Classification of Benign-Malignant Thyroid Nodules Based on Hyperspectral Technology.

In recent years, the incidence of thyroid cancer has rapidly increased. To address the issue of the inefficient diagnosis of thyroid cancer during surgery, we propose a rapid method for the diagnosis of benign and malignant thyroid nodules based on hyperspectral technology. Firstly, using our self-developed thyroid nodule hyperspectral acquisition system, data for a large number of diverse thyroid nodule samples were obtained, providing a foundation for subsequent diagnosis. Secondly, to better meet clinical practical needs, we address the current situation of medical hyperspectral image classification research being mainly focused on pixel-based region segmentation, by proposing a method for nodule classification as benign or malignant based on thyroid nodule hyperspectral data blocks. Using 3D CNN and VGG16 networks as a basis, we designed a neural network algorithm (V3Dnet) for classification based on three-dimensional hyperspectral data blocks. In the case of a dataset with a block size of 50 × 50 × 196, the classification accuracy for benign and malignant samples reaches 84.63%. We also investigated the impact of data block size on the classification performance and constructed a classification model that includes thyroid nodule sample acquisition, hyperspectral data preprocessing, and an algorithm for thyroid nodule classification as benign and malignant based on hyperspectral data blocks. The proposed model for thyroid nodule classification is expected to be applied in thyroid surgery, thereby improving surgical accuracy and providing strong support for scientific research in related fields.

A Snapshot Multi-Spectral Demosaicing Method for Multi-Spectral Filter Array Images Based on Channel Attention Network.

Multi-spectral imaging technologies have made great progress in the past few decades. The development of snapshot cameras equipped with a specific multi-spectral filter array (MSFA) allow dynamic scenes to be captured on a miniaturized platform across multiple spectral bands, opening up extensive applications in quantitative and visualized analysis. However, a snapshot camera based on MSFA captures a single band per pixel; thus, the other spectral band components of pixels are all missed. The raw images, which are captured by snapshot multi-spectral imaging systems, require a reconstruction procedure called demosaicing to estimate a fully defined multi-spectral image (MSI). With increasing spectral bands, the challenge of demosaicing becomes more difficult. Furthermore, the existing demosaicing methods will produce adverse artifacts and aliasing because of the adverse effects of spatial interpolation and the inadequacy of the number of layers in the network structure. In this paper, a novel multi-spectral demosaicing method based on a deep convolution neural network (CNN) is proposed for the reconstruction of full-resolution multi-spectral images from raw MSFA-based spectral mosaic images. The CNN is integrated with the channel attention mechanism to protect important channel features. We verify the merits of the proposed method using 5 × 5 raw mosaic images on synthetic as well as real-world data. The experimental results show that the proposed method outperforms the existing demosaicing methods in terms of spatial details and spectral fidelity.

Rapid Determination of Positive-Negative Bacterial Infection Based on Micro-Hyperspectral Technology.

To meet the demand for rapid bacterial detection in clinical practice, this study proposed a joint determination model based on spectral database matching combined with a deep learning model for the determination of positive-negative bacterial infection in directly smeared urine samples. Based on a dataset of 8124 urine samples, a standard hyperspectral database of common bacteria and impurities was established. This database, combined with an automated single-target extraction, was used to perform spectral matching for single bacterial targets in directly smeared data. To address the multi-scale features and the need for the rapid analysis of directly smeared data, a multi-scale buffered convolutional neural network, MBNet, was introduced, which included three convolutional combination units and four buffer units to extract the spectral features of directly smeared data from different dimensions. The focus was on studying the differences in spectral features between positive and negative bacterial infection, as well as the temporal correlation between positive-negative determination and short-term cultivation. The experimental results demonstrate that the joint determination model achieved an accuracy of 97.29%, a Positive Predictive Value (PPV) of 97.17%, and a Negative Predictive Value (NPV) of 97.60% in the directly smeared urine dataset. This result outperformed the single MBNet model, indicating the effectiveness of the multi-scale buffered architecture for global and large-scale features of directly smeared data, as well as the high sensitivity of spectral database matching for single bacterial targets. The rapid determination solution of the whole process, which combines directly smeared sample preparation, joint determination model, and software analysis integration, can provide a preliminary report of bacterial infection within 10 min, and it is expected to become a powerful supplement to the existing technologies of rapid bacterial detection.

Event-related potentials reveal visual episodic memory deficits in patients with temporal lobe epilepsy.

OBJECTIVE: Temporal lobe epilepsy (TLE) patients usually suffer from impaired episodic memory (EM), but its underlying electrophysiologic mechanism and impacted cognitive performance are unclear. We aim to investigate the association between episodic memory reserve and physiological measures of memory workload in TLE patients using Event-related potentials (ERP). METHODS: A change detection task with image stimuli assesses visual episodic memory. During the memory encoding and decoding phases, the ERP signals were analyzed from twenty-nine TLE patients (twelve with left TLE patients, seventeen with TLE), and thirty healthy controls. Given that EM is a complex process involving many fundamental cognitive processes, the amplitudes and latencies of EM-related ERP (FN400, late positive potential (LPC), and late posterior negativity (LPN)), and the ERP reflecting the fundamental processes (P100, N100, P200, and P300) were calculated. Then we used a three-by-two factorial design on the ERP metrics for interaction and main effects. The correlation analysis among Wechsler Memory Scales-Chinese Revision (WMS-RC) results, behavioral data, and the ERPs was carried out. RESULTS: The TLE patients performed worse in WMS-RC and the memory task. The increased P200 and decreased P300 amplitudes were observed in the TLE patients, and LPN was abnormal in only LTLE patients. For EM-related components, differences were observed in both the LTLE and RTLE patients: the lack of the FN400 effect, the lack of the reversed LPC effect, and the reduced FN400. No significant inter-group difference was detected for the latencies of all the ERPs. Additionally, there were significant correlations among WMS-RC scores, behaviors, and some ERP amplitudes. CONCLUSIONS: The impaired EM is linked to the increased P200 and decreased P300 amplitudes. LPN seems to be sensitive to left temporal lobe dysfunction. More importantly, the abnormal old or new effects of the FN400 and LPC, and the reduced FN400 amplitude might be associated with the visual EM deficit in the TLE patients. These findings may assist in the deep understanding of the EM disorder and the evaluation of the side effects of antiepileptic drugs.

Adaptive convolution kernel network for change detection in hyperspectral images.

Feature extraction is a key step in hyperspectral image change detection. However, many targets with great various sizes, such as narrow paths, wide rivers, and large tracts of cultivated land, can appear in a satellite remote sensing image at the same time, which will increase the difficulty of feature extraction. In addition, the phenomenon that the number of changed pixels is much less than unchanged pixels will lead to class imbalance and affect the accuracy of change detection. To address the above issues, based on the U-Net model, we propose an adaptive convolution kernel structure to replace the original convolution operations and design a weight loss function in the training stage. The adaptive convolution kernel contains two various kernel sizes and can automatically generate their corresponding weight feature map during training. Each output pixel obtains the corresponding convolution kernel combination according to the weight. This structure of automatically selecting the size of the convolution kernel can effectively adapt to different sizes of targets and extract multi-scale spatial features. The modified cross-entropy loss function solves the problem of class imbalance by increasing the weight of changed pixels. Study results on four datasets indicate that the proposed method performs better than most existing methods.

Analytical method for calculating internal stray radiation from an IR spectrometer based on the view factor.

Optomechanical components such as the lens barrels and frames of IR spectrometers produce strong internal stray radiation, which reduces the instrument's SNR and dynamic range. An IR internal stray radiation calculation method based on an analytical model of the view factor is proposed. The mathematical model of the view factor calculation method of typical optomechanical components is established. For any IR optical systems, the internal stray radiation can be quickly and accurately calculated by adjusting the coordinate systems in the calculation method. Based on the proposed method, the internal stray radiation of a double-pass long-wave IR spectrometer was calculated. The calculation results are consistent with the simulation results. The RMS value of the relative error between the calculated value and the simulated value is around 11%. To verify the proposed method, an experiment was conducted to test the internal stray radiation of the long-wave IR spectrometer. The internal stray radiation test results agree with the calculated and simulated results, and the relative error between the test results and the calculation results is within 9%.

Joint Texture Search and Histogram Redistribution for Hyperspectral Image Quality Improvement.

Due to optical noise, electrical noise, and compression error, data hyperspectral remote sensing equipment is inevitably contaminated by various noises, which seriously affect the applications of hyperspectral data. Therefore, it is of great significance to enhance hyperspectral imaging data quality. To guarantee the spectral accuracy during data processing, band-wise algorithms are not suitable for hyperspectral data. This paper proposes a quality enhancement algorithm based on texture search and histogram redistribution combined with denoising and contrast enhancement. Firstly, a texture-based search algorithm is proposed to improve the accuracy of denoising by improving the sparsity of 4D block matching clustering. Then, histogram redistribution and Poisson fusion are used to enhance spatial contrast while preserving spectral information. Synthesized noising data from public hyperspectral datasets are used to quantitatively evaluate the proposed algorithm, and multiple criteria are used to analyze the experimental results. At the same time, classification tasks were used to verify the quality of the enhanced data. The results show that the proposed algorithm is satisfactory for hyperspectral data quality improvement.

CMID: Crossmodal Image Denoising via Pixel-Wise Deep Reinforcement Learning.

Removing noise from acquired images is a crucial step in various image processing and computer vision tasks. However, the existing methods primarily focus on removing specific noise and ignore the ability to work across modalities, resulting in limited generalization performance. Inspired by the iterative procedure of image processing used by professionals, we propose a pixel-wise crossmodal image-denoising method based on deep reinforcement learning to effectively handle noise across modalities. We proposed a similarity reward to help teach an optimal action sequence to model the step-wise nature of the human processing process explicitly. In addition, We designed an action set capable of handling multiple types of noise to construct the action space, thereby achieving successful crossmodal denoising. Extensive experiments against state-of-the-art methods on publicly available RGB, infrared, and terahertz datasets demonstrate the superiority of our method in crossmodal image denoising.

Comprehensive design analysis and verification of space-based short-wave infrared coded spectrometer via curved prism dispersion.

The spaceborne dispersive spectrometer is widely used in environmental, resource, and ocean observations. The coded spectrometer has higher energy advantages than the dispersion spectrometer, so it has great application prospects. In the current study, we developed an off-axis short-wave infrared coded optical system (SICOS) based on curved prism dispersion, and we further explored the design and optimization of the SICOS structure. Finite element analyses of a space-based short-wave infrared coded spectrometer based on curved prism dispersion (SSICS-CPD), including static simulation, modal analysis, sinusoidal vibration mechanical analysis, and random vibration mechanical analysis, were carried out. Simulation results showed that the SICOS support structure had excellent mechanical and thermal stability. As off-axis optical systems cannot meet the requirements of optical position accuracy through centering processing, a point source microscope and three-coordinate measuring machines were employed to complete the high-precision and rapid assembly of the SSICS-CPD. In addition, verification tests of surface shape error, stress relief, random vibration, and optical design parameters were carried out to validate the high stability and imaging performance of the SSICS-CPD. Results showed that the average modulation transfer function in the full field was 0.43 at 16.67 lp/mm, the spectral smile was <0.2 pixels, and the spectral keystone was <0.1 pixels. The design, analysis, assembly, and verification of the SSICS-CPD provide a useful reference for the development of other spaceborne prism dispersion spectrometers.

Hyperspectral anomaly detection via super-resolution reconstruction with an attention mechanism.

Hyperspectral anomaly detection aims to classify the anomalous objects in the scene. However, the spatial resolution of the hyperspectral images is relatively low, leading to inaccurate detection of abnormal pixels. Existing methods either ignore the low-resolution problem or leverage super-resolution models to reconstruct the global image to detect abnormal pixels. We claim that reconstructing super-resolution of the global image is unnecessary, while the area where the abnormal target is located should be paid more attention to be reconstructed. In this paper, we propose a super-resolution reconstruction with an attention mechanism for hyperspectral anomaly detection. Our method can automatically extract additional high-frequency information from low-spatial-resolution images and detect abnormal pixels simultaneously. Furthermore, the spatial-channel attention mechanism is adopted to select significant features for reconstructing super-resolution images by assigning different weights to different channels and different spatial-spectral locations. Finally, a regularized join loss function is proposed that balances different tasks by adjusting the relative weight. The experimental results on the public hyperspectral real datasets demonstrate that the proposed method outperforms the state-of-the-art methods.

Effect of pupil matching of cold shield on the fringe contrast of long-wave infrared spatial heterodyne spectroscopy.

Matching the cold shield with the exit pupil of the fringe-imaging system of long-wave infrared (LWIR) spatial heterodyne spectroscopy (SHS) damages illumination uniformity of the interferogram and affects the fringe contrast, which is a significant parameter for LWIR SHS. The optical models of the fringe-imaging system considering and not considering the pupil matching of the cold shield are built to illustrate the effect on the fringe contrast. Simulations based on the optical design software ASAP are conducted to verify the fringe contrast loss for field-widened LWIR SHS. The result shows that the pupil matching of the cold shield decreases the fringe contrast of LWIR SHS and field-widened LWIR SHS by 0.049% and 0.053%, respectively, and the fringe contrast loss increases with the degree of deviation from the telecentric condition of the fringe-imaging system.

Design analysis and test verification of a rigid-flexible, dual-mode coupling support structure for space-based rectangular curved prisms.

In view of the functional requirements of high reliability and stability support of optical components of space remote sensors, a rigid-flexible, dual-mode coupling support structure for space-based rectangular curved prisms (SRCPs) was designed. In-depth studies of the support principle and engineering realization of the SRCPs and optimization of the flexible adhesive structure were performed. Static and dynamic simulations were conducted on the mirror subassembly by means of finite element analysis, and test verification was also performed. The tests revealed that the surface shape error of the mirror subassembly after mechanical testing was 0.021λ, the displacement of the mirror body was 0.008 mm, the inclination angle was ∼0.8'', the mass of the mirror subassembly was 4.79 kg, the fundamental frequency was 283 Hz, and the maximum amplification of the total rms acceleration was 4.37. All indexes were superior to those of the design requirements. On this basis, bonding tests and mechanical tests of a rectangular curved prism reflector, a rectangular curved prism, and a rectangular plane reflector employing this proposed support structure were continued. The test results verified the reliability, stability, and universal applicability of the proposed rigid-flexible, dual-mode peripheral bonding support structure.

Biomimetic curved compound-eye camera with a high resolution for the detection of distant moving objects.

In this Letter, we demonstrate the design and fabrication of a biomimetic curved compound-eye camera (BCCEC) with a high resolution for detecting distant moving objects purpose. In contrast to previously reported compound-eye cameras, our BCCEC has two distinct features. One is that the ommatidia of the compound eye are deployed on a curved surface which makes a large field of view (FOV) possible. The other is that each ommatidium has a relatively large optical entrance and long focal length so that a distant object can be imaged. To overcome the mismatch between the curved focal plane formed by the curved compound eye and the planar focal plane of the CMOS image sensor (CIS), an optical relay subsystem is introduced between the compound eye and the CIS. As a result, a BCCEC with 127 ommatidia in the compound eye is designed and fabricated to achieve a large FOV of up to 98∘×98∘. The experimental results show that objects with a size of 100 mm can be clearly resolved at a distance of 25 m. The capture of the motion trajectories of a moving object is also demonstrated, which makes it possible to detect and track the moving targets in a huge FOV for security surveillance purposes.

Hyperspectral deep convolution anomaly detection based on weight adjustment strategy.

Hyperspectral anomaly detection has garnered much research in recent years due to the excellent detection ability of hyperspectral remote sensing in agriculture, forestry, geological surveys, environmental monitoring, and battlefield target detection. The traditional anomaly detection method ignores the non-linearity and complexity of the hyperspectral image (HSI), while making use of the effectiveness of spatial information rarely. Besides, the anomalous pixels and the background are mixed, which causes a higher false alarm rate in the detection result. In this paper, a hyperspectral deep net-based anomaly detector using weight adjustment strategy (WAHyperDNet) is proposed to circumvent the above issues. We leverage three-dimensional convolution instead of the two-dimensional convolution to get a better way of handling high-dimensional data. In this study, the determinative spectrum-spatial features are extracted across the correlation between HSI pixels. Moreover, feature weights in the method are automatically generated based on absolute distance and the spectral similarity angle to describe the differences between the background pixels and the pixels to be tested. Experimental results on five public datasets show that the proposed approach outperforms the state-of-the-art baselines in both effectiveness and efficiency.

Meta-nanocavity model for dynamic super-resolution fluorescent imaging based on the plasmonic structure illumination microscopy method.

Biological research requires dynamic and wide-field optical microscopy with resolution down to nanometer to study the biological process in a sub-cell or single molecular level. To address this issue, we propose a dynamic wide-field optical nanoimaging method based on a meta-nanocavity platform (MNCP) model which can be incorporated in micro/nano-fluidic systems so that the samples to be observed can be confined in a nano-scale space for the ease of imaging. It is found that this platform can support standing wave surface plasmons (SW-SPs) interference pattern with a period of 105 nm for a 532 nm incident wavelength. Furthermore, the potential application of the NCP for wide-field super-resolution imaging was discussed and the simulation results show that an imaging resolution of sub-80 nm can be achieved.

Graphene on meta-surface for super-resolution optical imaging with a sub-10 nm resolution.

Nowadays, wide-field of view plasmonic structured illumination method (WFPSIM) has been extensively studied and experimentally demonstrated in biological researches. Normally, noble metal structures are used in traditional WFPSIM to support ultra-high wave-vector of SPs and an imaging resolution enhancement of 3-4 folds can be achieved. To further improve the imaging resolution of WFPSIM, we hereby propose a wide-field optical nanoimaging method based on a hybrid graphene on meta-surface structure (GMS) model. It is found that an ultra-high wave-vector of graphene SPs can be excited by a metallic nanoslits array with localized surface plasmon enhancement. As a result, a standing wave surface plasmons (SW-SPs) interference pattern with a period of 11 nm for a 980 nm incident wavelength can be obtained. The potential application of the GMS for wide-field of view super-resolution imaging is discussed followed by simulation results which show that an imaging resolution of sub-10 nm can be achieved. The demonstrated method paves a new route for wide field optical nanoimaging, with applications e.g. in biological research to study biological processes occurring in cell membrane.

Interference data correction methods for lunar observation with a large-aperture static imaging spectrometer.

The lunar spectrum has been used in radiometric calibration and sensor stability monitoring for spaceborne optical sensors. A ground-based large-aperture static image spectrometer (LASIS) can be used to acquire the lunar spectral image for lunar radiance model improvement when the moon orbits over its viewing field. The lunar orbiting behavior is not consistent with the desired scanning speed and direction of LASIS. To correctly extract interferograms from the obtained data, a translation correction method based on image correlation is proposed. This method registers the frames to a reference frame to reduce accumulative errors. Furthermore, we propose a circle-matching-based approach to achieve even higher accuracy during observation of the full moon. To demonstrate the effectiveness of our approaches, experiments are run on true lunar observation data. The results show that the proposed approaches outperform the state-of-the-art methods.

[A New Spectral-Spatial Algorithm Method for Hyperspectral Image Target Detection].

With high-resolution spatial information and continuous spectrum information, hyperspectral remote sensing image -has a unique advantage in the field of target detection. Traditional hyperspectral remote sensing image target detection methods emphasis on using spectral information to determine deterministic algorithm and statistical algorithms. Deterministic algorithms find the target by calculating the distance between the target spectrum and detected spectrum however, they are unable to detect sub-pixel target and are easily affected by noise. Statistical methods which calculate background statistical characteristics to detect abnormal point as target. It can detect subpixel target targets and small targets better thanbig size target,. With the spatial resolution increasing, subpixel target detection target has gradually grown to a single pixel and multi-pixel target. At this point, hyperspectral image usually has large homogeneous regions where the neighboring pixels wihin the regions consist of the same type of materials and have a similar spectral characteristics, therefore, the spatial information should be needed to incorporate into the algorithm for targe detection. This paper proposes an algorithm for hyperspectral target detection combined spectrum characteristics and spatial characteristics. The algorithm is based on traditional target detection operator and combined neighborhood clustering statistics. Firstly, the algorithm uses target detection operator to divided hyperspectral image into a potential target region and background region. Then, it calculates the centroid of the potential target area. Finally, as the centroid for neighborhood clustering center to clust data in order to exclud background from potential target area, through iterative calculation to obtain the final results of the target detection. The traditional statistics algorithms defines the total image as background area in order to extract background statistics features, and the algorithm propsed devided the total image into background part and potential target part, which cut off the target interference for background statistics feature extraction. Compared with CEM operators and ACE operators, the algorithm proposed outperforms than traditional operators in big target detection .

[A Novel Spatial-Spectral Sparse Representation for Hyperspectral Image Classification Based on Neighborhood Segmentation].

Traditional hyperspectral image classification algorithms focus on spectral information application, however, with the increase of spatial resolution of hyperspectral remote sensing images, hyperspectral imaging presents clustering properties on spatial domain for the same category. It is critical for hyperspectral image classification algorithms to use spatial information in order to improve the classification accuracy. However, the marginal differences of different categories display more obviously. If it is introduced directly into the spatial-spectral sparse representation for image classification without the selection of neighborhood pixels, the classification error and the computation time will increase. This paper presents a spatial-spectral joint sparse representation classification algorithm based on neighborhood segmentation. The algorithm calculates the similarity with spectral angel in order to choose proper neighborhood pixel into spatial-spectral joint sparse representation model. With simultaneous subspace pursuit and simultaneous orthogonal matching pursuit to solve the model, the classification is determined by computing the minimum reconstruction error between testing samples and training pixels. Two typical hyperspectral images from AVIRIS and ROSIS are chosen for simulation experiment and results display that the classification accuracy of two images both improves as neighborhood segmentation threshold increasing. It concludes that neighborhood segmentation is necessary for joint sparse representation classification.

Design of short wave infrared imaging spectrometer system based on CDP.

A compact static infrared snapshot imaging spectrometer (ISIS) is designed in order to satisfy the application requirements of real-time spectral imaging for the moving targets. It consists of a CDP (crossed dispersion prism), an imaging lens, and a detector. Here we describe the spectral imaging principle, and design a short wave infrared imaging spectrometer with 4.8° field of view, the measured spectrum is from 0.9µm to 2.5µm and is sampled by 40 spectral channels. This instrument has a large potential for detecting, locating and identifying unknown energetic events in real-time.