Phase unwrapping using Deep Learning in Holographic Tomography - dataset.

This dataset contains two types of data: phase images and trained model files. Real phase images - these phase images are contained with the files named with the prefix "real_". The type of the data files is ".npz", to be loaded with NumPy (np.load()), as a dictionary. The data is stored within the key ["arr_0"]. The images depict cells [1], organoids [2], phantoms [3-4] and regular 3D printed structures with high scattering properties [5]. The images have been augmented in order to expand the volume of the training dataset. All images are of shape (256,256,1). It is a big dataset containing 27,189 images of each type for training the unwrapping model: unwrapped - continuous phase distribution (float32) wrapped - phase wrapped into mod2\(\pi\) (float32) wrapcount - wrap count phase maps coded in the integer form (0,1,2...) (uint8) Synthetic phase images - phase images in these files were generated algorithmically in the MATLAB programming language. The files containing this dataset have a prefix "synthetic_". The type of the data files is ".npz", to be loaded with NumPy (np.load()), as a dictionary. The data is stored within the key ["arr_0"]. Phase images contained in the synthetic dataset can be split into 3 types by their type: spherical distribution, simulated cells w/ spherical background and simulated cells w/ introduced linear tilt. All images are of shape (256,256,1). This dataset contains 10,000 images of each type for training the unwrapping and denoising models: unwrapped - continuous phase distribution (float32) wrapped - phase wrapped into mod2\(\pi\) (float32) wrapcount - wrap count phase maps coded in the integer form (0,1,2...) (uint8) noised - wrapped phase images w/ synthetic noise (float32). Trained models - trained model files. These model files are in the format ".h5", which contains the model architecture and the weights. They have been developed and saved with the keras library, and are loaded with the keras.models.load_model() function. The models list: Unet_Denoising.h5 - U-Net model used for denoising as an image translation task. The input is a wrapped phase image with noise and the output is the same wrapped phase distribution, but denoised. Model is trained on the synthetic phase dataset. Attn_Unet_Unwrapping.h5 - U-Net model with Attention Gates and Residual Blocks trained for the semantic segmentation task. The input of the model is the wrapped phase image and its output is the wrap count map. Model is trained on the real phase dataset. [1] M. Baczewska, W. Krauze, A. Kuś, P. Stępień, K. Tokarska, K. Zukowski, E. Malinowska, Z. Brzózka, and M. Kujawińska, “On-chip holographic tomography for quantifying refractive index changes of cells’ dynamics,” in Quantitative Phase Imaging VIII, vol. 11970 Y. Liu, G. Popescu, and Y. Park, eds., International Society for Optics and Photonics (SPIE, 2022), p. 1197008. [2] P. Stępień, M. Ziemczonok, M. Kujawińska, M. Baczewska, L. Valenti, A. Cherubini, E. Casirati, and W. Krauze, “Numerical refractive index correction for the stitching procedure in tomographic quantitative phase imaging,” Biomed. Opt. Express 13, 5709–5720 (2022). [3] M. Ziemczonok, A. Kuś, P. Wasylczyk, and M. Kujawińska, “3d-printed biological cell phantom for testing 3d quantitative phase imaging systems,” Sci. Reports 9, 1–9 (2019). [4] M. Ziemczonok, A. Kuś, and M. Kujawińska, “Optical diffraction tomography meets metrology — measurement accuracy on cellular and subcellular level,” Measurement 195, 111106 (2022). [5] W. Krauze, A. Kuś, M. Ziemczonok, M. Haimowitz, S. Chowdhury, and M. Kujawińska, “3d scattering microphantom sample to assess quantitative accuracy in tomographic phase microscopy techniques,” Sci. Reports 12, 1–9 (2022).本数据集包含两类数据：相位图像与训练好的模型文件。 ## 真实相位图像 此类相位图像存储于前缀为“real_”的文件中，数据文件格式为“.npz”，需通过NumPy的`np.load()`函数加载为字典，数据存储于键`["arr_0"]`中。图像涵盖细胞[1]、类器官[2]、体模[3-4]以及具有高散射特性的常规3D打印结构[5]。为扩充训练数据集规模，所有图像均经过数据增强处理。所有图像的尺寸均为(256, 256, 1)。本数据集包含每种类型的27189张图像，用于训练相位解包裹模型： - 解包裹相位：连续相位分布（float32格式） - 包裹相位：相位经mod2π包裹处理（float32格式） - 包裹计数：以整数形式（0, 1, 2…）编码的包裹计数相位图（uint8格式） ## 合成相位图像 此类相位图像通过MATLAB编程语言算法生成，存储于前缀为“synthetic_”的文件中，数据文件格式为“.npz”，需通过NumPy的`np.load()`函数加载为字典，数据存储于键`["arr_0"]`中。合成数据集内的相位图像可分为三类：球形相位分布、带有球形背景的模拟细胞、带有引入线性倾斜的模拟细胞。所有图像的尺寸均为(256, 256, 1)。本数据集包含每种类型的10000张图像，用于训练相位解包裹与去噪模型： - 解包裹相位：连续相位分布（float32格式） - 包裹相位：相位经mod2π包裹处理（float32格式） - 包裹计数：以整数形式（0, 1, 2…）编码的包裹计数相位图（uint8格式） - 带噪图像：带有合成噪声的包裹相位图像（float32格式） ## 训练好的模型 此类模型文件格式为“.h5”，包含模型架构与权重，通过Keras库开发并保存，可使用`keras.models.load_model()`函数加载。包含的模型列表如下： - `Unet_Denoising.h5`：用于图像翻译任务的U-Net去噪模型，输入为带噪包裹相位图像，输出为去噪后的相同包裹相位分布，基于合成相位数据集训练得到。 - `Attn_Unet_Unwrapping.h5`：带有注意力门与残差块的U-Net模型，用于语义分割任务，输入为包裹相位图像，输出为包裹计数图，基于真实相位数据集训练得到。 ## 参考文献 [1] Baczewska M, Krauze W, Kuś A, Stępień P, Tokarska K, Zukowski K, Malinowska E, Brzózka Z, Kujawińska M. 用于量化细胞动态折射率变化的片上全息层析成像[C]// 定量相位成像VIII. 刘颖, Popescu G, Park Y, 编. 国际光学与光子学学会(SPIE), 2022: 1197008. [2] Stępień P, Ziemczonok M, Kujawińska M, Baczewska M, Valenti L, Cherubini A, Casirati E, Krauze W. 层析定量相位成像拼接程序的数值折射率校正[J]. 生物医学光学快报, 2022, 13: 5709–5720. [3] Ziemczonok M, Kuś A, Wasylczyk P, Kujawińska M. 用于测试3D定量相位成像系统的3D打印生物细胞体模[J]. 科学报告, 2019, 9: 1–9. [4] Ziemczonok M, Kuś A, Kujawińska M. 光学衍射层析与计量学结合：细胞及亚细胞水平的测量精度[J]. 测量, 2022, 195: 111106. [5] Krauze W, Kuś A, Ziemczonok M, Haimowitz M, Chowdhury S, Kujawińska M. 用于评估层析相位显微技术定量精度的3D散射微体模样品[J]. 科学报告, 2022, 12: 1–9.