Attention Guided Multi Scale Feature Fusion Network for Automatic Prostate Segmentation
Source abstract
Abstract
The precise and automatic segmentation of prostate magnetic resonance imaging (MRI) images is vital for assisting doctors in diagnosing prostate diseases. In recent years, many advanced methods have been applied to prostate segmentation, but due to the variability caused by prostate diseases, automatic segmentation of the prostate presents significant challenges. In this paper, we propose an attention-guided multi-scale feature fusion network (AGMSF-Net) to segment prostate MRI images. We propose an attention mechanism for extracting multi-scale features, and introduce a 3D transformer module to enhance global feature representation by adding it during the transition phase from encoder to decoder. In the decoder stage, a feature fusion module is proposed to obtain global context information. We evaluate our model on MRI images of the prostate acquired from a local hospital. The relative volume difference (RVD) and dice similarity coefficient (DSC) between the results of automatic prostate segmentation and ground truth were 1.21% and 93.68%, respectively. To quantitatively evaluate prostate volume on MRI, which is of significant clinical significance, we propose a unique AGMSF-Net. The essential performance evaluation and validation experiments have demonstrated the effectiveness of our method in automatic prostate segmentation.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Medical Image Segmentation Techniques · Medical Imaging and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (56)
Show source-provided references
1. Global cancer statistics 2022: The trends projection analysis
2. Evaluation of prostate segmentation algorithms for MRI: The PROMISE12 challenge10.1016/j.media.2013.12.002 ↗
3. Relationship between apparent diffusion coefficients at 3.0-T MR imaging and gleason grade in peripheral zone prostate cancer
4. Prostate cancer screening: The clinical value of diffusion-weighted imaging and dynamic MR imaging in combination with T2-weighted imaging10.1002/jmri.20793 ↗
5. Segmentation of prostate bound-aries from ultrasound images using statistical shape model10.1109/TMI.2003.809057 ↗
6. Deep learning10.1038/nature14539 ↗
7. Volumetric convnets with mixed residual connections for automated prostate segmentation from 3D MR images
8. Automatic prostate and peri-prostatic fat segmentation based on pyramid mechanism fusion network for T2-weighted MRI10.1016/j.cmpb.2022.106918 ↗
9. Automatic segmentation of prostate MRI based on 3D pyramid pooling Unet10.1002/mp.15895 ↗
10. U-Net: Convolutional networks for biomedical image segmentation
11. H-DenseUNet: Hybrid densely connected unet for liver and tumor segmentation from CT volumes10.1109/TMI.2018.2845918 ↗
12. ResUNet++: An advanced architecture for medical image segmentation
13. A deep neural network based on prior-driven and structural preserving for SAR image despeckling10.1109/JSTARS.2023.3292325 ↗
14. Neighborhood rough residual network-based outlier detection method in IoT-enabled maritime transportation systems10.1109/TITS.2023.3285615 ↗
15. Generalized interval type II fuzzy rough model based feature discretization for mixed pixels10.1109/TFUZZ.2022.3190625 ↗
16. Progressive feature fusion attention dense network for speckle noise removal in OCT images
17. Dual optimization based prostate zonal segmentation in 3D MR images10.1016/j.media.2014.02.009 ↗
18. Prostate MRI segmentation using learned semantic knowledge and graph cuts10.1109/TBME.2013.2289306 ↗
19. A supervoxel-based segmentation method for prostate MR images
20. Superpixel-based segmentation for 3D prostate MR images10.1109/TMI.2015.2496296 ↗
21. A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery10.1109/TMI.2010.2052065 ↗
22. Multi-atlas segmentation of the prostate: A zooming process with robust registration and atlas selection
23. A fully automatic multi-atlas based segmentation method for prostate MR images
24. Label image constrained multiatlas selection10.1109/TCYB.2014.2346394 ↗
25. Deformable landmark-free active appearance models: Application to segmentation of multi-institutional prostate MRI data
26. Multifeature landmark-free active appearance models: Application to prostate MRI segmentation10.1109/TMI.2012.2201498 ↗
27. Automated prostate gland segmentation based on an unsupervised fuzzy c-means clustering technique using multispectral T1w and T2w MR imaging10.3390/info8020049 ↗
28. Deformable mr prostate segmentation via deep feature learning and sparse patch matching10.1109/TMI.2015.2508280 ↗
29. Fully convolutional networks for semantic segmentation
30. A multi-scale U-Net for semantic segmentation of histological images from radical prostatectomies
31. Going deep in medical image analysis: Concepts, methods, challenges, and future directions10.1109/ACCESS.2019.2929365 ↗
32. Active appearance model and deep learning for more accurate prostate segmentation on MRI
33. Comparison of objective functions in CNN-based prostate magnetic resonance image segmentation
34. Exploiting interslice correlation for MRI prostate image segmentation, from recursive neural networks aspect10.1155/2018/4185279 ↗
35. Deep learning-based boundary detection for model-based segmentation with application to MR prostate segmentation
36. 3D APA-Net: 3D adversarial pyramid anisotropic convolutional network for prostate segmentation in MR images10.1109/TMI.2019.2928056 ↗
37. Boundary-weighted domain adaptive neural network for prostate MR image segmentation10.1109/TMI.2019.2935018 ↗
38. Reducing the hausdorff distance in medical image segmentation with convolutional neural networks10.1109/TMI.2019.2930068 ↗
39. USE-Net: Incorporating squeeze-and-excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets10.1016/j.neucom.2019.07.006 ↗
40. HD-Net: Hybrid discriminative network for prostate segmentation in MR images
41. Evaluation of deep neural networks for semantic segmentation of prostate in T2W MRI10.3390/s20113183 ↗
42. Attention-guided multi-scale learning network for automatic prostate and tumor segmentation on MRI10.1016/j.compbiomed.2023.107374 ↗
43. A dual attention-guided 3D convolution network for automatic segmentation of prostate and tumor10.1016/j.bspc.2023.104755 ↗
44. 3D U-Net: Learning dense volumetric segmentation from sparse annotation
45. UNet++: A nested u-net architecture for medical image segmentation
46. Unet 3+: A full-scale connected unet for medical image segmentation
47. Attention is all you need
48. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv preprint arXiv:2010.11929, 2020.
49. V-Net: Fully convolutional neural networks for volumetric medical image segmentation
50. Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images10.1016/j.neuroimage.2018.07.005 ↗
51. Learning normalized inputs for iterative estimation in medical image segmentation
52. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations
53. I. Voiculescu and V. Yeghiazaryan, “An overview of current evaluation methods used in medical image segmentation,” Department of Computer Science, no. RR-15-08, pp. 22, 2015.
54. Multi-task learning for neonatal brain segmentation using 3D Dense-Unet with dense attention guided by geodesic distance
55. HD-Net: Hybrid discriminative network for prostate segmentation in MR images
56. Evaluation of deep neural networks for semantic segmentation of prostate in T2W MRI10.3390/s20113183 ↗