Detection of Various Microplastics in Patients Undergoing Cardiac Surgery.

Microplastics have been detected in human stool, lungs, and placentas, which have direct exposure to the external environment through various body cavities, including the oral/anal cavity and uterine/vaginal cavity. Crucial data on microplastic exposure in completely enclosed human organs are still lacking. Herein, we used a laser direct infrared chemical imaging system and scanning electron microscopy to investigate whether microplastics exist in the human heart and its surrounding tissues. Microplastic specimens were collected from 15 cardiac surgery patients, including 6 pericardia, 6 epicardial adipose tissues, 11 pericardial adipose tissues, 3 myocardia, 5 left atrial appendages, and 7 pairs of pre- and postoperative venous blood samples. Microplastics were not universally present in all tissue samples, but nine types were found across five types of tissue with the largest measuring 469 µm in diameter. Nine types of microplastics were also detected in pre- and postoperative blood samples with a maximum diameter of 184 µm, and the type and diameter distribution of microplastics in the blood showed alterations following the surgical procedure. Moreover, the presence of poly(methyl methacrylate) in the left atrial appendage, epicardial adipose tissue, and pericardial adipose tissue cannot be attributed to accidental exposure during surgery, providing direct evidence of microplastics in patients undergoing cardiac surgery. Further research is needed to examine the impact of surgery on microplastic introduction and the potential effects of microplastics in internal organs on human health.

Metabolic signatures in pericardial fluid and serum are associated with new-onset atrial fibrillation after isolated coronary artery bypass grafting.

Postoperative atrial fibrillation (POAF) is a common complication of coronary artery bypass grafting (CABG) procedures. However, the molecular mechanism of POAF remains poorly understood, hence the absence of effective prevention strategies. Here we used targeted metabolomics on pericardial fluid and serum samples from CABG patients to investigate POAF-associated metabolic alterations and related risk prediction of new-onset AF. Nine differential metabolites in various metabolic pathways were found in both pericardial fluid and serum samples from patients with POAF and without POAF. By using machine learning algorithms and regression models, a 4-metabolite (aceglutamide, ornithine, methionine, and arginine) risk prediction model was constructed and showed accurate performance in predicting POAF in both discovery and validation sets. This work extends the metabolic insights of the cardiac microenvironment and blood in patients with POAF and paves the way for the use of targeted metabolomics for predicting POAF in patients with CABG surgery.

Towards Accurate and Robust Domain Adaptation Under Multiple Noisy Environments.

In many non-stationary environments, machine learning algorithms usually confront the distribution shift scenarios. Previous domain adaptation methods have achieved great success. However, they would lose algorithm robustness in multiple noisy environments where the examples of source domain become corrupted by label noise, feature noise, or open-set noise. In this paper, we report our attempt toward achieving noise-robust domain adaptation. We first give a theoretical analysis and find that different noises have disparate impacts on the expected target risk. To eliminate the effect of source noises, we propose offline curriculum learning minimizing a newly-defined empirical source risk. We suggest a proxy distribution-based margin discrepancy to gradually decrease the noisy distribution distance to reduce the impact of source noises. We propose an energy estimator for assessing the outlier degree of open-set-noise examples to defeat the harmful influence. We also suggest robust parameter learning to mitigate the negative effect further and learn domain-invariant feature representations. Finally, we seamlessly transform these components into an adversarial network that performs efficient joint optimization for them. A series of empirical studies on the benchmark datasets and the COVID-19 screening task show that our algorithm remarkably outperforms the state-of-the-art, with over 10% accuracy improvements in some transfer tasks.

Automatic acquisition method for evaluating the on-orbit modulation transfer function based on lunar targets.

In view of the existing method having a great subjectivity for the lunar edge selection, we propose an automatic knife-edge detection method based on the Hough transform to evaluate the on-orbit modulation transfer function (MTF) of the satellite remote sensor. This novel method avoids the dependence of the on-orbit MTF measurement on the edge selection location, overcoming the limitation of the traditional method needing to identify the lunar shape and fix its edge area. On basis of two different edge detection algorithms (Sobel operator and Prewitt operator), the binary edge images of the moon are acquired, thus obtaining a series of edges satisfying the determination requirement by the Hough transform, and the MTFs corresponding to each knife-edge are calculated to obtain the optimal MTF. The automatic knife-edge detection method greatly improves the accuracy of the lunar edge selection, and the MTF obtained by the novel method is obviously better than that of the traditional method. In order to verify the effectiveness of the novel method, the long time series of the on-orbit MTFs for the FY-2G and FY-2E satellite measurements are given, indicating that the FY-2E observation has higher stability and better performance compared with that of the FY-2G satellite. This study has an important practical significance for evaluating the on-orbit stability of the satellite its optical imaging quality.

Four-quadrant retarder array imaging spectropolarimeter for the full Stokes vector spectrum.

Aiming at the major demand for polarization information gap in earth observation and space exploration, we proposed a four-quadrant retarder array imaging spectropolarimeter (FQRAISP) in view of the existing technical problem of the spectral resolution degradation along with spectral aliasing crosstalk. The optical schematic diagram of the FQRAISP together with its interference model was conceptually described, and the effectiveness of the scheme was validated through the experimental simulation, which demonstrated the competitive efficiency and accuracy in the proposed FQRAISP. The FQRAISP could restore the incident Stokes vector spectrum without any errors, and the inversion accuracy was increased by seven times, avoiding the spectrum aliasing and channel filtering in the channel modulation. In order to evaluate the influences of the alignment deviation of four-partition phase retarder component, together with its thickness deviation on the reconstructed Stokes parameters, the numerical simulations were carried out, and the results showed that the alignment deviations had a relatively weak effect on the reconstructed Stokes spectra, while the thickness deviations had an obvious influence. Therefore, the alignment deviations controlled in a range of [-0.43∘,+0.43∘] and [-0.22∘, + 0.22∘] together with the thickness deviations in a range of [ - 0.03µm, + 0.03µm] were an optimal choice for the engineering implementation of the FQRAISP. This research provided a novel method for the hardware realization of the accurate acquisition of all-optical information, having broad application prospects in remote sensing (deep space exploration), biomedicine and other fields.

Learning Transferable Parameters for Unsupervised Domain Adaptation.

Unsupervised domain adaptation (UDA) enables a learning machine to adapt from a labeled source domain to an unlabeled target domain under the distribution shift. Thanks to the strong representation ability of deep neural networks, recent remarkable achievements in UDA resort to learning domain-invariant features. Intuitively, the goal is that a good feature representation and the hypothesis learned from the source domain can generalize well to the target domain. However, the learning processes of domain-invariant features and source hypotheses inevitably involve domain-specific information that would degrade the generalizability of UDA models on the target domain. The lottery ticket hypothesis proves that only partial parameters are essential for generalization. Motivated by it, we find in this paper that only partial parameters are essential for learning domain-invariant information. Such parameters are termed transferable parameters that can generalize well in UDA. In contrast, the rest parameters tend to fit domain-specific details and often cause the failure of generalization, which are termed untransferable parameters. Driven by this insight, we propose Transferable Parameter Learning (TransPar) to reduce the side effect of domain-specific information in the learning process and thus enhance the memorization of domain-invariant information. Specifically, according to the distribution discrepancy degree, we divide all parameters into transferable and untransferable ones in each training iteration. We then perform separate update rules for the two types of parameters. Extensive experiments on image classification and regression tasks (keypoint detection) show that TransPar outperforms prior arts by non-trivial margins. Moreover, experiments demonstrate that TransPar can be integrated into the most popular deep UDA networks and be easily extended to handle any data distribution shift scenarios.

Unifying neural learning and symbolic reasoning for spinal medical report generation.

Automated medical report generation in spine radiology, i.e., given spinal medical images and directly create radiologist-level diagnosis reports to support clinical decision making, is a novel yet fundamental study in the domain of artificial intelligence in healthcare. However, it is incredibly challenging because it is an extremely complicated task that involves visual perception and high-level reasoning processes. In this paper, we propose the neural-symbolic learning (NSL) framework that performs human-like learning by unifying deep neural learning and symbolic logical reasoning for the spinal medical report generation. Generally speaking, the NSL framework firstly employs deep neural learning to imitate human visual perception for detecting abnormalities of target spinal structures. Concretely, we design an adversarial graph network that interpolates a symbolic graph reasoning module into a generative adversarial network through embedding prior domain knowledge, achieving semantic segmentation of spinal structures with high complexity and variability. NSL secondly conducts human-like symbolic logical reasoning that realizes unsupervised causal effect analysis of detected entities of abnormalities through meta-interpretive learning. NSL finally fills these discoveries of target diseases into a unified template, successfully achieving a comprehensive medical report generation. When employed in a real-world clinical dataset, a series of empirical studies demonstrate its capacity on spinal medical report generation and show that our algorithm remarkably exceeds existing methods in the detection of spinal structures. These indicate its potential as a clinical tool that contributes to computer-aided diagnosis.

Accurate Screening of COVID-19 Using Attention-Based Deep 3D Multiple Instance Learning.

Automated Screening of COVID-19 from chest CT is of emergency and importance during the outbreak of SARS-CoV-2 worldwide in 2020. However, accurate screening of COVID-19 is still a massive challenge due to the spatial complexity of 3D volumes, the labeling difficulty of infection areas, and the slight discrepancy between COVID-19 and other viral pneumonia in chest CT. While a few pioneering works have made significant progress, they are either demanding manual annotations of infection areas or lack of interpretability. In this paper, we report our attempt towards achieving highly accurate and interpretable screening of COVID-19 from chest CT with weak labels. We propose an attention-based deep 3D multiple instance learning (AD3D-MIL) where a patient-level label is assigned to a 3D chest CT that is viewed as a bag of instances. AD3D-MIL can semantically generate deep 3D instances following the possible infection area. AD3D-MIL further applies an attention-based pooling approach to 3D instances to provide insight into each instance's contribution to the bag label. AD3D-MIL finally learns Bernoulli distributions of the bag-level labels for more accessible learning. We collected 460 chest CT examples: 230 CT examples from 79 patients with COVID-19, 100 CT examples from 100 patients with common pneumonia, and 130 CT examples from 130 people without pneumonia. A series of empirical studies show that our algorithm achieves an overall accuracy of 97.9%, AUC of 99.0%, and Cohen kappa score of 95.7%. These advantages endow our algorithm as an efficient assisted tool in the screening of COVID-19.

Spine-GAN: Semantic segmentation of multiple spinal structures.

Spinal clinicians still rely on laborious workloads to conduct comprehensive assessments of multiple spinal structures in MRIs, in order to detect abnormalities and discover possible pathological factors. The objective of this work is to perform automated segmentation and classification (i.e., normal and abnormal) of intervertebral discs, vertebrae, and neural foramen in MRIs in one shot, which is called semantic segmentation that is extremely urgent to assist spinal clinicians in diagnosing neural foraminal stenosis, disc degeneration, and vertebral deformity as well as discovering possible pathological factors. However, no work has simultaneously achieved the semantic segmentation of intervertebral discs, vertebrae, and neural foramen due to three-fold unusual challenges: 1) Multiple tasks, i.e., simultaneous semantic segmentation of multiple spinal structures, are more difficult than individual tasks; 2) Multiple targets: average 21 spinal structures per MRI require automated analysis yet have high variety and variability; 3) Weak spatial correlations and subtle differences between normal and abnormal structures generate dynamic complexity and indeterminacy. In this paper, we propose a Recurrent Generative Adversarial Network called Spine-GAN for resolving above-aforementioned challenges. Firstly, Spine-GAN explicitly solves the high variety and variability of complex spinal structures through an atrous convolution (i.e., convolution with holes) autoencoder module that is capable of obtaining semantic task-aware representation and preserving fine-grained structural information. Secondly, Spine-GAN dynamically models the spatial pathological correlations between both normal and abnormal structures thanks to a specially designed long short-term memory module. Thirdly, Spine-GAN obtains reliable performance and efficient generalization by leveraging a discriminative network that is capable of correcting predicted errors and global-level contiguity. Extensive experiments on MRIs of 253 patients have demonstrated that Spine-GAN achieves high pixel accuracy of 96.2%, Dice coefficient of 87.1%, Sensitivity of 89.1% and Specificity of 86.0%, which reveals its effectiveness and potential as a clinical tool.

Automated Pathogenesis-Based Diagnosis of Lumbar Neural Foraminal Stenosis via Deep Multiscale Multitask Learning.

Pathogenesis-based diagnosis is a key step to prevent and control lumbar neural foraminal stenosis (LNFS). It conducts both early diagnosis and comprehensive assessment by drawing crucial pathological links between pathogenic factors and LNFS. Automated pathogenesis-based diagnosis would simultaneously localize and grade multiple spinal organs (neural foramina, vertebrae, intervertebral discs) to diagnose LNFS and discover pathogenic factors. The automated way facilitates planning optimal therapeutic schedules and relieving clinicians from laborious workloads. However, no successful work has been achieved yet due to its extreme challenges since 1) multiple targets: each lumbar spine has at least 17 target organs, 2) multiple scales: each type of target organ has structural complexity and various scales across subjects, and 3) multiple tasks, i.e., simultaneous localization and diagnosis of all lumbar organs, are extremely difficult than individual tasks. To address these huge challenges, we propose a deep multiscale multitask learning network (DMML-Net) integrating a multiscale multi-output learning and a multitask regression learning into a fully convolutional network. 1) DMML-Net merges semantic representations to reinforce the salience of numerous target organs. 2) DMML-Net extends multiscale convolutional layers as multiple output layers to boost the scale-invariance for various organs. 3) DMML-Net joins a multitask regression module and a multitask loss module to prompt the mutual benefit between tasks. Extensive experimental results demonstrate that DMML-Net achieves high performance (0.845 mean average precision) on T1/T2-weighted MRI scans from 200 subjects. This endows our method an efficient tool for clinical LNFS diagnosis.

Breast Cancer Multi-classification from Histopathological Images with Structured Deep Learning Model.

Automated breast cancer multi-classification from histopathological images plays a key role in computer-aided breast cancer diagnosis or prognosis. Breast cancer multi-classification is to identify subordinate classes of breast cancer (Ductal carcinoma, Fibroadenoma, Lobular carcinoma, etc.). However, breast cancer multi-classification from histopathological images faces two main challenges from: (1) the great difficulties in breast cancer multi-classification methods contrasting with the classification of binary classes (benign and malignant), and (2) the subtle differences in multiple classes due to the broad variability of high-resolution image appearances, high coherency of cancerous cells, and extensive inhomogeneity of color distribution. Therefore, automated breast cancer multi-classification from histopathological images is of great clinical significance yet has never been explored. Existing works in literature only focus on the binary classification but do not support further breast cancer quantitative assessment. In this study, we propose a breast cancer multi-classification method using a newly proposed deep learning model. The structured deep learning model has achieved remarkable performance (average 93.2% accuracy) on a large-scale dataset, which demonstrates the strength of our method in providing an efficient tool for breast cancer multi-classification in clinical settings.