Patterns of sex behaviors and factors associated with condomless anal intercourse during the COVID-19 pandemic among men who have sex with men in Hong Kong: A cross-sectional study

OBJECTIVES

The present study examined the patterns of sex behaviors before and during COVID-19, and identified the factors associated with condomless anal intercourse during COVID-19 from individual, interpersonal, and contextual level among men who have sex with men (MSM) in Hong Kong.

METHODS

A cross-sectional study was conducted among MSM in Hong Kong. A total of 463 MSM completed a cross-sectional telephone survey between March 2021 and January 2022.

RESULTS

Among all participants, the mean number of regular sex partners, non-regular sex partners, and casual sex partners during the COVID-19 period were 1.24, 2.09, and 0.08 respectively. Among those who had sex with regular, non-regular, and casual sex partner during the COVID-19 period, respectively 52.4%, 31.8% and 46.7% reported condomless anal intercourse. Compared to the pre-COVID-19 period, participants reported significantly fewer number of regular and non-regular sex partners during the COVID-19 period. However, a higher level of condomless anal intercourse with all types of sex partners during the COVID-19 period was also observed. Adjusted for significant socio-demographic variables, results from logistic regression analyses revealed that perceived severity of COVID-19 (aOR = 0.72, 95% CI = 0.58, 0.88), COVID-19 risk reduction behaviors in general (aOR = 0.68, 95% CI = 0.48, 0.96), COVID-19 risk reduction behaviors during sex encounters (aOR = 0.45, 95% CI = 0.30, 0.66), condom negotiation (aOR = 0.61, 95% CI = 0.44, 0.86), and collective efficacy (aOR = 0.79, 95% CI = 0.64, 0.98) were protective factors of condomless anal intercourse with any type of sex partners during the COVID-19 period.

CONCLUSION

The COVID-19 control measures have caused a dramatic impact on the sexual behavior of MSM in Hong Kong. Interventions that promote condom use during the COVID-19 pandemic are still needed and such interventions could emphasize prevention of both COVID-19 and HIV.

DeepN4: Learning N4ITK Bias Field Correction for T1-weighted Images

T1-weighted (T1w) MRI has low frequency intensity artifacts due to magnetic field inhomogeneities. Removal of these biases in T1w MRI images is a critical preprocessing step to ensure spatially consistent image interpretation. N4ITK bias field correction, the current state-of-the-art, is implemented in such a way that makes it difficult to port between different pipelines and workflows, thus making it hard to reimplement and reproduce results across local, cloud, and edge platforms. Moreover, N4ITK is opaque to optimization before and after its application, meaning that methodological development must work around the inhomogeneity correction step. Given the importance of bias fields correction in structural preprocessing and flexible implementation, we pursue a deep learning approximation / reinterpretation of the N4ITK bias fields correction to create a method which is portable, flexible, and fully differentiable. In this paper, we trained a deep learning network "DeepN4" on eight independent cohorts from 72 different scanners and age ranges with N4ITK-corrected T1w MRI and bias field for supervision in log space. We found that we can closely approximate N4ITK bias fields correction with naïve networks. We evaluate the peak signal to noise ratio (PSNR) in test dataset against the N4ITK corrected images. The median PSNR of corrected images between N4ITK and DeepN4 was 47.96 dB. In addition, we assess the DeepN4 model on eight additional external datasets and show the generalizability of the approach. This study establishes that incompatible N4ITK preprocessing steps can be closely approximated by naïve deep neural networks, facilitating more flexibility. All code and models are released at https://github.com/MASILab/DeepN4 .

Deep conditional generative model for longitudinal single-slice abdominal computed tomography harmonization

Purpose

Two-dimensional single-slice abdominal computed tomography (CT) provides a detailed tissue map with high resolution allowing quantitative characterization of relationships between health conditions and aging. However, longitudinal analysis of body composition changes using these scans is difficult due to positional variation between slices acquired in different years, which leads to different organs/tissues being captured.

Approach

To address this issue, we propose C-SliceGen, which takes an arbitrary axial slice in the abdominal region as a condition and generates a pre-defined vertebral level slice by estimating structural changes in the latent space.

Results

Our experiments on 2608 volumetric CT data from two in-house datasets and 50 subjects from the 2015 Multi-Atlas Abdomen Labeling Challenge Beyond the Cranial Vault (BTCV) dataset demonstrate that our model can generate high-quality images that are realistic and similar. We further evaluate our method's capability to harmonize longitudinal positional variation on 1033 subjects from the Baltimore longitudinal study of aging dataset, which contains longitudinal single abdominal slices, and confirmed that our method can harmonize the slice positional variance in terms of visceral fat area.

Conclusion

This approach provides a promising direction for mapping slices from different vertebral levels to a target slice and reducing positional variance for single-slice longitudinal analysis. The source code is available at: https://github.com/MASILab/C-SliceGen.

Predicting Age from White Matter Diffusivity with Residual Learning

Imaging findings inconsistent with those expected at specific chronological age ranges may serve as early indicators of neurological disorders and increased mortality risk. Estimation of chronological age, and deviations from expected results, from structural magnetic resonance imaging (MRI) data has become an important proxy task for developing biomarkers that are sensitive to such deviations. Complementary to structural analysis, diffusion tensor imaging (DTI) has proven effective in identifying age-related microstructural changes within the brain white matter, thereby presenting itself as a promising additional modality for brain age prediction. Although early studies have sought to harness DTI's advantages for age estimation, there is no evidence that the success of this prediction is owed to the unique microstructural and diffusivity features that DTI provides, rather than the macrostructural features that are also available in DTI data. Therefore, we seek to develop white-matter-specific age estimation to capture deviations from normal white matter aging. Specifically, we deliberately disregard the macrostructural information when predicting age from DTI scalar images, using two distinct methods. The first method relies on extracting only microstructural features from regions of interest (ROIs). The second applies 3D residual neural networks (ResNets) to learn features directly from the images, which are non-linearly registered and warped to a template to minimize macrostructural variations. When tested on unseen data, the first method yields mean absolute error (MAE) of 6.11 ± 0.19 years for cognitively normal participants and MAE of 6.62 ± 0.30 years for cognitively impaired participants, while the second method achieves MAE of 4.69 ± 0.23 years for cognitively normal participants and MAE of 4.96 ± 0.28 years for cognitively impaired participants. We find that the ResNet model captures subtler, non-macrostructural features for brain age prediction.

Review of MR spectroscopy analysis and artificial intelligence applications for the detection of cerebral inflammation and neurotoxicity in Alzheimer's disease

INTRODUCTION

Magnetic resonance spectroscopy (MRS) has an emerging role as a neuroimaging tool for the detection of biomarkers of Alzheimer's disease (AD). To date, MRS has been established as one of the diagnostic tools for various diseases such as breast cancer and fatty liver, as well as brain tumours. However, its utility in neurodegenerative diseases is still in the experimental stages. The potential role of the modality has not been fully explored, as there is diverse information regarding the aberrations in the brain metabolites caused by normal ageing versus neurodegenerative disorders.

MATERIALS AND METHODS

A literature search was carried out to gather eligible studies from the following widely sourced electronic databases such as Scopus, PubMed and Google Scholar using the combination of the following keywords: AD, MRS, brain metabolites, deep learning (DL), machine learning (ML) and artificial intelligence (AI); having the aim of taking the readers through the advancements in the usage of MRS analysis and related AI applications for the detection of AD.

RESULTS

We elaborate on the MRS data acquisition, processing, analysis, and interpretation techniques. Recommendation is made for MRS parameters that can obtain the best quality spectrum for fingerprinting the brain metabolomics composition in AD. Furthermore, we summarise ML and DL techniques that have been utilised to estimate the uncertainty in the machine-predicted metabolite content, as well as streamline the process of displaying results of metabolites derangement that occurs as part of ageing.

CONCLUSION

MRS has a role as a non-invasive tool for the detection of brain metabolite biomarkers that indicate brain metabolic health, which can be integral in the management of AD.

UNesT: Local spatial representation learning with hierarchical transformer for efficient medical segmentation

Transformer-based models, capable of learning better global dependencies, have recently demonstrated exceptional representation learning capabilities in computer vision and medical image analysis. Transformer reformats the image into separate patches and realizes global communication via the self-attention mechanism. However, positional information between patches is hard to preserve in such 1D sequences, and loss of it can lead to sub-optimal performance when dealing with large amounts of heterogeneous tissues of various sizes in 3D medical image segmentation. Additionally, current methods are not robust and efficient for heavy-duty medical segmentation tasks such as predicting a large number of tissue classes or modeling globally inter-connected tissue structures. To address such challenges and inspired by the nested hierarchical structures in vision transformer, we proposed a novel 3D medical image segmentation method (UNesT), employing a simplified and faster-converging transformer encoder design that achieves local communication among spatially adjacent patch sequences by aggregating them hierarchically. We extensively validate our method on multiple challenging datasets, consisting of multiple modalities, anatomies, and a wide range of tissue classes, including 133 structures in the brain, 14 organs in the abdomen, 4 hierarchical components in the kidneys, inter-connected kidney tumors and brain tumors. We show that UNesT consistently achieves state-of-the-art performance and evaluate its generalizability and data efficiency. Particularly, the model achieves whole brain segmentation task complete ROI with 133 tissue classes in a single network, outperforming prior state-of-the-art method SLANT27 ensembled with 27 networks. Our model performance increases the mean DSC score of the publicly available Colin and CANDI dataset from 0.7264 to 0.7444 and from 0.6968 to 0.7025, respectively. Code, pre-trained models, and use case pipeline are available at: https://github.com/MASILab/UNesT.

DeepN4: Learning N4ITK Bias Field Correction for T1-weighted Images

T1-weighted (T1w) MRI has low frequency intensity artifacts due to magnetic field inhomogeneities. Removal of these biases in T1w MRI images is a critical preprocessing step to ensure spatially consistent image interpretation. N4ITK bias field correction, the current state-of-the-art, is implemented in such a way that makes it difficult to port between different pipelines and workflows, thus making it hard to reimplement and reproduce results across local, cloud, and edge platforms. Moreover, N4ITK is opaque to optimization before and after its application, meaning that methodological development must work around the inhomogeneity correction step. Given the importance of bias fields correction in structural preprocessing and flexible implementation, we pursue a deep learning approximation / reinterpretation of the N4ITK bias fields correction to create a method which is portable, flexible, and fully differentiable. In this paper, we trained a deep learning network "DeepN4" on eight independent cohorts from 72 different scanners and age ranges with N4ITK-corrected T1w MRI and bias field for supervision in log space. We found that we can closely approximate N4ITK bias fields correction with naïve networks. We evaluate the peak signal to noise ratio (PSNR) in test dataset against the N4ITK corrected images. The median PSNR of corrected images between N4ITK and DeepN4 was 47.96 dB. In addition, we assess the DeepN4 model on eight additional external datasets and show the generalizability of the approach. This study establishes that incompatible N4ITK preprocessing steps can be closely approximated by naïve deep neural networks, facilitating more flexibility. All code and models are released at https://github.com/MASILab/DeepN4.

Semantic-Aware Contrastive Learning for Multi-Object Medical Image Segmentation

Medical image segmentation, or computing voxel-wise semantic masks, is a fundamental yet challenging task in medical imaging domain. To increase the ability of encoder-decoder neural networks to perform this task across large clinical cohorts, contrastive learning provides an opportunity to stabilize model initialization and enhances downstream tasks performance without ground-truth voxel-wise labels. However, multiple target objects with different semantic meanings and contrast level may exist in a single image, which poses a problem for adapting traditional contrastive learning methods from prevalent "image-level classification" to "pixel-level segmentation". In this article, we propose a simple semantic-aware contrastive learning approach leveraging attention masks and image-wise labels to advance multi-object semantic segmentation. Briefly, we embed different semantic objects to different clusters rather than the traditional image-level embeddings. We evaluate our proposed method on a multi-organ medical image segmentation task with both in-house data and MICCAI Challenge 2015 BTCV datasets. Compared with current state-of-the-art training strategies, our proposed pipeline yields a substantial improvement of 5.53% and 6.09% on Dice score for both medical image segmentation cohorts respectively (p-value 0.01). The performance of the proposed method is further assessed on external medical image cohort via MICCAI Challenge FLARE 2021 dataset, and achieves a substantial improvement from Dice 0.922 to 0.933 (p-value 0.01).

Quantifying emphysema in lung screening computed tomography with robust automated lobe segmentation

Purpose

Anatomy-based quantification of emphysema in a lung screening cohort has the potential to improve lung cancer risk stratification and risk communication. Segmenting lung lobes is an essential step in this analysis, but leading lobe segmentation algorithms have not been validated for lung screening computed tomography (CT).

Approach

In this work, we develop an automated approach to lobar emphysema quantification and study its association with lung cancer incidence. We combine self-supervised training with level set regularization and finetuning with radiologist annotations on three datasets to develop a lobe segmentation algorithm that is robust for lung screening CT. Using this algorithm, we extract quantitative CT measures for a cohort (n=1189) from the National Lung Screening Trial and analyze the multivariate association with lung cancer incidence.

Results

Our lobe segmentation approach achieved an external validation Dice of 0.93, significantly outperforming a leading algorithm at 0.90 (p<0.01). The percentage of low attenuation volume in the right upper lobe was associated with increased lung cancer incidence (odds ratio: 1.97; 95% CI: [1.06, 3.66]) independent of PLCOm2012 risk factors and diagnosis of whole lung emphysema. Quantitative lobar emphysema improved the goodness-of-fit to lung cancer incidence (χ2=7.48, p=0.02).

Conclusions

We are the first to develop and validate an automated lobe segmentation algorithm that is robust to smoking-related pathology. We discover a quantitative risk factor, lending further evidence that regional emphysema is independently associated with increased lung cancer incidence. The algorithm is provided at https://github.com/MASILab/EmphysemaSeg.

Single slice thigh CT muscle group segmentation with domain adaptation and self-training

Purpose

Thigh muscle group segmentation is important for assessing muscle anatomy, metabolic disease, and aging. Many efforts have been put into quantifying muscle tissues with magnetic resonance (MR) imaging, including manual annotation of individual muscles. However, leveraging publicly available annotations in MR images to achieve muscle group segmentation on single-slice computed tomography (CT) thigh images is challenging.

Approach

We propose an unsupervised domain adaptation pipeline with self-training to transfer labels from three-dimensional MR to single CT slices. First, we transform the image appearance from MR to CT with CycleGAN and feed the synthesized CT images to a segmenter simultaneously. Single CT slices are divided into hard and easy cohorts based on the entropy of pseudo-labels predicted by the segmenter. After refining easy cohort pseudo-labels based on anatomical assumption, self-training with easy and hard splits is applied to fine-tune the segmenter.

Results

On 152 withheld single CT thigh images, the proposed pipeline achieved a mean Dice of 0.888 (0.041) across all muscle groups, including gracilis, hamstrings, quadriceps femoris, and sartorius muscle.

Conclusions

To our best knowledge, this is the first pipeline to achieve domain adaptation from MR to CT for thigh images. The proposed pipeline effectively and robustly extracts muscle groups on two-dimensional single-slice CT thigh images. The container is available for public use in GitHub repository available at: https://github.com/MASILab/DA_CT_muscle_seg.

The mediating role of resilience on the association between family satisfaction and lower levels of depression and anxiety among Chinese adolescents

PURPOSE

This study aimed to explore the association between family satisfaction, resilience, and anxiety and depression among adolescents, and the mediating role of resilience in these relationships.

METHODS

A cross-sectional study was conducted among grade 8 to 9 students from 4 secondary schools in Hong Kong. A total of 1,146 participants completed the survey.

RESULTS

Respectively 45.8% and 58.0% of students scored above the cut-off for mild anxiety and mild depression. Results from linear regression analyses showed that family satisfaction was positively associated with resilience, and both family satisfaction and resilience were and negatively associated with anxiety and depression. The mediating effects of resilience on the relationship between family satisfaction and anxiety/ depression (26.3% and 31.1% effects accounted for, respectively) were significant.

CONCLUSIONS

Both family satisfaction and resilience have important influence on adolescent mental health. Interventions that seek to promote positive family relationships and resilience of adolescents may be effective in preventing and reducing anxiety and depression symptoms among adolescents.

Implementation considerations for deep learning with diffusion MRI streamline tractography

One area of medical imaging that has recently experienced innovative deep learning advances is diffusion MRI (dMRI) streamline tractography with recurrent neural networks (RNNs). Unlike traditional imaging studies which utilize voxel-based learning, these studies model dMRI features at points in continuous space off the voxel grid in order to propagate streamlines, or virtual estimates of axons. However, implementing such models is non-trivial, and an open-source implementation is not yet widely available. Here, we describe a series of considerations for implementing tractography with RNNs and demonstrate they allow one to approximate a deterministic streamline propagator with comparable performance to existing algorithms. We release this trained model and the associated implementations leveraging popular deep learning libraries. We hope the availability of these resources will lower the barrier of entry into this field, spurring further innovation.

Convolutional-recurrent neural networks approximate diffusion tractography from T1-weighted MRI and associated anatomical context

Diffusion MRI (dMRI) streamline tractography is the gold-standard for in vivo estimation of white matter (WM) pathways in the brain. However, the high angular resolution dMRI acquisitions capable of fitting the microstructural models needed for tractography are often time-consuming and not routinely collected clinically, restricting the scope of tractography analyses. To address this limitation, we build on recent advances in deep learning which have demonstrated that streamline propagation can be learned from dMRI directly without traditional model fitting. Specifically, we propose learning the streamline propagator from T1w MRI to facilitate arbitrary tractography analyses when dMRI is unavailable. To do so, we present a novel convolutional-recurrent neural network (CoRNN) trained in a teacher-student framework that leverages T1w MRI, associated anatomical context, and streamline memory from data acquired for the Human Connectome Project. We characterize our approach under two common tractography paradigms, WM bundle analysis and structural connectomics, and find approximately a 5-15% difference between measures computed from streamlines generated with our approach and those generated using traditional dMRI tractography. When placed in the literature, these results suggest that the accuracy of WM measures computed from T1w MRI with our method is on the level of scan-rescan dMRI variability and raise an important question: is tractography truly a microstructural phenomenon, or has dMRI merely facilitated its discovery and implementation?

Topological-Preserving Membrane Skeleton Segmentation in Multiplex Immunofluorescence Imaging

Multiplex immunofluorescence (MxIF) is an emerging imaging technology whose downstream molecular analytics highly rely upon the effectiveness of cell segmentation. In practice, multiple membrane markers (e.g., NaKATPase, PanCK and β-catenin) are employed to stain membranes for different cell types, so as to achieve a more comprehensive cell segmentation since no single marker fits all cell types. However, prevalent watershed-based image processing might yield inferior capability for modeling complicated relationships between markers. For example, some markers can be misleading due to questionable stain quality. In this paper, we propose a deep learning based membrane segmentation method to aggregate complementary information that is uniquely provided by large scale MxIF markers. We aim to segment tubular membrane structure in MxIF data using global (membrane markers z-stack projection image) and local (separate individual markers) information to maximize topology preservation with deep learning. Specifically, we investigate the feasibility of four SOTA 2D deep networks and four volumetric-based loss functions. We conducted a comprehensive ablation study to assess the sensitivity of the proposed method with various combinations of input channels. Beyond using adjusted rand index (ARI) as the evaluation metric, which was inspired by the clDice, we propose a novel volumetric metric that is specific for skeletal structure, denoted as c l D i c e S K E L . In total, 80 membrane MxIF images were manually traced for 5-fold cross-validation. Our model outperforms the baseline with a 20.2% and 41.3% increase in c l D i c e S K E L and ARI performance, which is significant (p<0.05) using the Wilcoxon signed rank test. Our work explores a promising direction for advancing MxIF imaging cell segmentation with deep learning membrane segmentation. Tools are available at https://github.com/MASILab/MxIF_Membrane_Segmentation.

Longitudinal Variability Analysis on Low-dose Abdominal CT with Deep Learning-based Segmentation

Metabolic health is increasingly implicated as a risk factor across conditions from cardiology to neurology, and efficiency assessment of body composition is critical to quantitatively characterizing these relationships. 2D low dose single slice computed tomography (CT) provides a high resolution, quantitative tissue map, albeit with a limited field of view. Although numerous potential analyses have been proposed in quantifying image context, there has been no comprehensive study for low-dose single slice CT longitudinal variability with automated segmentation. We studied a total of 1816 slices from 1469 subjects of Baltimore Longitudinal Study on Aging (BLSA) abdominal dataset using supervised deep learning-based segmentation and unsupervised clustering method. 300 out of 1469 subjects that have two year gap in their first two scans were pick out to evaluate longitudinal variability with measurements including intraclass correlation coefficient (ICC) and coefficient of variation (CV) in terms of tissues/organs size and mean intensity. We showed that our segmentation methods are stable in longitudinal settings with Dice ranged from 0.821 to 0.962 for thirteen target abdominal tissues structures. We observed high variability in most organ with ICC<0.5, low variability in the area of muscle, abdominal wall, fat and body mask with average ICC≥0.8. We found that the variability in organ is highly related to the cross-sectional position of the 2D slice. Our efforts pave quantitative exploration and quality control to reduce uncertainties in longitudinal analysis.

Unsupervised Registration Refinement for Generating Unbiased Eye Atlas

With the confounding effects of demographics across large-scale imaging surveys, substantial variation is demonstrated with the volumetric structure of orbit and eye anthropometry. Such variability increases the level of difficulty to localize the anatomical features of the eye organs for populational analysis. To adapt the variability of eye organs with stable registration transfer, we propose an unbiased eye atlas template followed by a hierarchical coarse-to-fine approach to provide generalized eye organ context across populations. Furthermore, we retrieved volumetric scans from 1842 healthy patients for generating an eye atlas template with minimal biases. Briefly, we select 20 subject scans and use an iterative approach to generate an initial unbiased template. We then perform metric-based registration to the remaining samples with the unbiased template and generate coarse registered outputs. The coarse registered outputs are further leveraged to train a deep probabilistic network, which aims to refine the organ deformation in unsupervised setting. Computed tomography (CT) scans of 100 de-identified subjects are used to generate and evaluate the unbiased atlas template with the hierarchical pipeline. The refined registration shows the stable transfer of the eye organs, which were well-localized in the high-resolution (0.5 mm³) atlas space and demonstrated a significant improvement of 2.37% Dice for inverse label transfer performance. The subject-wise qualitative representations with surface rendering successfully demonstrate the transfer details of the organ context and showed the applicability of generalizing the morphological variation across patients.

Label efficient segmentation of single slice thigh CT with two-stage pseudo labels

Purpose: Muscle, bone, and fat segmentation from thigh images is essential for quantifying body composition. Voxelwise image segmentation enables quantification of tissue properties including area, intensity, and texture. Deep learning approaches have had substantial success in medical image segmentation, but they typically require a significant amount of data. Due to the high cost of manual annotation, training deep learning models with limited human label data is desirable, but it is a challenging problem. Approach: Inspired by transfer learning, we proposed a two-stage deep learning pipeline to address the thigh and lower leg segmentation issue. We studied three datasets, 3022 thigh slices and 8939 lower leg slices from the BLSA dataset and 121 thigh slices from the GESTALT study. First, we generated pseudo labels for thigh based on approximate handcrafted approaches using CT intensity and anatomical morphology. Then, those pseudo labels were fed into deep neural networks to train models from scratch. Finally, the first stage model was loaded as the initialization and fine-tuned with a more limited set of expert human labels of the thigh. Results: We evaluated the performance of this framework on 73 thigh CT images and obtained an average Dice similarity coefficient (DSC) of 0.927 across muscle, internal bone, cortical bone, subcutaneous fat, and intermuscular fat. To test the generalizability of the proposed framework, we applied the model on lower leg images and obtained an average DSC of 0.823. Conclusions: Approximated handcrafted pseudo labels can build a good initialization for deep neural networks, which can help to reduce the need for, and make full use of, human expert labeled data.

Workflow Integration of Research AI Tools into a Hospital Radiology Rapid Prototyping Environment

The field of artificial intelligence (AI) in medical imaging is undergoing explosive growth, and Radiology is a prime target for innovation. The American College of Radiology Data Science Institute has identified more than 240 specific use cases where AI could be used to improve clinical practice. In this context, thousands of potential methods are developed by research labs and industry innovators. Deploying AI tools within a clinical enterprise, even on limited retrospective evaluation, is complicated by security and privacy concerns. Thus, innovation must be weighed against the substantive resources required for local clinical evaluation. To reduce barriers to AI validation while maintaining rigorous security and privacy standards, we developed the AI Imaging Incubator. The AI Imaging Incubator serves as a DICOM storage destination within a clinical enterprise where images can be directed for novel research evaluation under Institutional Review Board approval. AI Imaging Incubator is controlled by a secure HIPAA-compliant front end and provides access to a menu of AI procedures captured within network-isolated containers. Results are served via a secure website that supports research and clinical data formats. Deployment of new AI approaches within this system is streamlined through a standardized application programming interface. This manuscript presents case studies of the AI Imaging Incubator applied to randomizing lung biopsies on chest CT, liver fat assessment on abdomen CT, and brain volumetry on head MRI.

Infection control measures for public transportation derived from the flow dynamics of obstructed cough jet

During the COVID-19 pandemic, WHO and CDC suggest people stay 1 m and 1.8 m away from others, respectively. Keeping social distance can avoid close contact and mitigate infection spread. Many researchers suspect that suggested distances are not enough because aerosols can spread up to 7-8 m away. Despite the debate on social distance, these social distances rely on unobstructed respiratory activities such as coughing and sneezing. Differently, in this work, we focused on the most common but less studied aerosol spread from an obstructed cough. The flow dynamics of a cough jet blocked by the backrest and gasper jet in a cabin environment was characterized by the particle image velocimetry (PIV) technique. It was proved that the backrest and the gasper jet can prevent the front passenger from droplet spray in public transportation where maintaining social distance was difficult. A model was developed to describe the cough jet trajectory due to the gasper jet, which matched well with PIV results. It was found that buoyancy and inside droplets almost do not affect the short-range cough jet trajectory. Infection control measures were suggested for public transportation, including using backrest/gasper jet, installing localized exhaust, and surface cleaning of the backrest.

Learning white matter subject-specific segmentation from structural MRI

PURPOSE

Mapping brain white matter (WM) is essential for building an understanding of brain anatomy and function. Tractography-based methods derived from diffusion-weighted MRI (dMRI) are the principal tools for investigating WM. These procedures rely on time-consuming dMRI acquisitions that may not always be available, especially for legacy or time-constrained studies. To address this problem, we aim to generate WM tracts from structural magnetic resonance imaging (MRI) image by deep learning.

METHODS

Following recently proposed innovations in structural anatomical segmentation, we evaluate the feasibility of training multiply spatial localized convolution neural networks to learn context from fixed spatial patches from structural MRI on standard template. We focus on six widely used dMRI tractography algorithms (TractSeg, RecoBundles, XTRACT, Tracula, automated fiber quantification (AFQ), and AFQclipped) and train 125 U-Net models to learn these techniques from 3870 T1-weighted images from the Baltimore Longitudinal Study of Aging, the Human Connectome Project S1200 release, and scans acquired at Vanderbilt University.

RESULTS

The proposed framework identifies fiber bundles with high agreement against tractography-based pathways with a median Dice coefficient from 0.62 to 0.87 on a test cohort, achieving improved subject-specific accuracy when compared to population atlas-based methods. We demonstrate the generalizability of the proposed framework on three externally available datasets.

CONCLUSIONS

We show that patch-wise convolutional neural network can achieve robust bundle segmentation from T1w. We envision the use of this framework for visualizing the expected course of WM pathways when dMRI is not available.

Supervised Deep Generation of High-Resolution Arterial Phase Computed Tomography Kidney Substructure Atlas

The Human BioMolecular Atlas Program (HuBMAP) provides an opportunity to contextualize findings across cellular to organ systems levels. Constructing an atlas target is the primary endpoint for generalizing anatomical information across scales and populations. An initial target of HuBMAP is the kidney organ and arterial phase contrast-enhanced computed tomography (CT) provides distinctive appearance and anatomical context on the internal substructure of kidney organs such as renal context, medulla, and pelvicalyceal system. With the confounding effects of demographics and morphological characteristics of the kidney across large-scale imaging surveys, substantial variation is demonstrated with the internal substructure morphometry and the intensity contrast due to the variance of imaging protocols. Such variability increases the level of difficulty to localize the anatomical features of the kidney substructure in a well-defined spatial reference for clinical analysis. In order to stabilize the localization of kidney substructures in the context of this variability, we propose a high-resolution CT kidney substructure atlas template. Briefly, we introduce a deep learning preprocessing technique to extract the volumetric interest of the abdominal regions and further perform a deep supervised registration pipeline to stably adapt the anatomical context of the kidney internal substructure. To generate and evaluate the atlas template, arterial phase CT scans of 500 control subjects are de-identified and registered to the atlas template with a complete end-to-end pipeline. With stable registration to the abdominal wall and kidney organs, the internal substructure of both left and right kidneys are substantially localized in the high-resolution atlas space. The atlas average template successfully demonstrated the contextual details of the internal structure and was applicable to generalize the morphological variation of internal substructure across patients.

Accelerating 2D Abdominal Organ Segmentation with Active Learning

Abdominal computed tomography CT imaging enables assessment of body habitus and organ health. Quantification of these health factors necessitates semantic segmentation of key structures. Deep learning efforts have shown remarkable success in automating segmentation of abdominal CT, but these methods largely rely on 3D volumes. Current approaches are not applicable when single slice imaging is used to minimize radiation dose. For 2D abdominal organ segmentation, lack of 3D context and variety in acquired image levels are major challenges. Deep learning approaches for 2D abdominal organ segmentation benefit by adding more images with manual annotation, but annotation is resource intensive to acquire given the large quantity and the requirement of expertise. Herein, we designed a gradient based active learning annotation framework by meta-parameterizing and optimizing the exemplars to dynamically select the 'hard cases' to achieve better results with fewer annotated slices to reduce the annotation effort. With the Baltimore Longitudinal Study on Aging (BLSA) cohort, we evaluated the performance with starting from 286 subjects and added 50 more subjects iteratively to 586 subjects in total. We compared the amount of data required to add to achieve the same Dice score between using our proposed method and the random selection in terms of Dice. When achieving 0.97 of the maximum Dice, the random selection needed 4.4 times more data compared with our active learning framework. The proposed framework maximizes the efficacy of manual efforts and accelerates learning.

Quantification of muscle, bones, and fat on single slice thigh CT

Muscle, bone, and fat segmentation of CT thigh slice is essential for body composition research. Voxel-wise image segmentation enables quantification of tissue properties including area, intensity and texture. Deep learning approaches have had substantial success in medical image segmentation, but they typically require substantial data. Due to high cost of manual annotation, training deep learning models with limited human labelled data is desirable but also a challenging problem. Inspired by transfer learning, we proposed a two-stage deep learning pipeline to address this issue in thigh segmentation. We study 2836 slices from Baltimore Longitudinal Study of Aging (BLSA) and 121 slices from Genetic and Epigenetic Signatures of Translational Aging Laboratory Testing (GESTALT). First, we generated pseudo-labels based on approximate hand-crafted approaches using CT intensity and anatomical morphology. Then, those pseudo labels are fed into deep neural networks to train models from scratch. Finally, the first stage model is loaded as initialization and fine-tuned with a more limited set of expert human labels. We evaluate the performance of this framework on 56 thigh CT scans and obtained average Dice of 0.979,0.969,0.953,0.980 and 0.800 for five tissues: muscle, cortical bone, internal bone, subcutaneous fat and intermuscular fat respectively. We evaluated generalizability by manually reviewing external 3504 BLSA single thighs from 1752 thigh slices. The result is consistent and passed human review with 150 failed thigh images, which demonstrates that the proposed method has strong generalizability.

Inpainting Missing Tissue in Multiplexed Immunofluorescence Imaging

Multiplex immunofluorescence (MxIF) is an emerging technique that allows for staining multiple cellular and histological markers to stain simultaneously on a single tissue section. However, with multiple rounds of staining and bleaching, it is inevitable that the scarce tissue may be physically depleted. Thus, a digital way of synthesizing such missing tissue would be appealing since it would increase the useable areas for the downstream single-cell analysis. In this work, we investigate the feasibility of employing generative adversarial network (GAN) approaches to synthesize missing tissues using 11 MxIF structural molecular markers (i.e., epithelial and stromal). Briefly, we integrate a multi-channel high-resolution image synthesis approach to synthesize the missing tissue from the remaining markers. The performance of different methods is quantitatively evaluated via the downstream cell membrane segmentation task. Our contribution is that we, for the first time, assess the feasibility of synthesizing missing tissues in MxIF via quantitative segmentation. The proposed synthesis method has comparable reproducibility with the baseline method on performance for the missing tissue region reconstruction only, but it improves 40% on whole tissue synthesis that is crucial for practical application. We conclude that GANs are a promising direction of advancing MxIF imaging with deep image synthesis.

A cross-platform informatics system for the Gut Cell Atlas: integrating clinical, anatomical and histological data

The Gut Cell Atlas (GCA), an initiative funded by the Helmsley Charitable Trust, seeks to create a reference platform to understand the human gut, with a specific focus on Crohn's disease. Although a primary focus of the GCA is on focusing on single-cell profiling, we seek to provide a framework to integrate other analyses on multi-modality data such as electronic health record data, radiological images, and histology tissues/images. Herein, we use the research electronic data capture (REDCap) system as the central tool for a secure web application that supports protected health information (PHI) restricted access. Our innovations focus on addressing the challenges with tracking all specimens and biopsies, validating manual data entry at scale, and sharing organizational data across the group. We present a scalable, cross-platform barcode printing/record system that integrates with REDCap. The central informatics infrastructure to support our design is a tuple table to track longitudinal data entry and sample tracking. The current data collection (by December 2020) is illustrated with types and formats of the data that the system collects. We estimate that one terabyte is needed for data storage per patient study. Our proposed data sharing informatics system addresses the challenges with integrating physical sample tracking, large files, and manual data entry with REDCap.

Random Multi-Channel Image Synthesis for Multiplexed Immunofluorescence Imaging

Multiplex immunofluorescence (MxIF) is an emerging imaging technique that produces the high sensitivity and specificity of single-cell mapping. With a tenet of "seeing is believing", MxIF enables iterative staining and imaging extensive antibodies, which provides comprehensive biomarkers to segment and group different cells on a single tissue section. However, considerable depletion of the scarce tissue is inevitable from extensive rounds of staining and bleaching ("missing tissue"). Moreover, the immunofluorescence (IF) imaging can globally fail for particular rounds ("missing stain"). In this work, we focus on the "missing stain" issue. It would be appealing to develop digital image synthesis approaches to restore missing stain images without losing more tissue physically. Herein, we aim to develop image synthesis approaches for eleven MxIF structural molecular markers (i.e., epithelial and stromal) on real samples. We propose a novel multi-channel high-resolution image synthesis approach, called pixN2N-HD, to tackle possible missing stain scenarios via a high-resolution generative adversarial network (GAN). Our contribution is three-fold: (1) a single deep network framework is proposed to tackle missing stain in MxIF; (2) the proposed "N-to-N" strategy reduces theoretical four years of computational time to 20 hours when covering all possible missing stains scenarios, with up to five missing stains (e.g., "(N-1)-to-1", "(N-2)-to-2"); and (3) this work is the first comprehensive experimental study of investigating cross-stain synthesis in MxIF. Our results elucidate a promising direction of advancing MxIF imaging with deep image synthesis.

RAP-NET: COARSE-TO-FINE MULTI-ORGAN SEGMENTATION WITH SINGLE RANDOM ANATOMICAL PRIOR

Performing coarse-to-fine abdominal multi-organ segmentation facilitates extraction of high-resolution segmentation minimizing the loss of spatial contextual information. However, current coarse-to-refine approaches require a significant number of models to perform single organ segmentation. We propose a coarse-to-fine pipeline RAP-Net, which starts from the extraction of the global prior context of multiple organs from 3D volumes using a low-resolution coarse network, followed by a fine phase that uses a single refined model to segment all abdominal organs instead of multiple organ corresponding models. We combine the anatomical prior with corresponding extracted patches to preserve the anatomical locations and boundary information for performing high-resolution segmentation across all organs in a single model. To train and evaluate our method, a clinical research cohort consisting of 100 patient volumes with 13 organs well-annotated is used. We tested our algorithms with 4-fold cross-validation and computed the Dice score for evaluating the segmentation performance of the 13 organs. Our proposed method using single auto-context outperforms the state-of-the-art on 13 models with an average Dice score 84.58% versus 81.69% (p<0.0001).

Renal Cortex, Medulla and Pelvicaliceal System Segmentation on Arterial Phase CT Images with Random Patch-based Networks

Renal segmentation on contrast-enhanced computed tomography (CT) provides distinct spatial context and morphology. Current studies for renal segmentations are highly dependent on manual efforts, which are time-consuming and tedious. Hence, developing an automatic framework for the segmentation of renal cortex, medulla and pelvicalyceal system is an important quantitative assessment of renal morphometry. Recent innovations in deep methods have driven performance toward levels for which clinical translation is appealing. However, the segmentation of renal structures can be challenging due to the limited field-of-view (FOV) and variability among patients. In this paper, we propose a method to automatically label the renal cortex, the medulla and pelvicalyceal system. First, we retrieved 45 clinically-acquired deidentified arterial phase CT scans (45 patients, 90 kidneys) without diagnosis codes (ICD-9) involving kidney abnormalities. Second, an interpreter performed manual segmentation to pelvis, medulla and cortex slice-by-slice on all retrieved subjects under expert supervision. Finally, we proposed a patch-based deep neural networks to automatically segment renal structures. Compared to the automatic baseline algorithm (3D U-Net) and conventional hierarchical method (3D U-Net Hierarchy), our proposed method achieves improvement of 0.7968 to 0.6749 (3D U-Net), 0.7482 (3D U-Net Hierarchy) in terms of mean Dice scores across three classes (p-value < 0.001, paired t-tests between our method and 3D U-Net Hierarchy). In summary, the proposed algorithm provides a precise and efficient method for labeling renal structures.

Construction of a Multi-Phase Contrast Computed Tomography Kidney Atlas

The Human BioMolecular Atlas Program (HuBMAP) seeks to create a molecular atlas at the cellular level of the human body to spur interdisciplinary innovations across spatial and temporal scales. While the preponderance of effort is allocated towards cellular and molecular scale mapping, differentiating and contextualizing findings within tissues, organs and systems are essential for the HuBMAP efforts. The kidney is an initial organ target of HuBMAP, and constructing a framework (or atlas) for integrating information across scales is needed for visualizing and integrating information. However, there is no abdominal atlas currently available in the public domain. Substantial variation in healthy kidneys exists with sex, body size, and imaging protocols. With the integration of clinical archives for secondary research use, we are able to build atlases based on a diverse population and clinically relevant protocols. In this study, we created a computed tomography (CT) phase-specific atlas for the abdomen, which is optimized for the kidney organ. A two-stage registration pipeline was used by registering extracted abdominal volume of interest from body part regression, to a high-resolution CT. Affine and non-rigid registration were performed to all scans hierarchically. To generate and evaluate the atlas, multiphase CT scans of 500 control subjects (age: 15 - 50, 250 males, 250 females) are registered to the atlas target through the complete pipeline. The abdominal body and kidney registration are shown to be stable with the variance map computed from the result average template. Both left and right kidneys are substantially localized in the high-resolution target space, which successfully demonstrated the sharp details of its anatomical characteristics across each phase. We illustrated the applicability of the atlas template for integrating across normal kidney variation from 64 cm³ to 302 cm³.

Phase identification for dynamic CT enhancements with generative adversarial network

PURPOSE

Dynamic contrast-enhanced computed tomography (CT) is widely used to provide dynamic tissue contrast for diagnostic investigation and vascular identification. However, the phase information of contrast injection is typically recorded manually by technicians, which introduces missing or mislabeling. Hence, imaging-based contrast phase identification is appealing, but challenging, due to large variations among different contrast protocols, vascular dynamics, and metabolism, especially for clinically acquired CT scans. The purpose of this study is to perform imaging-based phase identification for dynamic abdominal CT using a proposed adversarial learning framework across five representative contrast phases.

METHODS

A generative adversarial network (GAN) is proposed as a disentangled representation learning model. To explicitly model different contrast phases, a low dimensional common representation and a class specific code are fused in the hidden layer. Then, the low dimensional features are reconstructed following a discriminator and classifier. 36 350 slices of CT scans from 400 subjects are used to evaluate the proposed method with fivefold cross-validation with splits on subjects. Then, 2216 slices images from 20 independent subjects are employed as independent testing data, which are evaluated using multiclass normalized confusion matrix.

RESULTS

The proposed network significantly improved correspondence (0.93) over VGG, ResNet50, StarGAN, and 3DSE with accuracy scores 0.59, 0.62, 0.72, and 0.90, respectively (P < 0.001 Stuart-Maxwell test for normalized multiclass confusion matrix).

CONCLUSION

We show that adversarial learning for discriminator can be benefit for capturing contrast information among phases. The proposed discriminator from the disentangled network achieves promising results.

High-resolution 3D abdominal segmentation with random patch network fusion

Deep learning for three dimensional (3D) abdominal organ segmentation on high-resolution computed tomography (CT) is a challenging topic, in part due to the limited memory provide by graphics processing units (GPU) and large number of parameters and in 3D fully convolutional networks (FCN). Two prevalent strategies, lower resolution with wider field of view and higher resolution with limited field of view, have been explored but have been presented with varying degrees of success. In this paper, we propose a novel patch-based network with random spatial initialization and statistical fusion on overlapping regions of interest (ROIs). We evaluate the proposed approach using three datasets consisting of 260 subjects with varying numbers of manual labels. Compared with the canonical "coarse-to-fine" baseline methods, the proposed method increases the performance on multi-organ segmentation from 0.799 to 0.856 in terms of mean DSC score (p-value < 0.01 with paired t-test). The effect of different numbers of patches is evaluated by increasing the depth of coverage (expected number of patches evaluated per voxel). In addition, our method outperforms other state-of-the-art methods in abdominal organ segmentation. In conclusion, the approach provides a memory-conservative framework to enable 3D segmentation on high-resolution CT. The approach is compatible with many base network structures, without substantially increasing the complexity during inference. Given a CT scan with at high resolution, a low-res section (left panel) is trained with multi-channel segmentation. The low-res part contains down-sampling and normalization in order to preserve the complete spatial information. Interpolation and random patch sampling (mid panel) is employed to collect patches. The high-dimensional probability maps are acquired (right panel) from integration of all patches on field of views.

Prediction of Type II Diabetes Onset with Computed Tomography and Electronic Medical Records

Type II diabetes mellitus (T2DM) is a significant public health concern with multiple known risk factors (e.g., body mass index (BMI), body fat distribution, glucose levels). Improved prediction or prognosis would enable earlier intervention before possibly irreversible damage has occurred. Meanwhile, abdominal computed tomography (CT) is a relatively common imaging technique. Herein, we explore secondary use of the CT imaging data to refine the risk profile of future diagnosis of T2DM. In this work, we delineate quantitative information and imaging slices of patient history to predict onset T2DM retrieved from ICD-9 codes at least one year in the future. Furthermore, we investigate the role of five different types of electronic medical records (EMR), specifically 1) demographics; 2) pancreas volume; 3) visceral/subcutaneous fat volumes in L2 region of interest; 4) abdominal body fat distribution and 5) glucose lab tests in prediction. Next, we build a deep neural network to predict onset T2DM with pancreas imaging slices. Finally, motivated by multi-modal machine learning, we construct a merged framework to combine CT imaging slices with EMR information to refine the prediction. We empirically demonstrate our proposed joint analysis involving images and EMR leads to 4.25% and 6.93% AUC increase in predicting T2DM compared with only using images or EMR. In this study, we used case-control dataset of 997 subjects with CT scans and contextual EMR scores. To the best of our knowledge, this is the first work to show the ability to prognose T2DM using the patients' contextual and imaging history. We believe this study has promising potential for heterogeneous data analysis and multi-modal medical applications.

Validation and Optimization of Multi-Organ Segmentation on Clinical Imaging Archives

Segmentation of abdominal computed tomography (CT) provides spatial context, morphological properties, and a framework for tissue-specific radiomics to guide quantitative Radiological assessment. A 2015 MICCAI challenge spurred substantial innovation in multi-organ abdominal CT segmentation with both traditional and deep learning methods. Recent innovations in deep methods have driven performance toward levels for which clinical translation is appealing. However, continued cross-validation on open datasets presents the risk of indirect knowledge contamination and could result in circular reasoning. Moreover, "real world" segmentations can be challenging due to the wide variability of abdomen physiology within patients. Herein, we perform two data retrievals to capture clinically acquired deidentified abdominal CT cohorts with respect to a recently published variation on 3D U-Net (baseline algorithm). First, we retrieved 2004 deidentified studies on 476 patients with diagnosis codes involving spleen abnormalities (cohort A). Second, we retrieved 4313 deidentified studies on 1754 patients without diagnosis codes involving spleen abnormalities (cohort B). We perform prospective evaluation of the existing algorithm on both cohorts, yielding 13% and 8% failure rate, respectively. Then, we identified 51 subjects in cohort A with segmentation failures and manually corrected the liver and gallbladder labels. We re-trained the model adding the manual labels, resulting in performance improvement of 9% and 6% failure rate for the A and B cohorts, respectively. In summary, the performance of the baseline on the prospective cohorts was similar to that on previously published datasets. Moreover, adding data from the first cohort substantively improved performance when evaluated on the second withheld validation cohort.

Patterns in Pediatric Dental Surgery under General Anesthesia across 7 State Medicaid Programs

OBJECTIVES

Children's access to dental general anesthesia (DGA) is limited, with highly variable wait times. Access factors occur at the levels of facility, dental provider, and anesthesia provider. It is unknown if these factors also influence utilization of dental surgery. We characterized patterns in DGA utilization by system, provider, population, and individual disease levels to explain variation.

METHODS

We conducted a cross-sectional analysis of Medicaid-enrolled children (≤9 y) who received DGA in Massachusetts, Maryland, Texas, Connecticut, Washington, Illinois, and Florida from 2011 to 2012. DGA events were characterized by the place of service, measures of disease burden, average reimbursements for dental provider and anesthesia provider, and average total expenditures.

RESULTS

A total of 10,149,793 children met study eligibility criteria. States with similar patterns of caries-related visits, such as Illinois (16% of Medicaid enrollees had a caries-related claim) and Washington (22%), had different DGA rates (1% and 17%, respectively). Reimbursement rates for dental providers, DGA services, and nonhospital places of services did not consistently align in states with higher DGA rates. Surgical extraction rates, as a proxy for the most severe disease, exceeded 75% in Maryland, which had the lowest DGA rate (0.3%).

CONCLUSIONS

Variation in DGA rates across states was not explained by reimbursements rates (provider, DGA services, place of service) or population or individual level of caries burden. Efforts to evaluate and alter utilization of DGA should consider factors such as dental and anesthesia provider capacity, health facility capacity (hospital vs. ambulatory surgery center vs. office), and population- and individual-level disease burden. Our negative findings suggest the presence of other social determinants of oral health that influence utilization of services (e.g., race/ethnicity, language preference, immigration status, policy and budget goals), which should be explored. Our findings also raise the specter that variation in surgical rates may represent instances of unmet needs or overtreatment.

KNOWLEDGE TRANSFER STATEMENT

The results of this study can be used by clinicians and policy makers as they address policy and clinical interventions to influence children with severe caries. Interventions to change utilization of surgical services on a population level may need to include state-specific factors that extend beyond reimbursement, disease burden, anesthesia provider type, or facility type.

Contrast Phase Classification with a Generative Adversarial Network

Dynamic contrast enhanced computed tomography (CT) is an imaging technique that provides critical information on the relationship of vascular structure and dynamics in the context of underlying anatomy. A key challenge for image processing with contrast enhanced CT is that phase discrepancies are latent in different tissues due to contrast protocols, vascular dynamics, and metabolism variance. Previous studies with deep learning frameworks have been proposed for classifying contrast enhancement with networks inspired by computer vision. Here, we revisit the challenge in the context of whole abdomen contrast enhanced CTs. To capture and compensate for the complex contrast changes, we propose a novel discriminator in the form of a multi-domain disentangled representation learning network. The goal of this network is to learn an intermediate representation that separates contrast enhancement from anatomy and enables classification of images with varying contrast time. Briefly, our unpaired contrast disentangling GAN(CD-GAN) Discriminator follows the ResNet architecture to classify a CT scan from different enhancement phases. To evaluate the approach, we trained the enhancement phase classifier on 21060 slices from two clinical cohorts of 230 subjects. The scans were manually labeled with three independent enhancement phases (non-contrast, portal venous and delayed). Testing was performed on 9100 slices from 30 independent subjects who had been imaged with CT scans from all contrast phases. Performance was quantified in terms of the multi-class normalized confusion matrix. The proposed network significantly improved correspondence over baseline UNet, ResNet50 and StarGAN's performance of accuracy scores 0.54. 0.55, 0.62 and 0.91, respectively (p-value<0.0001 paired t-test for ResNet versus CD-GAN). The proposed discriminator from the disentangled network presents a promising technique that may allow deeper modeling of dynamic imaging against patient specific anatomies.

Development and control of a hybrid active mount module for precision stages

In recent years, precision stages, which are widely used in many industrial fields, have been required to have a higher speed, larger size, and higher precision to help realize higher productivity and product quality. High-performance positioning techniques for inspection and production equipment are classified as one of the most challenging technologies. Vibration control is crucial to realize high-precision positioning technologies. In a precision system, various vibrations exist, which act as disturbances and can degrade the system performance. Minimizing the vibrations generated by the system can, thus, help improve the accuracy of system positioning. This paper proposes a hybrid active mount module for a precision stage. The developed module improves stage performance by reducing the base vibration arising from the floor, minimizing the vibration caused by the driving linear motors of the precision stage, and reducing the settling time by compensating the offset displacement due to the nonlinearity of the passive mount during stage driving. The prototype design is presented herein, and the experimental results demonstrate the potential of the developed device. The developed system is expected to effectively improve the stage performance by controlling the various causes of vibration.

Semi-Supervised Multi-Organ Segmentation through Quality Assurance Supervision

Human in-the-loop quality assurance (QA) is typically performed after medical image segmentation to ensure that the systems are performing as intended, as well as identifying and excluding outliers. By performing QA on large-scale, previously unlabeled testing data, categorical QA scores (e.g. "successful" versus "unsuccessful") can be generated. Unfortunately, the precious use of resources for human in-the-loop QA scores are not typically reused in medical image machine learning, especially to train a deep neural network for image segmentation. Herein, we perform a pilot study to investigate if the QA labels can be used as supplementary supervision to augment the training process in a semi-supervised fashion. In this paper, we propose a semi-supervised multi-organ segmentation deep neural network consisting of a traditional segmentation model generator and a QA involved discriminator. An existing 3-D abdominal segmentation network is employed, while the pre-trained ResNet-18 network is used as discriminator. A large-scale dataset of 2027 volumes are used to train the generator, whose 2-D montage images and segmentation mask with QA scores are used to train the discriminator. To generate the QA scores, the 2-D montage images were reviewed manually and coded 0 (success), 1 (errors consistent with published performance), and 2 (gross failure). Then, the ResNet-18 network was trained with 1623 montage images in equal distribution of all three code labels and achieved an accuracy 94% for classification predictions with 404 montage images withheld for the test cohort. To assess the performance of using the QA supervision, the discriminator was used as a loss function in a multi-organ segmentation pipeline. The inclusion of QA-loss function boosted performance on the unlabeled test dataset from 714 patients to 951 patients over the baseline model. Additionally, the number of failures decreased from 606 (29.90%) to 402 (19.83%). The contributions of the proposed method are three-fold: We show that (1) the QA scores can be used as a loss function to perform semi-supervised learning for unlabeled data, (2) the well trained discriminator is learnt by QA score rather than traditional "true/false", and (3) the performance of multi-organ segmentation on unlabeled datasets can be fine-tuned with more robust and higher accuracy than the original baseline method. The use of QA-inspired loss functions represents a promising area of future research and may permit tighter integration of supervised and semi-supervised learning.

Outlier Guided Optimization of Abdominal Segmentation

Abdominal multi-organ segmentation of computed tomography (CT) images has been the subject of extensive research interest. It presents a substantial challenge in medical image processing, as the shape and distribution of abdominal organs can vary greatly among the population and within an individual over time. While continuous integration of novel datasets into the training set provides potential for better segmentation performance, collection of data at scale is not only costly, but also impractical in some contexts. Moreover, it remains unclear what marginal value additional data have to offer. Herein, we propose a single-pass active learning method through human quality assurance (QA). We built on a pre-trained 3D U-Net model for abdominal multi-organ segmentation and augmented the dataset either with outlier data (e.g., exemplars for which the baseline algorithm failed) or inliers (e.g., exemplars for which the baseline algorithm worked). The new models were trained using the augmented datasets with 5-fold cross-validation (for outlier data) and withheld outlier samples (for inlier data). Manual labeling of outliers increased Dice scores with outliers by 0.130, compared to an increase of 0.067 with inliers (p<0.001, two-tailed paired t-test). By adding 5 to 37 inliers or outliers to training, we find that the marginal value of adding outliers is higher than that of adding inliers. In summary, improvement on single-organ performance was obtained without diminishing multi-organ performance or significantly increasing training time. Hence, identification and correction of baseline failure cases present an effective and efficient method of selecting training data to improve algorithm performance.

The mental health burden in acne vulgaris and rosacea: an analysis of the US National Inpatient Sample

BACKGROUND

Little is known about the mental health (MH) hospitalization among patients with acne and rosacea.

AIMS

To determine the MH disorders and cost burden associated with acne and rosacea.

METHODS

Data were examined from the 2002-2012 US National Inpatient Sample, comprising a sample of ~20% of all US paediatric and adult hospitalizations (n = 87 053 155 admissions).

RESULTS

A diagnosis of ≥ 1 MH disorder was much more common among all inpatients with vs. those without a diagnosis of acne (43.7% vs. 20.0%, respectively) and rosacea (35.1% vs. 20.0%, respectively). In multivariable logistic regression models controlling for sex, age, race/ethnicity and insurance status, acne (adjusted OR = 13.02; 95% CI 11.75-14.42) and rosacea (adjusted OR = 1.70; 95% CI 1.56-1.95) were associated with significantly higher odds of a primary admission for an MH disorder (13 and 8, respectively, of 15 MH disorders examined). Both acne and rosacea were associated with higher risk of mood, anxiety, impulse control and personality disorders, and with > $2 million of excess mean annual costs of hospitalization for MH disorders in the USA.

CONCLUSION

In this study, inpatients with acne or rosacea had increased odds of comorbid MH disorders. In particular, there was an increased number of hospital admissions secondary to a primary MH disorder with coexistent acne/rosacea. MH comorbidities were associated with considerable excess costs among inpatients with acne or rosacea.

Changes in Bone Mineral Density After Kidney Transplantation

BACKGROUND

Numerous studies have shown that osteoporosis is common in kidney transplant recipients. However, the change in bone mineral density after kidney transplantation (KT) is not fully understood.

METHODS

Thirty-nine kidney transplant recipients with bone densitometry at pretransplant and 24 months after KT were reviewed.

RESULTS

The recipients' median age (44.5 ± 10.7 years) and dialysis duration before KT (4.2 ± 3.4 years) were recorded. The T-scores of the lumbar spine and femur neck at 24 months after KT were positively associated with the respective pretransplant T-score (P < .001 in the lumbar spine and P < .001 in the femur neck). However, the T-score after KT did not show significant change (P = .680 in lumbar spine, P = .093 in femur neck). Changes in the T-scores of the lumbar spine and femur neck over 24 months (delta T-score) were negatively associated with the respective pretransplant T-scores (P = .001 in lumbar spine, P = .026 in femur neck). Changes in the T-scores of the lumbar spine and femur neck over 24 months (delta T-score) were also associated with the pretransplant T-scores after the adjustment of other variables.

CONCLUSION

The change of bone mineral density was related with pretransplant bone mineral density. Careful follow-up of bone densitometry for KT recipients was needed.

Impact of Cigarette Smoking on Living Kidney Donors

BACKGROUND

Smoking is known to result in a decline in renal allograft function and survival of recipients; however, the effect of smoking on living kidney donors remains unknown. In this study we evaluated the impact of cigarette smoking on renal function of kidney donors.

METHODS

Among 1056 donors who underwent nephrectomy, 612 completed the 6-month follow-up protocol and were enrolled in the study. The association of smoking status, including pack-years smoking history, and postoperative renal function was evaluated.

RESULTS

Among donors, 68.1% had never smoked, 8% were former smokers, and 23.9% were current smokers. Donors who never smoked were older than former and current smokers (42.3 ± 11.8, 41.9 ± 11.1, and 38.3 ± 10.9 years, respectively; P < .001). There was no difference in preoperative renal function between groups; however, postoperative estimated glomerular filtration rate (eGFR) was lower in former and current smokers than in those who never smoked (64.6 ± 13.8, 64.7 ± 12.3, and 67.8 ± 13.1 mL/min/1.73 m², respectively; P = .023). In former and current smokers, pack-years smoking history was negatively associated with pre- and postoperative eGFR (r = -0.305 and -0.435, P < .001), and correlated with postoperative percent eGFR decline (r = 0.248, P < .001). Smoking history was associated with postoperative development of chronic kidney disease (CKD). Especially in former smokers, a smoking history of more than 12 pack-years was strongly associated with development of CKD (odds ratio = 7.5, P = .003).

CONCLUSION

Even if they no longer smoke, donors with a smoking history require close observation due to increased risk of CKD development after kidney donation. A detailed pack-years smoking history should be obtained, and smoking cessation strategies should be implemented in kidney donors.

Incidence of psoriasiform diseases secondary to tumour necrosis factor antagonists in patients with inflammatory bowel disease: a nationwide population-based cohort study

BACKGROUND

There are increasing reports of paradoxical psoriasiform diseases secondary to anti-tumour necrosis factor (TNF) agents.

AIMS

To determine the risks of paradoxical psoriasiform diseases secondary to anti-TNF agents in patients with inflammatory bowel disease (IBD).

METHODS

A nationwide population study was performed using the Korea National Health Insurance Claim Data. A total of 50 502 patients with IBD were identified between 2007 and 2016. We compared 5428 patients who were treated with any anti-TNF agent for more than 6 months (anti-TNF group) and 10 856 matched controls who had never taken anti-TNF agents (control group).

RESULTS

Incidence of psoriasis was significantly higher in the anti-TNF group (36.8 per 10 000 person-years) compared to the control group (14.5 per 10 000 person-years) (hazard ratio [HR] 2.357, 95% confidence interval [CI] 1.668-3.331). Palmoplantar pustulosis (HR 9.355, 95% CI 2.754-31.780) and psoriatic arthritis (HR 2.926, 95% CI 1.640-5.218) also showed higher risks in the anti-TNF group. In subgroup analyses, HRs for psoriasis by IBD subtype were 2.549 (95% CI 1.658-3.920) in Crohn's disease and 2.105 (95% CI 1.155-3.836) in ulcerative colitis. Interestingly, men and younger (10-39 years) patients have significantly higher risks of palmoplantar pustulosis (HR 19.682 [95% CI 3.867-100.169] and HR 14.318 [95% CI 2.915-70.315], respectively), whereas women and older (≥40 years) patients showed similar rates between the two groups.

CONCLUSIONS

The risks of psoriasiform diseases are increased by anti-TNF agents in patients with IBD. Among psoriasiform diseases, the risk of palmoplantar pustulosis shows the biggest increase particularly in male and younger patients.

Long-term Follow-up of Living Kidney Donors With Chronic Kidney Disease at 1 Year After Nephrectomy

BACKGROUND

Although renal function recovery of living kidney donors has been reported in a number of studies, many patients show poor recovery, and the long-term prognosis of these patients has not been well studied. In this investigation we explored the long-term prognosis of renal function in patients with chronic kidney disease (CKD) at 1 year after nephrectomy.

METHODS

Patients who underwent donor nephrectomy during the period from March 2006 to April 2014, with a follow-up creatinine study at 1 year postoperatively and more than 3 years of follow-up, were included in the study. Creatinine and estimated glomerular filtration rate (eGFR, using the Modification of Diet in Renal Disease formula) before and after surgery were studied. Age, sex, history of hypertension or diabetes, body mass index, blood pressure, complete blood count, preoperative routine serum chemistry, and urine study results were reviewed.

RESULTS

Among 841 patients who had donor nephrectomy, 362 were included in the study. There were 111 patients (30.6%) with eGFR <60 mL/min/1.73 m² at 1 year postsurgery, and the median follow-up period was 62.8 months (interquartile range [IQR] 42.0-86.3 months). The maximum eGFR after 3-year follow-up was studied, and 48 patients (43.2%) never recovered eGFR to >60 mL/min/1.73 m². Age, history of hypertension, preoperative eGFR, and eGFR at 1 year were predictive factors at univariate analysis. Multivariate analysis of these factors was studied, and age (52.5 [IQR 47-55.7] vs 47 [IQR 7-53] years, odds ratio [OR] 1.1, 95% confidence interval [CI] 1.02-1.15, P = .007), history of hypertension (16.7% vs 1.6%, OR 10.0, 95% CI 1.09-92.49, P = .042), and eGFR at 1 year (53.9 [IQR 50.3-56.0] vs 57.0 [IQR 54.2-58.4] mL/min/1.73 m², OR 0.8, 95% CI 0.72-0.92, P = .002) remained as significant risk factors.

CONCLUSION

Of all living donors, 15.7% had CKD after >3 years of follow-up. Close observation is warranted when donors have CKD after 1 year follow-up, as 43.2% fail to recover renal function. Patients who are older, have a history of hypertension, and have low eGFR at 1-year follow-up are especially at risk.

Delayed Recovery of Renal Function After Donor Nephrectomy

BACKGROUND

Many living kidney donors are still at risk of chronic kidney disease (CKD) 1 year after nephrectomy. Although some donors still experience poor renal function, many exhibit delayed recovery of renal function afterwards. We studied the factors related to delayed recovery of renal function in patients with CKD at 1 year after nephrectomy.

METHODS

Patients who underwent donor nephrectomy from March 2006 to April 2014 with a follow-up creatinine study at 1 month, 6 months, 1 year, and after 3 years of follow-up were included in the study. Age, sex, history of hypertension or diabetes, body mass index, blood pressure, complete blood cell count, preoperative routine serum chemistry, and urine study results were reviewed.

RESULTS

Among 275 donors, 83 (30.2%) who had an estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m² at 1 year of follow-up were included in the study, and the eGFR was observed during a median follow-up of 62.0 months (interquartile range [IQR], 48.9-83.1 months). Those who had improvements in eGFR of >5 mL/min/1.73 m² were included in the recovery group (n = 48 [57.8%]), and those who did not were included in the nonrecovery group (n = 35 [42.2%]). The preoperative and 1-year follow-up eGFR did not differ significantly between the 2 groups, and the maximum eGFR after 3 years was higher in the recovery group (68.68 mL/min/1.73 m² [IQR, 61.81-75.64 mL/min/1.73 m²] vs 55.63 mL/min/1.73 m² [IQR, 51.73-58.29 mL/min/1.73 m²]; P < .001). The recovery group was more likely to have a history of hypertension (4.2% vs 20%; P = .032), a lower body mass index (24.11 kg/m² [IQR, 22.04-25.20 kg/m²] vs 25.25 kg/m² [IQR, 23.23-26.44 kg/m²]; P = .01), and a lower preoperative uric acid level (4.7 mg/dL [IQR, 3.8-5.4 mg/dL] vs 5.3 mg/dL [IQR, 4.4-6.2 mg/dL]; P = .031). After multivariate logistic regression analysis, history of hypertension (odds ratio, 0.131; P = .022) and uric acid level (odds ratio, 0.641; P = .036,) remained as significant factors.

CONCLUSIONS

Although 30.2% of donors had CKD at 1 year after nephrectomy, 57.8% reported improved renal function. Those with a history of hypertension and high preoperative uric acid levels were less likely to have improvements in renal function and required close follow-up.

Suspected Frequent Relapsing IgG4-related Lung Disease in Kidney Transplant Patient: A Case Report

Besides the initial description of IgG4-related pancreatic disease, other sites are now commonly involved. However, occurrence of IgG4-related disease is rare in organ transplanted patients. A 57-year-old man who received a kidney transplantation presented with recurrent dyspnea on exertion. A computed tomography scan of the chest revealed bilateral interlobular septal thickening and multiple tubular and branching small nodular lesions in the right upper lobe, and mass-like consolidation of the left middle lobe. Despite no elevation of serum IgG4 level, a percutaneous core needle biopsy on consolidative mass showed interstitial fibrosis and infiltration of IgG4-positive plasma cells to be more than > 20 per high power field. After treatment with glucocorticoids and rituximab, the consolidative mass of the left middle lobe disappeared.

Renoprotective Effects of Carbon Monoxide-Releasing Molecule 3 in Ischemia-Reperfusion Injury and Cisplatin-Induced Toxicity

BACKGROUND

We investigated the effects of a soluble carbon monoxide-releasing molecule (CORM) in cisplatin-induced cytotoxicity and ischemia-reperfusion injury (IRI) in vitro.

METHODS

The effects of CORM-3 (12.5-200 μM) were assessed in normal kidney epithelial cells (HK-2, LLC-PK1) and renal cancer cells (Caki-1, Caki-2) subjected to cisplatin (50-200 μM) or IRI. To induce IRI, cells were placed in an anaerobic chamber (37°C, 95% nitrogen, 5% carbon dioxide) for 48 hours. Cells were transferred to complete medium and incubated at 37°C, 5% carbon dioxide for 6 hours. Cell viability (CCK assays), tumor necrosis factor (TNF)-α messenger RNA (mRNA) levels (quantitative reverse-transcriptase polymerase chain reaction), and protein expression of cleaved-caspase 3 and oxidative stress markers (including Erk1/2, JNK, and P38; Western blot) were assessed.

RESULTS

Viability after IRI was approximately 40% of control. Protective effects of CORM-3 in the IRI model were dose-dependent. Cell viability was 40% recovered in 200-μM CORM-3-pretreated cells compared with control. The protective effects of CORM-3 in cells exposed to cisplatin for 24 hours were weaker than in the IRI model. TNF-α mRNA was induced by stimulated IRI or cisplatin exposure; CORM-3 pretreatment attenuated the rise in TNF-α mRNA. IRI or cisplatin-induced activated oxidative stress markers decreased in CORM-3-pretreated cells. CORM-3 reduced expression of the apoptotic marker cleaved-caspase 3.

CONCLUSION

Our data demonstrate the protective effects of CORM-3 in cisplatin cytotoxicity and IRI in both normal kidney cells and renal cancer cells in vitro. CORM-3 exerts these effects by ameliorating inflammatory and oxidative stress pathways.

An animal model of co-existing sarcopenia and osteoporotic fracture in senescence accelerated mouse prone 8 (SAMP8)

Sarcopenia and osteoporotic fracture are common aging-related musculoskeletal problems. Recent evidences report that osteoporotic fracture patients showed high prevalence of sarcopenia; however, current clinical practice basically does not consider sarcopenia in the treatment or rehabilitation of osteoporotic fracture. There is almost no report studying the relationship of the co-existing of sarcopenia and osteoporotic fracture healing. In this study, we validated aged senescence accelerated mouse prone 8 (SAMP8) and senescence accelerated mouse resistant 1 (SAMR1) as animal models of senile osteoporosis with/without sarcopenia. Bone mineral density (BMD) at the 5th lumbar and muscle testing of the two animal strains were measured to confirm the status of osteoporosis and sarcopenia, respectively. Closed fracture was created on the right femur of 8-month-old animals. Radiographs were taken weekly post-fracture. MicroCT and histology of the fractured femur were performed at week 2, 4 and 6 post-fracture, while mechanical test of both femora at week 4 and 6 post-fracture. Results showed that the callus of SAMR1 was significantly larger at week 2 but smaller at week 6 post-fracture than SAMP8. Mechanical properties were significantly better at week 4 post-fracture in SAMR1 than SAMP8, indicating osteoporotic fracture healing was delayed in sarcopenic SAMP8. This study validated an animal model of co-existing sarcopenia and osteoporotic fracture, where a delayed fracture healing might be resulted in the presence of sarcopenia.

Impact of the Ratio of Visceral to Subcutaneous Adipose Tissue in Donor Nephrectomy Patients

OBJECTIVE

It was reported that a metabolic syndrome affected the remaining renal function after living donor nephrectomy. However, the measurement of waist circumference is unclear because it cannot distinguish between visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT). We investigate the clinical correlation between body adipose tissue and renal function recovery after living donor nephrectomy.

METHODS

From July 2013 to February 2015, 75 living kidney donors were enrolled. The VAT and SAT were measured by preoperative computed tomography (CT) scan. Body mass index (BMI), VAT, SAT, and VAT-to-SAT ratio were analyzed according to a postoperative renal function recovery. Receiver operating characteristic (ROC) was performed to predict estimated glomerular filtration rate (eGFR) less than 60 mL/min/1.73 m² at postoperative 6 months for BMI, VAT, SAT, and VAT-to-SAT ratio.

RESULTS

The lowest value of eGFR (57.52 ± 11.20 mL/min/1.73 m²) was measured at postoperative day 7. There was no statistically significant difference in eGFR between 1 month and 3 months. BMI, VAT, SAT, and VAT-to-SAT ratio showed a statistically significant correlation with each other (Pearson correlation, P < .05). Also, the recovery time of eGFR was correlated with VAT-to-SAT ratio; it was significant at postoperative 1, 3, and 6 months. VAT-to-SAT ratio (0.654, 95% confidence interval 0.525-0.783, P = .024) had higher predictive value in ROC.

CONCLUSION

We developed a new variable to predict the value of lower eGFR (less than 60 mL/min/1.73 m²) at a postoperative 6 months in living kidney donor. According to a CT scan, VAT-to-SAT ratio can predict renal function recovery.