Deep learning for denoising in a Mueller matrix microscope

Abstract

The Mueller matrix microscope is a powerful tool for characterizing the microstructural features of a complex biological sample. Performance of a Mueller matrix microscope usually relies on two major specifications: measurement accuracy and acquisition time, which may conflict with each other but both contribute to the complexity and expenses of the apparatus. In this paper, we report a learning-based method to improve both specifications of a Mueller matrix microscope using a rotating polarizer and a rotating waveplate polarization state generator. Low noise data from long acquisition time are used as the ground truth. A modified U-Net structured network incorporating channel attention effectively reduces the noise in lower quality Mueller matrix images obtained with much shorter acquisition time. The experimental results show that using high quality Mueller matrix data as ground truth, such a learning-based method can achieve both high measurement accuracy and short acquisition time in polarization imaging.

Near-real-time Mueller polarimetric image processing for neurosurgical intervention

“…The evaluated polarimetric instances comprised denoised and derived , as well as the scalar maps D , , R , and . Image quality scores including the root-mean-squared error (RMSE), the normalised peak signal-to-noise ratio (nPSNR) and the structural similarity index (SSIM) were pixel-wise computed for the paired test data, as in [ 23 ]. Values and deviations of angular data ( R and ), were computed with circular statistics and reported in degrees.…”

Data-driven polarimetric imaging: a review

“…Finally, the application fields tend to be semantic tasks based on convolutional enhancement or restoration imaging. Initially, image processing was the main field applied by data-driven polarimetric imaging, such as descattering imaging [46][47][48][49]66,70,72,76 , denoising 45,77,78 , demosaicing 43,44,68 , dynamic range enhancement 79 , reflection removal 53,73,74 , low-light imaging 42,50 , and even 3D reconstruction shape 64,65,67,71,80,81 . Next, semantic tasks appeared gradually similar to semantic segmentation 56,57,69,82,83 , camouflage object detection 84 , classification 60,61 , pathological diagnosis 62,63,85,86,87 .…”

“…However, all channel-wise features are treated equally, resulting in a lack of flexibility. Inspired by the attention mechanism, Liu et al proposed an attentionbased residual neural network to remove noise and restore the polarization information of polarimetric images 77 , as Fig. 7.…”

“…Compared to the MSE, the MAE has less blurriness and noise; however, it is more unstable. The utilization of the MAE loss function was similar to that of MSE because the range of AoLP is 0 to π that always maps into 0-1 77 . However, 0 and 1 indicate the same physical meaning where the error is the largest.…”

“…Frobenius matrix norm 45,46,68 Section Restoration and enhancement of accurate polarization information, Section Polarimetric descattering Weighted mean squared error (WMSE) 70 Section Polarimetric descattering Preceptual loss 53,70,77 Section Polarimetric descattering Mean squared error (MSE) 46,48,49,61,65,71−74,76−78 Section Restoration and enhancement of accurate polarization information, Section Polarimetric descattering, Section Three-dimensional shape reconstruction, Section Reflection removal…”