基于LVQ神经网络的水果图像分割研究

由于传统边沿检测算子在水果颜色多样、亮度不均匀时,难以分割得到完整、无噪声的二值图像且依赖优化的阈值,本研究提出了一种基于LVQ神经网络的水果图像分割方案。首先将彩色图像转变为灰度图像;然后对Canny算子获得的边沿图像随机选取一些像素作为网络的学习监督信号,仅以灰度图像中相同位置像素3×3邻域的Kirsch算子梯度值作为输入,训练权值;最后重新将原灰度图像的Kirsch算子梯度值输入到训练好的网络中,获得封闭的边沿并填充得到二值图像。考察了14幅像素为640×480的水果图像,结果表明：网络在很宽广的阈值范围内（0.001 ~ 0.99）分割得到完整、一致的二值图像;面积误差最小为0.9%,最大为8.83%,不依赖于优化的阈值,不需要对原始图像滤波预处理。与没有阈值及滤波的算法相比,本方案的误差和时间复杂度均更低;与设置了阈值和/或滤波的算法相比,本方案与之相当,甚至效果更优。     

基于目标检测的激光雷达道路边缘检测算法

道路边缘检测是自动驾驶车辆环境感知的重要组成部分,有效地从点云数据中提取道路边缘信息,有利于进行目标检测以及可行驶区域检测。针对点云道路边缘检测问题,提出了一种考虑车辆等道路参与者对道路边缘检测带来干扰的解决方案。首先,采用地面点云分割算法,将原始点云分割成地面点云和非地面点云;其次,根据车辆等道路参与者的固有特性,采用点云聚类算法对点云进行聚类,并将符合车辆等道路参与者特性的非地面点云进行滤除;再次,根据道路边缘点云在二维平面内,能够有效地遮挡激光发射中心点与非道路边缘点之间的连线,从而提取道路边缘点云;最后,采用随机抽样一致性(random sample consensus, RANSAC)算法对道路边缘点云进行多项式拟合,并使用扩展卡尔曼滤波器对道路边缘进行跟踪。实验结果表明,所提点云道路边缘检测算法能够消除车辆等道路参与则对点云道路边缘检测的影响,且算法满足实车实时性和鲁棒性要求。     

基于改进U-Net的量子点STM图像分割

为提升量子点图像分割精度,降低特征识别误差,提出一种基于改进U-Net的量子点图像分割方法.首先,在预处理阶段,设计了以色彩通道为权值的灰度化算法,以提升后续分割效果.其次,在STM图像分割部分,在原始U-Net结构上引入中间过渡层以均衡网络各层特征.而后,建立数据集,并通过实验对比不同分割算法的精确度、召回率、F-measure.最后,将分割算法应用于量子点的特征识别,并测试了不同分割方式对应用的影响.实验结果显示,改进灰度化方法保留细节信息丰富,明显提升了量子点分割精度;改进U-Net的平均精确率、召回率、F-measure相较原始网络分别提升了13.83%、2.16%、8.13%.同时,实验数据表明由于分割精度的提升,量子点数量、纵横比等特征参数的识别更加精确.     

基于数学形态学的表面原子熔融相的 STM图像识别算法

高温扫描隧道显微镜(HT-STM)可以实时原位地捕捉到表面原子的熔化相变过程.在这一原位变温实验中,快速可靠地识别出每帧STM图像中的熔融相十分关键.传统的手工统计方法存在效率低下、随意性大等问题.我们发展出一套基于数学形态学的算法,来自动快速地识别.与人工方法相比,该算法消除了人为主观误差,使确定的边界更加准确、光滑,处理效率提高了266倍.     

Effects of thermoultrasonic treatment on characteristics of micro-nano particles and flavor in Greenland halibut bone soup

In order to investigate the effects of thermoultrasonic treatment (TUT) on the formation of colloidal micro-nano particles (MNPs) and the quality of halibut bone soup, nutrients, particle characteristics, and flavor characteristics were analyzed. The morphology of MNPs was studied using an optical microscope. Results showed that TUT could increase the nutrient content (total sugars, 22.15 mg/100 mL; water soluble proteins, 173.24 mg/mL; fatty acids, 1779.7 mg/100 mL; solids, 3.16 g/100 mL), reduce the particle size (605.92 nm) and interfacial tension. Meanwhile, TUT make the halibut bone soup has better emulsifying characteristics and stability. The contents of flavor substances, such as esters, 5′-nucleotides, organic acids in the halibut bone soup were more abundant, while the contents of hexanal and 1-octen-3-ol and fishy off-flavor were reduced in TUT group. The overall odor and taste outline were more harmonious. Therefore, TUT can be used in the production of high quality fish bone soup, and TUT could be considered as a good deep processing technology for halibut bone and improve economic efficiency.     

BMP-6 Loaded Polyelectrolyte Complex Nanoparticles Inducing Osteogenic Differentiation and Apoptosis of Malignant Plasma Cells for Local Treatment of Multiple Myeloma

In the malignant plasma cell disease multiple myeloma (MM), bone lesions and resulting fractures caused by MM cell (MMC) accumulation represent a major cause of morbidity and mortality. Despite recent advantages in systemic treatment, residual MMCs remain, especially in bone lesions. Therefore an interfacial delivery system for local treatment of MM and induced bone disease based on polyelectrolyte complex nanoparticles (PEC NP) loaded with bone morphogenetic protein 6 (BMP-6) inducing de-novo bone formation and MMC apoptosis is presented herein. BMP-6 loaded PEC NP are fabricated by defined mixing bio-related cationic and anionic polysaccharides and BMP-6 according to molar ratio of BMP-6/PEC-NP of 1/3. BMP-6/PEC NP bound to a model substrate releases 10% BMP-6 sustainably within two weeks as accessed by infrared spectroscopy. BMP-6 loaded PEC NP adheres to cell membranes of MMCs and MSCs and activated phosphorylation of Smad 1/5. Osteogenic differentiation (ALP-concentration) is enhanced in MSCs (p < 0.05). All patient samples (10/10) of MMCs show significant induction of apoptosis (median 84%, p < 0.05). Finally, BMP-6/PEC NP are successfully integrated in a commercial hyaluronic acid based hydrogel material revealing MMC death as principal proof for the local treatment of MM induced bone lesions.     

Automated Spleen Injury Detection Using 3D Active Contours and Machine Learning

The spleen is one of the most frequently injured organs in blunt abdominal trauma. Computed tomography (CT) is the imaging modality of choice to assess patients with blunt spleen trauma, which may include lacerations, subcapsular or parenchymal hematomas, active hemorrhage, and vascular injuries. While computer-assisted diagnosis systems exist for other conditions assessed using CT scans, the current method to detect spleen injuries involves the manual review of scans by radiologists, which is a time-consuming and repetitive process. In this study, we propose an automated spleen injury detection method using machine learning. CT scans from patients experiencing traumatic injuries were collected from Michigan Medicine and the Crash Injury Research Engineering Network (CIREN) dataset. Ninety-nine scans of healthy and lacerated spleens were split into disjoint training and test sets, with random forest (RF), naive Bayes, SVM, k-nearest neighbors (k-NN) ensemble, and subspace discriminant ensemble models trained via 5-fold cross validation. Of these models, random forest performed the best, achieving an Area Under the receiver operating characteristic Curve (AUC) of 0.91 and an F1 score of 0.80 on the test set. These results suggest that an automated, quantitative assessment of traumatic spleen injury has the potential to enable faster triage and improve patient outcomes.     

Supervised Domain Adaptation for Automated Semantic Segmentation of the Atrial Cavity

Atrial fibrillation (AF) is the most common cardiac arrhythmia. At present, cardiac ablation is the main treatment procedure for AF. To guide and plan this procedure, it is essential for clinicians to obtain patient-specific 3D geometrical models of the atria. For this, there is an interest in automatic image segmentation algorithms, such as deep learning (DL) methods, as opposed to manual segmentation, an error-prone and time-consuming method. However, to optimize DL algorithms, many annotated examples are required, increasing acquisition costs. The aim of this work is to develop automatic and high-performance computational models for left and right atrium (LA and RA) segmentation from a few labelled MRI volumetric images with a 3D Dual U-Net algorithm. For this, a supervised domain adaptation (SDA) method is introduced to infer knowledge from late gadolinium enhanced (LGE) MRI volumetric training samples (80 LA annotated samples) to a network trained with balanced steady-state free precession (bSSFP) MR images of limited number of annotations (19 RA and LA annotated samples). The resulting knowledge-transferred model SDA outperformed the same network trained from scratch in both RA (Dice equals 0.9160) and LA (Dice equals 0.8813) segmentation tasks.     

Magnetic-resonance image segmentation based on improved variable weight multi-resolution Markov random field in undecimated complex wavelet domain

To solve the problem that the magnetic resonance (MR) image has weak boundaries, large amount of information, and low signal-to-noise ratio, we propose an image segmentation method based on the multi-resolution Markov random field (MRMRF) model. The algorithm uses undecimated dual-tree complex wavelet transformation to transform the image into multiple scales. The transformed low-frequency scale histogram is used to improve the initial clustering center of the K-means algorithm, and then other cluster centers are selected according to the maximum distance rule to obtain the coarse-scale segmentation. The results are then segmented by the improved MRMRF model. In order to solve the problem of fuzzy edge segmentation caused by the gray level inhomogeneity of MR image segmentation under the MRMRF model, it is proposed to introduce variable weight parameters in the segmentation process of each scale. Furthermore, the final segmentation results are optimized. We name this algorithm the variable-weight multi-resolution Markov random field (VWMRMRF). The simulation and clinical MR image segmentation verification show that the VWMRMRF algorithm has high segmentation accuracy and robustness, and can accurately and stably achieve low signal-to-noise ratio, weak boundary MR image segmentation.     

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.