Ten Good Reasons to Practice Neuroultrasound in Critical Care Setting

In the beginning, cerebral ultrasound (US) was not considered feasible because the intact skull was a seemingly impenetrable obstacle. For this reason, obtaining a clear image resolution had been a challenge since the first use of neuroultrasound (NUS) for the assessment of small deep brain structures. However, the improvements in transducer technologies and advances in signal processing have refined the image resolution, and the role of NUS has evolved as an imaging modality for the brain parenchyma within multiple pathologies. This article summarizes ten crucial applications of cerebral ultrasonography for the evaluation and management of neurocritical patients, whose transfer from and to intensive care units poses a real problem to medical care staff. This also encompasses ease of use, low cost, wide acceptance by patients, no radiation risk, and relative independence from movement artifacts. Bedsides, availability and reliability raised the interest of critical care intensivists in using it with increasing frequency. In this mini-review, the usefulness and the advantages of US in the neurocritical care setting are discussed regarding ten aspects to encourage the intensivist physician to practice this important tool.

IMSI—Guidelines for Sperm Quality Assessment

Intracytoplasmic sperm injection (ICSI) is a widely used and accepted treatment of choice for oocyte fertilization. However, the quality of sperm selection depends on the accurate visualization of the morphology, which can be achieved with a high image resolution. We aim to correct the conviction, shown in a myriad of publications, that an ultra-high magnification in the range of 6000×–10,000× can be achieved with an optical microscope. The goal of observing sperm under the microscope is not to simply get a larger image, but rather to obtain more detail—therefore, we indicate that the optical system’s resolution is what should be primarily considered. We provide specific microscope system setup recommendations sufficient for most clinical cases that are based on our experience showing that the optical resolution of 0.5 μm allows appropriate visualization of sperm defects. Last but not least, we suggest that mixed research results regarding the clinical value of IMSI, comparing to ICSI, can stem from a lack of standardization of microscopy techniques used for both ICSI and IMSI.

Cross-free in both lateral and axial directions Fourier-domain full-field optical coherence tomography

Fourier-domain full-field optical coherence tomography (FD-FF-OCT) has the advantages of high resolution and parallel detection. However, using parallel detection can result in optical crosstalk. Toward minimizing crosstalk, we implemented a very fast deformable membrane (DM) that introduces random phase illumination, which can effectively reduce the crosstalk by washing out fringes originating from multiply scattered light. However, for one thing, although the application of DM has reduced the crosstalk problem in parallel detection to a certain extent, there will still be a lot of background noises, which may come from the circadian rhythm of the sample and multiple scattered photons. The problem could be solved by employing the adaptive singular value decomposition (SVD) filtering. We also combined SVD with the cumulative sum method, which can improve image resolution well. For the other thing, the random phase introduced by DM in the spectral domain will cause axial crosstalk after inverse Fourier transform. As far as we know, we are the first team to notice axial crosstalk and proposes that this problem can be solved by controlling the deformation range of DM. We have carried out a theoretical analysis of the above methods and verified its feasibility by simulation.

Development of an Underground Tunnels Detection Algorithm for Electrical Resistivity Tomography Based on Deep Learning

Kinmen Island was in a state of combat readiness during the 1950s–1980s. It opened for tourism in 1992, when all troops withdrew from the island. Most military installations, such as bunkers, anti airborne piles, and underground tunnels, became deserted and disordered. The entries to numerous underground bunkers are closed or covered with weeds, creating dangerous spaces on the island. This study evaluates the feasibility of using Electrical Resistivity Tomography (ERT) to detect and discuss the location, size, and depth of underground tunnels. In order to discuss the reliability of the 2D-ERT result, this study built a numerical model to validate the correctness of in situ measured data. In addition, this study employed the artificial intelligence deep learning technique for reprocessing and predicting the ERT image and discussed using an artificial intelligence deep learning algorithm to enhance the image resolution and interpretation. A total of three 2D-ERT survey lines were implemented in this study. The results indicate that the three survey lines clearly show the tunnel location and shape. The numerical simulation results also indicate that using 2D-ERT to survey underground tunnels is highly feasible. Moreover, according to a series of studies in Multilayer Perceptron of deep learning, using deep learning can clearly show the tunnel location and path and effectively enhance the interpretation ability and resolution for 2D-ERT measurement results.

Rethinking Pooling Operation for Liver and Liver-Tumor Segmentations

Deep convolutional neural networks (DCNNs) have been widely used in medical image segmentation due to their excellent feature learning ability. In these DCNNs, the pooling operation is usually used for image down-sampling, which can gradually reduce the image resolution and thus expands the receptive field of convolution kernel. Although the pooling operation has the above advantages, it inevitably causes information loss during the down-sampling of the pooling process. This paper proposes an effective weighted pooling operation to address the problem of information loss. First, we set up a pooling window with learnable parameters, and then update these parameters during the training process. Secondly, we use weighted pooling to improve the full-scale skip connection and enhance the multi-scale feature fusion. We evaluated weighted pooling on two public benchmark datasets, the LiTS2017 and the CHAOS. The experimental results show that the proposed weighted pooling operation effectively improve network performance and improve the accuracy of liver and liver-tumor segmentation.

Multilevel Image Edge Detection Algorithm Based on Visual Perception

Multilevel image edge repair results directly affect the follow-up image quality evaluation and recognition. Current edge detection algorithms have the problem of unclear edge detection. In order to detect more accurate edge contour information, a multilevel image edge detection algorithm based on visual perception is proposed. Firstly, the digital image is processed by double filtering and fuzzy threshold segmentation; Through the analysis of the contour features of the moving image, the threshold of the moving image features is set, and the latest membership function is obtained to complete the multithreshold optimization. Adaptive smoothing is used to process the contour of the object in the moving image, and the geometric center values of the two adjacent contour points within the contour range are calculated. According to the calculation results, the curvature angle is further calculated, and the curvature symbol is obtained. According to the curvature symbol, the contour features of the moving image are detected. The experimental results show that the proposed algorithm can effectively and accurately detect the edge contour of the image and shorten the reconstruction time, and the detection image resolution is high.

The use of digital magnification to reduce radiation dose in the cardiac catheter laboratory

Objectives: To audit whether using magnification of images by use of a large viewing screen using digital matrix magnification which enlarges the image by 33% without using the X-ray machine zoom magnification protocols on a Siemens Artis Zee X-ray machine in a cardiac catheter laboratory results in a reduction of kerma–area product (KAP) for both diagnostic and interventional procedures. This reduction was predicted in an in vitro study in our laboratory, which has previously shown a 20.4% reduction in KAP. Methods: A retrospective analysis was conducted of the radiation exposure to compare the measured KAP recorded during the period when conventional magnification with automatic brightness and dose control was used on a Siemens Artis Zee X-ray machine with a flat panel detector and when magnification settings were avoided by using a large screen to enlarge and project a non-magnified image by digital magnification. The analysis was carried out for patients having a diagnostic coronary angiogram and those having an interventional coronary procedure. Results: For diagnostic coronary angiograms the median KAP per procedure in the period using conventional magnification was 2124.5 µGy.m2 compared to 1401 µGy.m2 when image matrix magnification was used, a 34% reduction (p < 0.0001). For interventional coronary procedures, the median KAP per procedure in the period using conventional magnification was 3791 µGy.m2 compared to 2568.5 µGy.m2 when image matrix magnification was used, a 32% reduction (p < 0.0001). Conclusion: Avoiding using conventional magnification in the cardiac catheter laboratory and using a large screen to magnify images was associated with a statistically significant greater than 30% reduction in KAP. Advances in knowledge: This paper is the proof in clinical practice of a theoretical conclusion that radiation dose (KAP) is reduced by use of Image matrix magnification using a large viewing screen without the need to use X-ray tube magnification without significant loss of image resolution in interventional cardiology. The same approach will be useful in interventional radiology.

A Deep Learning-Based Generalized System for Detecting Pine Wilt Disease Using RGB-Based UAV Images

Pine wilt is a devastating disease that typically kills affected pine trees within a few months. In this paper, we confront the problem of detecting pine wilt disease. In the image samples that have been used for pine wilt disease detection, there is high ambiguity due to poor image resolution and the presence of “disease-like” objects. We therefore created a new dataset using large-sized orthophotographs collected from 32 cities, 167 regions, and 6121 pine wilt disease hotspots in South Korea. In our system, pine wilt disease was detected in two stages: n the first stage, the disease and hard negative samples were collected using a convolutional neural network. Because the diseased areas varied in size and color, and as the disease manifests differently from the early stage to the late stage, hard negative samples were further categorized into six different classes to simplify the complexity of the dataset. Then, in the second stage, we used an object detection model to localize the disease and “disease-like” hard negative samples. We used several image augmentation methods to boost system performance and avoid overfitting. The test process was divided into two phases: a patch-based test and a real-world test. During the patch-based test, we used the test-time augmentation method to obtain the average prediction of our system across multiple augmented samples of data, and the prediction results showed a mean average precision of 89.44% in five-fold cross validation, thus representing an increase of around 5% over the alternative system. In the real-world test, we collected 10 orthophotographs in various resolutions and areas, and our system successfully detected 711 out of 730 potential disease spots.

Super-resolution imaging of negative-refractive graded-index photonic crystal flat lens

Photonic crystal (PC) not only breaks through the diffraction limit of traditional lenses but also can realize super-resolution imaging. Improving the resolution is the key task of PC imaging. The main work of this paper is to use a graded-index Photonic crystal (GPC) flat lens to improve the image resolution. An air-hole type two-dimensional (2D) GPC structure based on silicon medium is proposed in this paper. Numerical simulations through RSoft reveal that when the medium in the imaging area is air, the full width at half maximum (FWHM) value of a single image reaches 0.362λ. According to the Rayleigh criterion, the images of two point sources 0.57λ apart can also be distinguished. In the imaging system composed of cedar oil and GPC flat lens, the FWHM value of a single image reaches 0.34λ. In addition, the images of multiple point sources 0.49λ apart can still be distinguished.

Image Georeferencing using Artificial Neural Network Compared with Classical Methods

Georeferencing process is one of the most important prerequisites for various geomatics applications; for example, photogrammetry, laser scan analysis, remotely sensing, spatial and descriptive data collection, and others. Georeferencing mostly involves the transformation of coordinates obtained from images that are inhomogeneous due to accuracy differences. The georeferencing depends on image resolution and accuracy level of measurements of reference points ground coordinates. Accordingly, this study discusses the subject of coordinate’s transformation from the image to the global coordinates system (WGS84) to find a suitable method that provides more accurate results. In this study, the Artificial Neural Network (ANN) method was applied, in addition to several numerical methods, namely the Affine divided difference, Newton’s divided difference, and polynomial transformation. The four methods were modelled and coded using Matlab programming language based on an image captured from Google Earth. The image was used to determine reference points within the study area (University of Baghdad campus). The findings of this study showed that the ANN enhanced the results by about 50% in terms of accuracy and 90% in terms of homogeneity, compared with the other methods.