Detecting Small Anatomical Structures in 3D Knee MRI Segmentation by Fully Convolutional Networks
Source abstract
Abstract
Accurately identifying the pixels of small organs or lesions from magnetic resonance imaging (MRI) has a critical impact on clinical diagnosis. U-net is the most well-known and commonly used neural network for image segmentation. However, the small anatomical structures in medical images cannot be well recognised by U-net. This paper explores the performance of the U-net architectures in knee MRI segmentation to find a relative structure that can obtain high accuracies for both small and large anatomical structures. To maximise the utilities of U-net architecture, we apply three types of components, residual blocks, squeeze-and-excitation (SE) blocks, and dense blocks, to construct four variants of U-net, namely U-net variants. Among these variants, our experiments show that SE blocks can improve the segmentation accuracies of small labels. We adopt DeepLabv3plus architecture for 3D medical image segmentation by equipping SE blocks based on this discovery. The experimental results show that U-net with SE block achieves higher accuracy in parts of small anatomical structures. In contrast, DeepLabv3plus with SE block performs better on the average dice coefficient of small and large labels.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Medical Imaging and Analysis · Advanced X-ray and CT Imaging · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of ICT and Natural Sciences, Faculty of Information Technology and Electrical Engineering, Norwegian University of Science and Technology, 6009 Ålesund, Norway
Sunnmøre MR-Klinikk, 6010 Ålesund, Norway
References (43)
Show source-provided references
1. Panfilov, E., Tiulpin, A., Klein, S., Nieminen, M.T., and Saarakkala, S. (2019, January 27–28). Improving robustness of deep learning based knee mri segmentation: Mixup and adversarial domain adaptation. Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, Seoul, Korea.10.1109/ICCVW.2019.00057 ↗
2. Osteoarthritis year in review 2018: Imaging10.1016/j.joca.2018.12.009 ↗
3. Knee MRI: Vascular pathology10.2214/AJR.14.13422 ↗
4. Subchondral bone as a key target for osteoarthritis treatment10.1016/j.bcp.2011.09.018 ↗
5. Machine Learning Techniques for Quantification of Knee Segmentation from MRI10.1155/2020/6613191 ↗
6. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation10.1038/s41592-020-01008-z ↗
7. Li, Y., Zhao, H., Qi, X., Wang, L., Li, Z., Sun, J., and Jia, J. (2021, January 20–25). Fully Convolutional Networks for Panoptic Segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00028 ↗
8. AdaEn-Net: An ensemble of adaptive 2D–3D Fully Convolutional Networks for medical image segmentation10.1016/j.neunet.2020.03.007 ↗
9. Luo, X., Zeng, W., Fan, W., Zheng, S., Chen, J., Liu, R., Liu, Z., and Chen, Y. (2021, January 15–19). Towards cascaded V-Net for automatic accurate kidney segmentation from abdominal CT images. Proceedings of the Medical Imaging 2021: Image Processing, Online.10.1117/12.2581932 ↗
10. MSS U-Net: 3D segmentation of kidneys and tumors from CT images with a multi-scale supervised U-Net10.1016/j.imu.2020.100357 ↗
11. Zeng, G., Yang, X., Li, J., Yu, L., Heng, P.A., and Zheng, G. (2017, January 10). September. 3D U-net with multi-level deep supervision: Fully automatic segmentation of proximal femur in 3D MR images. Proceedings of the International Workshop on Machine Learning in Medical Imaging, Quebec City, QC, Canada.10.1007/978-3-319-67389-9_32 ↗
12. Zhang, S., Ma, Z., Zhang, G., Lei, T., Zhang, R., and Cui, Y. (2020). Semantic image segmentation with deep convolutional neural networks and quick shift. Symmetry, 12.10.3390/sym12030427 ↗
13. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs10.1109/TPAMI.2017.2699184 ↗
14. Chen, L.C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv Preprint.
15. Chen, L.C., 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, Munich, Germany.10.1007/978-3-030-01234-2_49 ↗
16. Alam, T.M., Shaukat, K., Mahboob, H., Sarwar, M.U., Iqbal, F., Nasir, A., Hameed, I.A., and Luo, S. (2021). A Machine Learning Approach for Identification of Malignant Mesothelioma Etiological Factors in an Imbalanced Dataset. Comput. J.10.1093/comjnl/bxab015 ↗
17. A comparative performance analysis of data resampling methods on imbalance medical data10.1109/ACCESS.2021.3102399 ↗
18. Yang, X., Khushi, M., and Shaukat, K. (2020, January 16–18). Biomarker CA125 Feature Engineering and Class Imbalance Learning Improves Ovarian Cancer Prediction. Proceedings of the 2020 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE), Gold Coast, Australia.10.1109/CSDE50874.2020.9411607 ↗
19. Latif, M.Z., Shaukat, K., Luo, S., Hameed, I.A., Iqbal, F., and Alam, T.M. (2020, January 12–13). Risk factors identification of malignant mesothelioma: A data mining based approach. Proceedings of the 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), Istanbul, Turkey.10.1109/ICECCE49384.2020.9179443 ↗
20. A novel framework for prognostic factors identification of malignant mesothelioma through association rule mining10.1016/j.bspc.2021.102726 ↗
21. The impact of artificial intelligence and robotics on the future employment opportunities
22. A survey on machine learning techniques for cyber security in the last decade10.1109/ACCESS.2020.3041951 ↗
23. Shaukat, K., Luo, S., Varadharajan, V., Hameed, I.A., Chen, S., Liu, D., and Li, J. (2020). Performance comparison and current challenges of using machine learning techniques in cybersecurity. Energies, 13.10.3390/en13102509 ↗
24. Shaukat, K., Luo, S., Chen, S., and Liu, D. (2020, January 20–21). Cyber Threat Detection Using Machine Learning Techniques: A Performance Evaluation Perspective. Proceedings of the 2020 International Conference on Cyber Warfare and Security (ICCWS), Islamabad, Pakistan.10.1109/ICCWS48432.2020.9292388 ↗
25. Segnet: A deep convolutional encoder-decoder architecture for image segmentation10.1109/TPAMI.2016.2644615 ↗
26. Lin, G., Milan, A., Shen, C., and Reid, I. (2017, January 21–26). Refinenet: Multi-path refinement networks for high-resolution semantic segmentation. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.549 ↗
27. Noh, H., Hong, S., and Han, B. (2015, January 7–13). Learning deconvolution network for semantic segmentation. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.178 ↗
28. Simonyan, K., and Zisserman, A. (2015, January 7–9). Very deep convolutional networks for large-scale image recognition. Proceedings of the International Conference on Learning Representations, San Diego, CA, USA.
29. Detection of Covid-19 from Chest CT Images using Xception Architecture: A Deep Transfer Learning based Approach
30. 3D-BoxSup: Positive-Unlabeled Learning of Brain Tumor Segmentation Networks from 3D Bounding Boxes10.3389/fnins.2020.00350 ↗
31. Semantic segmentation using stride spatial pyramid pooling and dual attention decoder10.1016/j.patcog.2020.107498 ↗
32. Song, Y., Yu, Z., Zhou, T., Teoh, J.Y.C., Lei, B., Choi, K.S., and Qin, J. (2020, January 4–8). Learning 3d features with 2d cnns via surface projection for ct volume segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Lima, Peru.10.1007/978-3-030-59719-1_18 ↗
33. Kaul, C., Manandhar, S., and Pears, N. (2019, January 8–11). Focusnet: An Attention-Based Fully Convolutional Network for Medical Image Segmentation. Proceedings of the 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy.10.1109/ISBI.2019.8759477 ↗
34. Clinical evaluation of fully automated thigh muscle and adipose tissue segmentation using a U-Net deep learning architecture in context of osteoarthritic knee pain10.1007/s10334-019-00816-5 ↗
35. The optimisation of deep neural networks for segmenting multiple knee joint tissues from MRIs10.1016/j.compmedimag.2020.101793 ↗
36. Use of 2D U-Net convolutional neural networks for automated cartilage and meniscus segmentation of knee MR imaging data to determine relaxometry and morphometry10.1148/radiol.2018172322 ↗
37. Javed Awan, M., Mohd Rahim, M.S., Salim, N., Mohammed, M.A., Garcia-Zapirain, B., and Abdulkareem, K.H. (2021). Efficient detection of knee anterior cruciate ligament from magnetic resonance imaging using deep learning approach. Diagnostics, 11.10.3390/diagnostics11010105 ↗
38. Cardiac mri segmentation with a dilated cnn incorporating domain-specific constraints10.1109/JSTSP.2020.3013351 ↗
39. AssemblyNet: A large ensemble of CNNs for 3D whole brain MRI segmentation10.1016/j.neuroimage.2020.117026 ↗
40. Mohammed, M.A., Abdulkareem, K.H., Mostafa, S.A., Ghani, M.K.A., Maashi, M.S., Garcia-Zapirain, B., Oleagordia, I., AlHakami, H., and Al-Dhief, F.T. (2020). Voice pathology detection and classification using convolutional neural network model. Appl. Sci., 10.10.3390/app10113723 ↗
41. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
42. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
43. Milletari, F., Navab, N., and Ahmadi, S. (2016, January 25–28). V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA.10.1109/3DV.2016.79 ↗