EPIIC: Edge-Preserving Method Increasing Nuclei Clarity for Compression Artifacts Removal in Whole-Slide Histopathological Images
Source abstract
Abstract
Hematoxylin and eosin (HE) staining is widely used in medical diagnosis. Stained slides provide crucial information to diagnose or monitor the progress of many diseases. Due to the large size of scanned images of whole tissues, a JPEG algorithm is commonly used for compression. This lossy compression method introduces artifacts visible as 8 × 8 pixel blocks and reduces overall quality, which may negatively impact further analysis. We propose a fully unsupervised Edge-Preserving method Increasing nucleI Clarity (EPIIC) for removing compression artifacts from whole-slide HE-stained images. The method is introduced in two versions, EPIIC and EPIIC Sobel, composed of stain deconvolution, gradient-based edge map estimation, and weighted smoothing. The performance of the method was evaluated using two image quality measures, PSNR and SSIM, and various datasets, including BreCaHAD with HE-stained histopathological images and five other natural image datasets, and compared with other edge-preserving filtering methods and a deep learning-based solution. The impact of compression artifacts removal on the nuclei segmentation task was tested using Hover-Net and STARDIST models. The proposed methods led to improved image quality in histopathological and natural images and better segmentation of cell nuclei compared to other edge-preserving filtering methods. The biggest improvement was observed for images compressed with a low compression quality factor. Compared to the method using neural networks, the developed algorithms have slightly worse performance in image enhancement, but they are superior in nuclei segmentation. EPIIC and EPIIC Sobel can efficiently remove compression artifacts, positively impacting the segmentation results of cell nuclei and overall image quality.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: AI in cancer detection · Medical Image Segmentation Techniques · Radiomics and Machine Learning in Medical Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland
Department of Data Science and Engineering, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland
Yale Cancer Center, Yale University, New Haven, CT 06511, USA
Funding
Excellence Initiative—Research University program 2023
References (49)
Show source-provided references
1. Detection of breast cancer on digital histopathology images: Present status and future possibilities10.1016/j.imu.2016.11.001 ↗
2. Introduction to digital pathology and computer-aided pathology10.4132/jptm.2019.12.31 ↗
3. Methods for nuclei detection, segmentation, and classification in digital histopathology: A review-current status and future potential10.1109/RBME.2013.2295804 ↗
4. Pathology Image Analysis Using Segmentation Deep Learning Algorithms10.1016/j.ajpath.2019.05.007 ↗
5. Whole Slide Image Quality in Digital Pathology: Review and Perspectives10.1109/ACCESS.2022.3227437 ↗
6. Current state of knowledge about digital pathology
7. Chaotic quantization based JPEG for effective compression of whole slide images
8. The JPEG still picture compression standard10.1109/30.125072 ↗
9. A Comprehensive Benchmark for Single Image Compression Artifact Reduction10.1109/TIP.2020.3007828 ↗
10. Vector-valued image regularization with PDEs: A common framework for different applications10.1109/TPAMI.2005.87 ↗
11. JPEG2000 image postprocessing with novel trilateral deringing filter10.1117/1.2844731 ↗
12. Pointwise Shape-Adaptive DCT for High-Quality Denoising and Deblocking of Grayscale and Color Images10.1109/TIP.2007.891788 ↗
13. Efficient quadtree based block-shift filtering for deblocking and deringing10.1016/j.jvcir.2009.06.004 ↗
14. Postprocessing of Low Bit-Rate Block DCT Coded Images Based on a Fields of Experts Prior10.1109/TIP.2007.904969 ↗
15. Liu, X., Wu, X., Zhou, J., and Zhao, D. (2015, January 7–12). Data-driven sparsity-based restoration of JPEG-compressed images in dual transform-pixel domain. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7299153 ↗
16. Data-Driven Soft Decoding of Compressed Images in Dual Transform-Pixel Domain10.1109/TIP.2016.2526910 ↗
17. Dong, C., Deng, Y., Loy, C.C., and Tang, X. (2015, January 7–13). Compression Artifacts Reduction by a Deep Convolutional Network. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.73 ↗
18. Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration10.1109/TPAMI.2016.2596743 ↗
19. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising10.1109/TIP.2017.2662206 ↗
20. Jiang, J., Zhang, K., and Timofte, R. (2021, January 10–17). Towards Flexible Blind JPEG Artifacts Removal. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00495 ↗
21. Ehrlich, M., Davis, L., Lim, S.N., and Shrivastava, A. (2020). Quantization Guided JPEG Artifact Correction. arXiv.10.1007/978-3-030-58598-3_18 ↗
22. Oztan, B., Malik, A., Fan, Z., and Eschbach, R. (February, January 30). Removal of artifacts from JPEG compressed document images. Proceedings of the Color Imaging XII: Processing, Hardcopy, and Applications, San Jose, CA, USA.
23. Bajkacz, S., and Ostrowski, Z. (2021). Removing compression artifacts on whole slide HE-stained histopathological images. Recent Advances in Computational Oncology and Personalized Medicine, Silesian University of Technology.
24. Quantification of histochemical staining by color deconvolution
25. Kather, J.N. (2025, April 14). Color Deconvolution in MATLAB. GitHub Repository. Available online: https://github.com/jnkather/ColorDeconvolutionMatlab.
26. Pratt, W.K. (2001). Digital Image Processing, PixelSoft, Inc.10.1002/0471221325 ↗
27. Cannistraci, C., Abbas, A., and Gao, X. (2015). Median Modified Wiener Filter for nonlinear adaptive spatial denoising of protein NMR multidimensional spectra. Sci. Rep., 5.10.1038/srep08017 ↗
28. Guided Image Filtering10.1109/TPAMI.2012.213 ↗
29. Scale-space and edge detection using anisotropic diffusion10.1109/34.56205 ↗
30. An Optimized Framework Using Adaptive Wavelet Thresholding and Total Variation Technique for De-noising Medical Images
31. Nonlinear anisotropic filtering of MRI data10.1109/42.141646 ↗
32. Tomasi, C., and Manduchi, R. (1998, January 7). Bilateral Filtering for Gray and Color Images. Proceedings of the 1998 IEEE International Conference on Computer Vision, Bombay, India.
33. Coll, B., and Morel, J.M. (2005, January 20–25). A non-local algorithm for image denoising. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA.
34. Image quality assessment: From error visibility to structural similarity10.1109/TIP.2003.819861 ↗
35. Building Predictive Models in R Using the caret Package10.18637/jss.v028.i05 ↗
36. Hover-net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images10.1016/j.media.2019.101563 ↗
37. Weigert, M., and Schmidt, U. (2022, January 28–31). Nuclei Instance Segmentation and Classification in Histopathology Images with Stardist. Proceedings of the 2022 IEEE International Symposium on Biomedical Imaging Challenges (ISBIC), Kolkata, India.10.1109/ISBIC56247.2022.9854534 ↗
38. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20–25). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.10.1109/CVPR.2009.5206848 ↗
39. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI), Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
40. Vu, Q.D., Graham, S., To, M.N.N., Shaban, M., Qaiser, T., Koohbanani, N.A., Khurram, S.A., Kurc, T., Farahani, K., and Zhao, T. (2018). Methods for Segmentation and Classification of Digital Microscopy Tissue Images. arXiv.10.3389/fbioe.2019.00053 ↗
41. A Dataset and a Technique for Generalized Nuclear Segmentation for Computational Pathology10.1109/TMI.2017.2677499 ↗
42. Kirillov, A., He, K., Girshick, R.B., Rother, C., and Dollár, P. (2019, January 15–20). Panoptic Segmentation. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00963 ↗
43. Aksac, A., Demetrick, D.J., Ozyer, T., and Alhajj, R. (2019). BreCaHAD: A dataset for breast cancer histopathological annotation and diagnosis. BMC Res. Notes, 12.10.1186/s13104-019-4121-7 ↗
44. Contour Detection and Hierarchical Image Segmentation10.1109/TPAMI.2010.161 ↗
45. Sheikh, H.R., Wang, Z., Cormack, L., and Bovik, A.C. (2025, April 06). LIVE Image Quality Assessment Database Release 2. Available online: http://live.ece.utexas.edu/research/quality.
46. Bevilacqua, M., Roumy, A., Guillemot, C., and Alberi-Morel, M.L. (2012, January 3–7). Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding. Proceedings of the British Machine Vision Conference, Surrey, UK.10.5244/C.26.135 ↗
47. Boissonnat, J.D., Chenin, P., Cohen, A., Gout, C., Lyche, T., Mazure, M.L., and Schumaker, L. (2012). On Single Image Scale-Up Using Sparse-Representations. Curves and Surfaces, Proceedings of the 7th International Conference, Avignon, France, 24–30 June 2010, Springer.10.1007/978-3-642-27413-8 ↗
48. Welch (1984). A Technique for High-Performance Data Compression. Computer, 17, 8–19.10.1109/MC.1984.1659158 ↗
49. Krylov, A., Karnaukhov, V., Mamaev, N., and Khvostikov, A. (2020, January 17–19). Hybrid Method for Biomedical Image Denoising. Proceedings of the 2019 4th International Conference on Biomedical Imaging, Signal Processing, New York, NY, USA. ICBSP ’19.10.1145/3366174.3366184 ↗