Convolutional Neural Network-Based Automatic Segmentation of Substantia Nigra on Nigrosome and Neuromelanin Sensitive MR Images
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Recently, neuromelanin and nigrosome imaging techniques have been developed to evaluate the substantia nigra in Parkinson’s disease. Previous studies have shown potential benefits of quantitative analysis of neuromelanin and nigrosome images in the substantia nigra, although visual assessments have been performed to evaluate structures in most studies. In this study, we investigate the potential of using deep learning based automatic region segmentation techniques for quantitative analysis of the substantia nigra. The deep convolutional neural network was trained to automatically segment substantia nigra regions on 3D nigrosome and neuromelanin sensitive MR images obtained from 30 subjects. With a 5-fold cross-validation, the mean calculated dice similarity coefficient between manual and deep learning was 0.70 ± 0.11. Although calculated dice similarity coefficients were relatively low due to empirically drawn margins, selected slices were overlapped for more than two slices of all subjects. Our results demonstrate that deep convolutional neural network-based method could provide reliable localization of substantia nigra regions on neuromelanin and nigrosome sensitive MR images.
Abstract
Recently, neuromelanin and nigrosome imaging techniques have been developed to evaluate the substantia nigra in Parkinson’s disease. Previous studies have shown potential benefits of quantitative analysis of neuromelanin and nigrosome images in the substantia nigra, although visual assessments have been performed to evaluate structures in most studies. In this study, we investigate the potential of using deep learning based automatic region segmentation techniques for quantitative analysis of the substantia nigra. The deep convolutional neural network was trained to automatically segment substantia nigra regions on 3D nigrosome and neuromelanin sensitive MR images obtained from 30 subjects. With a 5-fold cross-validation, the mean calculated dice similarity coefficient between manual and deep learning was 0.70 ± 0.11. Although calculated dice similarity coefficients were relatively low due to empirically drawn margins, selected slices were overlapped for more than two slices of all subjects. Our results demonstrate that deep convolutional neural network-based method could provide reliable localization of substantia nigra regions on neuromelanin and nigrosome sensitive MR images.
참고문헌 (13)
- Louis ED, "Alzheimer's disease, Parkinson's disease and essential tremor : three common degenerative diseases with shared mechanisms", Eur J Neurol, 17, pp.765~766 (2010)
- Ungerstedt U, "6-Hydroxy-dopamine induced degeneration of central monoamine neurons", Eur J Pharmacol, 5, pp.107~110 (1968)
- Reimao S, "Substantia nigra neuromelanin magnetic resonance imaging in de novo Parkinson's disease patients", Eur J Neurol, 22, pp.540~546 (2015)
- 조장희, "Review of Recent Advancement of Ultra High Field Magnetic Resonance Imaging: from Anatomy to Tractography", Investigative Magnetic Resonance Imaging, 20(3), pp.141~151 (2016), 대한자기공명의과학회[DOI]
- French ED, "Cannabinoids excite dopamine neurons in the ventral tegmentum and substantia nigra", Neuroreport, 8, pp.649~652 (1997)
- Sofic E, "Selective increase of iron in substantia nigra zona compacta of parkinsonian brains", J Neurochem, 56, pp.978~982 (1991)
- Noh H, "Learning deconvolution network for semantic segmentation", Proceedings of the IEEE International Conference on Computer Vision,, pp.1520~1528 (2015)
- 이두희, "Deep Learning in MR Image Processing", Investigative Magnetic Resonance Imaging, 23(2), pp.81~99 (2019), 대한자기공명의과학회
- Garcia-Garcia A, "A review on deep learning techniques applied to semantic segmentation", arXiv preprint. arXiv:1704.06857, ~ (2017)
- Nam Y, "Imaging of nigrosome 1 in substantia nigra at 3T using multiecho susceptibility map-weighted imaging(SMWI)", J Magn Reson Imaging, 46, pp.528~536 (2017)
- Sung YH, "Differential involvement of nigral subregions in idiopathic parkinson's disease", Hum Brain Mapp, 39, pp.542~553 (2018)
- Milletari F, "V-net: Fully convolutional neural networks for volumetric medical image segmentation", 2016 Fourth International Conference on 3D Vision (3DV) IEEE, pp.565~571 (2016)
- Sudre CH, "Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations", Deep Learn Med Image Anal Multimodal Learn Clin Decis Support, 2017, pp.240~248 (2017)