Digital processing of chest radiographs

Plain film radiography is the most common imaging method used in the diagnosis of diseases of the heart and lungs. Despite this, little attention has been given to the possible advantages of capturing and subsequently processing such images digitally. This paper describes the application of digital image processing techniques to chest radiographs. The use of different image enhancement techniques is discussed and their clinical value in diagnosis is illustrated. Attention is given to techniques that aid the clinician in visualizing detail in low contrast regions of the image and detecting lesions such as pneumothoraces. These techniques benefit the patient by reducing the X-ray dose, as well as increasing the information that may be extracted from the image.     

Image processing algorithms applied to rib boundary detection in chest radiographs

Two approaches to detecting rib boundaries in chest radiographs are compared, and directions for future developments in this area are discussed.     

基于卷积神经网络的胸片肺结节检测

针对目前胸片的肺结节检测方案的检出率较低,且存在大量的假阳性的问题,提出了一种新的基于卷积神经网络(CNN)的肺结节检测方案.增强肺结节区域的图像信号;选择正、负样本训练卷积神经网络模型,检测结节时用滑动窗口的方法对增强后的图片进行处理得到候选区域;根据候选区域的面积排除假阳性.方案中省略了传统方法中的肺区分割步骤,避免了因此可能丢失的肺结节图像.在日本放射技术学会(JSRT)数据库上测试结果显示,系统在平均每幅图5.0个假阳性水平下敏感度为86％,对不明显和非常不明显的结节检出率达到了84％,优于当前相关文献报道的方法.     

An adaptive speech signal processing for COVID-19 detection using deep learning approach

International Journal of Speech Technology - Researchers and scientists have been conducting plenty of research on COVID-19 since its outbreak. Healthcare professionals, laboratory technicians, and...     

Finding the rib cage in chest radiographs

We describe a system of computer algorithms that finds the rib cage in chest radiographs. Our algorithms link the dorsal and ventral portions of the rib contours such that each rib is identified and can be displayed individually. In a preliminary application of our system to five adult chest radiographs, about 90% of the ribs were found, and ca. 15% of the computed rib contours were false.     

基于自适应双阈值的地下目标自动检测算法

在使用探地雷达（GPR）生成的Bscan图像进行地下目标检测时,当前基于深度学习的目标检测网络模型存在训练样本需求量高、耗时长,不能区分目标显著程度,难以识别复杂目标等问题。针对以上问题,提出一种基于直方图的双阈值分割算法。首先,根据地下目标的GPR图像直方图分布特性,快速从直方图中计算出分割地下目标所需的两个阈值;然后,采用支持向量机（SVM）和LeNet的组合分类器模型对分割结果进行分类识别;最后,进行分类结果整合并统计精确度数值。相较于传统的最大类间方差法（Ostu）、迭代法等阈值分割算法,所提算法获得的地下目标分割结果结构更加完整,并且几乎不含噪声。在真实数据集上,所提算法的平均识别准确率达到了90%以上,比仅使用单一分类器的平均识别准确率提高40%以上。实验结果表明,所提算法能够同时有效分割显著和非显著性地下目标,且采用的组合分类器能够获得更好的分类结果,适用于小样本数据集的地下目标自动检测和识别。     

A non-invasive cancer gene detection technique using FLANN based adaptive filter

Microsystem Technologies - In recent years advancement in cross field technologies lead the world to the new era of genomic research. Several new technologies have been developed for early...     

SAR image processing using adaptive stack filter

Stack filters are a special case of non-linear filters. They have a good performance for filtering images with different types of noise while preserving edges and details. A stack filter decomposes an input image into several binary images according to a set of thresholds. Each binary image is filtered by a Boolean function. The Boolean function that characterizes an adaptive stack filter is optimal and is computed from a pair of images consisting of an ideal noiseless image and its noisy version. In this work the behavior of adaptive stack filters on synthetic aperture radar (SAR) data is evaluated. With this aim, the equivalent number of looks for stack filtered data are calculated to assess the speckle noise reduction capability of this filter. Then a classification of simulated and real SAR images is carried out on data filtered with a stack filter trained with selected samples. The results of a maximum likelihood classification of these data are evaluated and compared with the results of classifying images previously filtered using the Lee and the Frost filters.     

胸部解剖结构回归模型的虚拟双能量X线减影方法

目的 探索从常规X线胸片图像中分割出骨质结构,获取仅含软组织图像的虚拟双能量X线减影的方法,旨在不增加放射剂量的条件下获取高质量的临床肺结节影像诊断效果。方法 首先将肺区自动划分出8个特定解剖结构的子区域：左右侧肺叶的上、中、下部和左右肺门;然后针对每个特定解剖区域,利用从双能量设备获取的标准胸片和其对应的骨质图像对多分辨率的大规模训练人工神经网络（MTANNs）进行训练。训练好后,可以利用该ANN处理获得该解剖结构子区域的虚拟骨质图像。融合从8个多分辨率ANNs输出的骨质图像,融合得到一幅完整的虚拟骨质图像。接下来采用总变分最小化平滑的方法抑制虚拟骨质图像中的噪声,且增强骨骼边缘。最后将虚拟骨质图像从原图中相减获得虚拟软组织图像。结果 用110幅含有肺结节的胸片图像对算法进行了测试,新方法用于常规X线胸片所得虚拟软组织图像可有效地去除原片中骨质结构影像,较清晰地保留肺结节和血管影像,有利于临床肺结节的诊断。采用新方法可使肺结节的正确识别率提高到88%（传统方法识别率为70%）。结论 基于解剖结构的人工神经网络回归模型能有效地分离出骨骼,可以广泛地应用于临床诊断,帮助放射科医生检测出肺结节。     

Differentiation of COVID-19 conditions in planar chest radiographs using optimized convolutional neural networks

In this study, an attempt has been made to differentiate Novel Coronavirus-2019 (COVID-19) conditions from healthy subjects in Chest radiographs using a simplified end-to-end Convolutional Neural Network (CNN) model and occlusion sensitivity maps. Early detection and faster automated screening of the COVID-19 patients is essential. For this, the images are considered from publicly available datasets. Significant biomarkers representing critical image features are extracted from CNN by experimentally investigating on cross-validation methods and hyperparameter settings. The performance of the network is evaluated using standard metrics. Perturbation based occlusion sensitivity maps are employed on the features obtained from the classification model to visualise the localization of abnormal areas. Results demonstrate that the simplified CNN model with optimised parameters is able to extract significant features with a sensitivity of 97.35% and F-measure of 96.71% to detect COVID-19 images. The algorithm achieves an Area Under the Curve-Receiver Operating Characteristic score of 99.4% with Matthews correlation coefficient of 0.93. High value of Diagnostic odds ratio is also obtained. Occlusion sensitivity maps provide precise localization of abnormal regions by identifying COVID-19 conditions. As early detection through chest radiographic images are useful for automated screening of the disease, this method appears to be clinically relevant in providing a visual diagnostic solution using a simplified and efficient model.

     

Parallel algorithms for plane detection using an adaptive Hough transform

Two variations of an adaptive Hough transform for plane detection have been implemented on a multipleinstruction-multiple data architecture based on transputers. In each case, process and processor allocation is data-dependent. Load balancing is achieved by a mixture of geometric decomposition and the processor farm paradigm. Evaluation of the algorithms on synthetic and real image data show their viability in terms of plane detection and increased speed of parallel computation.     

Glaucoma detection using adaptive neuro-fuzzy inference system

Purpose. To develop an automated classifier based on adaptive neuro-fuzzy inference system (ANFIS) to differentiate between normal and glaucomatous eyes from the quantitative assessment of summary data reports of the Stratus optical coherence tomography (OCT) in Taiwan Chinese population.Methods. This observational non-interventional, cross-sectional, case–control study included one randomly selected eye from each of the 341 study participants (135 patients with glaucoma and 206 healthy controls). Measurements of glaucoma variables (retinal nerve fiber layer thickness and optic nerve head topography) were obtained by Stratus OCT. Decision making was performed in two stages: feature extraction using the orthogonal array and the selected variables were treated as the feeder to adaptive neuro-fuzzy inference system (ANFIS), which was trained with the back-propagation gradient descent method in combination with the least squares method. With the Stratus OCT parameters used as input, receiver operative characteristic (ROC) curves were generated by ANFIS to classify eyes as either glaucomatous or normal.Results. The mean deviation was −0.67 ± 0.62 dB in the normal group and −5.87 ± 6.48 dB in the glaucoma group (P < 0.0001). The inferior quadrant thickness was the best individual parameter for differentiating between normal and glaucomatous eyes (ROC area, 0.887). With ANFIS technique, the ROC area was increased to 0.925.Conclusions. With Stratus OCT parameters used as input, the results from ANFIS showed promise for discriminating between glaucomatous and normal eyes. ANFIS may be preferable since the output concludes the if–then rules and membership functions, which enhances the readability of the output.     

基于自适应邻居图的离群点检测方法

离群点检测的目标是识别数据集中与其他样本明显不同的个体,以便检测数据中的异常或异常状态。现有的方法难以有效应对复杂、非线性分布的数据,并且面临参数敏感性和数据分布多样性的问题。为此,现提出一种新型图结构——自适应邻居图,以边为导向,通过迭代的方式对数据进行特征提取,并计算近邻可达度对离群点进行识别,减小了参数的影响,同时可适用于不同分布类型的数据。为了充分验证其性能,将该方法在多个合成与真实数据集上同其他方法进行了比较分析。实验结果表明,该方法在所有19个数据集中平均排名第一,在保持高精度的同时表现出稳定性。     

New models for region of interest reader classification analysis in chest radiographs

In several computer-aided diagnosis (CAD) applications of image processing, there is no sufficiently sensitive and specific method for determining what constitutes a normal versus an abnormal classification of a chest radiograph. In the case of lung nodule detection or in classifying the perfusion of pneumoconiosis, multiple radiograph readers (radiologists) are asked to examine and score specific regions of interest (ROIs). The readers provide size, shape and perfusion grades for the presence of opacities in each region and then use all the ROI grades to classify the lung as normal or abnormal. The combined grades from all readers are then used to arrive at a consensus normal or abnormal classification. In this paper, using area under the ROC curve, we evaluate new mathematical models that are based on mathematical statistics, logic functions, and several statistical classifiers to analyze reader performance in grading chest radiographs for pneumoconiosis as the first step toward applying this technique to early detection of nodules found in lung cancer. In pneumoconiosis, rounded opacities are on the order of 1-10 mm in size, while lung nodules are often not diagnosed until they reach a size on the order of 1 cm.     

双重字典学习与自适应PCNN相结合的医学图像融合

目的 针对基于稀疏编码的医学图像融合方法存在的细节保存能力不足的问题,提出了一种基于卷积稀疏表示双重字典学习与自适应脉冲耦合神经网络（PCNN）的多模态医学图像融合方法。方法 首先通过已配准的训练图像去学习卷积稀疏与卷积低秩子字典,在两个字典下使用交替方向乘子法（ADMM）求得其卷积稀疏表示系数与卷积低秩表示系数,通过与对应的字典重构得到卷积稀疏与卷积低秩分量;然后利用改进的的拉普拉斯能量和（NSML）以及空间频率和（NMSF）去激励PCNN分别对卷积稀疏与卷积低秩分量进行融合;最后将融合后的卷积稀疏与卷积低秩分量进行组合得到最终的融合图像。结果 对灰度图像与彩色图像进行实验仿真并与其他融合方法进行比较,实验结果表明,所提出的融合方法在客观评估和视觉质量方面明显优于对比的6种方法,在4种指标上都有最优的表现;与6种多模态图像融合方法相比,3组实验平均标准差分别提高了7%、10%、5.2%;平均互信息分别提高了33.4%、10.9%、11.3%;平均空间频率分别提高了8.2%、9.6%、5.6%;平均边缘评价因子分别提高了16.9%、20.7%、21.6%。结论 与其他稀疏表示方法相比,有效提高了多模态医学图像融合的质量,更好地保留了源图像的细节信息,使融合图像的信息更加丰富,符合人眼的视觉特性,有效地辅助医生进行疾病诊断。     

A lightweight deep learning architecture for the automatic detection of pneumonia using chest X-ray images

Multimedia Tools and Applications - Pneumonia is a life-threatening respiratory lung disease. Children are more prone to be affected by the disease and accurate manual detection is not easy....     

A new approach for epileptic seizure detection using adaptive neural network

This paper presents new neural network models with adaptive activation function (NNAAF) to detect epileptic seizure. Our NNAAF models included three types named as NNAAF-1, NNAAF-2 and NNAAF-3. The activation function of hidden neuron in the model of NNAAF-1 is sigmoid function with free parameters. In the second model, NNAAF-2, activation function of hidden neuron is sum of sigmoid function with free parameters and sinusoidal function with free parameters. In the third model, NNAAF-3, hidden neurons’ activation function is Morlet Wavelet function with free parameters. In addition, we implemented traditional multilayer perceptron (MLP) neural network (NN) model with fixed sigmoid activation function in the hidden layer to compare NNAAF models. The proposed models were trained and tested using 5-fold cross-validation to prove robustness of these models and to find the best model. We achieved 100% average sensitivity, average specificity, and approximately 100% average classification rate in all the models. It was seen that their speeds and the number of maximum iteration were changed for each model. The training time and the number of maximum iteration were reduced on about 50% using NNAAF-3 model. Hence it can be remarkable that NNAAF-3 is more suitable than the other models for real-time application.     

Fall detection for multiple pedestrians using depth image processing technique

A fall detection method based on depth image analysis is proposed in this paper. As different from the conventional methods, if the pedestrians are partially overlapped or partially occluded, the proposed method is still able to detect fall events and has the following advantages: (1) single or multiple pedestrian detection; (2) recognition of human and non-human objects; (3) compensation for illumination, which is applicable in scenarios using indoor light sources of different colors; (4) using the central line of a human silhouette to obtain the pedestrian tilt angle; and (5) avoiding misrecognition of a squat or stoop as a fall. According to the experimental results, the precision of the proposed fall detection method is 94.31% and the recall is 85.57%. The proposed method is verified to be robust and specifically suitable for applying in family homes, corridors and other public places.