作者投稿
专家审稿
编辑办公
邮件订阅
RSS
Image Compression and Storage Algorithm of Histopathology Based on Matrix Calculation
-
摘要:
目的 评价基于矩阵计算的组织病理学图像压缩储存算法的临床应用价值，并寻求最佳图像压缩比。 方法 利用主成分分析法(principal component analysis，PCA)和奇异值分解法(singular value decomposition，SVD)两种经典矩阵算法，对低、中、高分化的宫颈癌组织免疫组化染色图像及HE染色图像进行压缩重建，并采用峰值信噪比和结构相似度针对图像重建质量进行评价。 结果 PCA重建图像压缩比为10.18(保留53个主成分)时，低、中、高分化宫颈癌组织免疫组化染色图像峰值信噪比均值分别为43.84±0.43、43.27±0.25、43.71±0.49，压缩图像结构相似度分别为0.964±0.004、0.963±0.006、0.965±0.005；HE染色图像峰值信噪比均值分别为43.41±0.78、42.95±1.03、43.52±0.69，压缩图像结构相似度分别为0.953±0.010、0.949±0.015、0.960±0.007。SVD重建图像压缩比为10.00(保留128个奇异值)时，低、中、高分化宫颈癌组织免疫组化染色图像峰值信噪比均值分别为39.89±1.69、38.20±2.19、40.90±0.50，压缩图像结构相似度分别为0.949±0.006、0.938±0.011、0.955±0.004；HE染色图像峰值信噪比均值分别为40.31±0.98、39.46±1.59、40.77±1.67，压缩图像结构相似度分别为0.965±0.006、0.943±0.010、0.969±0.005。 结论 采用PCA和SVD可实现对组织病理学图像进行压缩储存并获得较好的图像质量，为解决医院图像存储难题提供了解决方案。 Abstract:Objective To evaluate the clinical application value of the compression and storage algorithm of histopathological images based on matrix computing, and to seek the best image compression ratio. Methods Two classical matrix algorithms, principal component analysis (PCA) and singular value decomposition (SVD), were used to compress and reconstruct the immunohistochemical images and HE staining images of low, medium and high differentiated cervical cancer tissues. The peak signal-to-noise ratio(PSNR) and structural similarity (SSIM) were used to analyze and evaluate the quality of image reconstruction. Results When the compression ratio of PCA reconstruction image was 10.18 (53 principal components were retained), the mean PSNR of immunohistochemical images of low, medium and high differentiated cervical cancer tissues were 43.84±0.43, 43.27±0.25 and 43.71±0.49, respectively, and the SSIM were 0.964±0.004, 0.963±0.006 and 0.965±0.005, respectively. Meanwhile, the mean PSNR of HE staining images of low, medium and high differentiated cervical cancer tissues were 43.41±0.78, 42.95±1.03 and 43.52±0.69, respectively, and the SSIM were 0.953±0.010, 0.949±0.015 and 0.960±0.007, respectively. When the compression ratio of SVD reconstruction image was 10.00(128 singular values were retained), the mean PSNR of immunohistochemical images of low, medium and high differentiated cervical cancer tissues were 39.89±1.69, 38.20±2.19 and 40.90±0.50, respectively, and the SSIM were 0.949±0.006, 0.938±0.011 and 0.955±0.004, respectively. Meanwhile, the mean PSNR of HE staining images of low, medium and high differentiated cervical cancer tissues were 40.31±0.98, 39.46±1.59 and 40.77±1.67, respectively, and the SSIM were 0.965±0.006, 0.943±0.010 and 0.969±0.005, respectively. Conclusions PCA and SVD can compress and store histopathological images and obtain better image quality, which provides a solution to the problem of hospital image storage. 作者贡献：何睿琳负责结果分析、论文初稿撰写；刘子妤、杨欣怡负责临床试验；李晨、李晓燕构思论文框架、审核并修订论文。利益冲突：所有作者均声明不存在利益冲突 -
[1] Xu CX, Qi XG, Liu LF, et al. Research on performance of complex networks based on principal component analysis[J]. JCUPT, 2019, 26: 40-48. [2] Jaradat Y, Masoud M, Jannoud I, et al. A Tutorial on Singular Value Decomposition with Applications on Image Compression and Dimensionality Reduction[C]. 2021 International Conference on Information Technology (ICIT), 2021: 769-772. [3] Omar HM, Morsli M, Yaichi S, et al. Image Compression using Principal Component Analysis[C]. 2020 2nd International Conference on Mathematics and Information Technology (ICMIT), 2020: 226-231. [4] Lim ST, Yap DFW, Manap NA, et al. Medical image compression using block-based PCA algorithm[C]. 2014 International Conference on Computer, Communications, and Control Technology (I4CT), 2014: 171-175. [5] Yeganegi F, Hassanzade V, Ahadi SM. Comparative Performance Evaluation of SVD-Based Image Compression[C]. Electrical Engineering (ICEE), 2018: 464-469. [6] Guo P, Li D, Li X, et al. Deep OCT image compression with convolutional neural networks[J]. Biomed Opt Express, 2020, 11: 3543-3554. doi: 10.1364/BOE.392882 [7] Liu F, Hernandez-Cabronero M, Sanchez V, et al. The Current Role of Image Compression Standards in Medical Imaging[J]. Information (Basel), 2017, 8: 131. [8] Noreña T, Romero E. Compresión de imágenes médicas, et al. Medical image compression: a review[J]. Biomedica, 2013, 33: 137-151. [9] Chen Y, Janowczyk A, Madabhushi A, et al. Quantitative Assessment of the Effects of Compression on Deep Learning in Digital Pathology Image Analysis[J]. JCO Clin Cancer Inform, 2020, 4: 221-233. [10] Zhang X, Yu X. Color Image Reconstruction Based on Singular Value Decomposition of Quaternion Matrices[C]. 2018 2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), 2018: 2645-2647. [11] Alkandari A, Aljaber SJ. Principle Component Analysis algorithm (PCA) for image recognition[C]. 2015 Second International Conference on Computing Technology and Information Management (ICCTIM), 2015: 76-80. [12] Li SJ. Image compression based on SVD algorithm[C]. 2021 International Conference on Computer Information Science and Artificial Intelligence (CISAI), 2021: 306-309. [13] Pearson K. On lines and planes of closest fit to systems of points in space[J]. Philosophical Magazine, 1901, 2: 559-572. [14] 陈一虎. 基于SVD图像压缩技术研究[J]. 价值工程, 2011, 30: 169-170. https://www.cnki.com.cn/Article/CJFDTOTAL-JZGC201113120.htm -
下载:
点击查看大图
图(4)
计量
- 文章访问数: 240
- HTML全文浏览量: 54
- PDF下载量: 28
- 被引次数: 0
