nmODE-Unet: A Novel Network for Semantic Segmentation of Medical Images
Source abstract
Abstract
Diabetic retinopathy is a prevalent eye disease that poses a potential risk of blindness. Nevertheless, due to the small size of diabetic retinopathy lesions and the high interclass similarity in terms of location, color, and shape among different lesions, the segmentation task is highly challenging. To address these issues, we proposed a novel framework named nmODE-Unet, which is based on the nmODE (neural memory Ordinary Differential Equation) block and U-net backbone. In nmODE-Unet, the shallow features serve as input to the nmODE block, and the output of the nmODE block is fused with the corresponding deep features. Extensive experiments were conducted on the IDRiD dataset, e_ophtha dataset, and the LGG segmentation dataset, and the results demonstrate that, in comparison to other competing models, nmODE-Unet showcases a superior performance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Retinal Imaging and Analysis · Medical Image Segmentation Techniques · COVID-19 diagnosis using AI
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Intelligent Interdisciplinary Research Center and College of Computer Science, Sichuan University, Chengdu 610065, China
Funding
National Natural Science Foundation of China · National Major Science and Technology Projects of China
References (36)
Show source-provided references
1. Diabetic retinopathy: Global prevalence, major risk factors, screening practices and public health challenges: A review10.1111/ceo.12696 ↗
2. Diabetic retinopathy and diabetic macular edema: Pathophysiology, screening, and novel therapies10.2337/diacare.26.9.2653 ↗
3. (2018, January 25–29). Avula Benzamin and Chandan Chakraborty. Detection of hard exudates in retinal fundus images using deep learning. Proceedings of the 2018 Joint 7th International Conference on Informatics, Electronics & Vision (ICIEV) and 2018 2nd International Conference on Imaging, Vision & Pattern Recognition (icIVPR), Kitakyushu, Japan.
4. A new deep learning approach for the retinal hard exudates detection based on superpixel multi-feature extraction and patch-based cnn10.1016/j.neucom.2020.07.145 ↗
5. A review on exudates detection methods for diabetic retinopathy10.1016/j.biopha.2017.11.009 ↗
6. Hard exudate segmentation in retinal image with attention mechanism10.1049/ipr2.12007 ↗
7. Uniconv: An enhanced u-net based inceptionv3 convolutional model for dr semantic segmentation in retinal fundus images10.1002/cpe.7138 ↗
8. Modified u-net architecture for semantic segmentation of diabetic retinopathy images10.1016/j.bbe.2020.05.006 ↗
9. Diabetic retinopathy: Present and past10.1016/j.procs.2018.05.074 ↗
10. Clinical report guided retinal microaneurysm detection with multi-sieving deep learning10.1109/TMI.2018.2794988 ↗
11. Microaneurysm detection using deep learning and interleaved freezing
12. Sarhan, M.H., Albarqouni, S., Yigitsoy, M., Navab, N., and Eslami, A. (2019, January 13–17). Multi-scale microaneurysms segmentation using embedding triplet loss. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Shenzhen, China.10.1007/978-3-030-32239-7_20 ↗
13. Perumal, T.S.R., Jayachandran, A., and Kumar, S.R. (2023). Microaneurysms detection in fundus images using local fourier transform and neighbourhood analysis. Knowl. Inf. Syst., 1–21.10.1007/s10115-023-01991-7 ↗
14. Deep membrane systems for multitask segmentation in diabetic retinopathy10.1016/j.knosys.2019.104887 ↗
15. Lin, T., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
16. Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K. (2017, January 21–26). Aggregated residual transformations for deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.634 ↗
17. He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017, January 22–29). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.322 ↗
18. L-seg: An end-to-end unified framework for multi-lesion segmentation of fundus images10.1016/j.neucom.2019.04.019 ↗
19. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
20. Automated lesion segmentation in fundus images with many-to-many reassembly of features10.1016/j.patcog.2022.109191 ↗
21. Deep high-resolution representation learning for visual recognition10.1109/TPAMI.2020.2983686 ↗
22. Chen, R.T.Q., Rubanova, Y., Bettencourt, J., and Duvenaud, D.K. (2018). Advances in Neural Information Processing Systems, Curran Associates, Inc.
23. Poli, M., Massaroli, S., Park, J., Yamashita, A., Asama, H., and Park, J. (2019). Graph neural ordinary differential equations. arXiv.
24. Li, X., Wong, T.L., Chen, R.T.Q., and Duvenaud, D. (2020, January 26–28). Scalable gradients for stochastic differential equations. Proceedings of the International Conference on Artificial Intelligence and Statistics, Palermo, Italy.
25. nmode: Neural memory ordinary differential equation10.1007/s10462-023-10496-2 ↗
26. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany. Proceedings, Part III 18.
27. Porwal, P., Pachade, S., Kamble, R., Kokare, M., Deshmukh, G., Sahasrabuddhe, V., and Meriaudeau, F. (2018). Indian diabetic retinopathy image dataset (idrid): A database for diabetic retinopathy screening research. Data, 3.10.3390/data3030025 ↗
28. Teleophta: Machine learning and image processing methods for teleophthalmology10.1016/j.irbm.2013.01.010 ↗
29. Radiogenomics of lower-grade glioma: Algorithmically-assessed tumor shape is associated with tumor genomic subtypes and patient outcomes in a multi-institutional study with the cancer genome atlas data10.1007/s11060-017-2420-1 ↗
30. Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm10.1016/j.compbiomed.2019.05.002 ↗
31. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
32. Chen, L., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8–14). Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_49 ↗
33. Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., and Liang, J. (2018, January 20). Unet++: A nested u-net architecture for medical image segmentation. Proceedings of the Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain. Proceedings 4.
34. Bo, W., Li, T., Liu, X., and Wang, K. (2022, January 28–31). Saa: Scale-aware attention block for multi-lesion segmentation of fundus images. Proceedings of the 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), Kolkata, India.10.1109/ISBI52829.2022.9761529 ↗
35. Carnet: Cascade attentive refinenet for multi-lesion segmentation of diabetic retinopathy images10.1007/s40747-021-00630-4 ↗
36. Ma, J., and Wang, B. (2023). Segment anything in medical images. arXiv.