Using Super-Resolution for Enhancing Visual Perception and Segmentation Performance in Veterinary Cytology
Author:
Caputa Jakub1ORCID, Wielgosz Maciej12ORCID, Łukasik Daria1, Russek Paweł12ORCID, Grzeszczyk Jakub1, Karwatowski Michał12ORCID, Mazurek Szymon1ORCID, Frączek Rafał12ORCID, Śmiech Anna3ORCID, Jamro Ernest12ORCID, Koryciak Sebastian12ORCID, Dąbrowska-Boruch Agnieszka12ORCID, Pietroń Marcin12ORCID, Wiatr Kazimierz12ORCID
Affiliation:
1. ACC Cyfronet AGH, Nawojki 11, 30-950 Kraków, Poland 2. AGH University of Krakow, al. Mickiewicza 30, 30-059 Kraków, Poland 3. University of Life Sciences, al. Akademicka 13, 20-950 Lublin, Poland
Abstract
The primary objective of this research was to enhance the quality of semantic segmentation in cytology images by incorporating super-resolution (SR) architectures. An additional contribution was the development of a novel dataset aimed at improving imaging quality in the presence of inaccurate focus. Our experimental results demonstrate that the integration of SR techniques into the segmentation pipeline can lead to a significant improvement of up to 25% in the mean average precision (mAP) metric. These findings suggest that leveraging SR architectures holds great promise for advancing the state-of-the-art in cytology image analysis.
Reference30 articles.
1. Mazurek, S., Wielgosz, M., Caputa, J., Frączek, R., Karwatowski, M., Grzeszczyk, J., Łukasik, D., Śmiech, A., Russek, P., and Jamro, E. (2022, January 4–7). Canine age classification using Deep Learning as a step toward preventive medicine in animals. Proceedings of the 17th Conference on Computer Science and Intelligence Systems (FedCSIS), Sofia, Bulgaria. 2. Grzeszczyk, J., Karwatowski, M., Łukasik, D., Wielgosz, M., Russek, P., Mazurek, S., Caputa, J., Frączek, R., Śmiech, A., and Jamro, E. (2023). Segmentation of the Veterinary Cytological Images for Fast Neoplastic Tumors Diagnosis. arXiv. 3. Caputa, J., Łukasik, D., Wielgosz, M., Karwatowski, M., Frączek, R., Russek, P., and Wiatr, K. (2021). Fast Pre-Diagnosis of Neoplastic Changes in Cytology Images Using Machine Learning. Appl. Sci., 11. 4. He, K., Zhang, X., Ren, S., and Sun, J. (July, January 29). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA. 5. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015, Proceedings of the 18th International Conference, Munich, Germany. Proceedings, Part III.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
|
|