Abstract
To save patients’ lives, it is important to go for an early diagnosis of intracranial hemorrhage (ICH). For diagnosing ICH, the widely used method is non-contrast computed tomography (NCCT). It has fast acquisition and availability in medical emergency facilities. To predict hematoma progression and mortality, it is important to estimate the volume of intracranial hemorrhage. Radiologists can manually delineate the ICH region to estimate the hematoma volume. This process takes time and undergoes inter-rater variability. In this research paper, we develop and discuss a fine segmentation model and a coarse model for intracranial hemorrhage segmentations. Basically, two different models are discussed for intracranial hemorrhage segmentation. We trained a 2DDensNet in the first model for coarse segmentation and cascaded the coarse segmentation mask output in the fine segmentation model along with input training samples. A nnUNet model is trained in the second fine stage and will use the segmentation labels of the coarse model with true labels for intracranial hemorrhage segmentation. An optimal performance for intracranial hemorrhage segmentation solution is obtained.
Keywords
coarse; segmentation; artery segmentation; nnUNet; deep learning
References
Van Asch CJJ, Luitse MJA, Rinkel GJE, et al. Incidence, case fatality, and functional outcome of intracerebral haemorrhage over time, according to age, sex, and ethnic origin: A systematic review and meta-analysis. The Lancet Neurology 2010; 9(2): 167–176. doi: 10.1016/S1474-4422(09)70340-0
Goldstein JN, Gilson AJ. Critical care management of acute intracerebral hemorrhage. Current Treatment Options in Neurology 2011; 13: 204–216. doi: 10.1007/s11940-010-0109-2
Kothari RU, Brott T, Broderick JP, et al. The ABCs of measuring intracerebral hemorrhage volumes. Stroke 1996; 27(8): 1304–1305. doi: 10.1161/01.STR.27.8.1304
Payette K, Li HB, de Dumast P, et al. Fetal brain tissue annotation and segmentation challenge results. Medical Image Analysis 2023; 88: 102833. doi: 10.1016/j.media.2023.102833
Ma J, Zhang Y, Gu S, et al. Fast and low-GPU-memory abdomen CT organ segmentation: The flare challenge. Medical Image Analysis 2022; 82: 102616. doi: 10.1016/j.media.2022.102616
Lalande A, Chen Z, Pommier T, et al. Deep learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge. Medical Image Analysis 2022; 79: 102428. doi: 10.1016/j.media.2022.102428
Noreen N, Palaniappan S, Qayyum A, et al. Brain tumor classification based on fine-tuned models and the ensemble method. Computers, Materials & Continua 2021; 67(3): 3967–3982. doi: 10.32604/cmc.2021.014158
Chen Z, Lalande A, Salomon M, et al. Automatic deep learning-based myocardial infarction segmentation from delayed enhancement MRI. Computerized Medical Imaging and Graphics 2022; 95: 102014. doi: 10.1016/j.compmedimag.2021.102014
Bano S, Vasconcelos F, Stoyanov D. FetReg2021: A challenge on placental vessel segmentation and registration in fetoscopy. Available online: https://discovery.ucl.ac.uk/id/eprint/10157782/ (accessed on 25 October 2023)
Isensee F, Jaeger PF, Kohl SAA, et al. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nature Methods 2021; 18(2): 203–211. doi: 10.1038/s41592-020-01008-z
Li X, Luo G, Wang W, et al. Hematoma expansion context guided intracranial hemorrhage segmentation and uncertainty estimation. IEEE Journal of Biomedical and Health Informatics 2021; 26(3): 1140–1151. doi: 10.1109/JBHI.2021.3103850
Li X, Wang K, Liu J, et al. The 2022 intracranial hemorrhage segmentation challenge on non-contrast head CT (NCCT). Available online: https://zenodo.org/records/6362221 (accessed on 25 October 2023).
