Segmentation of Substantia Nigra in Brain Parenchyma Sonographic Images Using Deep Learning
Abstract
:1. Introduction
2. Related Work
3. Materials and Methods
3.1. BPS Imaging
3.2. Selection of CNN Models
3.3. Data Preparation
3.4. The Pre-Training Stage
3.5. The Training Stage
- from scratch;
- fine tuning after pre-training on Ultrasound Nerve dataset;
- transfer learning (from Ultrasound Nerve dataset) freezing encoder or decoder.
4. Results
5. Discussion
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
BPS | Brain Parenchyma Sonography |
CAD | Computer Aided Detection |
CNN | Convolutional Neural Networks |
DL | Deep Learning |
DSC | Dice Coefficient |
MRI | Magnetic Resonance Imaging |
MSA | Multiple System Atrophy |
PD | Parkinson’s Disease |
PET | Positron Emission Tomography |
SN | Substantia Nigra |
SPECT | Single Photon Emission Computer Tomography |
TCS | Transcranial Sonography |
US | Ultrasound |
References
- Fearnley, J.M.; Lees, A.J. Ageing and Parkinson’s disease: Substantia nigra regional selectivity. Brain 1991, 114, 2283–2301. [Google Scholar] [CrossRef]
- Postuma, R.B.; Berg, D.; Stern, M.; Poewe, W.; Olanow, C.W.; Oertel, W.; Obeso, J.; Marek, K.; Litvan, I.; Lang, A.E.; et al. MDS clinical diagnostic criteria for Parkinson’s disease. Mov. Disord. 2015, 30, 1591–1601. [Google Scholar] [CrossRef] [PubMed]
- Rizzo, G.; Copetti, M.; Arcuti, S.; Martino, D.; Fontana, A.; Logroscino, G. Accuracy of clinical diagnosis of Parkinson disease: A systematic review and meta-analysis. Neurology 2016, 86, 566–576. [Google Scholar] [CrossRef] [PubMed]
- Hughes, A.J.; Daniel, S.E.; Kilford, L.; Lees, A.J. Accuracy of clinical diagnosis of idiopathic Parkinson’s disease: A clinico-pathological study of 100 cases. J. Neurol. Neurosurg. Psychiatry 1992, 55, 181–184. [Google Scholar] [CrossRef] [PubMed]
- Piccini, P.; Whone, A. Functional brain imaging in the differential diagnosis of Parkinson’s disease. Lancet Neurol. 2004, 3, 284–290. [Google Scholar] [CrossRef]
- Berg, D.; Siefker, C.; Becker, G. Echogenicity of the substantia nigra in Parkinson’s disease and its relation to clinical findings. J. Neurol. 2001, 248, 684–689. [Google Scholar] [CrossRef]
- Becker, G.; Seufert, J.; Bogdahn, U.; Reichmann, H.; Reiners, K. Degeneration of substantia nigra in chronic Parkinson’s disease visualized by transcranial color-coded real-time sonography. Neurology 1995, 45, 182–184. [Google Scholar] [CrossRef]
- Gaenslen, A.; Unmuth, B.; Godau, J.; Liepelt, I.; Di Santo, A.; Schweitzer, K.J.; Gasser, T.; Machulla, H.J.; Reimold, M.; Marek, K.; et al. The specificity and sensitivity of transcranial ultrasound in the differential diagnosis of Parkinson’s disease: A prospective blinded study. Lancet Neurol. 2008, 7, 417–424. [Google Scholar] [CrossRef]
- Berg, D.; Becker, G.; Zeiler, B.; Tucha, O.; Hofmann, E.; Preier, M.; Benz, P.; Jost, W.; Reiners, K.; Lange, K. Vulnerability of the nigrostriatal system as detected by transcranial ultrasound. Neurology 1999, 53, 1026–1031. [Google Scholar] [CrossRef]
- Školoudík, D.; Walter, U. Method and validity of transcranial sonography in movement disorders. Int. Rev. Neurobiol. 2010, 90, 7–34. [Google Scholar]
- Berg, D.; Merz, B.; Reiners, K.; Naumann, M.; Becker, G. Five-year follow-up study of hyperechogenicity of the substantia nigra in Parkinson’s disease. Mov. Disord. 2005, 20, 383–385. [Google Scholar] [CrossRef]
- Berg, D. Ultrasound in the (premotor) diagnosis of Parkinson’s disease. Park. Relat. Disord. 2007, 13, S429–S433. [Google Scholar] [CrossRef] [PubMed]
- Goodfellow, I.J.; Bengio, Y.; Courville, A. Deep Learning; MIT Press: Cambridge, MA, USA, 2016; Available online: http://www.deeplearningbook.org (accessed on 1 September 2023).
- Minaee, S.; Boykov, Y.; Porikli, F.; Plaza, A.; Kehtarnavaz, N.; Terzopoulos, D. Image Segmentation Using Deep Learning: A Survey. IEEE Trans. Pattern Anal. Mach. Intell. 2022, 44, 3523–3542. [Google Scholar] [CrossRef] [PubMed]
- Ronneberger, O.; Fischer, P.; Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5–9 October 2015; pp. 234–241. [Google Scholar]
- Ronneberger, O. Invited talk: U-net convolutional networks for biomedical image segmentation. In Bildverarbeitung für die Medizin 2017; Springer: Berlin/Heidelberg, Germany, 2017; p. 3. [Google Scholar]
- Chen, L.C.; Zhu, Y.; Papandreou, G.; Schroff, F.; Adam, H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 801–818. [Google Scholar]
- Kier, C.; Cyrus, C.; Seidel, G.; Hofmann, U.G.; Aach, T. Segmenting the substantia nigra in ultrasound images for early diagnosis of Parkinson’s disease. Int. J. Comput. Assist. Radiol. Surg. 2007, 2, S83. [Google Scholar]
- Sakalauskas, A.; Lukoševičius, A.; Laučkaitė, K.; Jegelevičius, D.; Rutkauskas, S. Automated segmentation of transcranial sonographic images in the diagnostics of Parkinson’s disease. Ultrasonics 2013, 53, 111–121. [Google Scholar] [CrossRef]
- Xu, C.; Prince, J. Snakes, shapes, and gradient vector flow. IEEE Trans. Image Process. 1998, 7, 359–369. [Google Scholar]
- Kass, M.; Witkin, A.; Terzopoulos, D. Snakes: Active contour models. Int. J. Comput. Vis. 1988, 1, 321–331. [Google Scholar] [CrossRef]
- Ahmadi, S.A.; Baust, M.; Karamalis, A.; Plate, A.; Boetzel, K.; Klein, T.; Navab, N. Midbrain segmentation in transcranial 3D ultrasound for Parkinson diagnosis. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Toronto, ON, Canada, 18–22 September 2011; pp. 362–369. [Google Scholar]
- Milletari, F.; Ahmadi, S.A.; Kroll, C.; Hennersperger, C.; Tombari, F.; Shah, A.; Plate, A.; Boetzel, K.; Navab, N. Robust segmentation of various anatomies in 3d ultrasound using hough forests and learned data representations. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5–9 October 2015; pp. 111–118. [Google Scholar]
- Chen, H.; Zheng, Y.; Park, J.H.; Heng, P.A.; Zhou, S.K. Iterative multi-domain regularized deep learning for anatomical structure detection and segmentation from ultrasound images. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Athens, Greece, 17–21 October 2016; pp. 487–495. [Google Scholar]
- Juknevicius, A.R.; Sakalauskas, A. Algorithm for the detection of the mid-brain in B mode ultrasound images. In Proceedings of the Biomedical Engineering 2016, Kaunas, Lithuania, 24–25 November 2016; Volume 20. [Google Scholar]
- Sakalauskas, A.; Špečkauskienė, V.; Laučkaitė, K.; Jurkonis, R.; Rastenytė, D.; Lukoševičius, A. Transcranial ultrasonographic image analysis system for decision support in parkinson disease. J. Ultrasound Med. 2018, 37, 1753–1761. [Google Scholar] [CrossRef]
- Shen, L.; Farid, H.; McPeek, M.A. Modeling three-dimensional morphological structures using spherical harmonics. Evolution 2009, 63, 1003–1016. [Google Scholar] [CrossRef]
- Pauly, O.; Ahmadi, S.A.; Plate, A.; Boetzel, K.; Navab, N. Detection of substantia nigra echogenicities in 3D transcranial ultrasound for early diagnosis of Parkinson disease. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Nice, France, 1–5 October 2012; pp. 443–450. [Google Scholar]
- Rackerseder, J.; Göbl, R.; Navab, N.; Hennersperger, C. Fully automatic segmentation of 3D brain ultrasound: Learning from coarse annotations. arXiv 2019, arXiv:1904.08655. [Google Scholar]
- Anwar, S.M.; Majid, M.; Qayyum, A.; Awais, M.; Alnowami, M.; Khan, M.K. Medical image analysis using convolutional neural networks: A review. J. Med. Syst. 2018, 42, 226. [Google Scholar] [CrossRef] [PubMed]
- Alzubaidi, M.S.; Shah, U.; Dhia Zubaydi, H.; Dolaat, K.; Abd-Alrazaq, A.A.; Ahmed, A.; Househ, M. The role of neural network for the detection of Parkinson’s disease: A scoping review. Healthcare 2021, 9, 740. [Google Scholar] [CrossRef] [PubMed]
- Chen, G.; Dai, Y.; Zhang, J. C-Net: Cascaded convolutional neural network with global guidance and refinement residuals for breast ultrasound images segmentation. Comput. Methods Programs Biomed. 2022, 225, 107086. [Google Scholar] [CrossRef] [PubMed]
- Lin, X.; Zhou, X.; Tong, T.; Nie, X.; Wang, L.; Zheng, H.; Li, J.; Xue, E.; Chen, S.; Zheng, M.; et al. A Super-resolution Guided Network for Improving Automated Thyroid Nodule Segmentation. Comput. Methods Programs Biomed. 2022, 227, 107186. [Google Scholar] [CrossRef] [PubMed]
- Guo, S.; Liu, X.; Zhang, H.; Lin, Q.; Xu, L.; Shi, C.; Gao, Z.; Guzzo, A.; Fortino, G. Causal knowledge fusion for 3D cross-modality cardiac image segmentation. Inf. Fusion 2023, 99, 101864. [Google Scholar] [CrossRef]
- Shanila, N.; Kumar, R.V.; Ravi, R.R. Segmentation of liver computed tomography images using dictionary-based snakes. Int. J. Biomed. Eng. Technol. 2022, 39, 283–296. [Google Scholar] [CrossRef]
- Guo, J.; Odu, A.; Pedrosa, I. Deep learning kidney segmentation with very limited training data using a cascaded convolution neural network. PLoS ONE 2022, 17, e0267753. [Google Scholar] [CrossRef] [PubMed]
- Gibson, E.; Li, W.; Sudre, C.; Fidon, L.; Shakir, D.I.; Wang, G.; Eaton-Rosen, Z.; Gray, R.; Doel, T.; Hu, Y.; et al. NiftyNet: A deep-learning platform for medical imaging. Comput. Methods Programs Biomed. 2018, 158, 113–122. [Google Scholar] [CrossRef]
- Deng, J.; Dong, W.; Socher, R.; Li, L.J.; Li, K.; Li, F.-F. Imagenet: A large-scale hierarchical image database. In Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 20–25 June 2009; pp. 248–255. [Google Scholar]
- Everingham, M.; Van Gool, L.; Williams, C.K.I.; Winn, J.; Zisserman, A. The Pascal Visual Object Classes (VOC) Challenge. Int. J. Comput. Vis. 2010, 88, 303–338. [Google Scholar] [CrossRef]
- Cordts, M.; Omran, M.; Ramos, S.; Rehfeld, T.; Enzweiler, M.; Benenson, R.; Franke, U.; Roth, S.; Schiele, B. The Cityscapes Dataset for Semantic Urban Scene Understanding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016. [Google Scholar]
- Parkhi, O.M.; Vedaldi, A.; Zisserman, A.; Jawahar, C.V. The Oxford-IIIT Pet Dataset. Available online: https://www.robots.ox.ac.uk/~vgg/data/pets/ (accessed on 1 July 2022).
- kaggle.com. Kaggle Competition: Ultrasound Nerve Segmentation. Available online: https://www.kaggle.com/competitions/ultrasound-nerve-segmentation/ (accessed on 1 July 2022).
- Walter, U.; Školoudík, D. Transcranial sonography (TCS) of brain parenchyma in movement disorders: Quality standards, diagnostic applications and novel technologies. Ultraschall Der Med.-Eur. J. Ultrasound 2014, 35, 322–331. [Google Scholar] [CrossRef]
- Walter, U.; Behnke, S.; Eyding, J.; Niehaus, L.; Postert, T.; Seidel, G.; Berg, D. Transcranial brain parenchyma sonography in movement disorders: State of the art. Ultrasound Med. Biol. 2007, 33, 15–25. [Google Scholar] [CrossRef] [PubMed]
- Khan, M.Z.; Gajendran, M.K.; Lee, Y.; Khan, M.A. Deep neural architectures for medical image semantic segmentation. IEEE Access 2021, 9, 83002–83024. [Google Scholar] [CrossRef]
- Bianconi, F.; Fravolini, M.L.; Pizzoli, S.; Palumbo, I.; Minestrini, M.; Rondini, M.; Nuvoli, S.; Spanu, A.; Palumbo, B. Comparative evaluation of conventional and deep learning methods for semi-automated segmentation of pulmonary nodules on CT. Quant. Imaging Med. Surg. 2021, 11, 3286. [Google Scholar] [CrossRef] [PubMed]
- Behboodi, B.; Rivaz, H. Ultrasound segmentation using u-net: Learning from simulated data and testing on real data. In Proceedings of the 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, 23–27 July 2019; pp. 6628–6631. [Google Scholar]
- Amiri, M.; Brooks, R.; Rivaz, H. Fine-tuning U-Net for ultrasound image segmentation: Different layers, different outcomes. IEEE Trans. Ultrason. Ferroelectr. Freq. Control 2020, 67, 2510–2518. [Google Scholar] [CrossRef]
- Zhao, H.; Sun, N. Improved U-net model for nerve segmentation. In Proceedings of the International Conference on Image and Graphics, Quebec City, QC, Canada, 11–13 September 2017; Springer: Cham, Switzerland, 2017; pp. 496–504. [Google Scholar]
- Chen, L.C.; Papandreou, G.; Schroff, F.; Adam, H. Rethinking atrous convolution for semantic image segmentation. arXiv 2017, arXiv:1706.05587. [Google Scholar]
- bonline. Keras Implementation of Deeplabv3+. Available online: https://github.com/bonlime/keras-deeplab-v3-plus/ (accessed on 8 September 2022).
- Bhatia, V. Ultrasound Nerve Seg—UNET from Scratch. Available online: https://www.kaggle.com/code/vidushibhatia/2-ultrasound-nerve-seg-unet-from-scratch/ (accessed on 8 September 2022).
- Yap, M.H.; Goyal, M.; Osman, F.M.; Martí, R.; Denton, E.; Juette, A.; Zwiggelaar, R. Breast ultrasound lesions recognition: End-to-end deep learning approaches. J. Med. Imaging 2018, 6, 011007. [Google Scholar]
Male | Female | ||||
---|---|---|---|---|---|
n. | % | n. | % | Total | |
Patients | 14 | 60.9% | 9 | 39.1% | 23 |
Healthy Controls | 4 | 50.0% | 4 | 50.0% | 8 |
Total | 18 | 58.1% | 13 | 41.9% | 31 |
Dataset | # of Images | Reference |
---|---|---|
ImageNet ILSVRC2016 | 20,000 | [38] |
PASCAL VOC | 7000 | [39] |
Cityscapes | 25,000 | [40] |
Oxford-IIIT PET | 7300 | [41] |
Nerves Ultrasound | 5600 | [42] |
Parkinson (our) | 63 | This article |
# of Samples | % | |
---|---|---|
Training | 43 | 70% |
Validation | 6 | 10% |
Testing | 12 | 20% |
Total | 61 | 100% |
U-Net | DeepLabV3+/Xception | |
---|---|---|
Horizontal Flip | 0.819 | 0.540 |
Horizontal Flip + Rotation | 0.6452 | N/A |
Horizontal Flip + Translation | N/A | N/A |
Network Model | PASCAL VOC | Cityscapes | None |
---|---|---|---|
DeepLabV3+/MobileNetv2 | 0.5406 ± 0.0156 | 0.5436 ± 0.0041 | 0.5436 ± 0.0041 |
DeepLabV3+/Xception | 0.4815 ± 0.1441 | 0.5437 ± 0.0041 | 0.5400 ± 0.0 |
Network | A. From Scratch | B. Fine Tuning | C. Transfer Learning | |||
---|---|---|---|---|---|---|
Mean | SD | Mean | SD | Mean | SD | |
U-Net | 0.819 | 0.11 | 0.806 | 0.152 | 0.859 | 0.037 |
DeepLabV3+ | 0.540 | 0.0 | 0.687 | 0.143 | N/A | N/A |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Gusinu, G.; Frau, C.; Trunfio, G.A.; Solla, P.; Sechi, L.A. Segmentation of Substantia Nigra in Brain Parenchyma Sonographic Images Using Deep Learning. J. Imaging 2024, 10, 1. https://doi.org/10.3390/jimaging10010001
Gusinu G, Frau C, Trunfio GA, Solla P, Sechi LA. Segmentation of Substantia Nigra in Brain Parenchyma Sonographic Images Using Deep Learning. Journal of Imaging. 2024; 10(1):1. https://doi.org/10.3390/jimaging10010001
Chicago/Turabian StyleGusinu, Giansalvo, Claudia Frau, Giuseppe A. Trunfio, Paolo Solla, and Leonardo Antonio Sechi. 2024. "Segmentation of Substantia Nigra in Brain Parenchyma Sonographic Images Using Deep Learning" Journal of Imaging 10, no. 1: 1. https://doi.org/10.3390/jimaging10010001