Improving Classification Performance of Spatial Filters in Mammographic Microcalcifications Images Using Persistent Homology
DOI:
https://doi.org/10.11113/mjfas.v20n6.3714Keywords:
Spatial filter, breast cancer, classification, mammogram, persistent homology.Abstract
Noise and artefacts in mammogram images can obscure important indicators of microcalcifications, complicating accurate diagnosis. While traditional spatial filters can reduce noise and are effective to some extent, they often fail to enhance features crucial for classification. This study uses persistent homology (PH) to evaluate and improve the classification performance of various spatial filters on mammogram images. The evaluation process involves converting filtered images into persistence diagrams (PDs) to capture topological features. These diagrams are then vectorised into PH features for classification using a neural network classifier. This study also examines further filtering of PDs from filtered images to enhance classification performance. Using the Digital Database for Screening Mammography (DDSM) and Mammographic Image Analysis Society (MIAS) datasets, we evaluate Median, Wiener, Gaussian, and Bilateral filters alone and integrate them with PH-based filtering. Results show significant classification improvements, with Wiener filters achieving 96.33% accuracy on the DDSM dataset (up from 57.38%) and Gaussian filters reaching 85.33% on the MIAS dataset (up from 73.33%). These findings demonstrate the potential of PH-based filters to enhance diagnostic accuracy in breast cancer detection by refining topological features and effectively reducing noise.
References
Ferlay, J., et al. (2021). Cancer statistics for the year 2020: An overview. International Journal of Cancer, 148(4), 1–10. https://doi.org/10.1002/ijc.33588
Arnold, M., et al. (2022). Current and future burden of breast cancer: Global statistics for 2020 and 2040. The Breast, 66, 15–23. https://doi.org/10.1016/j.breast.2022.08.010
Ramadan, S. Z. (2020). Methods used in computer-aided diagnosis for breast cancer detection using mammograms: A review. Journal of Healthcare Engineering, 2020, 1–12. https://doi.org/10.1155/2020/9162464
Htay, M. N. N., et al. (2021). Breast cancer screening in Malaysia: A policy review. Asian Pacific Journal of Cancer Prevention, 22(6), 1685. https://doi.org/10.31557/APJCP.2021.22.6.1685
Yurdusev, A. A., Adem, K., & Hekim, M. (2023). Detection and classification of microcalcifications in mammogram images using difference filter and Yolov4 deep learning model. Biomedical Signal Processing and Control, 80, 1–7. https://doi.org/10.1016/j.bspc.2022.104360
Azam, S., et al. (2021). Mammographic microcalcifications and risk of breast cancer. British Journal of Cancer, 125(5), 759–765. https://doi.org/10.1038/s41416-021-01459-x
Loizidou, K., Skouroumouni, G., Nikolaou, C., & Pitris, C. (2020). An automated breast micro-calcification detection and classification technique using temporal subtraction of mammograms. IEEE Access, 8, 52785–52795. https://doi.org/10.1109/ACCESS.2020.2980616
Almalki, Y. E., Soomro, T. A., Irfan, M., Alduraibi, S. K., & Ali, A. (2022). Impact of image enhancement module for analysis of mammogram images for diagnostics of breast cancer. Sensors, 22(1868), 1–20.
Gowri, V., Valluvan, K. R., & Vijaya Chamundeeswari, V. (2018). Automated detection and classification of microcalcification clusters with enhanced preprocessing and fractal analysis. Asian Pacific Journal of Cancer Prevention, 19(11), 3093–3098. https://doi.org/10.31557/APJCP.2018.19.11.3093
Azam, A. S. B., Malek, A. A., Ramlee, A. S., Suhaimi, N. D. S. M., & Mohamed, N. (2020). Segmentation of breast microcalcification using hybrid method of Canny algorithm with Otsu thresholding and 2D wavelet transform. In 2020 10th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) (pp. 91–96). Penang, Malaysia. https://doi.org/10.1109/ICCSCE50387.2020.9204950
Fadil, R., Jackson, A., El Majd, B. A., El Ghazi, H., & Kaabouch, N. (2020). Classification of microcalcifications in mammograms using 2D discrete wavelet transform and random forest. In IEEE International Conference on Electro Information Technology (pp. 353–359). https://doi.org/10.1109/EIT48999.2020.9208290
Padmapriya, R., & Jeyasekar, A. (2022). Blind image quality assessment with image denoising: A survey. Journal of Pharmaceutical Negative Results, 13(3), 386–392. https://doi.org/10.47750/pnr.2022.13.S03.064
Melekoodappattu, J. G., Subbian, P. S., & Queen, M. P. F. (2021). Detection and classification of breast cancer from digital mammograms using hybrid extreme learning machine classifier. International Journal of Imaging Systems and Technology, 31(2), 909–920. https://doi.org/10.1002/ima.22484
Brito, F. A., Oliveira, H. C. R., Bakic, P. R., Maidment, A. D. A., & Vieira, M. A. C. (2016). Using bilateral filter to denoise digital mammograms acquired with reduced radiation dose. In Congresso Brasileiro de Engenharia Biomédica (pp. 1334–1337).
Patil, R. S., & Biradar, N. (2020). Automated mammogram breast cancer detection using the optimized combination of convolutional and recurrent neural network. Evolutionary Intelligence, 14(4), 1459–1474. https://doi.org/10.1007/s12065-020-00403-x
Rajaguru, H., & Sannasi Chakravarthy, S. R. (2020). Efficient denoising framework for mammogram images with a new impulse detector and non-local means. Asian Pacific Journal of Cancer Prevention, 21(1), 179–183. https://doi.org/10.31557/APJCP.2020.21.1.179
Fan, L., Zhang, F., Fan, H., & Zhang, C. (2019). Brief review of image denoising techniques. Visual Computing in Industry, Biomedicine, and Art, 2(1), 7. https://doi.org/10.1186/s42492-019-0016-7
Goyal, B., Dogra, A., Agrawal, S., Sohi, B. S., & Sharma, A. (2020). Image denoising review: From classical to state-of-the-art approaches. Information Fusion, 55, 220–244. https://doi.org/10.1016/j.inffus.2019.09.003
Boby, S. M. (2021). Medical image denoising techniques against hazardous noises: An IQA metrics based comparative analysis. I.J Image, Graphics and Signal Processing, 2(April), 25–43. https://doi.org/10.5815/ijigsp.2021.02.03
Spagnolo, F., Corsonello, P., Frustaci, F., & Perri, S. (2023). Design of approximate bilateral filters for image denoising on FPGAs. IEEE Access, 11, 1990–2000. https://doi.org/10.1109/ACCESS.2022.3233921
Boby, S. M. (2021). Medical image denoising techniques against hazardous noises: An IQA metrics based comparative analysis. I.J Image, Graphics and Signal Processing, 2(April), 25–43. https://doi.org/10.5815/ijigsp.2021.02.03
Kshema, M. J. George, & Dhas, D. A. S. (2017). Preprocessing filters for mammogram images: A review. In 2017 Conference on Emerging Devices and Smart Systems (ICEDSS) (pp. 1–7). https://doi.org/10.1109/ICEDSS.2017.8073694
Kusano, G., Fukumizu, K., & Hiraoka, Y. (2018). Kernel method for persistence diagrams via kernel embedding and weight factor. Journal of Machine Learning Research, 18, 1–41.
Sapini, M. L., Noorani, M. S. M., Razak, F. A., Alias, M. A., & Yusof, N. M. (2022). Understanding published literatures on persistent homology using social network analysis. Malaysian Journal of Fundamental and Applied Sciences, 18(4), 413–429. https://doi.org/10.11113/mjfas.v18n4.2418
Qaiser, T., Tsang, Y. W., Epstein, D., & Rajpoot, N. (2017). Tumor segmentation in whole slide images using persistent homology and deep convolutional features. Communications in Computer and Information Science, 723, 320–329. https://doi.org/10.1007/978-3-319-60964-5_28
Assaf, R., Goupil, A., Kacim, M., & Vrabie, V. (2017). Topological persistence based on pixels for object segmentation in biomedical images. In International Conference on Advances in Biomedical Engineering (ICABME) (pp. 1–6). https://doi.org/10.1109/ICABME.2017.8167531
Teramoto, T., Shinohara, T., & Takiyama, A. (2020). Computer-aided classification of hepatocellular ballooning in liver biopsies from patients with NASH using persistent homology. Computers in Biology and Medicine, 195, 105614. https://doi.org/10.1016/j.cmpb.2020.105614
Rammal, A., Assaf, R., Goupil, A., Kacim, M., & Vrabie, V. (2022). Machine learning techniques on homological persistence features for prostate cancer diagnosis. BMC Bioinformatics, 23(1), 1–22. https://doi.org/10.1186/s12859-022-04992-5
Asaad, A., Ali, D., Majeed, T., & Rashid, R. (2022). Persistent homology for breast tumor classification using mammogram scans. Mathematics, 10(21), 1–13. https://doi.org/10.3390/math10214039
Oyama, A., et al. (2019). Hepatic tumor classification using texture and topology analysis of non-contrast-enhanced three-dimensional T1-weighted MR images with a radiomics approach. Scientific Reports, 9(1), 2–11. https://doi.org/10.1038/s41598-019-45283-z
Avilés-Rodríguez, G. J., et al. (2021). Topological data analysis for eye fundus image quality assessment. Diagnostics, 11(8). https://doi.org/10.3390/diagnostics11081322
Malek, A. A., Alias, M. A., Razak, F. A., Noorani, M. S., Mahmud, R., & Zulkepli, N. F. (2023). Persistent homology-based machine learning method for filtering and classifying mammographic microcalcification images in early cancer detection. Cancers, 15(9). https://doi.org/10.3390/cancers15092606
Hu, C. S., Lawson, A., Chen, J. S., Chung, Y. M., Smyth, C., & Yang, S. M. (2021). Toporesnet: A hybrid deep learning architecture and its application to skin lesion classification. Mathematics, 9(22), 1–22. https://doi.org/10.3390/math9222924
Atienza, N., Escudero, L. M., & Jimenez, M. J. (2019). Persistent entropy: A scale-invariant topological statistic for analysing cell arrangements, 1–14.
Leykam, D., Rondón, I., & Angelakis, D. G. (2022). Dark soliton detection using persistent homology. Chaos: An Interdisciplinary Journal of Nonlinear Science, 32(7), 73133. https://doi.org/10.1063/5.0097053
Rammal, A., Assaf, R., Goupil, A., Kacim, M., & Vrabie, V. (2022). Machine learning techniques on homological persistence features for prostate cancer diagnosis. BMC Bioinformatics, 23(1), 1–22. https://doi.org/10.1186/s12859-022-04992-5
Adams, H., et al. (2017). Persistence images: A stable vector representation of persistent homology. Journal of Machine Learning Research, 18, 1–35.
Teramoto, T., Shinohara, T., & Takiyama, A. (2020). Computer-aided classification of hepatocellular ballooning in liver biopsies from patients with NASH using persistent homology. Comput Methods Programs Biomed, 195. https://doi.org/10.1016/j.cmpb.2020.105614
Asaad, A., Ali, D., Majeed, T., & Rashid, R. (2022). Persistent homology for breast tumor classification using mammogram scans. Mathematics, 10(21). https://doi.org/10.3390/math10214039
Suckling, J. (1994). The mammographic image analysis society digital mammogram database. Exerpta Medica International Congress, 375–386.
Heath, M., Bowyer, K., Kopans, D., Moore, R., & Kegelmeyer, P. (2000). The digital database for screening mammography. In Fifth International Workshop on Digital Mammography (pp. 212–218). Toronto, Canada.
Goyal, B., Dogra, A., Agrawal, S., Sohi, B. S., & Sharma, A. (2020). Image denoising review: From classical to state-of-the-art approaches. Information Fusion, 55(September 2019), 220–244. https://doi.org/10.1016/j.inffus.2019.09.003
Michael, E., Ma, H., Li, H., Kulwa, F., & Li, J. (2021). Breast cancer segmentation methods: Current status and future potentials. Biomed Res Int, 2021. https://doi.org/10.1155/2021/9962109
Garg, S., Vijay, R., & Urooj, S. (2019). Statistical approach to compare image denoising techniques in medical MR images. Procedia Comput Sci, 152, 367–374. https://doi.org/10.1016/j.procs.2019.05.004
Zhang, X., Gao, W., Zhu, S., & Engineering, I. (2020). Research on noise reduction and enhancement of weld image. In 9th International Conference on Signal, Image Processing and Pattern Recognition (SPPR 2020) (pp. 13–26). https://doi.org/10.5121/csit.2020.101902
Ramadan, Z. M. (2018). Optimum image filters for various types of noise. TELKOMNIKA, 16(5), 2458–2464. https://doi.org/10.12928/TELKOMNIKA.v16i5.10508
Rybakova, E. O., Limonova, E. E., & Nikolaev, D. P. (2024). Fast Gaussian filter approximations comparison on SIMD computing platforms. Applied Sciences, 14(11). https://doi.org/10.3390/app14114664
Ramadan, S. Z. (2020). Methods used in computer-aided diagnosis for breast cancer detection using mammograms: A review. J Healthc Eng, 2020. https://doi.org/10.1155/2020/9162464
Günther, D., Jacobson, A., Reininghaus, J., Seidel, H. P., Sorkine-Hornung, O., & Weinkauf, T. (2014). Fast and memory-efficient topological denoising of 2D and 3D scalar fields. IEEE Trans Vis Comput Graph, 20(12), 2585–2594. https://doi.org/10.1109/TVCG.2014.2346432
Fan, L., Zhang, F., Fan, H., & Zhang, C. (2019). Brief review of image denoising techniques. Vis Comput Ind Biomed Art, 2(1), 7. https://doi.org/10.1186/s42492-019-0016-7
Avilés-Rodríguez, G. J., et al. (2021). Topological data analysis for eye fundus image quality assessment. Diagnostics, 11(8). https://doi.org/10.3390/diagnostics11081322
Otter, N., Porter, M. A., Tillmann, U., Grindrod, P., & Harrington, H. A. (2017). A roadmap for the computation of persistent homology. EPJ Data Sci, 6, 1–38.
Garin, A., & Tauzin, G. (2019). A topological ‘reading’ lesson: Classification of MNIST using TDA. In Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019 (pp. 1551–1556). https://doi.org/10.1109/ICMLA.2019.00256
Adams, H., et al. (2017). Persistence images: A stable vector representation of persistent homology. Journal of Machine Learning Research, 18, 1–35.
Iqbal, S., Qureshi, A. N., Li, J., & Mahmood, T. (2023). On the analyses of medical images using traditional machine learning techniques and convolutional neural networks. Springer Netherlands, 30(5). https://doi.org/10.1007/s11831-023-09899-9
Jiao, Y., & Du, P. (2016). Performance measures in evaluating machine learning based bioinformatics predictors for classifications. Quantitative Biology, 4(4), 320–330. https://doi.org/10.1007/s40484-016-0081-2
Yurdusev, A. A., Adem, K., & Hekim, M. (2023). Detection and classification of microcalcifications in mammograms images using difference filter and Yolov4 deep learning model. Biomed Signal Process Control, 80. https://doi.org/10.1016/j.bspc.2022.104360
Kaji, S., Sudo, T., & Ahara, K. (2020). Cubical Ripser: Software for computing persistent homology of image and volume data. D, 1–9. Retrieved from http://arxiv.org/abs/2005.12692
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Aminah Abdul Malek, Mohd Almie Alias, Fatimah Abdul Razak, Mohd Salmi Md Norani
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
