Advancing Content-Based Histopathological Image Retrieval Pre-Processing: A Comparative Analysis of the Effects of Color Normalization Techniques
Source abstract
Abstract
Content-Based Histopathological Image Retrieval (CBHIR) is a search technique based on the visual content and histopathological features of whole-slide images (WSIs). CBHIR tools assist pathologists to obtain a faster and more accurate cancer diagnosis. Stain variation between hospitals hampers the performance of CBHIR tools. This paper explores the effects of color normalization (CN) in a recently proposed CBHIR approach to tackle this issue. In this paper, three different CN techniques were used on the CAMELYON17 (CAM17) data set, which is a breast cancer data set. CAM17 consists of images taken using different staining protocols and scanners in five hospitals. Our experiments reveal that a proper CN technique, which can transfer the color version into the most similar median values, has a positive impact on the retrieval performance of the proposed CBHIR framework. According to the obtained results, using CN as a pre-processing step can improve the accuracy of the proposed CBHIR framework to 97% (a 14% increase), compared to working with the original images.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: AI in cancer detection · Image Retrieval and Classification Techniques · Radiomics and Machine Learning in Medical Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Artificial Intelligence, Tyris Tech S.L., 46021 Valencia, Spain
Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano, HUMAN-Tech, Universitat Politècnica de València, 46022 Valencia, Spain
Basque Center on Cognition, Brain and Language, 20009 San Sebastián, Spain
Department of Ciencias de la Computación e Inteligencia Artificial, Universidad de Granada, 18071 Granada, Spain
Funding
European Union’s Horizon · Ayuda a Primeros Proyectos de Investigación · Vicerrectorado de Investigacion de la Universitat Politecnica de Valencia (UPV)
References (46)
Show source-provided references
1. Artificial intelligence in digital breast pathology: Techniques and applications10.1016/j.breast.2019.12.007 ↗
2. Al-Hussaeni, K., Karamitsos, I., Adewumi, E., and Amawi, R.M. (2023). CNN-Based Pill Image Recognition for Retrieval Systems. Appl. Sci., 13.10.3390/app13085050 ↗
3. Khalil, S., Nawaz, U., Mushtaq, Z., Arif, S., ur Rehman, M.Z., Qureshi, M.F., Malik, A., Aleid, A., and Alhussaini, K. (2023). Enhancing Ductal Carcinoma Classification Using Transfer Learning with 3D U-Net Models in Breast Cancer Imaging. Appl. Sci., 13.10.3390/app13074255 ↗
4. Fuster, S., Khoraminia, F., Eftestøl, T., Zuiverloon, T.C., and Engan, K. (2023, January 4–8). Active Learning Based Domain Adaptation for Tissue Segmentation of Histopathological Images. Proceedings of the 2023 31st European Signal Processing Conference (EUSIPCO), Helsinki, Finland.10.23919/EUSIPCO58844.2023.10290058 ↗
5. Multimodal image fusion using sparse representation classification in tetrolet domain10.1016/j.dsp.2018.04.002 ↗
6. Alrowais, F., Alotaibi, F.A., Hassan, A.Q., Marzouk, R., Alnfiai, M.M., and Sayed, A. (2023). Enhanced Pelican Optimization Algorithm with Deep Learning-Driven Mitotic Nuclei Classification on Breast Histopathology Images. Biomimetics, 8.10.3390/biomimetics8070538 ↗
7. Similar image search for histopathology: SMILY10.1038/s41746-019-0131-z ↗
8. Strittmatter, A., Caroli, A., and Zöllner, F.G. (2023). A Multistage Rigid-Affine-Deformable Network for Three-Dimensional Multimodal Medical Image Registration. Appl. Sci., 13.10.3390/app132413298 ↗
9. Kanwal, N., Fuster, S., Khoraminia, F., Zuiverloon, T.C., Rong, C., and Engan, K. (2022, January 26–29). Quantifying the effect of color processing on blood and damaged tissue detection in whole slide images. Proceedings of the 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), Nafplio, Greece.10.1109/IVMSP54334.2022.9816283 ↗
10. MRI and PET/SPECT image fusion at feature level using ant colony based segmentation10.1016/j.bspc.2018.08.017 ↗
11. Long, F., Zhang, H., and Feng, D.D. (2003). Multimedia Information Retrieval and Management: Technological Fundamentals and Applications, Springer.
12. Tabatabaei, Z., Colomer, A., Moll, J.O., and Naranjo, V. (2024). Siamese Content-based Search Engine for a More Transparent Skin and Breast Cancer Diagnosis through Histological Imaging. arXiv.10.2139/ssrn.4685960 ↗
13. Content-based image retrieval at the end of the early years10.1109/34.895972 ↗
14. Qi, X., Wang, D., Rodero, I., Diaz-Montes, J., Gensure, R.H., Xing, F., Zhong, H., Goodell, L., Parashar, M., and Foran, D.J. (2014). Content-based histopathology image retrieval using CometCloud. BMC Bioinform., 15.10.1186/1471-2105-15-287 ↗
15. Tabatabaei, Z., Colomer, A., Engan, K., Oliver, J., and Naranjo, V. (2022, January 26–29). Residual block convolutional auto encoder in content-based medical image retrieval. Proceedings of the 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), Nafplio, Greece.10.1109/IVMSP54334.2022.9816325 ↗
16. Bianconi, F., Kather, J.N., and Reyes-Aldasoro, C.C. (2020). Experimental assessment of color deconvolution and color normalization for automated classification of histology images stained with hematoxylin and eosin. Cancers, 12.10.3390/cancers12113337 ↗
17. Tabatabaei, Z., Wang, Y., Colomer, A., Oliver Moll, J., Zhao, Z., and Naranjo, V. (2023). WWFedCBMIR: World-Wide Federated Content-Based Medical Image Retrieval. Bioengineering, 10.10.3390/bioengineering10101144 ↗
18. Fuster, S., Khoraminia, F., Kiraz, U., Kanwal, N., Kvikstad, V., Eftestøl, T., Zuiverloon, T.C., Janssen, E.A., and Engan, K. (2022, January 26–29). Invasive cancerous area detection in Non-Muscle invasive bladder cancer whole slide images. Proceedings of the 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), Nafplio, Greece.10.1109/IVMSP54334.2022.9816352 ↗
19. Computational normalization of H&E-stained histological images: Progress, challenges and future potential10.1016/j.artmed.2018.10.004 ↗
20. From detection of individual metastases to classification of lymph node status at the patient level: The camelyon17 challenge10.1109/TMI.2018.2867350 ↗
21. Salvi, M., Acharya, U.R., Molinari, F., and Meiburger, K.M. (2021). The impact of pre-and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis. Comput. Biol. Med., 128.10.1016/j.compbiomed.2020.104129 ↗
22. A new complete color normalization method for H&E stained histopatholgical images10.1007/s10489-021-02231-7 ↗
23. A study about color normalization methods for histopathology images10.1016/j.micron.2018.07.005 ↗
24. Ionescu, B., Müller, H., Drăgulinescu, A.M., Popescu, A., Idrissi-Yaghir, A., García Seco de Herrera, A., Andrei, A., Stan, A., Storås, A.M., and Abacha, A.B. (2023, January 2–6). ImageCLEF 2023 Highlight: Multimedia Retrieval in Medical, Social Media and Content Recommendation Applications. Proceedings of the European Conference on Information Retrieval, Dublin, Ireland.10.1007/978-3-031-28241-6_64 ↗
25. Size-scalable content-based histopathological image retrieval from database that consists of WSIs10.1109/JBHI.2017.2723014 ↗
26. Towards large-scale histopathological image analysis: Hashing-based image retrieval10.1109/TMI.2014.2361481 ↗
27. Vanegas, J.A., Arevalo, J., and González, F.A. (2014, January 18–20). Unsupervised feature learning for content-based histopathology image retrieval. Proceedings of the 2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI), Klagenfurt, Austria.10.1109/CBMI.2014.6849815 ↗
28. Sukhia, K.N., Riaz, M.M., Ghafoor, A., Ali, S.S., and Iltaf, N. (2019). Content-based histopathological image retrieval using multi-scale and multichannel decoder based LTP. Biomed. Signal Process. Control, 54.10.1016/j.bspc.2019.101582 ↗
29. Fine-tuning and training of densenet for histopathology image representation using tcga diagnostic slides10.1016/j.media.2021.102032 ↗
30. Silva-Rodríguez, J., Colomer, A., Sales, M.A., Molina, R., and Naranjo, V. (2020). Going deeper through the Gleason scoring scale: An automatic end-to-end system for histology prostate grading and cribriform pattern detection. Comput. Methods Programs Biomed., 195.10.1016/j.cmpb.2020.105637 ↗
31. Shaban, M.T., Baur, C., Navab, N., and Albarqouni, S. (2019, January 8–11). Staingan: Stain style transfer for digital histological images. Proceedings of the 2019 Ieee 16th international symposium on biomedical imaging (Isbi 2019), Venice, Italy.10.1109/ISBI.2019.8759152 ↗
32. Macenko, M., Niethammer, M., Marron, J.S., Borland, D., Woosley, J.T., Guan, X., Schmitt, C., and Thomas, N.E. (July, January 28). A method for normalizing histology slides for quantitative analysis. Proceedings of the 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Boston, MA, USA.10.1109/ISBI.2009.5193250 ↗
33. Structure-preserving color normalization and sparse stain separation for histological images10.1109/TMI.2016.2529665 ↗
34. Adversarial stain transfer for histopathology image analysis10.1109/TMI.2017.2781228 ↗
35. Zanjani, F.G., Zinger, S., Bejnordi, B.E., van der Laak, J.A., and de With, P.H. (2018, January 4–7). Stain normalization of histopathology images using generative adversarial networks. Proceedings of the 2018 IEEE 15th International symposium on biomedical imaging (ISBI 2018), Washington, DC, USA.10.1109/ISBI.2018.8363641 ↗
36. Bayesian K-SVD for H and E blind color deconvolution. Applications to stain normalization, data augmentation and cancer classification10.1016/j.compmedimag.2022.102048 ↗
37. Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology10.1016/j.media.2019.101544 ↗
38. Deep feature learning for medical image analysis with convolutional autoencoder neural network10.1109/TBDATA.2017.2717439 ↗
39. Unsupervised domain adaptation to classify medical images using zero-bias convolutional auto-encoders and context-based feature augmentation10.1109/TMI.2020.2971258 ↗
40. Autoencoder-inspired convolutional network-based super-resolution method in MRI10.1109/JTEHM.2021.3076152 ↗
41. Daoud, M.I., Saleh, A., Hababeh, I., and Alazrai, R. (2019, January 24–26). Content-based Image Retrieval for Breast Ultrasound Images using Convolutional Autoencoders: A Feasibility Study. Proceedings of the 2019 3rd International Conference on Bio-engineering for Smart Technologies (BioSMART), Paris, France.10.1109/BIOSMART.2019.8734190 ↗
42. Tabatabaei, Z., Colomer, A., Engan, K., Oliver, J., and Naranjo, V. (2023, January 4–8). Self-supervised learning of a tailored Convolutional Auto Encoder for histopathological prostate grading. Proceedings of the 2023 31st European Signal Processing Conference (EUSIPCO), Helsinki, Finland.10.23919/EUSIPCO58844.2023.10289741 ↗
43. Adaptive color deconvolution for histological WSI normalization10.1016/j.cmpb.2019.01.008 ↗
44. Yottixel–an image search engine for large archives of histopathology whole slide images10.1016/j.media.2020.101757 ↗
45. Cao, Z., Long, M., Wang, J., and Yu, P.S. (2017, January 22–29). Hashnet: Deep learning to hash by continuation. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.598 ↗
46. Toward More Transparent and Accurate Cancer Diagnosis With an Unsupervised CAE Approach10.1109/ACCESS.2023.3343845 ↗