Image quality assessment in multiband DCT domain based on SSIM

The performance of image quality assessment method based on SSIM (structural similarity) is better than the PSNR (peak signal to noise ratio), but the assessment effects of SSIM is poor for seriously blurred image, therefore, the model that combined HVS (human visual sensitivity) and SSIM was established. The basic idea is based on the human eye's sensitivity to different frequency distortion image, the image is two-dimensional discrete cosine transform frequency component into low, mid, high-frequency component, to obtain the frequency component of light, contrast and structural information, using Pearson coefficient for weight and sum processing to the sub-image according to frequency bands of different sensitive degree, finally, get the sharpness of the image. Through nonlinear regression analysis of objective assessment and DMOS, experiments showed that this method was closer to human perception than SSIM and GSSIM for serious blurred distortion image. At the same time, compared to conventional algorithm MAE (mean absolute error), MSE (mean square error) and PSNR, this model was more consistent with human visual characteristics.     

Accelerated free-breathing 3D whole-heart magnetic resonance angiography with a radial phyllotaxis trajectory,compressed sensing,and curvelet transform

PurposeTo develop and validate an accelerated free-breathing 3D whole-heart magnetic resonance angiography (MRA) technique using a radial k-space trajectory with compressed sensing and curvelet transform.MethodA 3D radial phyllotaxis trajectory was implemented to traverse the centerline of k-space immediately before the segmented whole-heart MRA data acquisition at each cardiac cycle. The k-space centerlines were used to correct the respiratory-induced heart motion in the acquired MRA data. The corrected MRA data were then reconstructed by a novel compressed sensing algorithm using curvelets as the sparsifying domain. The proposed 3D whole-heart MRA technique (radial CS curvelet) was then prospectively validated against compressed sensing with a conventional wavelet transform (radial CS wavelet) and a standard Cartesian acquisition in terms of scan time and border sharpness.ResultsFifteen patients (females 10, median age 34-year-old) underwent 3D whole-heart MRA imaging using a standard Cartesian trajectory and our proposed radial phyllotaxis trajectory. Scan time for radial phyllotaxis was significantly shorter than Cartesian (4.88 ± 0.86 min. vs. 6.84 ± 1.79 min., P-value = 0.004). Radial CS curvelet border sharpness was slightly lower than Cartesian and, for the majority of vessels, was significantly better than radial CS wavelet (P-value < 0.050).ConclusionThe proposed technique of 3D whole-heart MRA acquisition with a radial CS curvelet has a shorter scan time and slightly lower vessel sharpness compared to the Cartesian acquisition with radial profile ordering, and has slightly better sharpness than radial CS wavelet. Future work on this technique includes additional clinical trials and extending this technique to 3D cine imaging.     

Deep learning for radial SMS myocardial perfusion reconstruction using the 3D residual booster U-net

PurposeTo develop an end-to-end deep learning solution for quickly reconstructing radial simultaneous multi-slice (SMS) myocardial perfusion datasets with comparable quality to the pixel tracking spatiotemporal constrained reconstruction (PT-STCR) method.MethodsDynamic contrast enhanced (DCE) radial SMS myocardial perfusion data were obtained from 20 subjects who were scanned at rest and/or stress with or without ECG gating using a saturation recovery radial CAIPI turboFLASH sequence. Input to the networks consisted of complex coil combined images reconstructed using the inverse Fourier transform of undersampled radial SMS k-space data. Ground truth images were reconstructed using the PT-STCR pipeline. The performance of the residual booster 3D U-Net was tested by comparing it to state-of-the-art network architectures including MoDL, CRNN-MRI, and other U-Net variants.ResultsResults demonstrate significant improvements in speed requiring approximately 8 seconds to reconstruct one radial SMS dataset which is approximately 200 times faster than the PT-STCR method. Images reconstructed with the residual booster 3D U-Net retain quality of ground truth PT-STCR images (0.963 SSIM/40.238 PSNR/0.147 NRMSE). The residual booster 3D U-Net has superior performance compared to existing network architectures in terms of image quality, temporal dynamics, and reconstruction time.ConclusionResidual and booster learning combined with the 3D U-Net architecture was shown to be an effective network for reconstructing high-quality images from undersampled radial SMS datasets while bypassing the reconstruction time of the PT-STCR method.     

Fast single image super-resolution using estimated low-frequency k-space data in MRI

PurposeSingle image super-resolution (SR) is highly desired in many fields but obtaining it is often technically limited in practice. The purpose of this study was to propose a simple, rapid and robust single image SR method in magnetic resonance (MR) imaging (MRI).MethodsThe idea is based on the mathematical formulation of the intrinsic link in k-space between a given (modulus) low-resolution (LR) image and the desired SR image. The method consists of two steps: 1) estimating the low-frequency k-space data of the desired SR image from a single LR image; 2) reconstructing the SR image using the estimated low-frequency and zero-filled high-frequency k-space data. The method was evaluated on digital phantom images, physical phantom MR images and real brain MR images, and compared with existing SR methods.ResultsThe proposed SR method exhibited a good robustness by reaching a clearly higher PSNR (25.77dB) and SSIM (0.991) averaged over different noise levels in comparison with existing edge-guided nonlinear interpolation (EGNI) (PSNR=23.78dB, SSIM=0.983), zero-filling (ZF) (PSNR=24.09dB, SSIM=0.985) and total variation (TV) (PSNR=24.54dB, SSIM=0.987) methods while presenting the same order of computation time as the ZF method but being much faster than the EGNI or TV method. The average PSNR or SSIM over different slice images of the proposed method (PSNR=26.33 dB or SSIM=0.955) was also higher than the EGNI (PSNR=25.07dB or SSIM=0.952), ZF (PSNR=24.97dB or SSIM=0.950) and TV (PSNR=25.70dB or SSIM=0.953) methods, demonstrating its good robustness to variation in anatomical structure of the images. Meanwhile, the proposed method always produced less ringing artifacts than the ZF method, gave a clearer image than the EGNI method, and did not exhibit any blocking effect presented in the TV method. In addition, the proposed method yielded the highest spatial consistency in the inter-slice dimension among the four methods.ConclusionsThis study proposed a fast, robust and efficient single image SR method with high spatial consistency in the inter-slice dimension for clinical MR images by estimating the low-frequency k-space data of the desired SR image from a single spatial modulus LR image.     

Correction of out-of-FOV motion artifacts using convolutional neural network

PurposeSubject motion during MRI scan can result in severe degradation of image quality. Existing motion correction algorithms rely on the assumption that no information is missing during motions. However, this assumption does not hold when out-of-FOV motion happens. Currently available algorithms are not able to correct for image artifacts introduced by out-of-FOV motion. The purpose of this study is to demonstrate the feasibility of incorporating convolutional neural network (CNN) derived prior image into solving the out-of-FOV motion problem.Methods and materialsA modified U-net network was proposed to correct out-of-FOV motion artifacts by incorporating motion parameters into the loss function. A motion model based data fidelity term was applied in combination with the CNN prediction to further improve the motion correction performance. We trained the CNN on 1113 MPRAGE images with simulated oscillating and sudden motion trajectories, and compared our algorithm to a gradient-based autofocusing (AF) algorithm in both 2D and 3D images. Additional experiment was performed to demonstrate the feasibility of transferring the networks to different dataset. We also evaluated the robustness of this algorithm by adding Gaussian noise to the motion parameters. The motion correction performance was evaluated using mean square error (NMSE), peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM).ResultsThe proposed algorithm outperformed AF-based algorithm for both 2D (NMSE: 0.0066 ± 0.0009 vs 0.0141 ± 0.008, P < .01; PSNR: 29.60 ± 0.74 vs 21.71 ± 0.27, P < .01; SSIM: 0.89 ± 0.014 vs 0.73 ± 0.004, P < .01) and 3D imaging (NMSE: 0.0067 ± 0.0008 vs 0.070 ± 0.021, P < .01; PSNR: 32.40 ± 1.63 vs 22.32 ± 2.378, P < .01; SSIM: 0.89 ± 0.01 vs 0.62 ± 0.03, P < .01). Robust reconstruction was achieved with 20% data missed due to the out-of-FOV motion.ConclusionIn conclusion, the proposed CNN-based motion correction algorithm can significantly reduce out-of-FOV motion artifacts and achieve better image quality compared to AF-based algorithm.     

基于深度反向投影的感知增强超分辨率重建模型

以SRCNN（super-resolution convolutional neural network）模型为代表的超分辨率重建模型通常都有很高的PSNR（peak signal to noise ratio）和SSIM（structural similarity）值，但其在视觉感知上并不令人满意，而以SRGAN为代表的拥有高感知质量的GAN（generative adversarial networks）模型却很容易产生大量的伪细节，这表现在其PSNR和SSIM值通常都较低。针对上述问题，提出了一种基于深度反向投影的感知增强超分辨率重建模型。该模型采用双尺度自适应加权融合特征提取模块进行特征提取，然后通过深度反向投影进行上采样，最终由增强模块增强后得到最终输出。模型采用残差连接与稠密连接，有助于特征的共享以及模型的有效训练。在指标评价上，引入了基于学习的LPIPS（learned perceptual image patch similarity）度量作为新的图像感知质量评价指标，与PSNR、SSIM一起作为模型评价指标。实验结果表明，模型在测试数据集上PSNR、SSIM、LPIPS的平均值分别为27.84、0.7320、0.1258，各项指标均优于对比算法。     

Denoising arterial spin labeling perfusion MRI with deep machine learning

PurposeArterial spin labeling (ASL) perfusion MRI is a noninvasive technique for measuring cerebral blood flow (CBF) in a quantitative manner. A technical challenge in ASL MRI is data processing because of the inherently low signal-to-noise-ratio (SNR). Deep learning (DL) is an emerging machine learning technique that can learn a nonlinear transform from acquired data without using any explicit hypothesis. Such a high flexibility may be particularly beneficial for ASL denoising. In this paper, we proposed and validated a DL-based ASL MRI denoising algorithm (DL-ASL).MethodsThe DL-ASL network was constructed using convolutional neural networks (CNNs) with dilated convolution and wide activation residual blocks to explicitly take the inter-voxel correlations into account, and preserve spatial resolution of input image during model learning.ResultsDL-ASL substantially improved the quality of ASL CBF in terms of SNR. Based on retrospective analyses, DL-ASL showed a high potential of reducing 75% of the original acquisition time without sacrificing CBF measurement quality.ConclusionDL-ASL achieved improved denoising performance for ASL MRI as compared with current routine methods in terms of higher PSNR, SSIM and Radiologic scores. With the help of DL-ASL, much fewer repetitions may be prescribed in ASL MRI, resulting in a great reduction of the total acquisition time.     

Objective Indices of Perceived Vocal Strain

BackgroundA limited number of experiments have investigated the perception of strain compared to the voice qualities of breathiness and roughness despite its widespread occurrence in patients who have hyperfunctional voice disorders, adductor spasmodic dysphonia, and vocal fold paralysis among others.ObjectiveThe purpose of this study is to determine the perceptual basis of strain through identification and exploration of acoustic and psychoacoustic measures.MethodsTwelve listeners evaluated the degree of strain for 28 dysphonic phonation samples on a five-point rating scale task. Computational estimates based on cepstrum, sharpness, and spectral moments (linear and transformed with auditory processing front-end) were correlated to the perceptual ratings.ResultsPerceived strain was strongly correlated with cepstral peak prominence, sharpness, and a subset of the spectral metrics. Spectral energy distribution measures from the output of an auditory processing front-end (ie, excitation pattern and specific loudness pattern) accounted for 77–79% of the model variance for strained voices in combination with the cepstral measure.ConclusionsModeling the perception of strain using an auditory front-end prior to acoustic analysis provides better characterization of the perceptual ratings of strain, similar to our prior work on breathiness and roughness. Results also provide evidence that the sharpness model of Fastl and Zwicker (2007) is one of the strong predictors of strain perception.     

Gradient induced artifacts in simultaneous EEG-fMRI: Effect of synchronization on spiral and EPI k-space trajectories

The nature of the gradient induced electroencephalography (EEG) artifact is analyzed and compared for two functional magnetic resonance imaging (fMRI) pulse sequences with different k-space trajectories: echo planar imaging (EPI) and spiral. Furthermore, the performance of the average artifact subtraction algorithm (AAS) to remove the gradient artifact for both sequences is evaluated. The results show that the EEG gradient artifact for spiral sequences is one order of magnitude higher than for EPI sequences due to the chirping spectrum of the spiral sequence and the dB/dt of its crusher gradients. However, in the presence of accurate synchronization, the use of AAS yields the same artifact suppression efficiency for both pulse sequences below 80 Hz. The quality of EEG signal after AAS is demonstrated for phantom and human data. EEG spectrogram and visual evoked potential (VEP) are compared outside the scanner and use both EPI and spiral pulse sequences. MR related artifact residues affect the spectra over 40 Hz (less than 0.2 μV up to 120 Hz) and modify the amplitude of P1, N2 and P300 in the VEP. These modifications in the EEG signal have to be taken into account when interpreting EEG data acquired in simultaneous EEG-fMRI experiments.     

高超声速流场成像质量特性及校正方法

光学成像制导飞行器在大气层中以高超声速飞行时，其成像窗口附近强压缩流场的气动光学效应会导致成像过程出现抖动、偏移和模糊，影响制导精度.为研究该问题，搭建了基于高超声速（Ma = 6.0）炮风洞的气动光学地面模拟平台.利用高速摄像机获取了多种喷流压比状态下光学头罩成像图片，研究了成像特性.基于背景纹影技术（background oriented schlieren，BOS）直接获取气动光学畸变的点扩散函数信息，结合Wiener滤波方法对地面模拟平台获取的成像畸变结果进行了校正，并结合灰度分布、峰值信噪比（peak signal-to-noise ratio，PSNR）和结构相似度（structural similarity，SSIM）对校正结果进行了定性和定量评价.成像结果表明，头罩无冷却喷流时成像质量最好，在压力匹配附近头罩成像质量相对于欠压喷流和过压喷流成像质量较好.图像校正结果表明，风洞运行过程中采集的时间序列图像在校正之后所对应的灰度分布情况、PSNR和SSIM都得到提高.      

A new perceptual difference model for diagnostically relevant quantitative image quality evaluation: A preliminary study

Purpose

Most objective image quality metrics average over a wide range of image degradations. However, human clinicians demonstrate bias toward different types of artifacts. Here, we aim to create a perceptual difference model based on Case-PDM that mimics the preference of human observers toward different artifacts.

Method

We measured artifact disturbance to observers and calibrated the novel perceptual difference model (PDM). To tune the new model, which we call Artifact-PDM, degradations were synthetically added to three healthy brain MR data sets. Four types of artifacts (noise, blur, aliasing or “oil painting” which shows up as flattened, over-smoothened regions) of standard compressed sensing (CS) reconstruction, within a reasonable range of artifact severity, as measured by both PDM and visual inspection, were considered. After the model parameters were tuned by each synthetic image, we used a functional measurement theory pair-comparison experiment to measure the disturbance of each artifact to human observers and determine the weights of each artifact's PDM score. To validate Artifact-PDM, human ratings obtained from a Double Stimulus Continuous Quality Scale experiment were compared to the model for noise, blur, aliasing, oil painting and overall qualities using a large set of CS-reconstructed MR images of varying quality. Finally, we used this new approach to compare CS to GRAPPA, a parallel MRI reconstruction algorithm.

Results

We found that, for the same Artifact-PDM score, the human observer found incoherent aliasing to be the most disturbing and noise the least. Artifact-PDM results were highly correlated to human observers in both experiments. Optimized CS reconstruction quality compared favorably to GRAPPA's for the same sampling ratio.

Conclusions

We conclude our novel metric can faithfully represent human observer artifact evaluation and can be useful in evaluating CS and GRAPPA reconstruction algorithms, especially in studying artifact trade-offs.     

Lung MRI assessment with high-frequency noninvasive ventilation at 3 T

PurposeTo investigate three MR pulse sequences under high-frequency noninvasive ventilation (HF-NIV) at 3 T and determine which one is better-suited to visualize the lung parenchyma.MethodsA 3D ultra-short echo time stack-of spirals Volumetric Interpolated Breath-hold Examination (UTE Spiral VIBE), without and with prospective gating, and a 3D double-echo UTE sequence with spiral phyllotaxis trajectory (3D radial UTE) were performed at 3 T in ten healthy volunteers under HF-NIV. Three experienced radiologists evaluated visibility and sharpness of normal anatomical structures, artifacts assessment, and signal and contrast ratio computation. The median of the three readers‘scores was used for comparison, p < .05 was considered statistically significant. Incidental findings were recorded and reported.ResultsThe 3D radial UTE resulted in less artifacts than the non-gated and gated UTE Spiral VIBE in inferior (score _{3D radial UTE} = 3, slight artifact without blurring vs. score _{UTE Spiral VIBE non-gated and gated} = 2, moderate artifact with blurring of anatomical structure, p = .018 and p = .047, respectively) and superior lung regions (score _{3D radial UTE} = 3, vs. score _{UTE Spiral VIBE non-gated} = 2.5, p = .48 and score _{UTE Spiral VIBE gated} = 1, severe artifact with no normal structure recognizable, p = .014), and higher signal and contrast ratios (p = .002, p = .093). UTE Spiral VIBE sequences provided higher peripheral vasculature visibility than the 3D radial UTE (94.4% vs 80.6%, respectively, p < .001). The HF-NIV was well tolerated by healthy volunteers who reported on average minor discomfort. In three volunteers, 12 of 18 nodules confirmed with low-dose CT were identified with MRI (average size 2.6 ± 1.2 mm).ConclusionThe 3D radial UTE provided higher image quality than the UTE Spiral VIBE. Nevertheless, a better nodule assessment was noticed with the UTE Spiral VIBE that might be due to better peripheral vasculature visibility, and requires confirmation in a larger cohort.     

IKWI-net: A cross-domain convolutional neural network for undersampled magnetic resonance image reconstruction

Magnetic resonance imaging (MRI) is widely used to get the information of anatomical structure and physiological function with the advantages of high resolution and non-invasive scanning. But the long acquisition time limits its application. To reduce the time consumption of MRI, compressed sensing (CS) theory has been proposed to reconstruct MRI images from undersampled k-space data. But conventional CS methods mostly use iterative methods that take lots of time. Recently, deep learning methods are proposed to achieve faster reconstruction, but most of them only pay attention to a single domain, such as the image domain or k-space. To take advantage of the feature representation in different domains, we propose a cross-domain method based on deep learning, which first uses convolutional neural networks (CNNs) in the image domain, k-space and wavelet domain simultaneously. The combined order of the three domains is also first studied in this work, which has a significant effect on reconstruction. The proposed IKWI-net achieves the best performance in various combinations, which utilizes CNNs in the image domain, k-space, wavelet domain and image domain sequentially. Compared with several deep learning methods, experiments show it also achieves mean improvements of 0.91 dB in peak signal-to-noise ratio (PSNR) and 0.005 in structural similarity (SSIM).     

Visual and Automatic Evaluation of Vocal Fold Mucosal Waves Through Sharpness of Lateral Peaks in High-Speed Videokymographic Images

IntroductionThe sharpness of lateral peaks is a visually helpful clinical feature in high-speed videokymographic (VKG) images indicating vertical phase differences and mucosal waves on the vibrating vocal folds and giving insights into the health and pliability of vocal fold mucosa. This study aims at investigating parameters that can be helpful in objectively quantifying the lateral peak sharpness from the VKG images.MethodForty-five clinical VKG images with different degrees of sharpness of lateral peaks were independently evaluated visually by three raters. The ratings were compared to parameters obtained by automatic image analysis of the vocal fold contours: Open Time Percentage Quotients (OTQ) and Plateau Quotients (PQ). The OTQ parameters were derived as fractions of the period during which the vocal fold displacement exceeds a predetermined percentage of the vibratory amplitude. The PQ parameters were derived similarly but as a fraction of the open phase instead of a period.ResultsThe best correspondence between the visual ratings and the automatically derived quotients were found for the OTQ and PQ parameters derived at 95% and 80% of the amplitude, named OTQ₉₅, PQ₉₅, OTQ₈₀ and PQ₈₀. Their Spearman's rank correlation coefficients were in the range of 0.73 to 0.77 (P < 0.001) indicating strong relationships with the visual ratings. The strengths of these correlations were similar to those found from inter-rater comparisons of visual evaluations of peak sharpness.ConclusionThe Open time percentage and Plateau quotients at 95% and 80% of the amplitude stood out as the possible candidates for capturing the sharpness of the lateral peaks with their reliability comparable to that of visual ratings.     

A multi-scale variational neural network for accelerating motion-compensated whole-heart 3D coronary MR angiography

PurposeTo enable fast reconstruction of undersampled motion-compensated whole-heart 3D coronary magnetic resonance angiography (CMRA) by learning a multi-scale variational neural network (MS-VNN) which allows the acquisition of high-quality 1.2 × 1.2 × 1.2 mm isotropic volumes in a short and predictable scan time.MethodsEighteen healthy subjects and one patient underwent free-breathing 3D CMRA acquisition with variable density spiral-like Cartesian sampling, combined with 2D image navigators for translational motion estimation/compensation. The proposed MS-VNN learns two sets of kernels and activation functions for the magnitude and phase images of the complex-valued data. For the magnitude, a multi-scale approach is applied to better capture the small calibre of the coronaries. Ten subjects were considered for training and validation. Prospectively undersampled motion-compensated data with 5-fold and 9-fold accelerations, from the remaining 9 subjects, were used to evaluate the framework. The proposed approach was compared to Wavelet-based compressed-sensing (CS), conventional VNN, and to an additional fully-sampled (FS) scan.ResultsThe average acquisition time (m:s) was 4:11 for 5-fold, 2:34 for 9-fold acceleration and 18:55 for fully-sampled. Reconstruction time with the proposed MS-VNN was ~14 s. The proposed MS-VNN achieves higher image quality than CS and VNN reconstructions, with quantitative right coronary artery sharpness (CS:43.0%, VNN:43.9%, MS-VNN:47.0%, FS:50.67%) and vessel length (CS:7.4 cm, VNN:7.7 cm, MS-VNN:8.8 cm, FS:9.1 cm) comparable to the FS scan.ConclusionThe proposed MS-VNN enables 5-fold and 9-fold undersampled CMRA acquisitions with comparable image quality that the corresponding fully-sampled scan. The proposed framework achieves extremely fast reconstruction time and does not require tuning of regularization parameters, offering easy integration into clinical workflow.     

Rapid acquisition of magnetic resonance imaging of the shoulder using three-dimensional fast spin echo sequence with compressed sensing

PurposeTo evaluate the feasibility of 3D fast spin-echo (FSE) imaging with compressed sensing (CS) for the assessment of shoulder.Materials and methodsTwenty-nine patients who underwent shoulder MRI including image sets of axial 3D-FSE sequence without CS and with CS, using an acceleration factor of 1.5, were included. Quantitative assessment was performed by calculating the root mean square error (RMSE) and structural similarity index (SSIM). Two musculoskeletal radiologists compared image quality of 3D-FSE sequences without CS and with CS, and scored the qualitative agreement between sequences, using a five-point scale. Diagnostic agreement for pathologic shoulder lesions between the two sequences was evaluated.ResultsThe acquisition time of 3D-FSE MRI was reduced using CS (3 min 23 s vs. 2 min 22 s). Quantitative evaluations showed a significant correlation between the two sequences (r = 0.872–0.993, p < 0.05) and SSIM was in an acceptable range (0.940–0.993; mean ± standard deviation, 0.968 ± 0.018). Qualitative image quality showed good to excellent agreement between 3D-FSE images without CS and with CS. Diagnostic agreement for pathologic shoulder lesions between the two sequences was very good (κ = 0.915–1).ConclusionsThe 3D-FSE sequence with CS is feasible in evaluating the shoulder joint with reduced scan time compared to 3D-FSE without CS.     

Single image motion deblurring: An accurate PSF estimation and ringing reduction

In this paper we have proposed a single image motion deblurring algorithm that is based on a novel use of dual Fourier spectrum combined with bit plane slicing algorithm and Radon transform (RT) for accurate estimation of PSF parameters such as, blur length and blur angle. Even after very accurate PSF estimation, the deconvolution algorithms tend to introduce ringing artifacts at boundaries and near strong edges. To prevent this post deconvolution effect, a post processing method is also proposed in the framework of traditional Richardson–Lucy (RL) deconvolution algorithm. Experimental results evaluated on the basis of both qualitative and quantitative (PSNR, SSIM) metrics, verified on the dataset of both grayscale and color blurred images show that the proposed method outperforms the existing algorithms for removal of uniform blur. A comparison with state-of-the-art methods proves the usefulness of the proposed algorithm for deblurring real-life images/photographs.     

Enhanced Slime Mould Algorithm for Multilevel Thresholding Image Segmentation Using Entropy Measures

Image segmentation is a fundamental but essential step in image processing because it dramatically influences posterior image analysis. Multilevel thresholding image segmentation is one of the most popular image segmentation techniques, and many researchers have used meta-heuristic optimization algorithms (MAs) to determine the threshold values. However, MAs have some defects; for example, they are prone to stagnate in local optimal and slow convergence speed. This paper proposes an enhanced slime mould algorithm for global optimization and multilevel thresholding image segmentation, namely ESMA. First, the Levy flight method is used to improve the exploration ability of SMA. Second, quasi opposition-based learning is introduced to enhance the exploitation ability and balance the exploration and exploitation. Then, the superiority of the proposed work ESMA is confirmed concerning the 23 benchmark functions. Afterward, the ESMA is applied in multilevel thresholding image segmentation using minimum cross-entropy as the fitness function. We select eight greyscale images as the benchmark images for testing and compare them with the other classical and state-of-the-art algorithms. Meanwhile, the experimental metrics include the average fitness (mean), standard deviation (Std), peak signal to noise ratio (PSNR), structure similarity index (SSIM), feature similarity index (FSIM), and Wilcoxon rank-sum test, which is utilized to evaluate the quality of segmentation. Experimental results demonstrated that ESMA is superior to other algorithms and can provide higher segmentation accuracy.     

基于混合高斯模型的红外图像自适应校正算法

针对传统时域高通滤波校正算法存在的鬼影问题,提出一种新的基于混合高斯模型的红外图像自适应校正算法。新算法利用混合高斯模型对场景进行建模,只有在像元输出值满足一定条件的时候,才将其更新到校正系数中,实现有选择性地更新校正系数。通过一组仿真和真实的红外图像序列评价算法的性能,仿真图像采用峰值信噪比指标进行定量评价,新算法比传统时域高通滤波校正算法的峰值信噪比提高了约9 dB。真实图像采用主观的定性评价,传统算法校正结果中存在着明显的鬼影,而新算法校正结果中不存在鬼影。     

Deep neural network inspired by iterative shrinkage-thresholding algorithm with data consistency (NISTAD) for fast Undersampled MRI reconstruction

With the aim of developing a fast algorithm for high-quality MRI reconstruction from undersampled k-space data, we propose a novel deep neural Network, which is inspired by Iterative Shrinkage Thresholding Algorithm with Data consistency (NISTAD). NISTAD consists of three consecutive blocks: an encoding block, which models the flow graph of ISTA, a classical iteration-based compressed sensing magnetic resonance imaging (CS-MRI) method; a decoding block, which recovers the image from sparse representation; a data consistency block, which adaptively enforces consistency with the acquired raw data according to learned noise level. The ISTA method is thereby mapped to an end-to-end deep neural network, which greatly reduces the reconstruction time and simplifies the tuning of hyper-parameters, compared to conventional model-based CS-MRI methods. On the other hand, compared to general deep learning-based MRI reconstruction methods, the proposed method uses a simpler network architecture with fewer parameters. NISTAD has been validated on retrospectively undersampled diencephalon standard challenge data using different acceleration factors, and compared with DAGAN and Cascade CNN, two state-of-the-art deep neural network-based methods which outperformed many other state-of-the-art model-based and deep learning-based methods. Experimental results demonstrated that NISTAD reconstruction achieved comparable image quality with DAGAN and Cascade CNN reconstruction in terms of both PSNR and SSIM metrics, and subjective assessment, though with a simpler network structure.