Improved 3D image segmentation for X-ray tomographic analysis of packed particle beds

Although High Resolution X-ray Micro Tomography (HRXMT) has been developed in the past years for the 3D analysis of multiphase mineral particles in packed particle beds, image analysis of fine and/or high-density/high atomic number particles has been limited by existing segmentation algorithms. In this regard, a feature-based segmentation algorithm has been developed and demonstrated to provide a more accurate image processing method for the analysis of such multiphase particle populations. Based on this improved segmentation algorithm, image analyses of packed particle bed samples were compared to segmentation by traditional 3D watershed segmentation. Also, calculation of particle number using optical microscopy, together with a digital camera, was accomplished to validate feature-based segmentation. Detailed procedures and results for sample preparation, image analysis and validation are presented and discussed.     

Hybrid Segmentation Scheme for Skin Features Extraction Using Dermoscopy Images

Objective and quantitative assessment of skin conditions is essential for cosmeceutical studies and research on skin aging and skin regeneration. Various handcraft-based image processing methods have been proposed to evaluate skin conditions objectively, but they have unavoidable disadvantages when used to analyze skin features accurately. This study proposes a hybrid segmentation scheme consisting of Deeplab v3+ with an Inception-ResNet-v2 backbone, LightGBM, and morphological processing (MP) to overcome the shortcomings of handcraft-based approaches. First, we apply Deeplab v3+ with an Inception-ResNet-v2 backbone for pixel segmentation of skin wrinkles and cells. Then, LightGBM and MP are used to enhance the pixel segmentation quality. Finally, we determine several skin features based on the results of wrinkle and cell segmentation. Our proposed segmentation scheme achieved a mean accuracy of 0.854, mean of intersection over union of 0.749, and mean boundary F1 score of 0.852, which achieved 1.1%, 6.7%, and 14.8% improvement over the panoptic-based semantic segmentation method, respectively.     

基于线特征及迭代最近点算法的地基建筑物点云自动配准方法

为克服迭代最近点(ICP)算法易陷入局部最优的缺陷，提出一种基于线特征及ICP算法的地基建筑物点云自动配准方法。首先，基于法向一致性进行建筑物点云平面分割；接着，采用alpha-shape算法进行点簇轮廓线提取，并拆分和拟合处理得到特征线段；然后，以线对作为配准基元，以线对夹角和距离作为相似性测度进行同名特征匹配，实现建筑物点云的粗配准；最后，以粗配准结果为初值，进一步采用ICP算法完成点云精确配准。利用两组部分重叠的建筑物点云进行配准实验，实验结果表明，采用由粗到精的配准方法能有效改善ICP算法对初值依赖的问题，实现具有部分重叠的建筑物点云的有效配准。     

结合注意力的3D卷积网络脑胶质瘤分割算法

为了提升脑胶质瘤分割精度，提出一种结合注意力机制的3D卷积神经网络算法。输入3个不同尺度的图像块，经过9个卷积层和1个分类层后得到3个不同的分类结果，将分类结果与注意力学习到的权重相乘并逐体素相加得到输出。此外该算法采用了一种混合Dice损失函数与Focal损失函数的超参数损失函数。实验表明，该算法的Dice系数在整体区域、核心区域以及增强区域分别达到了95.31%、80.12%、82.25%。与已有的一种脑胶质瘤分割算法deepmedic相比，整体区域、核心区域以及增强区域的Dice系数分别提升了3%、2%、6%。在脑胶质瘤分割方面，具有重要的临床意义。     

基于卷积神经网络的单目深度估计

针对利用深度学习方法对街道图像进行深度估计，提出采用语义分割的方法解决深度图出现边界模糊等问题；估计深度通过左右视角图生成视差图进行无监督的训练。在网络模型中添加语义分割层，采取多个空洞卷积并行的结构增加感受野，同时减少了图像下采样的次数，降低了由于下采样带来的信息损失，使得的结果更加准确。这也是在深度估计中首次与空洞卷积相结合增加准确率。通过对KITTI街道数据集进行训练，与现有结果相比，除了增加检测准确性，降低错误率之外，使得效果图中的物体更加清晰，并且在效果图中还保留了一些原模型中被忽视掉的细节信息，将原始图像更加完整的表现出来。     

R2D2: A scalable deep learning toolkit for medical imaging segmentation

Deep learning has gained a significant popularity in recent years thanks to its tremendous success across a wide range of relevant fields of applications, including medical image analysis domain in particular. Although convolutional neural networks (CNNs) based medical applications have been providing powerful solutions and revolutionizing medicine, efficiently training of CNNs models is a tedious and challenging task. It is a computationally intensive process taking long time and rare system resources, which represents a significant hindrance to scientific research progress. In order to address this challenge, we propose in this article, R2D2, a scalable intuitive deep learning toolkit for medical imaging semantic segmentation. To the best of our knowledge, the present work is the first that aims to tackle this issue by offering a novel distributed versions of two well-known and widely used CNN segmentation architectures [ie, fully convolutional network (FCN) and U-Net]. We introduce the design and the core building blocks of R2D2. We further present and analyze its experimental evaluation results on two different concrete medical imaging segmentation use cases. R2D2 achieves up to 17.5× and 10.4× speedup than single-node based training of U-Net and FCN, respectively, with a negligible, though still unexpected segmentation accuracy loss. R2D2 offers not only an empirical evidence and investigates in-depth the latest published works but also it facilitates and significantly reduces the effort required by researchers to quickly prototype and easily discover cutting-edge CNN configurations and architectures.     

基于Spider卷积的三维点云分类与分割网络

针对传统的卷积神经网络（CNN）不能直接处理点云数据，需先将点云数据转换为多视图或者体素化网格，导致过程复杂且点云识别精度低的问题，提出一种新型的点云分类与分割网络Linked-Spider CNN。首先，在Spider CNN基础上通过增加Spider卷积层数以获取点云深层次特征；其次，引入残差网络的思想在每层Spider卷积增加短连接构成残差块；然后，将每层残差块的输出特征进行拼接融合形成点云特征；最后，使用三层全连接层对点云特征进行分类或者利用多层卷积层对点云特征进行分割。在ModelNet40和ShapeNet Parts数据集上将所提网络与PointNet、PointNet++和Spider CNN等网络进行对比实验，实验结果表明，所提网络可以提高点云的分类精度和分割效果，说明该网络具有更快的收敛速度和更强的鲁棒性。     

结合时间戳的指纹密钥数据加解密传输方案

目的 对于生物密钥而言，生物特征数据的安全与生物密钥的管理存储都很关键。为了构造能够应用在通信数据传输场景的生物密钥，同时保证生物特征本身的模糊性与密码学的精确性处于一种相对平衡状态，提出一种基于时间戳与指纹密钥的数据加解密传输方案。方法 利用发送方指纹特征点之间的相对信息，与保密随机矩阵生成发送方指纹密钥；借助通信双方的预先设定数与时间戳，生成接收方恢复指纹密钥时所需的辅助信息；利用发送方指纹密钥加密数据，实现密文数据的传输。结果 本文方法在仿真通信双方数据加解密的实现中，测试再生指纹密钥的识别率（GAR）与误识率（FAR）。通过实验数据分析，表明了本文提出的指纹密钥生成方法的可用性，以及指纹密钥作为数字身份所具备的可认证性，其中真实发送方的再生指纹密钥识别率可高达99.8%，并且本方案还可用于即时通信、对称加密等多种场景当中。结论 本文方法利用时间戳确定了通信事件的唯一性与不可否认性，同时实现了指纹密钥恢复时的"一次一密"。此外，方案通过保密随机矩阵实现了发送方指纹密钥的可撤销，极大程度保障了指纹数据的安全性。     

Multi-path connected network for medical image segmentation

In recent years, deep learning has been successfully applied to medical image segmentation. However, as the network extends deeper, the consecutive downsampling operations will lead to more loss of spatial information. In addition, the limited data and diverse targets increase the difficulty for medical image segmentation. To address these issues, we propose a multi-path connected network (MCNet) for medical segmentation problems. It integrates multiple paths generated by pyramid pooling into the encoding phase to preserve semantic information and spatial details. We utilize multi-scale feature extractor block (MFE block) in the encoder to obtain large and multi-scale receptive fields. We evaluated MCNet on three medical datasets with different image modalities. The experimental results show that our method achieves better performance than the state-of-the-art approaches. Our model has strong feature learning ability and is robust to capture different scale targets. It can achieve satisfactory results while using only 0.98 million (M) parameters.     

A Feature Selection Strategy to Optimize Retinal Vasculature Segmentation

Diabetic retinopathy (DR) is a complication of diabetes mellitus that appears in the retina. Clinitians use retina images to detect DR pathological signs related to the occlusion of tiny blood vessels. Such occlusion brings a degenerative cycle between the breaking off and the new generation of thinner and weaker blood vessels. This research aims to develop a suitable retinal vasculature segmentation method for improving retinal screening procedures by means of computer-aided diagnosis systems. The blood vessel segmentation methodology relies on an effective feature selection based on Sequential Forward Selection, using the error rate of a decision tree classifier in the evaluation function. Subsequently, the classification process is performed by three alternative approaches: artificial neural networks, decision trees and support vector machines. The proposed methodology is validated on three publicly accessible datasets and a private one provided by Hospital Sant Joan of Reus. In all cases we obtain an average accuracy above 96% with a sensitivity of 72% in the blood vessel segmentation process. Compared with the state-of-the-art, our approach achieves the same performance as other methods that need more computational power. Our method significantly reduces the number of features used in the segmentation process from 20 to 5 dimensions. The implementation of the three classifiers confirmed that the five selected features have a good effectiveness, independently of the classification algorithm.