Towards Efficient and Accurate CT Segmentation via Edge-Preserving Probabilistic Downsampling (2404.03991v1)
Abstract: Downsampling images and labels, often necessitated by limited resources or to expedite network training, leads to the loss of small objects and thin boundaries. This undermines the segmentation network's capacity to interpret images accurately and predict detailed labels, resulting in diminished performance compared to processing at original resolutions. This situation exemplifies the trade-off between efficiency and accuracy, with higher downsampling factors further impairing segmentation outcomes. Preserving information during downsampling is especially critical for medical image segmentation tasks. To tackle this challenge, we introduce a novel method named Edge-preserving Probabilistic Downsampling (EPD). It utilizes class uncertainty within a local window to produce soft labels, with the window size dictating the downsampling factor. This enables a network to produce quality predictions at low resolutions. Beyond preserving edge details more effectively than conventional nearest-neighbor downsampling, employing a similar algorithm for images, it surpasses bilinear interpolation in image downsampling, enhancing overall performance. Our method significantly improved Intersection over Union (IoU) to 2.85%, 8.65%, and 11.89% when downsampling data to 1/2, 1/4, and 1/8, respectively, compared to conventional interpolation methods.
- “Shufflenet v2: Practical guidelines for efficient cnn architecture design,” in Proceedings of the European Conference on Computer Vision (ECCV), September 2018.
- “Espnet: Efficient spatial pyramid of dilated convolutions for semantic segmentation,” in Proceedings of the european conference on computer vision (ECCV), 2018, pp. 552–568.
- “Searching for mobilenetv3,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2019.
- “Efficientnetv2: Smaller models and faster training,” in Proceedings of the 38th International Conference on Machine Learning, Marina Meila and Tong Zhang, Eds. 18–24 Jul 2021, vol. 139 of Proceedings of Machine Learning Research, pp. 10096–10106, PMLR.
- “Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation,” International Journal of Computer Vision, vol. 129, pp. 3051–3068, 2021.
- “Miniseg: An extremely minimum network based on lightweight multiscale learning for efficient covid-19 segmentation,” IEEE Transactions on Neural Networks and Learning Systems, pp. 1–15, 2022.
- “Mscfnet: A lightweight network with multi-scale context fusion for real-time semantic segmentation,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 12, pp. 25489–25499, 2022.
- “Soft labelling for semantic segmentation: Bringing coherence to label down-sampling,” arXiv preprint arXiv:2302.13961, 2023.
- “Lightweight real-time semantic segmentation network with efficient transformer and cnn,” IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 12, pp. 15897–15906, 2023.
- “Using soft labels to model uncertainty in medical image segmentation,” in Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Alessandro Crimi and Spyridon Bakas, Eds., Cham, 2022, pp. 585–596, Springer International Publishing.
- “A soft label method for medical image segmentation with multirater annotations,” Computational Intelligence and Neuroscience, vol. 2023, 2023.
- “Softseg: Advantages of soft versus binary training for image segmentation,” Medical Image Analysis, vol. 71, pp. 102038, 2021.
- “Superpixel-guided label softening for medical image segmentation,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part IV 23. Springer, 2020, pp. 227–237.
- “When does label smoothing help?,” Advances in neural information processing systems, vol. 32, 2019.
- “Does label smoothing mitigate label noise?,” in Proceedings of the 37th International Conference on Machine Learning, Hal Daumé III and Aarti Singh, Eds. 13–18 Jul 2020, vol. 119 of Proceedings of Machine Learning Research, pp. 6448–6458, PMLR.
- “From label smoothing to label relaxation,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 10, pp. 8583–8591, May 2021.
- “Data augmentation for medical imaging: A systematic literature review,” Computers in Biology and Medicine, vol. 152, pp. 106391, 2023.
- “Lightweight encoder-decoder architecture for foot ulcer segmentation,” Commun. in Comput. and Inf. Sci., vol. 1578 CCIS, pp. 242–253, 2022.
- “Multi-task learning using uncertainty to weigh losses for scene geometry and semantics,” 2018, pp. 7482–7491.
- “Auxiliary tasks in multi-task learning,” arXiv preprint arXiv:1805.06334, 5 2018.
- Michael T. Paris et al., “Automated body composition analysis of clinically acquired computed tomography scans using neural networks,” Clin. Nutrition, vol. 39, pp. 3049–3055, 10 2020.
- Shahzad Ali (5 papers)
- Yu Rim Lee (3 papers)
- Soo Young Park (4 papers)
- Won Young Tak (3 papers)
- Soon Ki Jung (13 papers)