Structurally constrained and pathology-aware convolutional transformer generative adversarial network for virtual histology staining of human coronary optical coherence tomography images.

Significance: There is a significant need for the generation of virtual histological information from coronary optical coherence tomography (OCT) images to better guide the treatment of coronary artery disease (CAD). However, existing methods either require a large pixel-wise paired training dataset or have limited capability to map pathological regions. Aim: The aim of this work is to generate virtual histological information from coronary OCT images, without a pixel-wise paired training dataset while capable of providing pathological patterns. Approach: We design a structurally constrained, pathology-aware, transformer generative adversarial network, namely structurally constrained pathology-aware convolutional transformer generative adversarial network (SCPAT-GAN), to generate virtual stained H&E histology from OCT images. We quantitatively evaluate the quality of virtual stained histology images by measuring the Fréchet inception distance (FID) and perceptual hash value (PHV). Moreover, we invite experienced pathologists to evaluate the virtual stained images. Furthermore, we visually inspect the virtual stained image generated by SCPAT-GAN. Also, we perform an ablation study to validate the design of the proposed SCPAT-GAN. Finally, we demonstrate 3D virtual stained histology images. Results: Compared to previous research, the proposed SCPAT-GAN achieves better FID and PHV scores. The visual inspection suggests that the virtual histology images generated by SCPAT-GAN resemble both normal and pathological features without artifacts. As confirmed by the pathologists, the virtual stained images have good quality compared to real histology images. The ablation study confirms the effectiveness of the combination of proposed pathological awareness and structural constraining modules. Conclusions: The proposed SCPAT-GAN is the first to demonstrate the feasibility of generating both normal and pathological patterns without pixel-wisely supervised training. We expect the SCPAT-GAN to assist in the clinical evaluation of treating the CAD by providing 2D and 3D histopathological visualizations.

Frequency-aware optical coherence tomography image super-resolution via conditional generative adversarial neural network.

Optical coherence tomography (OCT) has stimulated a wide range of medical image-based diagnosis and treatment in fields such as cardiology and ophthalmology. Such applications can be further facilitated by deep learning-based super-resolution technology, which improves the capability of resolving morphological structures. However, existing deep learning-based method only focuses on spatial distribution and disregards frequency fidelity in image reconstruction, leading to a frequency bias. To overcome this limitation, we propose a frequency-aware super-resolution framework that integrates three critical frequency-based modules (i.e., frequency transformation, frequency skip connection, and frequency alignment) and frequency-based loss function into a conditional generative adversarial network (cGAN). We conducted a large-scale quantitative study from an existing coronary OCT dataset to demonstrate the superiority of our proposed framework over existing deep learning frameworks. In addition, we confirmed the generalizability of our framework by applying it to fish corneal images and rat retinal images, demonstrating its capability to super-resolve morphological details in eye imaging.

CMTM6 shapes antitumor T cell response through modulating protein expression of CD58 and PD-L1.

The dysregulated expression of immune checkpoint molecules enables cancer cells to evade immune destruction. While blockade of inhibitory immune checkpoints like PD-L1 forms the basis of current cancer immunotherapies, a deficiency in costimulatory signals can render these therapies futile. CD58, a costimulatory ligand, plays a crucial role in antitumor immune responses, but the mechanisms controlling its expression remain unclear. Using two systematic approaches, we reveal that CMTM6 positively regulates CD58 expression. Notably, CMTM6 interacts with both CD58 and PD-L1, maintaining the expression of these two immune checkpoint ligands with opposing functions. Functionally, the presence of CMTM6 and CD58 on tumor cells significantly affects T cell-tumor interactions and response to PD-L1-PD-1 blockade. Collectively, these findings provide fundamental insights into CD58 regulation, uncover a shared regulator of stimulatory and inhibitory immune checkpoints, and highlight the importance of tumor-intrinsic CMTM6 and CD58 expression in antitumor immune responses.

Frequency-aware optical coherence tomography image super-resolution via conditional generative adversarial neural network.

Optical coherence tomography (OCT) has stimulated a wide range of medical image-based diagnosis and treatment in fields such as cardiology and ophthalmology. Such applications can be further facilitated by deep learning-based super-resolution technology, which improves the capability of resolving morphological structures. However, existing deep learning-based method only focuses on spatial distribution and disregard frequency fidelity in image reconstruction, leading to a frequency bias. To overcome this limitation, we propose a frequency-aware super-resolution framework that integrates three critical frequency-based modules (i.e., frequency transformation, frequency skip connection, and frequency alignment) and frequency-based loss function into a conditional generative adversarial network (cGAN). We conducted a large-scale quantitative study from an existing coronary OCT dataset to demonstrate the superiority of our proposed framework over existing deep learning frameworks. In addition, we confirmed the generalizability of our framework by applying it to fish corneal images and rat retinal images, demonstrating its capability to super-resolve morphological details in eye imaging.

Automated player identification and indexing using two-stage deep learning network.

American football games attract significant worldwide attention every year. Identifying players from videos in each play is also essential for the indexing of player participation. Processing football game video presents great challenges such as crowded settings, distorted objects, and imbalanced data for identifying players, especially jersey numbers. In this work, we propose a deep learning-based player tracking system to automatically track players and index their participation per play in American football games. It is a two-stage network design to highlight areas of interest and identify jersey number information with high accuracy. First, we utilize an object detection network, a detection transformer, to tackle the player detection problem in a crowded context. Second, we identify players using jersey number recognition with a secondary convolutional neural network, then synchronize it with a game clock subsystem. Finally, the system outputs a complete log in a database for play indexing. We demonstrate the effectiveness and reliability of player tracking system by analyzing the qualitative and quantitative results on football videos. The proposed system shows great potential for implementation in and analysis of football broadcast video.

Deep learning empowered highly compressive SS-OCT via learnable spectral-spatial sub-sampling.

With the rapid advances of light source technology, the A-line imaging rate of swept-source optical coherence tomography (SS-OCT) has experienced a great increase in the past three decades. The bandwidths of data acquisition, data transfer, and data storage, which can easily reach several hundred megabytes per second, have now been considered major bottlenecks for modern SS-OCT system design. To address these issues, various compression schemes have been previously proposed. However, most of the current methods focus on enhancing the capability of the reconstruction algorithm and can only provide a data compression ratio (DCR) up to 4 without impairing the image quality. In this Letter, we proposed a novel design paradigm, in which the sub-sampling pattern for interferogram acquisition is jointly optimized with the reconstruction algorithm in an end-to-end manner. To validate the idea, we retrospectively apply the proposed method on an ex vivo human coronary optical coherence tomography (OCT) dataset. The proposed method could reach a maximum DCR of ∼62.5 with peak signal-to-noise ratio (PSNR) of 24.2 dB, while a DCR of ∼27.78 could yield a visually pleasant image with a PSNR of ∼24.6 dB. We believe the proposed system could be a viable remedy for the ever-growing data issue in SS-OCT.

Toward reliable calcification detection: calibration of uncertainty in object detection from coronary optical coherence tomography images.

Significance: Optical coherence tomography (OCT) has become increasingly essential in assisting the treatment of coronary artery disease (CAD). However, unidentified calcified regions within a narrowed artery could impair the outcome of the treatment. Fast and objective identification is paramount to automatically procuring accurate readings on calcifications within the artery. Aim: We aim to rapidly identify calcification in coronary OCT images using a bounding box and reduce the prediction bias in automated prediction models. Approach: We first adopt a deep learning-based object detection model to rapidly draw the calcified region from coronary OCT images using a bounding box. We measure the uncertainty of predictions based on the expected calibration errors, thus assessing the certainty level of detection results. To calibrate confidence scores of predictions, we implement dependent logistic calibration using each detection result's confidence and center coordinates. Results: We implemented an object detection module to draw the boundary of the calcified region at a rate of 140 frames per second. With the calibrated confidence score of each prediction, we lower the uncertainty of predictions in calcification detection and eliminate the estimation bias from various object detection methods. The calibrated confidence of prediction results in a confidence error of ∼ 0.13 , suggesting that the confidence calibration on calcification detection could provide a more trustworthy result. Conclusions: Given the rapid detection and effective calibration of the proposed work, we expect that it can assist in clinical evaluation of treating the CAD during the imaging-guided procedure.

Circ_0000285 regulates nasopharyngeal carcinoma progression through miR-1278/FNDC3B axis.

BACKGROUND: Nasopharyngeal carcinoma (NPC) is cancer with high mortality and poor prognosis. Circular RNAs (circRNAs) have been identified in a wide variety of cancers. But the functional mechanism of circ_000285 in NPC remains unclear. PURPOSE: To decipher the biological function and molecular mechanism of circ_000285 in NPC. METHODS: Quantitative PCR (RT-qPCR) was applied for detecting the expression of circ_0000285, miR-1278, and FNDC3B. Western blot was used to measure the protein levels of Fibronectin type III domain containing 3B (FNDC3B), Bcl2 associated X (Bax), and B cell leukemia/lymphoma 2 (Bcl2). Cell proliferation, migration, and invasion were analyzed by colony formation, 5-ethynyl-2'-deoxyuridine (EdU), and transwell assays. Cell apoptosis was detected by flow cytometry assays. ELISA assay was used to analyze Caspase-3 activity. Bioinformatics was used to predict, and the target relationship between miR-1278 and circ_0000285 or FNDC3B was verified by luciferase reporter assay. Tumor xenograft models were established to examine how circ_0000285 functions during the mediation of NPC tumor growth in vivo. RESULTS: Increased circ_0000285 and FNDC3B expressions, and a decreased miR-1278 expression were observed in NPC tissues and cell lines. Knockdown of circ_0000285 inhibited NPC cell proliferation, migration, invasion, and while promoting NPC cell apoptosis in vitro. Circ_0000285 knockdown-mediated anti-tumor effects in NPC cells could be largely reversed by silencing of miR-1278 or overexpression of FNDC3B. Circ_0000285 could up-regulate FNDC3B expression by sponging miR-1278 in NPC cells. Knockdown of circ_0000285 could inhibit tumor growth in vivo. CONCLUSION: Circ_0000285 upregulates FNDC3B expression by adsorbing miR-1278 to promote NPC development.

Non-Invasive Screen Exposure Time Assessment Using Wearable Sensor and Object Detection.

Cumulative screen exposure has been increased due to the explosion of digital technology ownership in the past decade for all people, including children who face exposure related risks such as obesity, eye problems, and disrupted sleep. Screen exposure is linked to physical and mental health risks among both children and adults. Current methods of screen exposure assessment have their limitations, mostly in the prospective of objectiveness, robustness, and invasiveness. In this paper, we propose a novel method to measure screen exposure time using a wearable sensor and computer vision technology. We use a customized, lightweight, wearable senor to capture egocentric images and use deep learning-based object detection module to identify the existence of electronic screens. The duration of screen exposure is further estimated using post-processing technology to filter consecutive frames regarding to the screen usage. Our method is non-invasive and robust, providing an objective and accurate means to screen exposure measurement. We conduct experiments on various environments to identify the existence of three types of screens and duration of screen exposure. The experimental results demonstrate the feasibility of automatically assessing screen time exposure and great potential to be applied in large scale experiments for behavioral study.

Multi-Scale Reconstruction of Undersampled Spectral-Spatial OCT Data for Coronary Imaging Using Deep Learning.

Coronary artery disease (CAD) is a cardiovascular condition with high morbidity and mortality. Intravascular optical coherence tomography (IVOCT) has been considered as an optimal imagining system for the diagnosis and treatment of CAD. Constrained by Nyquist theorem, dense sampling in IVOCT attains high resolving power to delineate cellular structures/features. There is a trade-off between high spatial resolution and fast scanning rate for coronary imaging. In this paper, we propose a viable spectral-spatial acquisition method that down-scales the sampling process in both spectral and spatial domain while maintaining high quality in image reconstruction. The down-scaling schedule boosts data acquisition speed without any hardware modifications. Additionally, we propose a unified multi-scale reconstruction framework, namely Multiscale-Spectral-Spatial-Magnification Network (MSSMN), to resolve highly down-scaled (compressed) OCT images with flexible magnification factors. We incorporate the proposed methods into Spectral Domain OCT (SD-OCT) imaging of human coronary samples with clinical features such as stent and calcified lesions. Our experimental results demonstrate that spectral-spatial down-scaled data can be better reconstructed than data that are down-scaled solely in either spectral or spatial domain. Moreover, we observe better reconstruction performance using MSSMN than using existing reconstruction methods. Our acquisition method and multi-scale reconstruction framework, in combination, may allow faster SD-OCT inspection with high resolution during coronary intervention.

Time-accuracy imaging quality prediction method for an infrared detection system under hypersonic conditions.

The imaging quality of infrared detection systems over time directly affects their ability to track targets accurately. In this study, a prediction scheme for the image quality of infrared detection system under hypersonic conditions based on time accuracy has been developed. Further, based on the time discretization, a calculation model has been established for the prediction scheme to perform numerical simulation. In particular, for verifying the reliability of this prediction method and the associated numerical calculation model, a comparison has been made between the numerical simulation results and the wind tunnel test results. The maximum error of the comparison result is less than 4.5%, and the reliability of the method proposed in this paper has been proved.

Aberration characteristic correlation configuration optimization of a conformal dome based on the von Karman surface.

In this paper, the von Karman surface is used in the configuration design of the infrared conformal dome to improve its aerodynamic performance. The principle of differential geometry is used to study the geometric characteristics of the von Karman dome. Additionally, by using ray tracing, the geometric aberrations and wave aberrations of the von Karman dome are analyzed. Further, considering the geometric characteristics and aberration characteristics, an optimization method for the configuration of the von Karman dome is proposed. To prove the effectiveness of the optimization method, the aberrations introduced by the conformal dome after the configuration optimization and the original von Karman dome are compared. The comparison showed that the geometric aberration of the optimized conformal dome is reduced by 43.68%. The optimization method can significantly correct the aberration introduced by the von Karman dome and improve the guidance capability of infrared detection technology.

Analog optical deconvolution computing for wavefront coding based on nanoantennas metasurfaces.

Analog optical computing based on metasurfaces has attracted much attention for achieving high-speed calculating without the electronic processing unit. Wavefront coding imaging systems involve the joint design of an encoded image-capturing module and decoding postprocessing algorithms to obtain a required final image. The decoding postprocessing algorithms, as a typical deconvolution computation, require an additional electronic processing unit to yield a high-quality decoded image. We demonstrate an analog optical deconvolution computing kernel based on nanoantennas metasurfaces for the postprocessing calculation of wavefront coding systems. Numerical simulations are presented to prove that the encoded point spread function can be refocused through a designed optical computing metasurface. The proposed approach opens an opportunity for real-time recovering images in wavefront coding optical systems.

Transmissive mid-infrared achromatic bifocal metalens with polarization sensitivity.

Metasurfaces have shown great potential in versatile areas such as vortex-beam generators, metalenses, holograms and so on. However, chromatic error hinders metasurfaces, especially metalenses, from wider applications. In this paper, we demonstrate a novel design for a transmissive mid-infrared achromatic bifocal metalens with polarization sensitivity. The compensation phase is used to eliminate the chromatic aberration. Simulation results show that, over a continuous waveband from 3.9 to 4.6µm, the focal length only changes by 2.26% with an average focusing efficiency of about 18%. This work can push the practical application of mid-infrared metasurfaces.

miR-143 inhibits proliferation and metastasis of nasopharyngeal carcinoma cells via targeting FMNL1 based on clinical and radiologic findings.

Mounting evidence has reported that microRNA-143 (miR-143) is involved in the development of multiple cancers. To investigate the underlying mechanisms of miR-143 regulating proliferation and metastasis in nasopharyngeal carcinoma (NPC) cells, we evaluated the levels of miR-143 and formin-like protein 1 (FMNL1) in NPC tissues. The results of qRT-PCR and Western blot analysis showed that the expression of miR-143 was decreased, while FMNL1 was increased in NPC tissues. The expression of miR-143 was significantly elevated in NPC cells compared with that of human nasopharyngeal epithelial cells. The results of MiRcode prediction, dual-luciferase reporter, and Western blot analysis assays indicated that miR-143 negatively regulated the expression of FMNL1 (r2 = 0.4365P = 0.0001). Overexperssion of miR-143 or FMNL1 knockdown inhibited cell proliferation, migration, and invasion in NPC cells (P < 0.05). Ectopic expression of FMNL1 undermined the inhibition effect of miR-143 on proliferation, migration, and invasion in NPC cells. The findings of this study revealed that miR-143 functioned as a tumor suppressor and inhibited the NPC progression by targeting FMNL1.

The Long Noncoding RNA NEAT1 Targets miR-34a-5p and Drives Nasopharyngeal Carcinoma Progression via Wnt/ß-Catenin Signaling.

PURPOSE: Long noncoding RNA nuclear paraspeckle assembly transcript 1 (NEAT1) has been deemed an oncogene in many human cancers. However, the underlying mechanism of NEAT1 in nasopharyngeal carcinoma (NPC) progression remains largely unclear. MATERIALS AND METHODS: Quantitative real-time PCR assay was performed to assess the expression of NEAT1 and miR-34a-5p in NPC tissues and cells. Western blot analysis was used to observe cell epithelial to mesenchymal transition (EMT) and the activation of Wnt/ß-catenin signaling in 5-8F cells. MiRNA directly interacting with NEAT1 were verified by dual-luciferase reporter assay and RNA immunoprecipitation. Cell proliferation ability was determined by CCK-8 assay, and cell migration and invasion capacities were assessed by transwell assays. An animal model was used to investigate the regulatory effect of NEAT1 on tumor growth in vivo. RESULTS: Our data revealed that NEAT1 is upregulated, while miR-34a-5p is downregulated in NPC tissues and cell lines. NEAT1 knockdown repressed tumor growth in vitro and in vivo. Additionally, we discovered that NEAT1 directly binds to miR-34a-5p and suppresses miR-34a-5p expression. Moreover, NEAT1 knockdown exerted suppression effects on cell proliferation, migration, invasion, and EMT by miR-34a-5p. NEAT1 knockdown blocked Wnt/ß-catenin signaling via miR-34a-5p. CONCLUSION: Our study demonstrated that NEAT1 targets miR-34a-5p at least partly to drive NPC progression by regulating Wnt/ß-catenin signaling, suggesting a potential therapeutic target for NPC.

Effects of typical modified passivators on speciation of heavy metals in protein extracted from sewage sludge.

The sewage sludge contains abundant organic substances as well as a complex variety of inorganic substances (such as heavy metals). The extraction of protein from sludge is a new treatment approach to promote the utilization of sludge as a resource. However, heavy metals in sludge are extracted together with organic matter during the extraction process. In this study, the amounts of protein and heavy metal in the supernatant extracted from sewage sludge were investigated, and the effects of different passivator (modified fly ash and modified sepiolite) on the speciation of different heavy metals in the sludge were examined. Both materials reduced the contents of protein and heavy metal in the supernatant. When the dosage of sepiolite was 0.10 g/g total suspended solids of sludge, the content of heavy metals was the lowest and the protein content had little change. It can be deduced by analysis of specific area that sepiolite can complex with heavy metal ions and the fly ash adsorb the metals by physical adsorption. The modified sepiolite can be seen as an ideal passivator due to higher protein content and less heavy metals in the supernatant, as well as more stable heavy metals in the sediments.

Hybrid MoSe2-indocyanine green nanosheets as a highly efficient phototheranostic agent for photoacoustic imaging guided photothermal cancer therapy.

Phototheranostic technology based on photoacoustic imaging (PAI) and photothermal therapy (PTT) is emerging as a powerful tool for tumor theranostic applications. For effective tumor eradication, a novel PAI/PTT theranostic nanoagent with an excellent optical absorption and photothermal capability is highly desired. Herein, we present a new PAI/PTT nanohybrid named sMoSe2-ICG NSs by covalently conjugating aminated indocyanine green (ICG) onto a single layer of molybdenum selenide nanosheets (sMoSe2 NSs). We first validate the sMoSe2-ICG NS agent for the PAI and PTT effect in vitro and then use it for highly-sensitive PAI guided highly efficient tumor PTT in vivo. The sMoSe2-ICG NS hybrid possesses several advantages for PAI/PTT applications: (1) the sMoSe2-ICG NSs have strong absorbance in the broad near-infrared (NIR) region, enabling a highly efficient PAI/PTT theranostic effect and the selection of the most widely used excitation wavelength of 808 nm for PTT; (2) the photothermal ability of ICG in sMoSe2-ICG NSs is augmented due to ICG aggregation induced fluorescence quenching and the re-absorbance of ICG fluorescence by sMoSe2 NSs, which further enhances the PAI/PTT theranostic effect. (3) The characteristic absorption peak of sMoSe2-ICG NSs is red-shifted compared to free ICG, resulting in a higher PAI signal-to-noise ratio (SNR) in vivo. Thus, combined with the good stability, high biocompatibility and minimal toxicity properties, the obtained sMoSe2-ICG NSs hybrid has bright prospects for use in future PAI/PTT clinical applications.