Titre abrégé: Med Phys
Pays: United States
ID NLM: 0425746
Informations de publication
Date de publication:
Jan 2022
Jan 2022
Historique:
revised:
30
09
2021
received:
03
05
2021
accepted:
19
10
2021
pubmed:
16
11
2021
medline:
18
1
2022
entrez:
15
11
2021
Statut:
ppublish
Résumé
Motion-mask segmentation from thoracic computed tomography (CT) images is the process of extracting the region that encompasses lungs and viscera, where large displacements occur during breathing. It has been shown to help image registration between different respiratory phases. This registration step is, for example, useful for radiotherapy planning or calculating local lung ventilation. Knowing the location of motion discontinuity, that is, sliding motion near the pleura, allows a better control of the registration preventing unrealistic estimates. Nevertheless, existing methods for motion-mask segmentation are not robust enough to be used in clinical routine. This article shows that it is feasible to overcome this lack of robustness by using a lightweight deep-learning approach usable on a standard computer, and this even without data augmentation or advanced model design. A convolutional neural-network architecture with three 2D U-nets for the three main orientations (sagittal, coronal, axial) was proposed. Predictions generated by the three U-nets were combined by majority voting to provide a single 3D segmentation of the motion mask. The networks were trained on a database of nonsmall cell lung cancer 4D CT images of 43 patients. Training and evaluation were done with a K-fold cross-validation strategy. Evaluation was based on a visual grading by two experts according to the appropriateness of the segmented motion mask for the registration task, and on a comparison with motion masks obtained by a baseline method using level sets. A second database (76 CT images of patients with early-stage COVID-19), unseen during training, was used to assess the generalizability of the trained neural network. The proposed approach outperformed the baseline method in terms of quality and robustness: the success rate increased from With 5-s processing time on a mid-range GPU and success rates around
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
420-431Subventions
Organisme : Agence Nationale de la Recherche
ID : ANR-11-LABX-0063
Organisme : Grand Équipement National De Calcul Intensif
ID : 2019-101203
Organisme : Institut National de la Santé et de la Recherche Médicale
ID : INCa-INSERM-DGOS-12563
Informations de copyright
© 2021 American Association of Physicists in Medicine.
Références
McClelland JR, Modat M, Arridge S, et al. A generalized framework unifying image registration and respiratory motion models and incorporating image reconstruction, for partial image data or full images. Phys Med Biol. 2017;62:4273-4292.
Guy C, Weiss E, Christensen G, Jan N, Hugo G. CALIPER: a deformable image registration algorithm for large geometric changes during radiotherapy for locally advanced nonsmall cell lung cancer. Med Phys. 2018;45:2498-2508.
Chae KJ, Choi J, Jin GY, et al. Relative regional air volume change maps at the acinar scale reflect variable ventilation in low lung attenuation of COPD patients. Acad Radiol. 2020;27:1540-1548.
Orkisz M, Morales Pinzón A, Richard J-C, et al. Voxel-wise assessment of lung aeration changes on CT images using image registration: application to acute respiratory distress syndrome (ARDS). Int J Comput Assist Radiol Surg. 2019;14:1945-1953.
Sotiras A, Davatzikos C, Paragios N. Deformable medical image registration: a survey. IEEE Trans Med Imaging. 2013;32:1153-1190.
Sarrut D, Baudier T, Ayadi M, Tanguy R, Rit S. Deformable image registration applied to lung SBRT: usefulness and limitations. Physica Med. 2017;44:108-112.
Wu Z, Rietzel E, Boldea V, Sarrut D, Sharp GC. Evaluation of deformable registration of patient lung 4DCT with subanatomical region segmentations: evaluation of deformable registration of 4DCT with segmentations. Med Phys. 2008;35:775-781.
Schmidt-Richberg A, Ehrhardt J, Werner R, Handels H. Slipping objects in image registration: improved motion field estimation with direction-dependent regularization. In: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2009, LNCS 5761 (London, UK), Springer; 2009:755-762.
Delmon V, Rit S, Pinho R, Sarrut D. Registration of sliding objects using direction dependent B-splines decomposition. Phys Med Biol. 2013;58:1303-1314.
Derksen A, Heldmann S, Polzin T, Berkels B. Image registration with sliding motion constraints for 4D CT motion correction. In: Informatik Aktuell - Bildverarbeitung für die Medizin 2015 (Lübeck, Germany), Springer, Vieweg; 2015:335-340.
Hua R, Pozo JM, Taylor ZA, Frangi AF. Multiresolution eXtended Free-Form Deformations (XFFD) for non-rigid registration with discontinuous transforms. Med Image Anal. 2017;36:113-122.
Vandemeulebroucke J, Bernard O, Rit S, Kybic J, Clarysse P, Sarrut D. Automated segmentation of a motion mask to preserve sliding motion in deformable registration of thoracic CT. Med Phys. 2012;39:1006-1015.
Morales Pinzón A, Orkisz M, Richard J-C, Hernández Hoyos M. Lung segmentation by cascade registration. IRBM. 2017;38:266-280.
Ayadi M, Baudier T, Bouilhol G, et al. Mid-position treatment strategy for locally advanced lung cancer: a dosimetric study. Br J Radiol. 2020;93:20190692.
Litjens G, Kooi T, Ehteshami Bejnordi B, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60-88.
Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, LNCS 9351 (Munich, Germany), Springer; 2015:234-241.
Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O. 3D U-net: learning dense volumetric segmentation from sparse annotation. Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016, LNCS 9901 (Athens, Greece), Springer; 2016:424-432.
Milletari F, Navab N, Ahmadi S-A. V-net: fully convolutional neural networks for volumetric medical image segmentation. In: Fourth International Conference on 3D Vision - 3DV (Stanford, CA, USA), IEEE; 2016:565-571.
Li X, Chen H, Qi X, Dou Q, Fu C-W, Heng P-A. H-DenseUNet: hybrid densely connected unet for liver and liver tumor segmentation from CT volumes. IEEE Trans Med Imaging. 2018;37:2663-2674.
Isensee F, Petersen J, Klein A, et al. nnU-netself-adapting framework for U-net-based medical image segmentation. In: Informatik aktuell - Bildverarbeitung für die Medizin (Lübeck, Germany), Vieweg, Springer; 2018.
Gerard SE, Herrmann J, Kaczka DW, Musch G, Fernandez-Bustamante A, Reinhardt JM. Multiresolution convolutional neural networks for fully automated segmentation of acutely injured lungs in multiple species. Med Image Anal. 2020;60:101592.
Moeskops P, Wolterink JM, Van der Velden BH, et al. Deep learning for multi-task medical image segmentation in multiple modalities. In: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016, LNCS 9901 (Athens, Greece), Springer; 2016:478-486.
Lyksborg M, Puonti O, Agn M, Larsen R. An ensemble of 2D convolutional neural networks for tumor segmentation. In: Scandinavian Conference on Image Analysis - SCIA 2015, LNCS 9127 (Copenhagen, Denmark), Springer; 2015:201-211.
Prasoon A, Petersen K, Igel C, Lauze F, Dam E, Nielsen M. Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network. In: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013, LNCS 8150 (Nagoya, Japan), Springer; 2013:246-253.
Automatic liver lesion segmentation using A deep convolutional neural network method. arXiv:abs/1704.07239 (2017).
Wardhana G, Naghibi H, Sirmacek B, Abayazid M. Toward reliable automatic liver and tumor segmentation using convolutional neural network based on 2.5D models. Int J Comput Assist Radiol Surg. 2020;16:41-51.
Perslev M, Dam EB, Pai A, Igel C. One network to segment them all: A general, lightweight system for accurate 3D medical image segmentation. In: Medical Image Computing and Computer Assisted Intervention - MICCAI 2019, LNCS 11765 (Shenzhen, China), Springer; 2019:30-38.
Roth HR, Lu L, Seff A, et al. A new 2.5D representation for lymph node detection using random sets of deep convolutional neural network observations. In: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2014, LNCS 8673 (Boston, MA, USA), Springer; 2014:520-527.
Kingma DP, Ba J. Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations - ICLR (San Diego, CA, USA) (2015).
Taha AA, Hanbury A. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med Imaging. 2015;15.
Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O. 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016, LNCS 9901 Springer International Publishing; 2016:424-432.
McHugh ML. Interrater reliability: the kappa statistic. Biochem Med. 2012;22:276-282.