Zebrafish Histotomography Noise Removal In Projection And Reconstruction Domains

X-ray “Histotomography” built on the basic principles of CT can be used to create 3D images of zebrafish at resolutions one thousand times greater than CT, enabling the visualization of cell nuclei and other subcellular structures in 3D. Noise in the scans caused either through natural Xray phenomena or other distortions can lead to low accuracy in tasks related to detection and segmentation of anatomically significant objects. We evaluate the use of supervised Encoder-Decoder models for noise removal in projection and reconstruction domain images in absence of clean training targets. We propose the use of a Noise-2-Noise architecture with U-Net backbone along with structural similarity index loss as an addendum to help maintain and sharpen pathologically relevant details. We empirically show that our technique outperforms existing methods, with an average peak signal to noise ratio (PSNR) gain of 14. 50dB and 15. 05dB for noise removal in the reconstruction domain when trained without and with clean targets respectively. Using the same network architecture, we obtain a gain in structural similarity index (SSIM) in the projection domain by an average of 0.213 when trained without clean targets and 0.259 with clean targets. Additionally, by comparing reconstructions from denoised projections with those from original projections, we establish that noise removal in the projection domain is beneficial to improve the quality of reconstructed scans.

[1]  Yining Zhu,et al.  Noise reduction with low dose CT data based on a modified ROF model. , 2012, Optics express.

[2]  Andreas K. Maier,et al.  Noise reduction in low-dose ct using a 3D multiscale sparse denoising autoencoder , 2017, 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP).

[3]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[4]  Klaus Mueller,et al.  Low-Dose CT Streak Artifacts Removal using Deep Residual Neural Network , 2017 .

[5]  Guang Li,et al.  CT Super-Resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE) , 2018, IEEE Transactions on Medical Imaging.

[6]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[7]  Jong Chul Ye,et al.  Cycle‐consistent adversarial denoising network for multiphase coronary CT angiography , 2018, Medical physics.

[8]  Kavita Tewari,et al.  Efficient Removal of Impulse Noise in Digital Images , 2012 .

[9]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[10]  P. Switzer,et al.  A transformation for ordering multispectral data in terms of image quality with implications for noise removal , 1988 .

[11]  Uwe Kruger,et al.  Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction , 2019, Nat. Mach. Intell..

[12]  Ziyang Zeng,et al.  DN-GAN: Denoising generative adversarial networks for speckle noise reduction in optical coherence tomography images , 2020, Biomed. Signal Process. Control..

[13]  Karen O. Egiazarian,et al.  Image denoising with block-matching and 3D filtering , 2006, Electronic Imaging.

[14]  Frederick R. Forst,et al.  On robust estimation of the location parameter , 1980 .

[15]  Javad Alirezaie,et al.  Low-dose CT Denoising Using Edge Detection Layer and Perceptual Loss , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[16]  Jan Kautz,et al.  Loss Functions for Image Restoration With Neural Networks , 2017, IEEE Transactions on Computational Imaging.

[17]  Sang Joon Lee,et al.  Whole-body imaging of a hypercholesterolemic female zebrafish by using synchrotron X-ray micro-CT. , 2015, Zebrafish.

[18]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[19]  Feng Lin,et al.  Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network , 2017, IEEE Transactions on Medical Imaging.

[20]  Manoj Kumar,et al.  A review on CT image noise and its denoising , 2018, Biomed. Signal Process. Control..

[21]  Francesco De Carlo,et al.  Computational 3D histological phenotyping of whole zebrafish by X-ray histotomography , 2019, eLife.

[22]  L. Zon,et al.  Transparent adult zebrafish as a tool for in vivo transplantation analysis. , 2008, Cell stem cell.