Protocol for evaluating the fitness for purpose of an artificial intelligence product for radiology reporting in the BreastScreen New South Wales breast cancer screening programme.

INTRODUCTION: Radiologist shortages threaten the sustainability of breast cancer screening programmes. Artificial intelligence (AI) products that can interpret mammograms could mitigate this risk. While previous studies have suggested this technology has accuracy comparable to radiologists most have been limited by using 'enriched' datasets and/or not considering the interaction between the algorithm and human readers. This study will address these limitations by comparing the accuracy of a workflow using AI alongside radiologists on a large consecutive cohort of examinations from a breast cancer screening programme. The study will combine the strengths of a large retrospective design with the benefit of prospective data collection. It will test this technology without risk to screening programme participants nor the need to wait for follow-up data. With a sample of 2 years of consecutive screening examinations, it is likely the largest test of this technology to date. The study will help determine whether this technology can safely be introduced into the BreastScreen New South Wales (NSW) population-based screening programme to address radiology workforce risks without compromising cancer detection rates or increasing false-positive recalls. METHODS AND ANALYSIS: A retrospective, consecutive cohort of digital mammography screens from 658 207 examinations from BreastScreen NSW will be reinterpreted by the Lunit Insight MMG AI product. The cohort includes 4383 screen-detected and 1171 interval cancers. The results will be compared with radiologist single reading and the AI results will also be used to replace the second reader in a double-reading model. New adjudication reading will be performed where the AI disagrees with the first reader. Recall rates and cancer detection rates of combined AI-radiologist reading will be compared with the rates obtained at the time of screening. ETHICS AND DISSEMINATION: This study has ethical approval from the NSW Health Population Health Services Research Ethics Committee (2022/ETH02397). Findings will be published in peer-reviewed journals and presented at conferences. The findings of this evaluation will be provided to programme managers, governance bodies and other stakeholders in Australian breast cancer screening programmes.

Dynamic Multiple Object Segmentation with Spatio-Temporal Filtering.

This article primarily focuses on the localization and extraction of multiple moving objects in images taken from a moving camera platform, such as image sequences captured by drones. The positions of moving objects in the images are influenced by both the camera's motion and the movement of the objects themselves, while the background position in the images is related to the camera's motion. The main objective of this article was to extract all moving objects from the background in an image. We first constructed a motion feature space containing motion distance and direction, to map the trajectories of feature points. Subsequently, we employed a clustering algorithm based on trajectory distinctiveness to differentiate between moving objects and the background, as well as feature points corresponding to different moving objects. The pixels between the feature points were then designated as source points. Within local regions, complete moving objects were segmented by identifying these pixels. We validated the algorithm on some sequences in the Video Verification of Identity (VIVID) program database and compared it with relevant algorithms. The experimental results demonstrated that, in the test sequences when the feature point trajectories exceed 10 frames, there was a significant difference in the feature space between the feature points on the moving objects and those on the background. Correctly classified frames with feature points accounted for 67% of the total frames.The positions of the moving objects in the images were accurately localized, with an average IOU value of 0.76 and an average contour accuracy of 0.57. This indicated that our algorithm effectively localized and segmented the moving objects in images captured by moving cameras.

Maritime Infrared Small Target Detection Based on the Appearance Stable Isotropy Measure in Heavy Sea Clutter Environments.

Infrared small target detection plays a crucial role in maritime security. However, detecting small targets within heavy sea clutter environments remains challenging. Existing methods often fail to deliver satisfactory performance in the presence of substantial clutter interference. This paper analyzes the spatial-temporal appearance characteristics of small targets and sea clutter. Based on this analysis, we propose a novel detection method based on the appearance stable isotropy measure (ASIM). First, the original images are processed using the Top-Hat transformation to obtain the salient regions. Next, a preliminary threshold operation is employed to extract the candidate targets from these salient regions, forming a candidate target array image. Third, to distinguish between small targets and sea clutter, we introduce two characteristics: the gradient histogram equalization measure (GHEM) and the local optical flow consistency measure (LOFCM). GHEM evaluates the isotropy of the candidate targets by examining their gradient histogram equalization, while LOFCM assesses their appearance stability based on local optical flow consistency. To effectively combine the complementary information provided by GHEM and LOFCM, we propose ASIM as a fusion characteristic, which can effectively enhance the real target. Finally, a threshold operation is applied to determine the final targets. Experimental results demonstrate that our proposed method exhibits superior comprehensive performance compared to baseline methods.

An improved U-net based retinal vessel image segmentation method.

Diabetic retinopathy is not just the most common complication of diabetes but also the leading cause of adult blindness. Currently, doctors determine the cause of diabetic retinopathy primarily by diagnosing fundus images. Large-scale manual screening is difficult to achieve for retinal health screen. In this paper, we proposed an improved U-net network for segmenting retinal vessels. Firstly, due to the lack of retinal data, pre-processing of the raw data is required. The data processed by grayscale transformation, normalization, CLAHE, gamma transformation. Data augmentation can prevent overfitting in the training process. Secondly, the basic network structure model U-net is built, and the Bi-FPN network is fused based on U-net. Datasets from a public challenge are used to evaluate the performance of the proposed method, which is able to detect vessel SP of 0.8604, SE of 0.9767, ACC of 0.9651, and AUC of 0.9787.

Bandwidth extension method based on the field-shunting effect in a high-gain photoelectric receiver circuit.

In the high-gain photoelectric receiver circuit, the method based on the field-shunting effect is applied to improve the bandwidth of the transimpedance amplifier. This method is implemented by adding a ground trace under the gain resistor, which reduces the parasitic capacitance of the gain resistor and thus increases the bandwidth. To obtain the specific impact of this method on bandwidth, a series of simulations are carried out, including electromagnetic simulations of a three-dimensional structure of circuit gain part and simulation program with integrated circuit emphasis (SPICE) simulations of the high-gain voltage-current feedback transimpedance amplifier. Finally, the optimal simulation result shows that selecting a 1206 size chip fixed resistor and setting the ground trace width to 1.1 mm can greatly reduce the influence of resistor parasitic effects on the circuit, thereby achieving the best performance of bandwidth extension. Further, the comparative experiment also verifies the effectiveness of the method for bandwidth enhancement.

Pulsed light time-of-flight measurement based on a differential hysteresis timing discrimination method.

In the pulsed light time-of-flight (ToF) measurement, the timing point generated in the receiver channel is very important to the measurement accuracy. Therefore, a differential hysteresis timing discrimination method is proposed to generate timing points of the receiver channel. This method is based on utilizing the unbalanced characteristics of the fully differential operational amplifier circuit as well as introducing extra hysteresis levels to achieve the stable generation of timing points. With this method, fewer circuit components are consumed and the dynamic range of the receiver channel is not limited by its linear range. The experiments demonstrate that a receiver channel applying the proposed discrimination reaches better single shot accuracy compared to that using leading-edge timing discrimination. This method is also suitable for the timing walk error compensation by means of pulse width. Finally, these results verify the effectiveness of the proposed method in pulsed light ToF measurement.

Improved algorithm for expanding the measurement linear range of a four-quadrant detector.

A four-quadrant detector is a kind of photoelectric detector that can quickly and accurately measure the incident angle of light. However, its ability to measure in a large field of view (FOV) is limited by its hardware structure and its calculation principle. To solve these problems, this paper proposes an improved algorithm that can extend the measurement linear range without reducing its measurement accuracy. After that, through simulation and experiment, we compare it with many other location algorithms, including the most widely used classical algorithm and the logarithmic algorithm suitable for large FOVs. Finally, the following conclusions can be drawn from both theoretical data and experimental data: the improved algorithm can significantly improve the measurement accuracy over 50% in the same FOV condition, and the measurable range can be expanded over 25% in the same accuracy requirement. At the same time, the robustness of noise does not decrease; when the root mean square error of the classical algorithm fluctuates at 0.1° in different SNR conditions, the improved algorithm is also 0.1°, while the logarithmic algorithm can reach 1.7°, and other algorithms are around 0.25°. In addition, the improved algorithm is more stable in measuring a certain direction and can effectively avoid the influence from the offset of incident light in another axis.

Calculating the model of a nondiagonal rotation invariant angle for a complicated scatterer.

In the research on scattering polarimetry, a scattering mechanism is described by an internal degree of freedom called rotation invariant parameter α. Traditionally, α is calculated by the diagonal scattering matrix of the single scatterer. However, when the research object is a scatterer with complicated surface and microstructure, the traditional calculation of parameter α is biased, since the corresponding scattering matrix is a nondiagonal matrix. To address this problem, this paper proposes a scientific model based on Cameron decomposition to raise the accuracy of parameter α in the complicated scatterer. The rotation invariant parameter with higher accuracy is renamed as a nondiagonal rotation invariant angle. In the verified experiments, the experimental values of each nondiagonal rotation invariant angle are compared with the referenced values calculated by optical constant and incident angle. The results demonstrate that fewer residuals are achieved than by the traditional method. Based on the presented calculating model, the scattering mechanism difference interval between two different materials is proposed as a judging area to distinguish the differences between scattering mechanisms in application.

Calculation method of multiangle polarization measurement for oil spill detection.

This paper takes thin oil film on the sea surface in oil spill pollution as the subject of our research. Combined with physical characteristics of the target, the Mueller matrix of the target is analyzed via a polarization technique. The paper uses the Mueller matrix derived from the Mueller-Jones matrix. Based on the Mueller-Jones matrix, the optical recognition model of oil film on the sea surface is established. This paper proposes a multiangle polarization measurement technology for oil spill pollution on the sea surface and proposes a new data processing method. By calculating the corresponding amplitude ratio, phase retardation, refractive index, and degree of polarization of each pixel, the optical properties of the oil film on the sea surface are analyzed; the surface characteristics of oil film on the sea surface are extracted; the calculation accuracy is improved; and ocean oil spill optical recognition is developed.

Real-time signal processing for sub-THz range grating-based distributed fiber sensing.

Distributed optical fiber sensors are an increasingly utilized method of gathering distributed strain and temperature data. However, the large amount of data they generate presents a challenge that limits their use in real-time, in situ applications. This article describes a parallel and pipelined computing architecture that accelerates the signal-processing speed of sub-terahertz fiber sensor arrays, maintaining high spatial resolution while allowing for expanded use of real-time sensing and control applications. The computing architecture described was successfully implemented in a field programmable gate array chip. The signal processing for the entire array takes only 12 system clock cycles. In addition, this design removes the necessity of storing any raw or intermediate data.

Quadrant response model and error analysis of four-quadrant detectors related to the non-uniform spot and blind area.

In the system of tracking and detection based on the four-quadrant detector (4-QD), the energy distribution of the incident spot and the blind area of the photosensitive surface will affect the location accuracy. The current model of the spot is based on the ideal circular Gauss spot, which makes the error caused by the spot shape easily ignored. In this paper, the model of the spot energy distribution is improved, which can adapt to the elliptical Gauss distribution. The width of the blind area is also added to the response models of the detector so that the output of each quadrant and the error of the localization algorithm can be calculated more accurately. The simulation results show that the measurement accuracy of 4-QD decreases with the increase of the blind area, the shape, and the inclination of the light spot. In the experiment, we first verify the correctness and practicability of the improved model of the spot energy distribution, and then the improved model is proved to be able to make the response and error calculation more accurate.

Inclinometer Assembly Error Calibration and Horizontal Image Correction in Photoelectric Measurement Systems.

Inclinometer assembly error is one of the key factors affecting the measurement accuracy of photoelectric measurement systems. In order to solve the problem of the lack of complete attitude information in the measurement system, this paper proposes a new inclinometer assembly error calibration and horizontal image correction method utilizing plumb lines in the scenario. Based on the principle that the plumb line in the scenario should be a vertical line on the image plane when the camera is placed horizontally in the photoelectric system, the direction cosine matrix between the geodetic coordinate system and the inclinometer coordinate system is calculated firstly by three-dimensional coordinate transformation. Then, the homography matrix required for horizontal image correction is obtained, along with the constraint equation satisfying the inclinometer-camera system requirements. Finally, the assembly error of the inclinometer is calibrated by the optimization function. Experimental results show that the inclinometer assembly error can be calibrated only by using the inclination angle information in conjunction with plumb lines in the scenario. Perturbation simulation and practical experiments using MATLAB indicate the feasibility of the proposed method. The inclined image can be horizontally corrected by the homography matrix obtained during the calculation of the inclinometer assembly error, as well.

Robust infrared small target detection via non-negativity constraint-based sparse representation.

Infrared (IR) small target detection is one of the vital techniques in many military applications, including IR remote sensing, early warning, and IR precise guidance. Over-complete dictionary based sparse representation is an effective image representation method that can capture geometrical features of IR small targets by the redundancy of the dictionary. In this paper, we concentrate on solving the problem of robust infrared small target detection under various scenes via sparse representation theory. First, a frequency saliency detection based preprocessing is developed to extract suspected regions that may possibly contain the target so that the subsequent computing load is reduced. Second, a target over-complete dictionary is constructed by a varietal two-dimensional Gaussian model with an extent feature constraint and a background term. Third, a sparse representation model with a non-negativity constraint is proposed for the suspected regions to calculate the corresponding coefficient vectors. Fourth, the detection problem is skillfully converted to an l1-regularized optimization through an accelerated proximal gradient (APG) method. Finally, based on the distinct sparsity difference, an evaluation index called sparse rate (SR) is presented to extract the real target by an adaptive segmentation directly. Large numbers of experiments demonstrate both the effectiveness and robustness of this method.

Stokes-vector-based polarimetric imaging system for adaptive target/background contrast enhancement.

A novel method to optimize the polarization state of a polarimetric imaging system is proposed to solve the problem of target/background contrast enhancement in an outdoor environment adaptively. First, the last three elements of the Stokes vector are selected to be the observed object's polarization features, the discriminant projection of which is regarded as the detecting function of our imaging system. Then, the polarization state of the system, which can be seen as a physical classifier, is calculated by training samples with a support vector machine method. Finally, images processed by the system with the designed optimal polarization state become discriminative output directly. By this means, the target/background contrast is enhanced greatly, which results in a more accurate and convenient target discrimination. Experimental results demonstrate that the effectiveness and discriminative ability of the optimal polarization state are credible and stable.

Protective effects of the aqueous extract of Scutellaria baicalensis against acrolein-induced oxidative stress in cultured human umbilical vein endothelial cells.

CONTEXT: Scutellaria baicalensis Georgi (Labiatae) (SbG), one of the fifty fundamental herbs of Chinese herbology, has been reported to have anti-asthmatic, antifungal, antioxidative, and anti-inflammatory activities. OBJECTIVE: This study was designed to determine the protective effects of the extract of SbG against the acrolein-induced oxidative stress in cultured human umbilical vein endothelial cells (HUVEC). MATERIALS AND METHODS: The MTT reduction assay was employed to determine cell viability. The total cellular glutathione (GSH) level was detected using a colorimetric GSH assay kit. Cellular GSH production was conducted by detecting the mRNA expression levels of γ-glutamylcysteine ligase catalytic subunit and modifier subunit. RESULTS: Concentration-dependent cytotoxic effects of acrolein were observed while SbG could effectively protect the acrolein-induced oxidative damage. The protective mechanism was investigated, showing that the increased GSH content in the SbG-incubated HUVE cells was associated with the protective effects of SbG-treated cells. Further RT-PCR data confirmed the elevated mRNA expressions of GSH synthesis enzymes. DISCUSSION AND CONCLUSION: The current study strongly indicated that SbG could be a potential antioxidant against oxidative stress in treating cardiovascular diseases.