Abstract
AbstractAs the rise in cancer cases, there is an increasing demand to develop accurate and rapid diagnostic tools for early intervention. Pathologists are looking to augment manual analysis with computer-based evaluation to develop more efficient cancer diagnostics reports. The processing of these reports from manual evaluation is time-consuming, where the pathologists focus on accurately segmenting individual cancer cells, a vital step in analysis. This paper describes the design and validation of an application which has been developed based on deep learning networks. The application includes a workflow of image pre-processing followed by synthetic image generation, which is crucial due to the lack of training data in pathology settings. The next steps are the segmentation of nuclei regions and overlapping nuclei splitting. An improved approach has been considered based on a cycle-consistent GAN network for synthetic image generation. The synthetic images were utilized in a modified U-net network. Accurately outlining the individual nucleus border assisted an automated system that split the nuclei cluster into the individual nucleus. The SSIM and PSNR values of synthetic images corresponding to original were 0.204 and 10.610. The DSC value of the network trained by the synthetic data was 0.984 which was higher than the network trained by original images (0.805). The developed application provided better individual nuclei segmentation performance, where the average accuracy of different group images was 0.97. This higher accuracy suggests the benefit of using synthetic images in a situation to avoid the scarcity of labeled histopathology images in deep networks.
Publisher
Springer Science and Business Media LLC
Reference63 articles.
1. Panagiotakis C, Argyros A. Region-based Fitting of Overlapping Ellipses and its application to cells segmentation. Image Vis Comput. 2020;93: 103810.
2. Isaksson J, Arvidsson I, Åaström K and Heyden A. Semantic segmentation of microscopic images of H&E stained prostatic tissue using CNN. In: 2017 International Joint Conference on Neural Networks (IJCNN), 2017: IEEE, pp. 1252–6.
3. Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. Springer; 2015. p. 234–41.
4. Koyuncu CF, Cetin-Atalay R, Gunduz-Demir C. Object-oriented segmentation of cell nuclei in fluorescence microscopy images. Cytometry A. 2018;93(10):1019–28.
5. He K, Gkioxari G, Dollár P and Girshick R. Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, 2017, pp. 2961–9.